Mercurial > repos > bgruening > bismark
changeset 3:91f07ff056ca draft
Uploaded
| author | bgruening |
|---|---|
| date | Mon, 14 Apr 2014 16:43:14 -0400 |
| parents | 82814a8a2395 |
| children | 243e8f9fb75b |
| files | bismark bismark_bowtie2_wrapper.xml bismark_bowtie_wrapper.xml bismark_genome_preparation bismark_methylation_extractor bismark_methylation_extractor.py bismark_methylation_extractor.xml bismark_wrapper.py readme.rst tool_dependencies.xml |
| diffstat | 10 files changed, 2428 insertions(+), 1256 deletions(-) [+] |
line wrap: on
line diff
--- a/bismark Wed Aug 21 05:19:54 2013 -0400 +++ b/bismark Mon Apr 14 16:43:14 2014 -0400 @@ -24,7 +24,7 @@ my $parent_dir = getcwd; -my $bismark_version = 'v0.7.12'; +my $bismark_version = 'v0.10.0'; my $command_line = join (" ",@ARGV); ### before processing the command line we will replace --solexa1.3-quals with --phred64-quals as the '.' in the option name will cause Getopt::Long to fail @@ -35,7 +35,7 @@ } my @filenames; # will be populated by processing the command line -my ($genome_folder,$CT_index_basename,$GA_index_basename,$path_to_bowtie,$sequence_file_format,$bowtie_options,$directional,$unmapped,$ambiguous,$phred64,$solexa,$output_dir,$bowtie2,$vanilla,$sam_no_hd,$skip,$upto,$temp_dir,$non_bs_mm,$insertion_open,$insertion_extend,$deletion_open,$deletion_extend,$gzip,$bam,$samtools_path,$pbat) = process_command_line(); +my ($genome_folder,$CT_index_basename,$GA_index_basename,$path_to_bowtie,$sequence_file_format,$bowtie_options,$directional,$unmapped,$ambiguous,$phred64,$solexa,$output_dir,$bowtie2,$vanilla,$sam_no_hd,$skip,$upto,$temp_dir,$non_bs_mm,$insertion_open,$insertion_extend,$deletion_open,$deletion_extend,$gzip,$bam,$samtools_path,$pbat,$prefix,$old_flag) = process_command_line(); my @fhs; # stores alignment process names, bisulfite index location, bowtie filehandles and the number of times sequences produced an alignment my %chromosomes; # stores the chromosome sequences of the mouse genome @@ -293,9 +293,13 @@ ### printing all alignments to a results file my $outfile = $filename; + if ($prefix){ + $outfile = "$prefix.$outfile"; + } + if ($bowtie2){ # SAM format is the default for Bowtie 2 - $outfile =~ s/$/_bt2_bismark.sam/; + $outfile =~ s/$/_bismark_bt2.sam/; } elsif ($vanilla){ # vanilla custom Bismark output single-end output (like Bismark versions 0.5.X) $outfile =~ s/$/_bismark.txt/; @@ -327,8 +331,12 @@ ### printing alignment and methylation call summary to a report file my $reportfile = $filename; + if ($prefix){ + $reportfile = "$prefix.$reportfile"; + } + if ($bowtie2){ - $reportfile =~ s/$/_bt2_bismark_SE_report.txt/; + $reportfile =~ s/$/_bismark_bt2_SE_report.txt/; } else{ $reportfile =~ s/$/_bismark_SE_report.txt/; @@ -339,12 +347,19 @@ if ($unmapped){ my $unmapped_file = $filename; + if ($prefix){ + $unmapped_file = "$prefix.$unmapped_file"; + } + $unmapped_file =~ s/$/_unmapped_reads.txt/; open (UNMAPPED,'>',"$output_dir$unmapped_file") or die "Failed to write to $unmapped_file: $!\n"; print "Unmapped sequences will be written to $output_dir$unmapped_file\n"; } if ($ambiguous){ my $ambiguous_file = $filename; + if ($prefix){ + $ambiguous_file = "$prefix.$ambiguous_file"; + } $ambiguous_file =~ s/$/_ambiguous_reads.txt/; open (AMBIG,'>',"$output_dir$ambiguous_file") or die "Failed to write to $ambiguous_file: $!\n"; print "Ambiguously mapping sequences will be written to $output_dir$ambiguous_file\n"; @@ -399,7 +414,12 @@ } ### printing all alignments to a results file - my $outfile = $filename_1; + my $outfile = $filename_1; + + if ($prefix){ + $outfile = "$prefix.$outfile"; + } + if ($bowtie2){ # SAM format is the default Bowtie 2 output $outfile =~ s/$/_bismark_bt2_pe.sam/; } @@ -433,6 +453,10 @@ ### printing alignment and methylation call summary to a report file my $reportfile = $filename_1; + if ($prefix){ + $reportfile = "$prefix.$reportfile"; + } + if ($bowtie2){ $reportfile =~ s/$/_bismark_bt2_PE_report.txt/; } @@ -449,6 +473,10 @@ if ($unmapped){ my $unmapped_1 = $filename_1; my $unmapped_2 = $filename_2; + if ($prefix){ + $unmapped_1 = "$prefix.$unmapped_1"; + $unmapped_2 = "$prefix.$unmapped_2"; + } $unmapped_1 =~ s/$/_unmapped_reads_1.txt/; $unmapped_2 =~ s/$/_unmapped_reads_2.txt/; open (UNMAPPED_1,'>',"$output_dir$unmapped_1") or die "Failed to write to $unmapped_1: $!\n"; @@ -459,6 +487,11 @@ if ($ambiguous){ my $amb_1 = $filename_1; my $amb_2 = $filename_2; + if ($prefix){ + $amb_1 = "$prefix.$amb_1"; + $amb_2 = "$prefix.$amb_2"; + } + $amb_1 =~ s/$/_ambiguous_reads_1.txt/; $amb_2 =~ s/$/_ambiguous_reads_2.txt/; open (AMBIG_1,'>',"$output_dir$amb_1") or die "Failed to write to $amb_1: $!\n"; @@ -578,19 +611,38 @@ warn "Total number of C's analysed:\t$total_number_of_C\n\n"; warn "Total methylated C's in CpG context:\t$counting{total_meCpG_count}\n"; warn "Total methylated C's in CHG context:\t$counting{total_meCHG_count}\n"; - warn "Total methylated C's in CHH context:\t$counting{total_meCHH_count}\n\n"; - warn "Total C to T conversions in CpG context:\t$counting{total_unmethylated_CpG_count}\n"; - warn "Total C to T conversions in CHG context:\t$counting{total_unmethylated_CHG_count}\n"; - warn "Total C to T conversions in CHH context:\t$counting{total_unmethylated_CHH_count}\n\n"; + warn "Total methylated C's in CHH context:\t$counting{total_meCHH_count}\n"; + if ($bowtie2){ + warn "Total methylated C's in Unknown context:\t$counting{total_meC_unknown_count}\n"; + } + warn "\n"; + + warn "Total unmethylated C's in CpG context:\t$counting{total_unmethylated_CpG_count}\n"; + warn "Total unmethylated C's in CHG context:\t$counting{total_unmethylated_CHG_count}\n"; + warn "Total unmethylated C's in CHH context:\t$counting{total_unmethylated_CHH_count}\n"; + if ($bowtie2){ + warn "Total unmethylated C's in Unknown context:\t$counting{total_unmethylated_C_unknown_count}\n"; + } + warn "\n"; print REPORT "Final Cytosine Methylation Report\n",'='x33,"\n"; print REPORT "Total number of C's analysed:\t$total_number_of_C\n\n"; - print REPORT "Total methylated C's in CpG context:\t $counting{total_meCpG_count}\n"; + + print REPORT "Total methylated C's in CpG context:\t$counting{total_meCpG_count}\n"; print REPORT "Total methylated C's in CHG context:\t$counting{total_meCHG_count}\n"; - print REPORT "Total methylated C's in CHH context:\t$counting{total_meCHH_count}\n\n"; - print REPORT "Total C to T conversions in CpG context:\t$counting{total_unmethylated_CpG_count}\n"; - print REPORT "Total C to T conversions in CHG context:\t$counting{total_unmethylated_CHG_count}\n"; - print REPORT "Total C to T conversions in CHH context:\t$counting{total_unmethylated_CHH_count}\n\n"; + print REPORT "Total methylated C's in CHH context:\t$counting{total_meCHH_count}\n"; + if ($bowtie2){ + print REPORT "Total methylated C's in Unknown context:\t$counting{total_meC_unknown_count}\n"; + } + print REPORT "\n"; + + print REPORT "Total unmethylated C's in CpG context:\t$counting{total_unmethylated_CpG_count}\n"; + print REPORT "Total unmethylated C's in CHG context:\t$counting{total_unmethylated_CHG_count}\n"; + print REPORT "Total unmethylated C's in CHH context:\t$counting{total_unmethylated_CHH_count}\n"; + if ($bowtie2){ + print REPORT "Total unmethylated C's in Unknown context:\t$counting{total_unmethylated_C_unknown_count}\n"; + } + print REPORT "\n"; my $percent_meCHG; if (($counting{total_meCHG_count}+$counting{total_unmethylated_CHG_count}) > 0){ @@ -607,6 +659,12 @@ $percent_meCpG = sprintf("%.1f",100*$counting{total_meCpG_count}/($counting{total_meCpG_count}+$counting{total_unmethylated_CpG_count})); } + my $percent_meC_unknown; + if (($counting{total_meC_unknown_count}+$counting{total_unmethylated_C_unknown_count}) > 0){ + $percent_meC_unknown = sprintf("%.1f",100*$counting{total_meC_unknown_count}/($counting{total_meC_unknown_count}+$counting{total_unmethylated_C_unknown_count})); + } + + ### printing methylated CpG percentage if applicable if ($percent_meCpG){ warn "C methylated in CpG context:\t${percent_meCpG}%\n"; @@ -629,20 +687,117 @@ ### printing methylated C percentage (CHH context) if applicable if ($percent_meCHH){ - warn "C methylated in CHH context:\t${percent_meCHH}%\n\n\n"; - print REPORT "C methylated in CHH context:\t${percent_meCHH}%\n\n\n"; + warn "C methylated in CHH context:\t${percent_meCHH}%\n"; + print REPORT "C methylated in CHH context:\t${percent_meCHH}%\n"; } else{ - warn "Can't determine percentage of methylated Cs in CHH context if value was 0\n\n\n"; - print REPORT "Can't determine percentage of methylated Cs in CHH context if value was 0\n\n\n"; - } + warn "Can't determine percentage of methylated Cs in CHH context if value was 0\n"; + print REPORT "Can't determine percentage of methylated Cs in CHH context if value was 0\n"; + } + + ### printing methylated C percentage (Unknown C context) if applicable + if ($bowtie2){ + if ($percent_meC_unknown){ + warn "C methylated in Unknown context (CN or CHN):\t${percent_meC_unknown}%\n"; + print REPORT "C methylated in Unknown context (CN or CHN):\t${percent_meC_unknown}%\n"; + } + else{ + warn "Can't determine percentage of methylated Cs in Unknown context (CN or CHN) if value was 0\n"; + print REPORT "Can't determine percentage of methylated Cs in Unknown context (CN or CHN) if value was 0\n"; + } + } + print REPORT "\n\n"; + warn "\n\n"; if ($seqID_contains_tabs){ warn "The sequence IDs in the provided file contain tab-stops which might prevent sequence alignments. If this happened, please replace all tab characters within the seqID field with spaces before running Bismark.\n\n"; print REPORT "The sequence IDs in the provided file contain tab-stops which might prevent sequence alignments. If this happened, please replace all tab characters within the seqID field with spaces before running Bismark.\n\n"; } + + + ########################################################################################################################################### + ### create pie-chart with mapping stats + ########################################################################################################################################### + + + my $filename; + if ($pbat){ + $filename = $G_to_A_infile; + } + else{ + $filename = $C_to_T_infile; + } + + my $pie_chart = (split (/\//,$filename))[-1]; # extracting the filename if a full path was specified + $pie_chart =~ s/gz$//; + $pie_chart =~ s/_C_to_T\.fastq$//; + $pie_chart =~ s/_G_to_A\.fastq$//; + + # if ($prefix){ + # $pie_chart = "$prefix.$pie_chart"; # this is now being taken care of in file transformation + # } + $pie_chart = "${output_dir}${pie_chart}_bismark_SE.alignment_overview.png"; + + + #Check whether the module GD::Graph is installed + my $gd_graph_installed = 0; + eval{ + require GD::Graph::pie; + GD::Graph::pie->import(); + }; + + unless($@) { + $gd_graph_installed = 1; + } + else{ + warn "Perl module GD::Graph::pie is not installed, skipping graphical alignment summary\n"; + sleep(2); + } + + if ($gd_graph_installed){ + warn "Generating pie chart\n\n"; + sleep(1); + my $graph = GD::Graph::pie->new(600,600); + + my $percent_unaligned; + my $percent_multiple; + my $percent_unextractable; + + if ($counting{sequences_count}){ + $percent_unaligned = sprintf ("%.1f",$counting{no_single_alignment_found}*100/$counting{sequences_count}); + $percent_multiple = sprintf ("%.1f",$counting{unsuitable_sequence_count}*100/$counting{sequences_count}); + $percent_unextractable = sprintf ("%.1f",$counting{genomic_sequence_could_not_be_extracted_count}*100/$counting{sequences_count}); + } + else{ + $percent_unaligned = $percent_multiple = $percent_unextractable = 'N/A'; + } + + my @aln_stats = ( + ["Uniquely aligned $percent_alignable_sequences%","Unaligned $percent_unaligned%","Multiple alignments $percent_multiple%","sequence unextractable $percent_unextractable%"], + [$counting{unique_best_alignment_count},$counting{no_single_alignment_found},$counting{unsuitable_sequence_count},$counting{genomic_sequence_could_not_be_extracted_count}], + ); + + $graph->set( + start_angle => 180, + '3d' => 0, + label => 'Alignment stats (single-end)', + suppress_angle => 2, # Only label slices of sufficient size + transparent => 0, + dclrs => [ qw(red lorange dgreen cyan) ], + ) or die $graph->error; + + my $gd = $graph->plot(\@aln_stats) or die $graph->error; + + open (PIE,'>',$pie_chart) or die "Failed to write to file for alignments pie chart: $!\n\n"; + binmode PIE; + print PIE $gd->png; + } + + warn "====================\nBismark run complete\n====================\n\n"; + } + sub print_final_analysis_report_paired_ends{ my ($C_to_T_infile_1,$G_to_A_infile_1,$C_to_T_infile_2,$G_to_A_infile_2) = @_; ### All sequences from the original sequence file have been analysed now, therefore deleting temporary C->T or G->A infiles @@ -736,18 +891,36 @@ warn "Total number of C's analysed:\t$total_number_of_C\n\n"; warn "Total methylated C's in CpG context:\t$counting{total_meCpG_count}\n"; warn "Total methylated C's in CHG context:\t$counting{total_meCHG_count}\n"; - warn "Total methylated C's in CHH context:\t$counting{total_meCHH_count}\n\n"; - warn "Total C to T conversions in CpG context:\t$counting{total_unmethylated_CpG_count}\n"; - warn "Total C to T conversions in CHG context:\t$counting{total_unmethylated_CHG_count}\n"; - warn "Total C to T conversions in CHH context:\t$counting{total_unmethylated_CHH_count}\n\n"; + warn "Total methylated C's in CHH context:\t$counting{total_meCHH_count}\n"; + if ($bowtie2){ + warn "Total methylated C's in Unknown context:\t$counting{total_meC_unknown_count}\n"; + } + warn "\n"; + + warn "Total unmethylated C's in CpG context:\t$counting{total_unmethylated_CpG_count}\n"; + warn "Total unmethylated C's in CHG context:\t$counting{total_unmethylated_CHG_count}\n"; + warn "Total unmethylated C's in CHH context:\t$counting{total_unmethylated_CHH_count}\n"; + if ($bowtie2){ + warn "Total unmethylated C's in Unknown context:\t$counting{total_unmethylated_C_unknown_count}\n"; + } + warn "\n"; print REPORT "Total number of C's analysed:\t$total_number_of_C\n\n"; print REPORT "Total methylated C's in CpG context:\t$counting{total_meCpG_count}\n"; print REPORT "Total methylated C's in CHG context:\t$counting{total_meCHG_count}\n"; - print REPORT "Total methylated C's in CHH context:\t$counting{total_meCHH_count}\n\n"; - print REPORT "Total C to T conversions in CpG context:\t$counting{total_unmethylated_CpG_count}\n"; - print REPORT "Total C to T conversions in CHG context:\t$counting{total_unmethylated_CHG_count}\n"; - print REPORT "Total C to T conversions in CHH context:\t$counting{total_unmethylated_CHH_count}\n\n"; + print REPORT "Total methylated C's in CHH context:\t$counting{total_meCHH_count}\n"; + if ($bowtie2){ + print REPORT "Total methylated C's in Unknown context:\t$counting{total_meC_unknown_count}\n\n"; + } + print REPORT "\n"; + + print REPORT "Total unmethylated C's in CpG context:\t$counting{total_unmethylated_CpG_count}\n"; + print REPORT "Total unmethylated C's in CHG context:\t$counting{total_unmethylated_CHG_count}\n"; + print REPORT "Total unmethylated C's in CHH context:\t$counting{total_unmethylated_CHH_count}\n"; + if ($bowtie2){ + print REPORT "Total unmethylated C's in Unknown context:\t$counting{total_unmethylated_C_unknown_count}\n\n"; + } + print REPORT "\n"; my $percent_meCHG; if (($counting{total_meCHG_count}+$counting{total_unmethylated_CHG_count}) > 0){ @@ -764,6 +937,12 @@ $percent_meCpG = sprintf("%.1f",100*$counting{total_meCpG_count}/($counting{total_meCpG_count}+$counting{total_unmethylated_CpG_count})); } + my $percent_meC_unknown; + if (($counting{total_meC_unknown_count}+$counting{total_unmethylated_C_unknown_count}) > 0){ + $percent_meC_unknown = sprintf("%.1f",100*$counting{total_meC_unknown_count}/($counting{total_meC_unknown_count}+$counting{total_unmethylated_C_unknown_count})); + } + + ### printing methylated CpG percentage if applicable if ($percent_meCpG){ warn "C methylated in CpG context:\t${percent_meCpG}%\n"; @@ -786,13 +965,112 @@ ### printing methylated C percentage in CHH context if applicable if ($percent_meCHH){ - warn "C methylated in CHH context:\t${percent_meCHH}%\n\n\n"; - print REPORT "C methylated in CHH context:\t${percent_meCHH}%\n\n\n"; + warn "C methylated in CHH context:\t${percent_meCHH}%\n"; + print REPORT "C methylated in CHH context:\t${percent_meCHH}%\n"; + } + else{ + warn "Can't determine percentage of methylated Cs in CHH context if value was 0\n"; + print REPORT "Can't determine percentage of methylated Cs in CHH context if value was 0\n"; + } + + ### printing methylated C percentage (Unknown C context) if applicable + if ($bowtie2){ + if ($percent_meC_unknown){ + warn "C methylated in unknown context (CN or CHN):\t${percent_meC_unknown}%\n"; + print REPORT "C methylated in unknown context (CN or CHN):\t${percent_meC_unknown}%\n"; + } + else{ + warn "Can't determine percentage of methylated Cs in unknown context (CN or CHN) if value was 0\n"; + print REPORT "Can't determine percentage of methylated Cs in unknown context (CN or CHN) if value was 0\n"; + } + } + print REPORT "\n\n"; + warn "\n\n"; + + + ############################################################################################################################################ + ### create pie-chart with mapping stats + ########################################################################################################################################### + + my $filename; + if ($pbat){ + $filename = $G_to_A_infile_1; } else{ - warn "Can't determine percentage of methylated Cs in CHH context if value was 0\n\n\n"; - print REPORT "Can't determine percentage of methylated Cs in CHH context if value was 0\n\n\n"; - } + $filename = $C_to_T_infile_1; + } + + my $pie_chart = (split (/\//,$filename))[-1]; # extracting the filename if a full path was specified + $pie_chart =~ s/gz$//; + $pie_chart =~ s/_C_to_T.fastq$//; + $pie_chart =~ s/_G_to_A.fastq$//; + ### special format for gzipped PE Bowtie1 files + $pie_chart =~ s/\.CT_plus_GA\.fastq\.$//; + $pie_chart =~ s/\.GA_plus_CT\.fastq\.$//; + + if ($prefix){ + # prefix is now being prepended to the temp files already + # $pie_chart = "$prefix.$pie_chart"; + } + $pie_chart = "${output_dir}${pie_chart}_bismark_PE.alignment_overview.png"; + + #Check whether the module GD::Graph is installed + my $gd_graph_installed = 0; + eval{ + require GD::Graph::pie; + GD::Graph::pie->import(); + }; + + unless($@) { + $gd_graph_installed = 1; + } + else{ + warn "Perl module GD::Graph::pie is not installed, skipping graphical alignment summary\n"; + sleep(2); + } + + if ($gd_graph_installed){ + warn "Generating pie chart\n\n"; + sleep(1); + my $graph = GD::Graph::pie->new(600,600); + + my $percent_unaligned; + my $percent_multiple; + my $percent_unextractable; + + if ($counting{sequences_count}){ + $percent_unaligned = sprintf ("%.1f",$counting{no_single_alignment_found}*100/$counting{sequences_count}); + $percent_multiple = sprintf ("%.1f",$counting{unsuitable_sequence_count}*100/$counting{sequences_count}); + $percent_unextractable = sprintf ("%.1f",$counting{genomic_sequence_could_not_be_extracted_count}*100/$counting{sequences_count}); + } + else{ + $percent_unaligned = $percent_multiple = $percent_unextractable = 'N/A'; + } + + my @aln_stats = ( + ["Uniquely aligned pairs $percent_alignable_sequence_pairs%","Unaligned $percent_unaligned%","Multiple alignments $percent_multiple%","sequence unextractable $percent_unextractable%"], + [$counting{unique_best_alignment_count},$counting{no_single_alignment_found},$counting{unsuitable_sequence_count},$counting{genomic_sequence_could_not_be_extracted_count}], + ); + + # push @{$mbias_read1[0]},$pos; + + $graph->set( + start_angle => 180, + '3d' => 0, + label => 'Alignment stats (paired-end)', + suppress_angle => 2, # Only label slices of sufficient size + transparent => 0, + dclrs => [ qw(red lorange dgreen cyan) ], + ) or die $graph->error; + + my $gd = $graph->plot(\@aln_stats) or die $graph->error; + + open (PIE,'>',$pie_chart) or die "Failed to write to file for alignments pie chart: $!\n\n"; + binmode PIE; + print PIE $gd->png; + } + + warn "====================\nBismark run complete\n====================\n\n"; } @@ -831,7 +1109,7 @@ } $counting{sequences_count}++; - if ($counting{sequences_count}%100000==0) { + if ($counting{sequences_count}%1000000==0) { warn "Processed $counting{sequences_count} sequences so far\n"; } chomp $sequence; @@ -993,8 +1271,8 @@ } $counting{sequences_count}++; - if ($counting{sequences_count}%100000==0) { - warn "Processed $counting{sequences_count} sequences so far\n"; + if ($counting{sequences_count}%1000000==0) { + warn "Processed $counting{sequences_count} sequence pairs so far\n"; } my $orig_identifier_1 = $identifier_1; my $orig_identifier_2 = $identifier_2; @@ -1090,8 +1368,8 @@ } $counting{sequences_count}++; - if ($counting{sequences_count}%100000==0) { - warn "Processed $counting{sequences_count} sequences so far\n"; + if ($counting{sequences_count}%1000000==0) { + warn "Processed $counting{sequences_count} sequence pairs so far\n"; } my $orig_identifier_1 = $identifier_1; @@ -2778,12 +3056,12 @@ ### check to see if the genomic sequences we extracted has the same length as the observed sequences +2, and only then we perform the methylation call if (length($methylation_call_params->{$identifier}->{unmodified_genomic_sequence_1}) != length($sequence_1)+2){ - warn "Chromosomal sequence could not be extracted for\t$identifier\t$methylation_call_params->{$identifier}->{chromosome}\t$methylation_call_params->{$identifier}->{start_seq_1}\n"; + warn "Chromosomal sequence could not be extracted for\t$identifier\t$methylation_call_params->{$identifier}->{chromosome}\t$methylation_call_params->{$identifier}->{position_1}\n"; $counting{genomic_sequence_could_not_be_extracted_count}++; return 0; } if (length($methylation_call_params->{$identifier}->{unmodified_genomic_sequence_2}) != length($sequence_2)+2){ - warn "Chromosomal sequence could not be extracted for\t$identifier\t$methylation_call_params->{$identifier}->{chromosome}\t$methylation_call_params->{$identifier}->{start_seq_2}\n"; + warn "Chromosomal sequence could not be extracted for\t$identifier\t$methylation_call_params->{$identifier}->{chromosome}\t$methylation_call_params->{$identifier}->{position_2}\n"; $counting{genomic_sequence_could_not_be_extracted_count}++; return 0; } @@ -3077,7 +3355,8 @@ my $cigar_2 = $methylation_call_params->{$sequence_identifier}->{CIGAR_2}; my $flag_1 = $methylation_call_params->{$sequence_identifier}->{flag_1}; my $flag_2 = $methylation_call_params->{$sequence_identifier}->{flag_2}; -# print "$cigar_1\t$cigar_2\t$flag_1\t$flag_2\n"; + # print "$cigar_1\t$cigar_2\t$flag_1\t$flag_2\n"; + # sleep(10); ### We are now extracting the corresponding genomic sequence, +2 extra bases at the end (or start) so that we can also make a CpG methylation call and ### in addition make differential calls for Cs in CHG or CHH context if the C happens to be at the last (or first) position of the actually observed sequence @@ -3111,7 +3390,7 @@ my $indels_1 = 0; # addiong these to the hemming distance value (needed for the NM field in the final SAM output my $indels_2 = 0; - + ### Extracting read 1 genomic sequence ### # extracting 2 additional bp at the 5' end (read 1) @@ -3160,6 +3439,7 @@ $methylation_call_params->{$sequence_identifier}->{unmodified_genomic_sequence_1} = $non_bisulfite_sequence_1; return; } + $non_bisulfite_sequence_1 .= substr ($chromosomes{$methylation_call_params->{$sequence_identifier}->{chromosome}},$pos_1,2); } @@ -3209,6 +3489,10 @@ if ( ($methylation_call_params->{$sequence_identifier}->{index} == 0) or ($methylation_call_params->{$sequence_identifier}->{index} == 2) ){ ## checking if the substring will be valid or if we can't extract the sequence because we are right at the edge of a chromosome unless (length($chromosomes{$methylation_call_params->{$sequence_identifier}->{chromosome}}) >= $pos_2+2){# exiting with en empty genomic sequence otherwise + # need to set read 1 as well now to prevent warning + # warn "'$non_bisulfite_sequence_1'\n'$non_bisulfite_sequence_2'\n\n"; + # sleep(5); + $methylation_call_params->{$sequence_identifier}->{unmodified_genomic_sequence_1} = $non_bisulfite_sequence_1; $methylation_call_params->{$sequence_identifier}->{unmodified_genomic_sequence_2} = $non_bisulfite_sequence_2; return; } @@ -3809,6 +4093,8 @@ ### h for not methylated C in CHH context (was converted) ### ### Z for methylated C in CpG context (was protected) ### ### z for not methylated C in CpG context (was converted) ### + ### U for methylated C in unknown context (was protected) ### + ### u for not methylated C in unknwon context (was converted) ### ################################################################# my @match =(); @@ -3816,9 +4102,11 @@ my $methyl_CHH_count = 0; my $methyl_CHG_count = 0; my $methyl_CpG_count = 0; + my $methyl_C_unknown_count = 0; my $unmethylated_CHH_count = 0; my $unmethylated_CHG_count = 0; my $unmethylated_CpG_count = 0; + my $unmethylated_C_unknown_count = 0; if ($read_conversion eq 'CT'){ for my $index (0..$#seq) { @@ -3832,7 +4120,10 @@ ++$methyl_CpG_count; push @match,'Z'; # protected C, methylated, in CpG context } - + elsif ($downstream_base eq 'N'){ # if the downstream base was an N we cannot really be sure about the sequence context (as it might have been a CG) + ++$methyl_C_unknown_count; + push @match,'U'; # protected C, methylated, in Unknown context + } else { ### C in not in CpG-context, determining the second downstream base context my $second_downstream_base = $genomic[$index+2]; @@ -3841,6 +4132,10 @@ ++$methyl_CHG_count; push @match,'X'; # protected C, methylated, in CHG context } + elsif ($second_downstream_base eq 'N'){ + ++$methyl_C_unknown_count; # if the second downstream base was an N we cannot really be sure about the sequence context (as it might have been a CHH or CHG) + push @match,'U'; # protected C, methylated, in Unknown context + } else{ ++$methyl_CHH_count; push @match,'H'; # protected C, methylated, in CHH context @@ -3862,7 +4157,10 @@ ++$unmethylated_CpG_count; push @match,'z'; # converted C, not methylated, in CpG context } - + elsif ($downstream_base eq 'N'){ # if the downstream base was an N we cannot really be sure about the sequence context (as it might have been a CG) + ++$unmethylated_C_unknown_count; + push @match,'u'; # converted C, not methylated, in Unknown context + } else{ ### C in not in CpG-context, determining the second downstream base context my $second_downstream_base = $genomic[$index+2]; @@ -3871,6 +4169,10 @@ ++$unmethylated_CHG_count; push @match,'x'; # converted C, not methylated, in CHG context } + elsif ($second_downstream_base eq 'N'){ + ++$unmethylated_C_unknown_count; # if the second downstream base was an N we cannot really be sure about the sequence context (as it might have been a CHH or CHG) + push @match,'u'; # converted C, not methylated, in Unknown context + } else{ ++$unmethylated_CHH_count; push @match,'h'; # converted C, not methylated, in CHH context @@ -3903,7 +4205,10 @@ ++$methyl_CpG_count; push @match,'Z'; # protected C on opposing strand, methylated, in CpG context } - + elsif ($upstream_base eq 'N'){ # if the upstream base was an N we cannot really be sure about the sequence context (as it might have been a CG) + ++$methyl_C_unknown_count; + push @match,'U'; # protected C on opposing strand, methylated, in Unknown context + } else{ ### C in not in CpG-context, determining the second upstream base context my $second_upstream_base = $genomic[$index]; @@ -3912,6 +4217,10 @@ ++$methyl_CHG_count; push @match,'X'; # protected C on opposing strand, methylated, in CHG context } + elsif ($second_upstream_base eq 'N'){ + ++$methyl_C_unknown_count; # if the second upstream base was an N we cannot really be sure about the sequence context (as it might have been a CHH or CHG) + push @match,'U'; # protected C, methylated, in Unknown context + } else{ ++$methyl_CHH_count; push @match,'H'; # protected C on opposing strand, methylated, in CHH context @@ -3935,7 +4244,10 @@ ++$unmethylated_CpG_count; push @match,'z'; # converted C on opposing strand, not methylated, in CpG context } - + elsif ($upstream_base eq 'N'){ # if the upstream base was an N we cannot really be sure about the sequence context (as it might have been a CG) + ++$unmethylated_C_unknown_count; + push @match,'u'; # converted C on opposing strand, not methylated, in Unknown context + } else{ ### C in not in CpG-context, determining the second upstream base context my $second_upstream_base = $genomic[$index]; @@ -3944,6 +4256,10 @@ ++$unmethylated_CHG_count; push @match,'x'; # converted C on opposing strand, not methylated, in CHG context } + elsif ($second_upstream_base eq 'N'){ + ++$unmethylated_C_unknown_count; # if the second upstream base was an N we cannot really be sure about the sequence context (as it might have been a CHH or CHG) + push @match,'u'; # converted C on opposing strand, not methylated, in Unknown context + } else{ ++$unmethylated_CHH_count; push @match,'h'; # converted C on opposing strand, not methylated, in CHH context @@ -3969,9 +4285,11 @@ $counting{total_meCHH_count} += $methyl_CHH_count; $counting{total_meCHG_count} += $methyl_CHG_count; $counting{total_meCpG_count} += $methyl_CpG_count; + $counting{total_meC_unknown_count} += $methyl_C_unknown_count; $counting{total_unmethylated_CHH_count} += $unmethylated_CHH_count; $counting{total_unmethylated_CHG_count} += $unmethylated_CHG_count; $counting{total_unmethylated_CpG_count} += $unmethylated_CpG_count; + $counting{total_unmethylated_C_unknown_count} += $unmethylated_C_unknown_count; # print "\n$sequence_actually_observed\n$genomic_sequence\n",@match,"\n$read_conversion\n\n"; return $methylation_call; @@ -4106,6 +4424,13 @@ $G_to_A_infile =~ s/$/_G_to_A.fa/; } + if ($prefix){ + # warn "Prefixing $prefix:\nold: $C_to_T_infile\nold: $G_to_A_infile\n\n"; + $C_to_T_infile = "$prefix.$C_to_T_infile"; + $G_to_A_infile = "$prefix.$G_to_A_infile"; + # warn "Prefixing $prefix:\nnew: $C_to_T_infile\nnew: $G_to_A_infile\n\n"; + } + warn "Writing a C -> T converted version of the input file $filename to $temp_dir$C_to_T_infile\n"; if ($gzip){ @@ -4209,9 +4534,17 @@ } my $C_to_T_infile = my $G_to_A_infile = $filename; + $C_to_T_infile =~ s/$/_C_to_T.fa/; $G_to_A_infile =~ s/$/_G_to_A.fa/; + if ($prefix){ + # warn "Prefixing $prefix:\nold: $C_to_T_infile\nold: $G_to_A_infile\n\n"; + $C_to_T_infile = "$prefix.$C_to_T_infile"; + $G_to_A_infile = "$prefix.$G_to_A_infile"; + # warn "Prefixing $prefix:\nnew: $C_to_T_infile\nnew: $G_to_A_infile\n\n"; + } + if ($directional){ if ($read_number == 1){ warn "Writing a C -> T converted version of the input file $filename to $temp_dir$C_to_T_infile\n"; @@ -4354,6 +4687,13 @@ my $C_to_T_infile = my $G_to_A_infile = $filename; + if ($prefix){ + # warn "Prefixing $prefix:\nold: $C_to_T_infile\nold: $G_to_A_infile\n\n"; + $C_to_T_infile = "$prefix.$C_to_T_infile"; + $G_to_A_infile = "$prefix.$G_to_A_infile"; + # warn "Prefixing $prefix:\nnew: $C_to_T_infile\nnew: $G_to_A_infile\n\n"; + } + if ($pbat){ # PBAT-Seq if ($gzip){ $G_to_A_infile =~ s/$/_G_to_A.fastq.gz/; @@ -4515,6 +4855,13 @@ $G_to_A_infile =~ s/$/_G_to_A.fastq/; } + if ($prefix){ + # warn "Prefixing $prefix:\nold: $C_to_T_infile\nold: $G_to_A_infile\n\n"; + $C_to_T_infile = "$prefix.$C_to_T_infile"; + $G_to_A_infile = "$prefix.$G_to_A_infile"; + # warn "Prefixing $prefix:\nnew: $C_to_T_infile\nnew: $G_to_A_infile\n\n"; + } + if ($directional){ if ($read_number == 1){ warn "Writing a C -> T converted version of the input file $filename to $temp_dir$C_to_T_infile\n"; @@ -4685,8 +5032,16 @@ my $CT_plus_GA_infile = my $GA_plus_CT_infile = $filename; + if ($prefix){ + # warn "Prefixing $prefix:\nold: $CT_plus_GA_infile\nold: $GA_plus_CT_infile\n\n"; + $CT_plus_GA_infile = "$prefix.$CT_plus_GA_infile"; + $GA_plus_CT_infile = "$prefix.$GA_plus_CT_infile"; + # warn "Prefixing $prefix:\nnew: $CT_plus_GA_infile\nnew: $GA_plus_CT_infile\n\n"; + } + $CT_plus_GA_infile =~ s/$/.CT_plus_GA.fastq.gz/; $GA_plus_CT_infile =~ s/$/.GA_plus_CT.fastq.gz/; + # warn "Prefixing $prefix:\nnew: $CT_plus_GA_infile\nnew: $GA_plus_CT_infile\n\n"; warn "Writing a C -> T converted version of $file_1 and a G -> A converted version of $file_2 to $temp_dir$CT_plus_GA_infile\n"; open (CTPLUSGA,"| gzip -c - > ${temp_dir}${CT_plus_GA_infile}") or die "Can't write to file: $!\n"; @@ -5557,9 +5912,11 @@ total_meCHH_count => 0, total_meCHG_count => 0, total_meCpG_count => 0, + total_meC_unknown_count => 0, total_unmethylated_CHH_count => 0, total_unmethylated_CHG_count => 0, total_unmethylated_CpG_count => 0, + total_unmethylated_C_unknown_count => 0, sequences_count => 0, no_single_alignment_found => 0, unsuitable_sequence_count => 0, @@ -5743,6 +6100,8 @@ my $bam; my $gzip; my $pbat; + my $prefix; + my $old_flag; my $command_line = GetOptions ('help|man' => \$help, '1=s' => \$mates1, @@ -5784,6 +6143,8 @@ 'bam' => \$bam, 'gzip' => \$gzip, 'pbat' => \$pbat, + 'prefix=s' => \$prefix, + 'old_flag' => \$old_flag, ); @@ -5939,7 +6300,7 @@ my @CT_bowtie_index = ('BS_CT.1.bt2','BS_CT.2.bt2','BS_CT.3.bt2','BS_CT.4.bt2','BS_CT.rev.1.bt2','BS_CT.rev.2.bt2'); foreach my $file(@CT_bowtie_index){ unless (-f $file){ - die "The Bowtie 2 index of the C->T converted genome seems to be faulty ($file). Please run the bismark_genome_preparation before running Bismark.\n"; + die "The Bowtie 2 index of the C->T converted genome seems to be faulty ($file doesn't exist). Please run the bismark_genome_preparation before running Bismark\n"; } } ### checking the integrity of $GA_dir @@ -5947,7 +6308,7 @@ my @GA_bowtie_index = ('BS_GA.1.bt2','BS_GA.2.bt2','BS_GA.3.bt2','BS_GA.4.bt2','BS_GA.rev.1.bt2','BS_GA.rev.2.bt2'); foreach my $file(@GA_bowtie_index){ unless (-f $file){ - die "The Bowtie 2 index of the G->A converted genome seems to be faulty ($file). Please run bismark_genome_preparation before running Bismark.\n"; + die "The Bowtie 2 index of the G->A converted genome seems to be faulty ($file doesn't exist). Please run bismark_genome_preparation before running Bismark\n"; } } } @@ -5958,7 +6319,7 @@ my @CT_bowtie_index = ('BS_CT.1.ebwt','BS_CT.2.ebwt','BS_CT.3.ebwt','BS_CT.4.ebwt','BS_CT.rev.1.ebwt','BS_CT.rev.2.ebwt'); foreach my $file(@CT_bowtie_index){ unless (-f $file){ - die "The Bowtie index of the C->T converted genome seems to be faulty ($file). Please run bismark_genome_preparation before running Bismark.\n"; + die "The Bowtie index of the C->T converted genome seems to be faulty ($file doesn't exist). Please run bismark_genome_preparation before running Bismark.\n"; } } ### checking the integrity of $GA_dir @@ -5966,7 +6327,7 @@ my @GA_bowtie_index = ('BS_GA.1.ebwt','BS_GA.2.ebwt','BS_GA.3.ebwt','BS_GA.4.ebwt','BS_GA.rev.1.ebwt','BS_GA.rev.2.ebwt'); foreach my $file(@GA_bowtie_index){ unless (-f $file){ - die "The Bowtie index of the G->A converted genome seems to be faulty ($file). Please run bismark_genome_preparation before running Bismark.\n"; + die "The Bowtie index of the G->A converted genome seems to be faulty ($file doesn't exist). Please run bismark_genome_preparation before running Bismark.\n"; } } } @@ -6247,6 +6608,11 @@ push @bowtie_options,'--no-mixed'; ## By default Bowtie 2 is not looking for single-end alignments if it can't find concordant or discordant alignments push @bowtie_options,'--no-discordant';## By default Bowtie 2 is not looking for discordant alignments if it can't find concordant ones } + + if ($old_flag){ + warn "\nUsing FLAG values for paired-end SAM output used up to Bismark v0.8.2. In addition, paired-end sequences will have /1 and /2 appended to their read IDs\n\n" unless($vanilla); + sleep(3); + } } elsif ($mates2){ die "Paired-end mapping requires the format: -1 <mates1> -2 <mates2>, please respecify!\n"; @@ -6400,7 +6766,18 @@ } } - return ($genome_folder,$CT_index_basename,$GA_index_basename,$path_to_bowtie,$sequence_format,$bowtie_options,$directional,$unmapped,$multi_map,$phred64,$solexa,$output_dir,$bowtie2,$vanilla,$sam_no_hd,$skip,$qupto,$temp_dir,$non_bs_mm,$insertion_open,$insertion_extend,$deletion_open,$deletion_extend,$gzip,$bam,$samtools_path,$pbat); + ### PREFIX FOR OUTPUT FILES + if ($prefix){ + # removing trailing dots + + $prefix =~ s/\.+$//; + + warn "Using the following prefix for output files: $prefix\n\n"; + sleep(1); + } + + + return ($genome_folder,$CT_index_basename,$GA_index_basename,$path_to_bowtie,$sequence_format,$bowtie_options,$directional,$unmapped,$multi_map,$phred64,$solexa,$output_dir,$bowtie2,$vanilla,$sam_no_hd,$skip,$qupto,$temp_dir,$non_bs_mm,$insertion_open,$insertion_extend,$deletion_open,$deletion_extend,$gzip,$bam,$samtools_path,$pbat,$prefix,$old_flag); } @@ -6638,8 +7015,17 @@ my $read_conversion_2 = $methylation_call_params->{$id}->{read_conversion_2}; my $genome_conversion = $methylation_call_params->{$id}->{genome_conversion}; - my $id_1 = $id.'/1'; - my $id_2 = $id.'/2'; + my $id_1; + my $id_2; + + if ($old_flag){ + $id_1 = $id.'/1'; + $id_2 = $id.'/2'; + } + else{ + $id_1 = $id; # appending /1 or /2 confuses some downstream programs such as Picard + $id_2 = $id; + } # Allows all degenerate nucleotide sequences in reference genome die "Reference sequence ($ref_seq_1) contains invalid nucleotides!\n" if $ref_seq_1 =~ /[^ACTGNRYMKSWBDHV]/i; @@ -6759,24 +7145,50 @@ # strands OT and CTOT will be treated as aligning to the top strand (both sequences are scored as aligning to the top strand) # strands OB and CTOB will be treated as aligning to the bottom strand (both sequences are scored as reverse complemented sequences) - my $flag_1; # FLAG variable used for SAM format + my $flag_1; # FLAG variable used for SAM format my $flag_2; + ### The new default FLAG values have been suggested by Peter Hickey, Australia (PH) + if ($index == 0){ # OT - $flag_1 = 67; # Read 1 is on the + strand (1+2+64) (Read 2 is technically reverse-complemented, but we do not score it) - $flag_2 = 131; # Read 2 is on - strand but informative for the OT (1+2+128) + unless ($old_flag){ + $flag_1 = 99; # PH: Read 1 is on the + strand and Read 2 is reversed (1+2+32+64) + $flag_2 = 147; # PH: Read 2 is on - strand but informative for the OT (1+2+16+128) + } + else{ + $flag_1 = 67; # Read 1 is on the + strand (1+2+64) (Read 2 is technically reverse-complemented, but we do not score it) + $flag_2 = 131; # Read 2 is on - strand but informative for the OT (1+2+128) + } } elsif ($index == 1){ # CTOB - $flag_1 = 115; # Read 1 is on the + strand, we score for OB (1+2+16+32+64) - $flag_2 = 179; # Read 2 is on the - strand (1+2+16+32+128) + unless($old_flag){ + $flag_1 = 83; # PH: Read 1 is on the - strand, mapped in proper pair and Read 1 is reversed (1+2+16+64) + $flag_2 = 163; # PH: read 2 is on the - strand, mapped in proper pair and Read 1 is reversed (1+2+32+128) + } + else{ + $flag_1 = 115; # Read 1 is on the + strand, we score for OB (1+2+16+32+64) + $flag_2 = 179; # Read 2 is on the - strand (1+2+16+32+128) + } } elsif ($index == 2){ # CTOT - $flag_1 = 67; # Read 1 is on the - strand (CTOT) strand, but we score it for OT (1+2+64) - $flag_2 = 131; # Read 2 is on the + strand, score it for OT (1+2+128) + unless ($old_flag){ + $flag_1 = 99; # PH: Read 1 is on the + strand and Read 2 is reversed (1+2+32+64) + $flag_2 = 147; # PH: Read 2 is on - strand but informative for the OT (1+2+16+128) + } + else{ + $flag_1 = 67; # Read 1 is on the - strand (CTOT) strand, but we score it for OT (1+2+64) + $flag_2 = 131; # Read 2 is on the + strand, score it for OT (1+2+128) + } } elsif ($index == 3){ # OB - $flag_1 = 115; # Read 1 is on the - strand, we score for OB (1+2+16+32+64) - $flag_2 = 179; # Read 2 is on the + strand (1+2+16+32+128) + unless ($old_flag){ + $flag_1 = 83; # PH: Read 1 is on the - strand, mapped in proper pair and Read 1 is reversed (1+2+16+64) + $flag_2 = 163; # PH: read 2 is on the - strand, mapped in proper pair and Read 1 is reversed (1+2+32+128) + } + else{ + $flag_1 = 115; # Read 1 is on the - strand, we score for OB (1+2+16+32+64) + $flag_2 = 179; # Read 2 is on the + strand (1+2+16+32+128) + } } ##### @@ -6846,11 +7258,12 @@ # or # # -------------------------> read 1 - # <----------- read 2 read 2 contained within read 1 - - # start and end of read 2 are fully contained within read 1 - $tlen_1 = 0; # Set as 0 when the information is unavailable - $tlen_2 = 0; # Set as 0 when the information is unavailable + # <------------------------ read 2 read 2 contained within read 1 + + # start and end of read 2 are fully contained within read 1, using the length of read 1 for the TLEN variable + $tlen_1 = $end_read_1 - $start_read_1 + 1; # Set to length of read 1 Leftmost read has a + sign, + $tlen_2 = ($end_read_1 - $start_read_1 + 1) * -1; # Set to length of read 1 Rightmost read has a - sign. well this is debatable. Changed this + ### as a request by frozenlyse on SeqAnswers on 24 July 2013 } } @@ -6882,12 +7295,13 @@ # or # # -------------------------> read 2 - # <----------- read 1 read 1 contained within read 2 + # <------------------------ read 1 read 1 contained within read 2 - # start and end of read 1 are fully contained within read 2 - $tlen_1 = 0; # Set as 0 when the information is unavailable - $tlen_2 = 0; # Set as 0 when the information is unavailable - } + # start and end of read 1 are fully contained within read 2, using the length of read 2 for the TLEN variable + $tlen_1 = ($end_read_2 - $start_read_2 + 1) * -1; # Set to length of read 2 Shorter read receives a - sign, + $tlen_2 = $end_read_2 - $start_read_2 + 1; # Set to length of read 2 Longer read receives a +. Well this is debatable. Changed this + ### as a request by frozenlyse on SeqAnswers on 24 July 2013 + } } } @@ -7353,6 +7767,27 @@ --samtools_path The path to your Samtools installation, e.g. /home/user/samtools/. Does not need to be specified explicitly if Samtools is in the PATH already. +--prefix <prefix> Prefixes <prefix> to the output filenames. Trailing dots will be replaced by a single one. For + example, '--prefix test' with 'file.fq' would result in the output file 'test.file.fq_bismark.sam' etc. + +--old_flag Only in paired-end SAM mode, uses the FLAG values used by Bismark v0.8.2 and before. In addition, + this options appends /1 and /2 to the read IDs for reads 1 and 2 relative to the input file. Since + both the appended read IDs and custom FLAG values may cause problems with some downstream tools + such as Picard, new defaults were implemented as of version 0.8.3. + + + default old_flag + =================== =================== + Read 1 Read 2 Read 1 Read 2 + + OT: 99 147 67 131 + + OB: 83 163 115 179 + + CTOT: 99 147 67 131 + + CTOB: 83 163 115 179 + Other: @@ -7518,7 +7953,7 @@ Each read of paired-end alignments is written out in a separate line in the above format. -Last edited on 10 May 2013. +Last edited on 07 October 2013. HOW_TO }
--- a/bismark_bowtie2_wrapper.xml Wed Aug 21 05:19:54 2013 -0400 +++ b/bismark_bowtie2_wrapper.xml Mon Apr 14 16:43:14 2014 -0400 @@ -1,5 +1,5 @@ -<tool id="bismark_bowtie2" name="Bismark" version="0.7.12.1"> - <!-- Wrapper compatible with Bismark version 0.7.11 --> +<tool id="bismark_bowtie2" name="Bismark" version="0.10.1"> + <!-- Wrapper compatible with Bismark version 0.10 --> <description>bisulfite mapper (bowtie2)</description> <!--<version_command>bismark version</version_command>--> <requirements> @@ -12,7 +12,7 @@ bismark_wrapper.py ## Change this to accommodate the number of threads you have available. - --num-threads 24 + --num-threads "\${GALAXY_SLOTS:-24}" --bismark_path \$SCRIPT_PATH @@ -71,6 +71,9 @@ -X $singlePaired.maxInsert #end if + #if $sort_bam: + --sort-bam + #end if ## for now hardcode the value for the required memory per thread in --best mode --chunkmbs 512 @@ -176,6 +179,7 @@ </when> </conditional> + <param name="sort_bam" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Sort BAM file by chromosomal position (not compatibile with methylation extractor)"/> <conditional name="params"> <param name="settingsType" type="select" label="Bismark settings to use" help="You can use the default settings or set custom values for any of Bismark's parameters."> @@ -342,8 +346,6 @@ </conditional> </actions> </data> - - </outputs> <tests>
--- a/bismark_bowtie_wrapper.xml Wed Aug 21 05:19:54 2013 -0400 +++ b/bismark_bowtie_wrapper.xml Mon Apr 14 16:43:14 2014 -0400 @@ -1,5 +1,5 @@ -<tool id="bismark_bowtie" name="Bismark" version="0.7.12.1"> - <!-- Wrapper compatible with Bismark version 0.7.11 --> +<tool id="bismark_bowtie" name="Bismark" version="0.10.0"> + <!-- Wrapper compatible with Bismark version 0.10 --> <description>bisulfite mapper (bowtie)</description> <!--<version_command>bismark version</version_command>--> <requirements>
--- a/bismark_genome_preparation Wed Aug 21 05:19:54 2013 -0400 +++ b/bismark_genome_preparation Mon Apr 14 16:43:14 2014 -0400 @@ -33,7 +33,7 @@ my $single_fasta; my $bowtie2; -my $bismark_version = 'v0.7.12'; +my $bismark_version = 'v0.10.0'; GetOptions ('verbose' => \$verbose, 'help' => \$help, @@ -44,10 +44,6 @@ 'bowtie2' => \$bowtie2, ); -my $genome_folder = shift @ARGV; # mandatory -my $CT_dir; -my $GA_dir; - if ($help or $man){ print_helpfile(); exit; @@ -66,6 +62,31 @@ exit; } +my $genome_folder = shift @ARGV; # mandatory + +# Ensuring a genome folder has been specified +if ($genome_folder){ + unless ($genome_folder =~ /\/$/){ + $genome_folder =~ s/$/\//; + } + $verbose and print "Path to genome folder specified as: $genome_folder\n"; + chdir $genome_folder or die "Could't move to directory $genome_folder. Make sure the directory exists! $!"; + + # making the genome folder path abolsolute so it won't break if the path was specified relative + $genome_folder = getcwd; + unless ($genome_folder =~ /\/$/){ + $genome_folder =~ s/$/\//; + } +} +else{ + die "Please specify a genome folder to be used for bisulfite conversion\n\n"; +} + + +my $CT_dir; +my $GA_dir; + + if ($single_fasta){ print "Writing individual genomes out into single-entry fasta files (one per chromosome)\n\n"; $multi_fasta = 0; @@ -309,41 +330,6 @@ $verbose and print "Bismark Genome Preparation - Step I: Preparing folders\n\n"; - # Ensuring a genome folder has been specified - if ($genome_folder){ - unless ($genome_folder =~ /\/$/){ - $genome_folder =~ s/$/\//; - } - $verbose and print "Path to genome folder specified: $genome_folder\n"; - chdir $genome_folder or die "Could't move to directory $genome_folder. Make sure the directory exists! $!"; - - # making the genome folder path abolsolute so it won't break if the path was specified relative - $genome_folder = getcwd; - unless ($genome_folder =~ /\/$/){ - $genome_folder =~ s/$/\//; - } - } - - else{ - $verbose and print "Genome folder was not provided as argument "; - while (1){ - print "Please specify a genome folder to be bisulfite converted:\n"; - $genome_folder = <STDIN>; - chomp $genome_folder; - - # adding a trailing slash unless already present - unless ($genome_folder =~ /\/$/){ - $genome_folder =~ s/$/\//; - } - if (chdir $genome_folder){ - last; - } - else{ - warn "Could't move to directory $genome_folder! $!"; - } - } - } - if ($path_to_bowtie){ unless ($path_to_bowtie =~ /\/$/){ $path_to_bowtie =~ s/$/\//; @@ -376,7 +362,7 @@ die "The specified genome folder $genome_folder does not contain any sequence files in FastA format (with .fa or .fasta file extensions\n"; } - warn "Bisulfite Genome Indexer version $bismark_version (last modified 17 Nov 2011)\n\n"; + warn "Bisulfite Genome Indexer version $bismark_version (last modified 19 Sept 2013)\n\n"; sleep (3); # creating a directory inside the genome folder to store the bisfulfite genomes unless it already exists @@ -386,27 +372,10 @@ $verbose and print "Created Bisulfite Genome folder $bisulfite_dir\n"; } else{ - while (1){ - print "\nA directory called $bisulfite_dir already exists. Bisulfite converted sequences and/or already existing Bowtie (1 or 2) indexes might be overwritten!\nDo you want to continue anyway?\t"; - my $proceed = <STDIN>; - chomp $proceed; - if ($proceed =~ /^y/i ){ - last; - } - elsif ($proceed =~ /^n/i){ - die "Terminated by user\n\n"; - } - } + print "\nA directory called $bisulfite_dir already exists. Bisulfite converted sequences and/or already existing Bowtie (1 or 2) indices will be overwritten!\n\n"; + sleep(5); } - ### as of version 0.6.0 the Bismark indexer will no longer delete the Bisulfite_Genome directory if it was present already, since it could store the Bowtie 1 or 2 indexes already - # removing any existing files and subfolders in the bisulfite directory (the specified directory won't be deleted) - # rmtree($bisulfite_dir, {verbose => 1,keep_root => 1}); - # unless (-d $bisulfite_dir){ # had to add this after changing remove_tree to rmtree // suggested by Samantha Cooper @ Illumina - # mkdir $bisulfite_dir or die "Unable to create directory $bisulfite_dir $!\n"; - # } - # } - chdir $bisulfite_dir or die "Unable to move to $bisulfite_dir\n"; $CT_dir = "${bisulfite_dir}CT_conversion/"; $GA_dir = "${bisulfite_dir}GA_conversion/"; @@ -440,15 +409,14 @@ bisulfite genome will have all Cs converted to Ts (C->T), and the other one will have all Gs converted to As (G->A). Both bisulfite genomes will be stored in subfolders within the reference genome folder. Once the bisulfite conversion has been completed the program will fork and launch -two simultaneous instances of the bowtie 1 or 2 indexer (bowtie-build or bowtie2-build). Be aware +two simultaneous instances of the Bowtie 1 or 2 indexer (bowtie-build or bowtie2-build). Be aware that the indexing process can take up to several hours; this will mainly depend on genome size and system resources. - The following is a brief description of command line options and arguments to control the -Bismark Genome Preparation script: +Bismark Genome Preparation: USAGE: bismark_genome_preparation [options] <arguments> @@ -462,8 +430,9 @@ --verbose Print verbose output for more details or debugging. ---path_to_bowtie The full path to the Bowtie 1 or Bowtie 2 installation on your system.If - the path </../../> is not provided as an option you will be prompted for it. +--path_to_bowtie </../> The full path to the Bowtie 1 or Bowtie 2 installation on your system + (depending on which aligner/indexer you intend to use). Unless this path + is specified it is assumed that Bowtie is in the PATH. --bowtie2 This will create bisulfite indexes for Bowtie 2. (Default: Bowtie 1). @@ -481,12 +450,10 @@ ARGUMENTS: <path_to_genome_folder> The path to the folder containing the genome to be bisulfite converted. - At the current time Bismark Genome Preparation expects one or more fastA - files in the folder (with the file extension: .fa or .fasta). If the path - is not provided as an argument you will be prompted for it. + The Bismark Genome Preparation expects one or more fastA files in the folder + (with the file extension: .fa or .fasta). Specifying this path is mandatory. - -This script was last modified on 18 Nov 2011. +This script was last modified on 19 Sept 2013. HOW_TO }
--- a/bismark_methylation_extractor Wed Aug 21 05:19:54 2013 -0400 +++ b/bismark_methylation_extractor Mon Apr 14 16:43:14 2014 -0400 @@ -8,6 +8,7 @@ use FindBin qw($Bin); use lib "$Bin/../lib"; + ## This program is Copyright (C) 2010-13, Felix Krueger (felix.krueger@babraham.ac.uk) ## This program is free software: you can redistribute it and/or modify @@ -29,8 +30,8 @@ my %fhs; -my $version = 'v0.7.11'; -my ($ignore,$genomic_fasta,$single,$paired,$full,$report,$no_overlap,$merge_non_CpG,$vanilla,$output_dir,$no_header,$bedGraph,$remove,$coverage_threshold,$counts,$cytosine_report,$genome_folder,$zero,$CpG_only,$CX_context,$split_by_chromosome,$sort_size,$samtools_path,$gzip) = process_commandline(); +my $version = 'v0.10.1'; +my ($ignore,$genomic_fasta,$single,$paired,$full,$report,$no_overlap,$merge_non_CpG,$vanilla,$output_dir,$no_header,$bedGraph,$remove,$coverage_threshold,$counts,$cytosine_report,$genome_folder,$zero,$CpG_only,$CX_context,$split_by_chromosome,$sort_size,$samtools_path,$gzip,$ignore_r2,$mbias_only,$gazillion,$ample_mem) = process_commandline(); ### only needed for bedGraph output @@ -41,6 +42,9 @@ ### only needed for genome-wide cytosine methylation report my %chromosomes; +my %mbias_1; +my %mbias_2; + ############################################################################################## ### Summarising Run Parameters ############################################################################################## @@ -67,9 +71,20 @@ } } -if ($ignore){ - warn "First $ignore bases will be disregarded when processing the methylation call string\n"; +if ($single){ + if ($ignore){ + warn "First $ignore bp will be disregarded when processing the methylation call string\n"; + } } +else{ ## paired-end + if ($ignore){ + warn "First $ignore bp will be disregarded when processing the methylation call string of Read 1\n"; + } + if ($ignore_r2){ + warn "First $ignore_r2 bp will be disregarded when processing the methylation call string of Read 2\n"; + } +} + if ($full){ warn "Strand-specific outputs will be skipped. Separate output files for cytosines in CpG, CHG and CHH context will be generated\n"; @@ -95,7 +110,7 @@ warn '='x63,"\n"; if ($counts){ - warn "Generating additional output in bedGraph format including methylating counts (output format: <Chromosome> <Start Position> <End Position> <Methylation Percentage> <count methylated> <count non-methylated>)\n"; + warn "Generating additional output in bedGraph and coverage format\nbedGraph format:\t<Chromosome> <Start Position> <End Position> <Methylation Percentage>\ncoverage format:\t<Chromosome> <Start Position> <End Position> <Methylation Percentage> <count methylated> <count non-methylated>\n\n"; } else{ warn "Generating additional sorted output in bedGraph format (output format: <Chromosome> <Start Position> <End Position> <Methylation Percentage>)\n"; @@ -115,7 +130,10 @@ warn "White spaces in read ID names will be removed prior to sorting\n"; } - if (defined $sort_size){ + if ($ample_mem){ + warn "Sorting chromosomal postions for the bedGraph step using arrays instead of using UNIX sort\n"; + } + elsif (defined $sort_size){ warn "The bedGraph UNIX sort command will use the following memory setting:\t'$sort_size'. Temporary directory used for sorting is the output directory\n"; } else{ @@ -186,9 +204,20 @@ total_unmethylated_CpG_count => 0, sequences_count => 0, ); + @sorting_files = (); @bedfiles = (); + %mbias_1 = (); + %mbias_2 = (); + + ### performing a quick check to see if a paired-end SAM file has been sorted by positions which does interfere with the logic used by the extractor + unless ($vanilla){ + if ($paired){ + test_positional_sorting($filename); + } + } + process_Bismark_results_file($filename); ### Closing all filehandles so that the Bismark methylation extractor output doesn't get truncated due to buffering issues @@ -196,13 +225,18 @@ if ($fh =~ /^[1230]$/) { foreach my $context (keys %{$fhs{$fh}}) { close $fhs{$fh}->{$context} or die $!; - } - } else { + } + else{ close $fhs{$fh} or die $!; } } + ### printing out all M-Bias data + produce_mbias_plots ($filename); + + delete_unused_files(); + if ($bedGraph){ my $out = (split (/\//,$filename))[-1]; # extracting the filename if a full path was specified @@ -212,8 +246,6 @@ $out =~ s/txt$//; $out =~ s/$/bedGraph/; - - my $bedGraph_output = $out; my @args; @@ -226,10 +258,18 @@ if ($no_header){ push @args, '--no_header'; } - if ($counts){ - push @args, "--counts"; + if ($gazillion){ + push @args, '--gazillion'; + } + if ($ample_mem){ + push @args, '--ample_memory'; } + + # if ($counts){ + # push @args, "--counts"; + # } + push @args, "--buffer_size $sort_size"; push @args, "--cutoff $coverage_threshold"; push @args, "--output $bedGraph_output"; @@ -254,6 +294,7 @@ ### genome-wide cytosine methylation report requires bedGraph processing anyway if ($cytosine_report){ + @args = (); # resetting @args my $cytosine_out = $out; $cytosine_out =~ s/bedGraph$//; @@ -280,21 +321,343 @@ push @args, '--split_by_chromosome'; } - push @args, $bedGraph_output; # this will be the infile - - system ("$Bin/bedGraph2cytosine @args"); + my $coverage_output = $bedGraph_output; + $coverage_output =~ s/bedGraph$/bismark.cov/; + + push @args, $output_dir . $coverage_output; # this will be the infile + + system ("$Bin/coverage2cytosine @args"); # generate_genome_wide_cytosine_report($bedGraph_output,$cytosine_out); warn "\n\nFinished generating genome-wide cytosine report\n\n"; } } } +sub delete_unused_files{ + + warn "Deleting unused files ...\n\n"; sleep(1); + + my $index = 0; + + while ($index <= $#sorting_files){ + if ($sorting_files[$index] =~ /gz$/){ + open (USED,"zcat $sorting_files[$index] |") or die "Failed to read from methylation extractor output file $sorting_files[$index]: $!\n"; + } + else{ + open (USED,$sorting_files[$index]) or die "Failed to read from methylation extractor output file $sorting_files[$index]: $!\n"; + } + + my $used = 0; + + while (<USED>){ + next if (/^Bismark/); + if ($_){ + $used = 1; + last; + } + } + + if ($used){ + warn "$sorting_files[$index] contains data ->\tkept\n"; + ++$index; + } + else{ + + my $delete = unlink $sorting_files[$index]; + + if ($delete){ + warn "$sorting_files[$index] was empty ->\tdeleted\n"; + } + else{ + warn "$sorting_files[$index] was empty, however deletion was unsuccessful: $!\n" + } + + ### we also need to remove the element from @sorting_files + splice @sorting_files, $index, 1; + } + } + warn "\n\n"; ## can't close the piped filehandles at this point because it will die (unfortunately) +} + +sub produce_mbias_plots{ + + my $filename = shift; + + my $mbias = (split (/\//,$filename))[-1]; # extracting the filename if a full path was specified + $mbias =~ s/gz$//; + $mbias =~ s/sam$//; + $mbias =~ s/bam$//; + $mbias =~ s/txt$//; + my $mbias_graph_1 = my $mbias_graph_2 = $mbias; + $mbias_graph_1 = $output_dir . $mbias_graph_1 . 'M-bias_R1.png'; + $mbias_graph_2 = $output_dir . $mbias_graph_2 . 'M-bias_R2.png'; + + $mbias =~ s/$/M-bias.txt/; + + open (MBIAS,'>',"$output_dir$mbias") or die "Failed to open file for the M-bias data\n\n"; + + # determining maximum read length + my $max_length_1 = 0; + my $max_length_2 = 0; + + foreach my $context (keys %mbias_1){ + foreach my $pos (sort {$a<=>$b} keys %{$mbias_1{$context}}){ + $max_length_1 = $pos unless ($max_length_1 >= $pos); + } + } + if ($paired){ + foreach my $context (keys %mbias_2){ + foreach my $pos (sort {$a<=>$b} keys %{$mbias_2{$context}}){ + $max_length_2 = $pos unless ($max_length_2 >= $pos); + } + } + } + + if ($single){ + warn "Determining maximum read length for M-Bias plot\n"; + warn "Maximum read length of Read 1: $max_length_1\n\n"; + } + else{ + warn "Determining maximum read lengths for M-Bias plots\n"; + warn "Maximum read length of Read 1: $max_length_1\n"; + warn "Maximum read length of Read 2: $max_length_2\n\n"; + } + # sleep(3); + + my @mbias_read1; + my @mbias_read2; + + #Check whether the module GD::Graph:lines is installed + my $gd_graph_installed = 0; + eval{ + require GD::Graph::lines; + GD::Graph::lines->import(); + }; + + unless($@) { # syntax or routine error variable, set if something goes wron in the last eval{ require ...} + $gd_graph_installed = 1; + + #Check whether the module GD::Graph::colour is installed + eval{ + require GD::Graph::colour; + GD::Graph::colour->import(qw(:colours :lists :files :convert)); + }; + + if ($@) { + warn "Perl module GD::Graph::colour not found, skipping drawing M-bias plots (only writing out M-bias plot table)\n"; + sleep(2); + $gd_graph_installed = 0; + } + + + } + else{ + warn "Perl module GD::Graph::lines is not installed, skipping drawing M-bias plots (only writing out M-bias plot table)\n"; + sleep(2); + } + + + my $graph_title; + my $graph1; + my $graph2; + + if ( $gd_graph_installed){ + $graph1 = GD::Graph::lines->new(800,600); + if ($paired){ + $graph2 = GD::Graph::lines->new(800,600); + } + } + + foreach my $context (qw(CpG CHG CHH)){ + @{$mbias_read1[0]} = (); + + if ($paired){ + print MBIAS "$context context (R1)\n================\n"; + $graph_title = 'M-bias (Read 1)'; + } + else{ + print MBIAS "$context context\n===========\n"; + $graph_title = 'M-bias'; + } + print MBIAS "position\tcount methylated\tcount unmethylated\t% methylation\tcoverage\n"; + + foreach my $pos (1..$max_length_1){ + + unless (defined $mbias_1{$context}->{$pos}->{meth}){ + $mbias_1{$context}->{$pos}->{meth} = 0; + } + unless (defined $mbias_1{$context}->{$pos}->{un}){ + $mbias_1{$context}->{$pos}->{un} = 0; + } + + my $percent = ''; + if (($mbias_1{$context}->{$pos}->{meth} + $mbias_1{$context}->{$pos}->{un}) > 0){ + $percent = sprintf("%.2f",$mbias_1{$context}->{$pos}->{meth} * 100/ ( $mbias_1{$context}->{$pos}->{meth} + $mbias_1{$context}->{$pos}->{un}) ); + } + my $coverage = $mbias_1{$context}->{$pos}->{un} + $mbias_1{$context}->{$pos}->{meth}; + + print MBIAS "$pos\t$mbias_1{$context}->{$pos}->{meth}\t$mbias_1{$context}->{$pos}->{un}\t$percent\t$coverage\n"; + push @{$mbias_read1[0]},$pos; + + if ($context eq 'CpG'){ + push @{$mbias_read1[1]},$percent; + push @{$mbias_read1[4]},$coverage; + } + elsif ($context eq 'CHG'){ + push @{$mbias_read1[2]},$percent; + push @{$mbias_read1[5]},$coverage; + } + elsif ($context eq 'CHH'){ + push @{$mbias_read1[3]},$percent; + push @{$mbias_read1[6]},$coverage; + } + } + print MBIAS "\n"; + } + + if ( $gd_graph_installed){ + + add_colour(nice_blue => [31,120,180]); + add_colour(nice_orange => [255,127,0]); + add_colour(nice_green => [51,160,44]); + add_colour(pale_blue => [153,206,227]); + add_colour(pale_orange => [253,204,138]); + add_colour(pale_green => [191,230,207]); + + $graph1->set( + x_label => 'position (bp)', + y1_label => '% methylation', + y2_label => '# methylation calls', + title => $graph_title, + line_width => 2, + x_max_value => $max_length_1, + x_min_value => 0, + y_tick_number => 10, + y_label_skip => 2, + y1_max_value => 100, + y1_min_value => 0, + y_label_skip => 2, + y2_min_value => 0, + x_label_skip => 5, + x_label_position => 0.5, + x_tick_offset => -1, + bgclr => 'white', + transparent => 0, + two_axes => 1, + use_axis => [1,1,1,2,2,2], + legend_placement => 'RC', + legend_spacing => 6, + legend_marker_width => 24, + legend_marker_height => 18, + dclrs => [ qw(nice_blue nice_orange nice_green pale_blue pale_orange pale_green)], + ) or die $graph1->error; + + $graph1->set_legend('CpG methylation','CHG methylation','CHH methylation','CpG total calls','CHG total calls','CHH total calls'); + + my $gd1 = $graph1->plot(\@mbias_read1) or die $graph1->error; + + open (MBIAS_G1,'>',$mbias_graph_1) or die "Failed to write to file for M-bias plot 1: $!\n\n"; + binmode MBIAS_G1; + print MBIAS_G1 $gd1->png; + } + + if ($paired){ + + foreach my $context (qw(CpG CHG CHH)){ + @{$mbias_read2[0]} = (); + + print MBIAS "$context context (R2)\n================\n"; + print MBIAS "position\tcount methylated\tcount unmethylated\t% methylation\tcoverage\n"; + foreach my $pos (1..$max_length_2){ + + unless (defined $mbias_2{$context}->{$pos}->{meth}){ + $mbias_2{$context}->{$pos}->{meth} = 0; + } + unless (defined $mbias_2{$context}->{$pos}->{un}){ + $mbias_2{$context}->{$pos}->{un} = 0; + } + + my $percent = ''; + if (($mbias_2{$context}->{$pos}->{meth} + $mbias_2{$context}->{$pos}->{un}) > 0){ + $percent = sprintf("%.2f",$mbias_2{$context}->{$pos}->{meth} * 100/ ($mbias_2{$context}->{$pos}->{meth} + $mbias_2{$context}->{$pos}->{un}) ); + } + my $coverage = $mbias_2{$context}->{$pos}->{un} + $mbias_2{$context}->{$pos}->{meth}; + + print MBIAS "$pos\t$mbias_2{$context}->{$pos}->{meth}\t$mbias_2{$context}->{$pos}->{un}\t$percent\t$coverage\n"; + + push @{$mbias_read2[0]},$pos; + + if ($context eq 'CpG'){ + push @{$mbias_read2[1]},$percent; + push @{$mbias_read2[4]},$coverage; + } + elsif ($context eq 'CHG'){ + push @{$mbias_read2[2]},$percent; + push @{$mbias_read2[5]},$coverage; + } + elsif ($context eq 'CHH'){ + push @{$mbias_read2[3]},$percent; + push @{$mbias_read2[6]},$coverage; + } + } + print MBIAS "\n"; + } + + if ( $gd_graph_installed){ + + add_colour(nice_blue => [31,120,180]); + add_colour(nice_orange => [255,127,0]); + add_colour(nice_green => [51,160,44]); + add_colour(pale_blue => [153,206,227]); + add_colour(pale_orange => [253,204,138]); + add_colour(pale_green => [191,230,207]); + + $graph2->set( + x_label => 'position (bp)', + line_width => 2, + x_max_value => $max_length_1, + x_min_value => 0, + y_tick_number => 10, + y_label_skip => 2, + y1_max_value => 100, + y1_min_value => 0, + y_label_skip => 2, + y2_min_value => 0, + x_label_skip => 5, + x_label_position => 0.5, + x_tick_offset => -1, + bgclr => 'white', + transparent => 0, + two_axes => 1, + use_axis => [1,1,1,2,2,2], + legend_placement => 'RC', + legend_spacing => 6, + legend_marker_width => 24, + legend_marker_height => 18, + dclrs => [ qw(nice_blue nice_orange nice_green pale_blue pale_orange pale_green)], + x_label => 'position (bp)', + y1_label => '% methylation', + y2_label => '# calls', + title => 'M-bias (Read 2)', + ) or die $graph2->error; + + $graph2->set_legend('CpG methylation','CHG methylation','CHH methylation','CpG total calls','CHG total calls','CHH total calls'); + my $gd2 = $graph2->plot(\@mbias_read2) or die $graph2->error; + + open (MBIAS_G2,'>',$mbias_graph_2) or die "Failed to write to file for M-bias plot 2: $!\n\n"; + binmode MBIAS_G2; + print MBIAS_G2 $gd2->png; + + } + } +} sub process_commandline{ my $help; my $single_end; my $paired_end; my $ignore; + my $ignore_r2; my $genomic_fasta; my $full; my $report; @@ -317,33 +680,40 @@ my $sort_size; my $samtools_path; my $gzip; - - my $command_line = GetOptions ('help|man' => \$help, - 'p|paired-end' => \$paired_end, - 's|single-end' => \$single_end, - 'fasta' => \$genomic_fasta, - 'ignore=i' => \$ignore, - 'comprehensive' => \$full, - 'report' => \$report, - 'version' => \$extractor_version, - 'no_overlap' => \$no_overlap, - 'merge_non_CpG' => \$merge_non_CpG, - 'vanilla' => \$vanilla, - 'o|output=s' => \$output_dir, - 'no_header' => \$no_header, - 'bedGraph' => \$bedGraph, - "cutoff=i" => \$coverage_threshold, - "remove_spaces" => \$remove, - "counts" => \$counts, - "cytosine_report" => \$cytosine_report, - 'g|genome_folder=s' => \$genome_folder, - "zero_based" => \$zero, - "CX|CX_context" => \$CX_context, - "split_by_chromosome" => \$split_by_chromosome, - "buffer_size=s" => \$sort_size, - 'samtools_path=s' => \$samtools_path, - "gzip" => \$gzip, - ); + my $mbias_only; + my $gazillion; + my $ample_mem; + + my $command_line = GetOptions ('help|man' => \$help, + 'p|paired-end' => \$paired_end, + 's|single-end' => \$single_end, + 'fasta' => \$genomic_fasta, + 'ignore=i' => \$ignore, + 'ignore_r2=i' => \$ignore_r2, + 'comprehensive' => \$full, + 'report' => \$report, + 'version' => \$extractor_version, + 'no_overlap' => \$no_overlap, + 'merge_non_CpG' => \$merge_non_CpG, + 'vanilla' => \$vanilla, + 'o|output=s' => \$output_dir, + 'no_header' => \$no_header, + 'bedGraph' => \$bedGraph, + "cutoff=i" => \$coverage_threshold, + "remove_spaces" => \$remove, + "counts" => \$counts, + "cytosine_report" => \$cytosine_report, + 'g|genome_folder=s' => \$genome_folder, + "zero_based" => \$zero, + "CX|CX_context" => \$CX_context, + "split_by_chromosome" => \$split_by_chromosome, + "buffer_size=s" => \$sort_size, + 'samtools_path=s' => \$samtools_path, + "gzip" => \$gzip, + "mbias_only" => \$mbias_only, + "gazillion|scaffolds" => \$gazillion, + "ample_memory" => \$ample_mem, + ); ### EXIT ON ERROR if there were errors with any of the supplied options unless ($command_line){ @@ -380,10 +750,23 @@ warn "\n *** Bismark methylation extractor version $version ***\n\n"; - ### IGNORING <INT> bases at the start of the read when processing the methylation call string - unless ($ignore){ - $ignore = 0; + ### M-BIAS ONLY + if ($mbias_only){ + if ($bedGraph){ + die "Option '--mbias_only' skips all sorts of methylation extraction, including the bedGraph generation. Please respecify!\n"; + } + if ($cytosine_report){ + die "Option '--mbias_only' skips all sorts of methylation extraction, including the genome-wide cytosine methylation report generation. Please respecify!\n"; + } + if ($merge_non_CpG){ + warn "Option '--mbias_only' skips all sorts of methylation extraction, thus '--merge' won't have any effect\n"; + } + if ($full){ + warn "Option '--mbias_only' skips all sorts of methylation extraction, thus '--comprehensive' won't have any effect\n"; + } + sleep(3); } + ### PRINT A REPORT unless ($report){ $report = 0; @@ -416,9 +799,65 @@ $single_end = 0; ### PAIRED-END ALIGNMENTS } else{ - die "Please specify whether the supplied file(s) are in Bismark single-end or paired-end format\n\n"; + + ### we will try to determine whether the input file was a single-end or paired-end sequencing run from the SAM header + + if ($vanilla){ + die "Please specify whether the supplied file(s) are in Bismark single-end or paired-end format with '-s' or '-p'\n\n"; + } + else{ # SAM/BAM format + + my $file = $filenames[0]; + warn "Trying to determine the type of mapping from the SAM header line of file $file\n"; sleep(1); + + ### if the user did not specify whether the alignment file was single-end or paired-end we are trying to get this information from the @PG header line in the SAM/BAM file + if ($file =~ /\.gz$/){ + open (DETERMINE,"zcat $file |") or die "Unable to read from gzipped file $file: $!\n"; + } + elsif ($file =~ /\.bam$/ || `file -b $file` =~ /^gzip/){ + open (DETERMINE,"samtools view -h $file |") or die "Unable to read from BAM file $file: $!\n"; + } + else{ + open (DETERMINE,$file) or die "Unable to read from $file: $!\n"; + } + + while (<DETERMINE>){ + last unless (/^\@/); + if ($_ =~ /^\@PG/){ + # warn "found the \@PG line:\n"; + # warn "$_"; + + if ($_ =~ /-1/ and $_ =~ /-2/){ + warn "Treating file(s) as paired-end data (as extracted from \@PG line)\n\n"; sleep(1); + $paired_end = 1; + $single_end = 0; + } + else{ + warn "Treating file(s) as single-end data (as extracted from \@PG line)\n\n"; sleep(1); + $paired_end = 0; + $single_end = 1; + } + } + } + + close DETERMINE or warn $!; + + } } + ### IGNORING <INT> bases at the start of the read when processing the methylation call string + unless ($ignore){ + $ignore = 0; + } + + if (defined $ignore_r2){ + die "You can only specify --ignore_r2 for paired-end result files\n" unless ($paired_end); + } + else{ + $ignore_r2 = 0; + } + + ### NO OVERLAP if ($no_overlap){ die "The option '--no_overlap' can only be specified for paired-end input!\n" unless ($paired_end); @@ -474,7 +913,7 @@ } unless ($counts){ - $counts = 0; + $counts = 1; # counts will always be set } if ($cytosine_report){ @@ -494,7 +933,7 @@ $bedGraph = 1; } unless ($counts){ - warn "Setting the option '--counts' since this is required for the genome-wide cytosine report\n"; + # warn "Setting the option '--counts' since this is required for the genome-wide cytosine report\n"; $counts = 1; } warn "\n"; @@ -536,7 +975,80 @@ $samtools_path = ''; } - return ($ignore,$genomic_fasta,$single_end,$paired_end,$full,$report,$no_overlap,$merge_non_CpG,$vanilla,$output_dir,$no_header,$bedGraph,$remove,$coverage_threshold,$counts,$cytosine_report,$genome_folder,$zero,$CpG_only,$CX_context,$split_by_chromosome,$sort_size,$samtools_path,$gzip); + + if ($gazillion){ + if ($ample_mem){ + die "You can't currently select '--ample_mem' together with '--gazillion'. Make your pick!\n\n"; + } + } + + return ($ignore,$genomic_fasta,$single_end,$paired_end,$full,$report,$no_overlap,$merge_non_CpG,$vanilla,$output_dir,$no_header,$bedGraph,$remove,$coverage_threshold,$counts,$cytosine_report,$genome_folder,$zero,$CpG_only,$CX_context,$split_by_chromosome,$sort_size,$samtools_path,$gzip,$ignore_r2,$mbias_only,$gazillion,$ample_mem); +} + + +sub test_positional_sorting{ + + my $filename = shift; + + print "\nNow testing Bismark result file $filename for positional sorting (which would be bad...)\t"; + sleep(1); + + if ($filename =~ /\.gz$/) { + open (TEST,"zcat $filename |") or die "Can't open gzipped file $filename: $!\n"; + } + elsif ($filename =~ /bam$/ || `file -b $filename` =~ /^gzip/) { + if ($samtools_path){ + open (TEST,"$samtools_path view -h $filename |") or die "Can't open BAM file $filename: $!\n"; + } + else{ + die "Sorry couldn't find an installation of Samtools. Either specifiy an alternative path using the option '--samtools_path /your/path/', or use a SAM file instead\n\n"; + } + } + else { + open (TEST,$filename) or die "Can't open file $filename: $!\n"; + } + + my $count = 0; + + while (<TEST>) { + if (/^\@/) { # testing header lines if they contain the @SO flag (for being sorted) + if (/^\@SO/) { + die "SAM/BAM header line '$_' indicates that the Bismark aligment file has been sorted by chromosomal positions which is is incompatible with correct methylation extraction. Please use an unsorted file instead\n\n"; + } + next; + } + $count++; + + last if ($count > 100000); # else we test the first 100000 sequences if they start with the same read ID + + my ($id_1) = (split (/\t/)); + + ### reading the next line which should be read 2 + $_ = <TEST>; + my ($id_2) = (split (/\t/)); + last unless ($id_2); + ++$count; + + if ($id_1 eq $id_2){ + ### ids are the same + next; + } + else{ ### in previous versions of Bismark we appended /1 and /2 to the read IDs for easier eyeballing which read is which. These tags need to be removed first + my $id_1_trunc = $id_1; + $id_1_trunc =~ s/\/1$//; + my $id_2_trunc = $id_2; + $id_2_trunc =~ s/\/2$//; + + unless ($id_1_trunc eq $id_2_trunc){ + die "The IDs of Read 1 ($id_1) and Read 2 ($id_2) are not the same. This might be a result of sorting the paired-end SAM/BAM files by chromosomal position which is not compatible with correct methylation extraction. Please use an unsorted file instead\n\n"; + } + } + } + # close TEST or die $!; somehow fails on our cluster... + ### If it hasen't died so far then it seems the file is in the correct Bismark format (read 1 and read 2 of a pair directly following each other) + warn "...passed!\n"; + sleep(1); + } @@ -548,7 +1060,7 @@ if ($filename =~ /\.gz$/) { open (IN,"zcat $filename |") or die "Can't open gzipped file $filename: $!\n"; } - elsif ($filename =~ /bam$/) { + elsif ($filename =~ /bam$/ || `file -b $filename` =~ /^gzip/) { if ($samtools_path){ open (IN,"$samtools_path view -h $filename |") or die "Can't open BAM file $filename: $!\n"; } @@ -609,9 +1121,18 @@ print REPORT "Bismark result file: single-end (SAM format)\n"; # default } } - - if ($ignore) { - print REPORT "Ignoring first $ignore bases\n"; + if ($single){ + if ($ignore) { + print REPORT "Ignoring first $ignore bp\n"; + } + } + else{ # paired-end + if ($ignore) { + print REPORT "Ignoring first $ignore bp of Read 1\n"; + } + if ($ignore_r2){ + print REPORT "Ignoring first $ignore_r2 bp of Read 2\n"; + } } if ($full) { @@ -648,17 +1169,17 @@ if ($gzip){ $cpg_output .= '.gz'; - open ($fhs{CpG_context},"| gzip -c - > $cpg_output") or die "Failed to write to $cpg_output $! \n"; + open ($fhs{CpG_context},"| gzip -c - > $cpg_output") or die "Failed to write to $cpg_output $! \n" unless($mbias_only); } else{ - open ($fhs{CpG_context},'>',$cpg_output) or die "Failed to write to $cpg_output $! \n"; + open ($fhs{CpG_context},'>',$cpg_output) or die "Failed to write to $cpg_output $! \n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context to $cpg_output\n"; + warn "Writing result file containing methylation information for C in CpG context to $cpg_output\n" unless($mbias_only); push @sorting_files,$cpg_output; unless ($no_header) { - print {$fhs{CpG_context}} "Bismark methylation extractor version $version\n"; + print {$fhs{CpG_context}} "Bismark methylation extractor version $version\n" unless($mbias_only); } ### C in any other context than CpG @@ -670,18 +1191,18 @@ if ($gzip){ $other_c_output .= '.gz'; - open ($fhs{other_context},"| gzip -c - > $other_c_output") or die "Failed to write to $other_c_output $! \n"; + open ($fhs{other_context},"| gzip -c - > $other_c_output") or die "Failed to write to $other_c_output $! \n" unless($mbias_only); } else{ - open ($fhs{other_context},'>',$other_c_output) or die "Failed to write to $other_c_output $!\n"; + open ($fhs{other_context},'>',$other_c_output) or die "Failed to write to $other_c_output $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in any other context to $other_c_output\n"; + warn "Writing result file containing methylation information for C in any other context to $other_c_output\n" unless($mbias_only); push @sorting_files,$other_c_output; unless ($no_header) { - print {$fhs{other_context}} "Bismark methylation extractor version $version\n"; + print {$fhs{other_context}} "Bismark methylation extractor version $version\n" unless($mbias_only); } } @@ -699,17 +1220,17 @@ if ($gzip){ $cpg_ot .= '.gz'; - open ($fhs{0}->{CpG},"| gzip -c - > $cpg_ot") or die "Failed to write to $cpg_ot $!\n"; + open ($fhs{0}->{CpG},"| gzip -c - > $cpg_ot") or die "Failed to write to $cpg_ot $!\n" unless($mbias_only); } else{ - open ($fhs{0}->{CpG},'>',$cpg_ot) or die "Failed to write to $cpg_ot $!\n"; + open ($fhs{0}->{CpG},'>',$cpg_ot) or die "Failed to write to $cpg_ot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context from the original top strand to $cpg_ot\n"; + warn "Writing result file containing methylation information for C in CpG context from the original top strand to $cpg_ot\n" unless($mbias_only); push @sorting_files,$cpg_ot; unless($no_header){ - print {$fhs{0}->{CpG}} "Bismark methylation extractor version $version\n"; + print {$fhs{0}->{CpG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $cpg_ctot =~ s/^/CpG_CTOT_/; @@ -720,17 +1241,17 @@ if ($gzip){ $cpg_ctot .= '.gz'; - open ($fhs{1}->{CpG},"| gzip -c - > $cpg_ctot") or die "Failed to write to $cpg_ctot $!\n"; + open ($fhs{1}->{CpG},"| gzip -c - > $cpg_ctot") or die "Failed to write to $cpg_ctot $!\n" unless($mbias_only); } else{ - open ($fhs{1}->{CpG},'>',$cpg_ctot) or die "Failed to write to $cpg_ctot $!\n"; + open ($fhs{1}->{CpG},'>',$cpg_ctot) or die "Failed to write to $cpg_ctot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context from the complementary to original top strand to $cpg_ctot\n"; + warn "Writing result file containing methylation information for C in CpG context from the complementary to original top strand to $cpg_ctot\n" unless($mbias_only); push @sorting_files,$cpg_ctot; unless($no_header){ - print {$fhs{1}->{CpG}} "Bismark methylation extractor version $version\n"; + print {$fhs{1}->{CpG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $cpg_ctob =~ s/^/CpG_CTOB_/; @@ -741,17 +1262,17 @@ if ($gzip){ $cpg_ctob .= '.gz'; - open ($fhs{2}->{CpG},"| gzip -c - > $cpg_ctob") or die "Failed to write to $cpg_ctob $!\n"; + open ($fhs{2}->{CpG},"| gzip -c - > $cpg_ctob") or die "Failed to write to $cpg_ctob $!\n" unless($mbias_only); } else{ - open ($fhs{2}->{CpG},'>',$cpg_ctob) or die "Failed to write to $cpg_ctob $!\n"; + open ($fhs{2}->{CpG},'>',$cpg_ctob) or die "Failed to write to $cpg_ctob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context from the complementary to original bottom strand to $cpg_ctob\n"; + warn "Writing result file containing methylation information for C in CpG context from the complementary to original bottom strand to $cpg_ctob\n" unless($mbias_only); push @sorting_files,$cpg_ctob; unless($no_header){ - print {$fhs{2}->{CpG}} "Bismark methylation extractor version $version\n"; + print {$fhs{2}->{CpG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $cpg_ob =~ s/^/CpG_OB_/; @@ -762,17 +1283,17 @@ if ($gzip){ $cpg_ob .= '.gz'; - open ($fhs{3}->{CpG},"| gzip -c - > $cpg_ob") or die "Failed to write to $cpg_ob $!\n"; + open ($fhs{3}->{CpG},"| gzip -c - > $cpg_ob") or die "Failed to write to $cpg_ob $!\n" unless($mbias_only); } else{ - open ($fhs{3}->{CpG},'>',$cpg_ob) or die "Failed to write to $cpg_ob $!\n"; + open ($fhs{3}->{CpG},'>',$cpg_ob) or die "Failed to write to $cpg_ob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context from the original bottom strand to $cpg_ob\n\n"; + warn "Writing result file containing methylation information for C in CpG context from the original bottom strand to $cpg_ob\n\n" unless($mbias_only); push @sorting_files,$cpg_ob; unless($no_header){ - print {$fhs{3}->{CpG}} "Bismark methylation extractor version $version\n"; + print {$fhs{3}->{CpG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } ### For cytosines in Non-CpG (CC, CT or CA) context @@ -786,17 +1307,17 @@ if ($gzip){ $other_c_ot .= '.gz'; - open ($fhs{0}->{other_c},"| gzip -c - > $other_c_ot") or die "Failed to write to $other_c_ot $!\n"; + open ($fhs{0}->{other_c},"| gzip -c - > $other_c_ot") or die "Failed to write to $other_c_ot $!\n" unless($mbias_only); } else{ - open ($fhs{0}->{other_c},'>',$other_c_ot) or die "Failed to write to $other_c_ot $!\n"; + open ($fhs{0}->{other_c},'>',$other_c_ot) or die "Failed to write to $other_c_ot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in any other context from the original top strand to $other_c_ot\n"; + warn "Writing result file containing methylation information for C in any other context from the original top strand to $other_c_ot\n" unless($mbias_only); push @sorting_files,$other_c_ot; unless($no_header){ - print {$fhs{0}->{other_c}} "Bismark methylation extractor version $version\n"; + print {$fhs{0}->{other_c}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $other_c_ctot =~ s/^/Non_CpG_CTOT_/; @@ -807,17 +1328,17 @@ if ($gzip){ $other_c_ctot .= '.gz'; - open ($fhs{1}->{other_c},"| gzip -c - > $other_c_ctot") or die "Failed to write to $other_c_ctot $!\n"; + open ($fhs{1}->{other_c},"| gzip -c - > $other_c_ctot") or die "Failed to write to $other_c_ctot $!\n" unless($mbias_only); } else{ - open ($fhs{1}->{other_c},'>',$other_c_ctot) or die "Failed to write to $other_c_ctot $!\n"; + open ($fhs{1}->{other_c},'>',$other_c_ctot) or die "Failed to write to $other_c_ctot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in any other context from the complementary to original top strand to $other_c_ctot\n"; + warn "Writing result file containing methylation information for C in any other context from the complementary to original top strand to $other_c_ctot\n" unless($mbias_only); push @sorting_files,$other_c_ctot; unless($no_header){ - print {$fhs{1}->{other_c}} "Bismark methylation extractor version $version\n"; + print {$fhs{1}->{other_c}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $other_c_ctob =~ s/^/Non_CpG_CTOB_/; @@ -828,17 +1349,17 @@ if ($gzip){ $other_c_ctob .= '.gz'; - open ($fhs{2}->{other_c},"| gzip -c - > $other_c_ctob") or die "Failed to write to $other_c_ctob $!\n"; + open ($fhs{2}->{other_c},"| gzip -c - > $other_c_ctob") or die "Failed to write to $other_c_ctob $!\n" unless($mbias_only); } else{ - open ($fhs{2}->{other_c},'>',$other_c_ctob) or die "Failed to write to $other_c_ctob $!\n"; + open ($fhs{2}->{other_c},'>',$other_c_ctob) or die "Failed to write to $other_c_ctob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in any other context from the complementary to original bottom strand to $other_c_ctob\n"; + warn "Writing result file containing methylation information for C in any other context from the complementary to original bottom strand to $other_c_ctob\n" unless($mbias_only); push @sorting_files,$other_c_ctob; unless($no_header){ - print {$fhs{2}->{other_c}} "Bismark methylation extractor version $version\n"; + print {$fhs{2}->{other_c}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $other_c_ob =~ s/^/Non_CpG_OB_/; @@ -849,17 +1370,17 @@ if ($gzip){ $other_c_ob .= '.gz'; - open ($fhs{3}->{other_c},"| gzip -c - > $other_c_ob") or die "Failed to write to $other_c_ob $!\n"; + open ($fhs{3}->{other_c},"| gzip -c - > $other_c_ob") or die "Failed to write to $other_c_ob $!\n" unless($mbias_only); } else{ - open ($fhs{3}->{other_c},'>',$other_c_ob) or die "Failed to write to $other_c_ob $!\n"; + open ($fhs{3}->{other_c},'>',$other_c_ob) or die "Failed to write to $other_c_ob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in any other context from the original bottom strand to $other_c_ob\n\n"; + warn "Writing result file containing methylation information for C in any other context from the original bottom strand to $other_c_ob\n\n" unless($mbias_only); push @sorting_files,$other_c_ob; unless($no_header){ - print {$fhs{3}->{other_c}} "Bismark methylation extractor version $version\n"; + print {$fhs{3}->{other_c}} "Bismark methylation extractor version $version\n" unless($mbias_only); } } ### THIS SECTION IS THE DEFAULT (CpG, CHG and CHH context) @@ -876,17 +1397,17 @@ if ($gzip){ $cpg_output .= '.gz'; - open ($fhs{CpG_context},"| gzip -c - > $cpg_output") or die "Failed to write to $cpg_output $! \n"; + open ($fhs{CpG_context},"| gzip -c - > $cpg_output") or die "Failed to write to $cpg_output $! \n" unless($mbias_only); } else{ - open ($fhs{CpG_context},'>',$cpg_output) or die "Failed to write to $cpg_output $! \n"; + open ($fhs{CpG_context},'>',$cpg_output) or die "Failed to write to $cpg_output $! \n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context to $cpg_output\n"; + warn "Writing result file containing methylation information for C in CpG context to $cpg_output\n" unless($mbias_only); push @sorting_files,$cpg_output; unless($no_header){ - print {$fhs{CpG_context}} "Bismark methylation extractor version $version\n"; + print {$fhs{CpG_context}} "Bismark methylation extractor version $version\n" unless($mbias_only); } ### C in CHG context @@ -898,17 +1419,17 @@ if ($gzip){ $chg_output .= '.gz'; - open ($fhs{CHG_context},"| gzip -c - > $chg_output") or die "Failed to write to $chg_output $!\n"; + open ($fhs{CHG_context},"| gzip -c - > $chg_output") or die "Failed to write to $chg_output $!\n" unless($mbias_only); } else{ - open ($fhs{CHG_context},'>',$chg_output) or die "Failed to write to $chg_output $!\n"; + open ($fhs{CHG_context},'>',$chg_output) or die "Failed to write to $chg_output $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHG context to $chg_output\n"; + warn "Writing result file containing methylation information for C in CHG context to $chg_output\n" unless($mbias_only); push @sorting_files,$chg_output; unless($no_header){ - print {$fhs{CHG_context}} "Bismark methylation extractor version $version\n"; + print {$fhs{CHG_context}} "Bismark methylation extractor version $version\n" unless($mbias_only); } ### C in CHH context @@ -920,17 +1441,17 @@ if ($gzip){ $chh_output .= '.gz'; - open ($fhs{CHH_context},"| gzip -c - > $chh_output") or die "Failed to write to $chh_output $!\n"; + open ($fhs{CHH_context},"| gzip -c - > $chh_output") or die "Failed to write to $chh_output $!\n" unless($mbias_only); } else{ - open ($fhs{CHH_context},'>',$chh_output) or die "Failed to write to $chh_output $!\n"; + open ($fhs{CHH_context},'>',$chh_output) or die "Failed to write to $chh_output $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHH context to $chh_output\n"; + warn "Writing result file containing methylation information for C in CHH context to $chh_output\n" unless($mbias_only); push @sorting_files, $chh_output; unless($no_header){ - print {$fhs{CHH_context}} "Bismark methylation extractor version $version\n"; + print {$fhs{CHH_context}} "Bismark methylation extractor version $version\n" unless($mbias_only); } } ### else we will write out 12 different output files, depending on where the (first) unique best alignment was found @@ -946,17 +1467,17 @@ if ($gzip){ $cpg_ot .= '.gz'; - open ($fhs{0}->{CpG},"| gzip -c - > $cpg_ot") or die "Failed to write to $cpg_ot $!\n"; + open ($fhs{0}->{CpG},"| gzip -c - > $cpg_ot") or die "Failed to write to $cpg_ot $!\n" unless($mbias_only); } else{ - open ($fhs{0}->{CpG},'>',$cpg_ot) or die "Failed to write to $cpg_ot $!\n"; + open ($fhs{0}->{CpG},'>',$cpg_ot) or die "Failed to write to $cpg_ot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context from the original top strand to $cpg_ot\n"; + warn "Writing result file containing methylation information for C in CpG context from the original top strand to $cpg_ot\n" unless($mbias_only); push @sorting_files,$cpg_ot; unless($no_header){ - print {$fhs{0}->{CpG}} "Bismark methylation extractor version $version\n"; + print {$fhs{0}->{CpG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $cpg_ctot =~ s/^/CpG_CTOT_/; @@ -967,17 +1488,17 @@ if ($gzip){ $cpg_ctot .= '.gz'; - open ($fhs{1}->{CpG},"| gzip -c - > $cpg_ctot") or die "Failed to write to $cpg_ctot $!\n"; + open ($fhs{1}->{CpG},"| gzip -c - > $cpg_ctot") or die "Failed to write to $cpg_ctot $!\n" unless($mbias_only); } else{ - open ($fhs{1}->{CpG},'>',$cpg_ctot) or die "Failed to write to $cpg_ctot $!\n"; + open ($fhs{1}->{CpG},'>',$cpg_ctot) or die "Failed to write to $cpg_ctot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context from the complementary to original top strand to $cpg_ctot\n"; + warn "Writing result file containing methylation information for C in CpG context from the complementary to original top strand to $cpg_ctot\n" unless($mbias_only); push @sorting_files,$cpg_ctot; unless($no_header){ - print {$fhs{1}->{CpG}} "Bismark methylation extractor version $version\n"; + print {$fhs{1}->{CpG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $cpg_ctob =~ s/^/CpG_CTOB_/; @@ -988,17 +1509,17 @@ if ($gzip){ $cpg_ctob .= '.gz'; - open ($fhs{2}->{CpG},"| gzip -c - > $cpg_ctob") or die "Failed to write to $cpg_ctob $!\n"; + open ($fhs{2}->{CpG},"| gzip -c - > $cpg_ctob") or die "Failed to write to $cpg_ctob $!\n" unless($mbias_only); } else{ - open ($fhs{2}->{CpG},'>',$cpg_ctob) or die "Failed to write to $cpg_ctob $!\n"; + open ($fhs{2}->{CpG},'>',$cpg_ctob) or die "Failed to write to $cpg_ctob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context from the complementary to original bottom strand to $cpg_ctob\n"; + warn "Writing result file containing methylation information for C in CpG context from the complementary to original bottom strand to $cpg_ctob\n" unless($mbias_only); push @sorting_files,$cpg_ctob; unless($no_header){ - print {$fhs{2}->{CpG}} "Bismark methylation extractor version $version\n"; + print {$fhs{2}->{CpG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $cpg_ob =~ s/^/CpG_OB_/; @@ -1009,17 +1530,17 @@ if ($gzip){ $cpg_ob .= '.gz'; - open ($fhs{3}->{CpG},"| gzip -c - > $cpg_ob") or die "Failed to write to $cpg_ob $!\n"; + open ($fhs{3}->{CpG},"| gzip -c - > $cpg_ob") or die "Failed to write to $cpg_ob $!\n" unless($mbias_only); } else{ - open ($fhs{3}->{CpG},'>',$cpg_ob) or die "Failed to write to $cpg_ob $!\n"; + open ($fhs{3}->{CpG},'>',$cpg_ob) or die "Failed to write to $cpg_ob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CpG context from the original bottom strand to $cpg_ob\n\n"; + warn "Writing result file containing methylation information for C in CpG context from the original bottom strand to $cpg_ob\n\n" unless($mbias_only); push @sorting_files,$cpg_ob; unless($no_header){ - print {$fhs{3}->{CpG}} "Bismark methylation extractor version $version\n"; + print {$fhs{3}->{CpG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } ### For cytosines in CHG context @@ -1033,17 +1554,17 @@ if ($gzip){ $chg_ot .= '.gz'; - open ($fhs{0}->{CHG},"| gzip -c - > $chg_ot") or die "Failed to write to $chg_ot $!\n"; + open ($fhs{0}->{CHG},"| gzip -c - > $chg_ot") or die "Failed to write to $chg_ot $!\n" unless($mbias_only); } else{ - open ($fhs{0}->{CHG},'>',$chg_ot) or die "Failed to write to $chg_ot $!\n"; + open ($fhs{0}->{CHG},'>',$chg_ot) or die "Failed to write to $chg_ot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHG context from the original top strand to $chg_ot\n"; + warn "Writing result file containing methylation information for C in CHG context from the original top strand to $chg_ot\n" unless($mbias_only); push @sorting_files,$chg_ot; unless($no_header){ - print {$fhs{0}->{CHG}} "Bismark methylation extractor version $version\n"; + print {$fhs{0}->{CHG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $chg_ctot =~ s/^/CHG_CTOT_/; @@ -1054,17 +1575,17 @@ if ($gzip){ $chg_ctot .= '.gz'; - open ($fhs{1}->{CHG},"| gzip -c - > $chg_ctot") or die "Failed to write to $chg_ctot $!\n"; + open ($fhs{1}->{CHG},"| gzip -c - > $chg_ctot") or die "Failed to write to $chg_ctot $!\n" unless($mbias_only); } else{ - open ($fhs{1}->{CHG},'>',$chg_ctot) or die "Failed to write to $chg_ctot $!\n"; + open ($fhs{1}->{CHG},'>',$chg_ctot) or die "Failed to write to $chg_ctot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHG context from the complementary to original top strand to $chg_ctot\n"; + warn "Writing result file containing methylation information for C in CHG context from the complementary to original top strand to $chg_ctot\n" unless($mbias_only); push @sorting_files,$chg_ctot; unless($no_header){ - print {$fhs{1}->{CHG}} "Bismark methylation extractor version $version\n"; + print {$fhs{1}->{CHG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $chg_ctob =~ s/^/CHG_CTOB_/; @@ -1075,17 +1596,17 @@ if ($gzip){ $chg_ctob .= '.gz'; - open ($fhs{2}->{CHG},"| gzip -c - > $chg_ctob") or die "Failed to write to $chg_ctob $!\n"; + open ($fhs{2}->{CHG},"| gzip -c - > $chg_ctob") or die "Failed to write to $chg_ctob $!\n" unless($mbias_only); } else{ - open ($fhs{2}->{CHG},'>',$chg_ctob) or die "Failed to write to $chg_ctob $!\n"; + open ($fhs{2}->{CHG},'>',$chg_ctob) or die "Failed to write to $chg_ctob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHG context from the complementary to original bottom strand to $chg_ctob\n"; + warn "Writing result file containing methylation information for C in CHG context from the complementary to original bottom strand to $chg_ctob\n" unless($mbias_only); push @sorting_files,$chg_ctob; unless($no_header){ - print {$fhs{2}->{CHG}} "Bismark methylation extractor version $version\n"; + print {$fhs{2}->{CHG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $chg_ob =~ s/^/CHG_OB_/; @@ -1096,17 +1617,17 @@ if ($gzip){ $chg_ob .= '.gz'; - open ($fhs{3}->{CHG},"| gzip -c - > $chg_ob") or die "Failed to write to $chg_ob $!\n"; + open ($fhs{3}->{CHG},"| gzip -c - > $chg_ob") or die "Failed to write to $chg_ob $!\n" unless($mbias_only); } else{ - open ($fhs{3}->{CHG},'>',$chg_ob) or die "Failed to write to $chg_ob $!\n"; + open ($fhs{3}->{CHG},'>',$chg_ob) or die "Failed to write to $chg_ob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHG context from the original bottom strand to $chg_ob\n\n"; + warn "Writing result file containing methylation information for C in CHG context from the original bottom strand to $chg_ob\n\n" unless($mbias_only); push @sorting_files,$chg_ob; unless($no_header){ - print {$fhs{3}->{CHG}} "Bismark methylation extractor version $version\n"; + print {$fhs{3}->{CHG}} "Bismark methylation extractor version $version\n" unless($mbias_only); } ### For cytosines in CHH context @@ -1120,17 +1641,17 @@ if ($gzip){ $chh_ot .= '.gz'; - open ($fhs{0}->{CHH},"| gzip -c - > $chh_ot") or die "Failed to write to $chh_ot $!\n"; + open ($fhs{0}->{CHH},"| gzip -c - > $chh_ot") or die "Failed to write to $chh_ot $!\n" unless($mbias_only); } else{ - open ($fhs{0}->{CHH},'>',$chh_ot) or die "Failed to write to $chh_ot $!\n"; + open ($fhs{0}->{CHH},'>',$chh_ot) or die "Failed to write to $chh_ot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHH context from the original top strand to $chh_ot\n"; + warn "Writing result file containing methylation information for C in CHH context from the original top strand to $chh_ot\n" unless($mbias_only); push @sorting_files,$chh_ot; unless($no_header){ - print {$fhs{0}->{CHH}} "Bismark methylation extractor version $version\n"; + print {$fhs{0}->{CHH}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $chh_ctot =~ s/^/CHH_CTOT_/; @@ -1141,17 +1662,17 @@ if ($gzip){ $chh_ctot .= '.gz'; - open ($fhs{1}->{CHH},"| gzip -c - > $chh_ctot") or die "Failed to write to $chh_ctot $!\n"; + open ($fhs{1}->{CHH},"| gzip -c - > $chh_ctot") or die "Failed to write to $chh_ctot $!\n" unless($mbias_only); } else{ - open ($fhs{1}->{CHH},'>',$chh_ctot) or die "Failed to write to $chh_ctot $!\n"; + open ($fhs{1}->{CHH},'>',$chh_ctot) or die "Failed to write to $chh_ctot $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHH context from the complementary to original top strand to $chh_ctot\n"; + warn "Writing result file containing methylation information for C in CHH context from the complementary to original top strand to $chh_ctot\n" unless($mbias_only); push @sorting_files,$chh_ctot; unless($no_header){ - print {$fhs{1}->{CHH}} "Bismark methylation extractor version $version\n"; + print {$fhs{1}->{CHH}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $chh_ctob =~ s/^/CHH_CTOB_/; @@ -1162,17 +1683,17 @@ if ($gzip){ $chh_ctob .= '.gz'; - open ($fhs{2}->{CHH},"| gzip -c - > $chh_ctob") or die "Failed to write to $chh_ctob $!\n"; + open ($fhs{2}->{CHH},"| gzip -c - > $chh_ctob") or die "Failed to write to $chh_ctob $!\n" unless($mbias_only); } else{ - open ($fhs{2}->{CHH},'>',$chh_ctob) or die "Failed to write to $chh_ctob $!\n"; + open ($fhs{2}->{CHH},'>',$chh_ctob) or die "Failed to write to $chh_ctob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHH context from the complementary to original bottom strand to $chh_ctob\n"; + warn "Writing result file containing methylation information for C in CHH context from the complementary to original bottom strand to $chh_ctob\n" unless($mbias_only); push @sorting_files,$chh_ctob; unless($no_header){ - print {$fhs{2}->{CHH}} "Bismark methylation extractor version $version\n"; + print {$fhs{2}->{CHH}} "Bismark methylation extractor version $version\n" unless($mbias_only); } $chh_ob =~ s/^/CHH_OB_/; @@ -1183,17 +1704,17 @@ if ($gzip){ $chh_ob .= '.gz'; - open ($fhs{3}->{CHH},"| gzip -c - > $chh_ob") or die "Failed to write to $chh_ob $!\n"; + open ($fhs{3}->{CHH},"| gzip -c - > $chh_ob") or die "Failed to write to $chh_ob $!\n" unless($mbias_only); } else{ - open ($fhs{3}->{CHH},'>',$chh_ob) or die "Failed to write to $chh_ob $!\n"; + open ($fhs{3}->{CHH},'>',$chh_ob) or die "Failed to write to $chh_ob $!\n" unless($mbias_only); } - warn "Writing result file containing methylation information for C in CHH context from the original bottom strand to $chh_ob\n\n"; + warn "Writing result file containing methylation information for C in CHH context from the original bottom strand to $chh_ob\n\n" unless($mbias_only); push @sorting_files,$chh_ob; unless($no_header){ - print {$fhs{3}->{CHH}} "Bismark methylation extractor version $version\n"; + print {$fhs{3}->{CHH}} "Bismark methylation extractor version $version\n" unless($mbias_only); } } @@ -1327,6 +1848,7 @@ # print "\n\n$meth_call\n"; $meth_call = substr($meth_call,$ignore,length($meth_call)-$ignore); # print "$meth_call\n"; + ### If we are ignoring a part of the sequence we also need to adjust the cigar string accordingly my @len = split (/\D+/,$cigar); # storing the length per operation @@ -1444,14 +1966,20 @@ if ($meth_call_1 and $meth_call_2) { ### Clipping off the first <int> number of bases from the methylation call strings as specified with '--ignore <int>' + if ($ignore) { $meth_call_1 = substr($meth_call_1,$ignore,length($meth_call_1)-$ignore); - $meth_call_2 = substr($meth_call_2,$ignore,length($meth_call_2)-$ignore); - + ### we also need to adjust the start and end positions of the alignments accordingly if '--ignore' was specified $start_read_1 += $ignore; - $end_read_2 -= $ignore; } + if ($ignore_r2) { + $meth_call_2 = substr($meth_call_2,$ignore_r2,length($meth_call_2)-$ignore_r2); + + ### we also need to adjust the start and end positions of the alignments accordingly if '--ignore_r2' was specified + $end_read_2 -= $ignore_r2; + } + my $end_read_1; my $start_read_2; @@ -1459,30 +1987,32 @@ $end_read_1 = $start_read_1+length($meth_call_1)-1; $start_read_2 = $end_read_2-length($meth_call_2)+1; - + ## we first pass the first read which is in + orientation on the forward strand - print_individual_C_methylation_states_paired_end_files($meth_call_1,$chrom,$start_read_1,$id,'+',$index,0,0); + print_individual_C_methylation_states_paired_end_files($meth_call_1,$chrom,$start_read_1,$id,'+',$index,0,0,undef,1); # the last two values are CIGAR string and read identity # we next pass the second read which is in - orientation on the reverse strand ### if --no_overlap was specified we also pass the end of read 1. If read 2 starts to overlap with read 1 we can stop extracting methylation calls from read 2 - print_individual_C_methylation_states_paired_end_files($meth_call_2,$chrom,$end_read_2,$id,'-',$index,$no_overlap,$end_read_1); - } else { + print_individual_C_methylation_states_paired_end_files($meth_call_2,$chrom,$end_read_2,$id,'-',$index,$no_overlap,$end_read_1,undef,2); + } + else { $end_read_1 = $start_read_1+length($meth_call_2)-1; # read 1 is the second reported read! $start_read_2 = $end_read_2-length($meth_call_1)+1; # read 2 is the first reported read! ## we first pass the first read which is in - orientation on the reverse strand - print_individual_C_methylation_states_paired_end_files($meth_call_1,$chrom,$end_read_2,$id,'-',$index,0,0); + print_individual_C_methylation_states_paired_end_files($meth_call_1,$chrom,$end_read_2,$id,'-',$index,0,0,undef,1); # we next pass the second read which is in + orientation on the forward strand ### if --no_overlap was specified we also pass the end of read 2. If read 2 starts to overlap with read 1 we will stop extracting methylation calls from read 2 - print_individual_C_methylation_states_paired_end_files($meth_call_2,$chrom,$start_read_1,$id,'+',$index,$no_overlap,$start_read_2); + print_individual_C_methylation_states_paired_end_files($meth_call_2,$chrom,$start_read_1,$id,'+',$index,$no_overlap,$start_read_2,undef,2); } $methylation_call_strings_processed += 2; # paired-end = 2 methylation calls } } - } else { # Bismark paired-end SAM output format (default) + } + else { # Bismark paired-end SAM output format (default) while (<IN>) { ### SAM format can either start with header lines (starting with @) or start with alignments directly if (/^\@/) { # skipping header lines (starting with @) @@ -1585,7 +2115,8 @@ my @len_1 = split (/\D+/,$cigar_1); # storing the length per operation my @ops_1 = split (/\d+/,$cigar_1); # storing the operation shift @ops_1; # remove the empty first element - die "CIGAR string contained a non-matching number of lengths and operations\n" unless (scalar @len_1 == scalar @ops_1); + + die "CIGAR string contained a non-matching number of lengths and operations: $cigar_1\n".join(" ",@len_1)."\n".join(" ",@ops_1)."\n" unless (scalar @len_1 == scalar @ops_1); my @comp_cigar_1; # building an array with all CIGAR operations foreach my $index (0..$#len_1) { @@ -1612,20 +2143,19 @@ # print "original CIGAR read 2: $cigar_2\n"; # print "original CIGAR read 2: @comp_cigar_2\n"; + + if ($ignore) { - ### Clipping off the first <int> number of bases from the methylation call strings as specified with '--ignore <int>' + ### Clipping off the first <int> number of bases from the methylation call strings as specified with '--ignore <int>' for read 1 ### the methylation calls have already been reversed where necessary $meth_call_1 = substr($meth_call_1,$ignore,length($meth_call_1)-$ignore); - $meth_call_2 = substr($meth_call_2,$ignore,length($meth_call_2)-$ignore); - - ### If we are ignoring a part of the sequence we also need to adjust the cigar string accordingly if ($strand eq '+') { ### if the (read 1) strand information is '+', read 1 needs to be trimmed from the start my $D_count_1 = 0; # counting all deletions that affect the ignored genomic position for read 1, i.e. Deletions and insertions my $I_count_1 = 0; - + for (1..$ignore) { my $op = shift @comp_cigar_1; # adjusting composite CIGAR string of read 1 by removing $ignore operations from the start # print "$_ deleted $op\n"; @@ -1642,17 +2172,10 @@ $start_read_1 += $ignore + $D_count_1 - $I_count_1; # print "start read 1 $start_read_1\t ignore: $ignore\t D count 1: $D_count_1\tI_count 1: $I_count_1\n"; - - ### if the (read 1) strand information is '+', read 2 needs to be trimmed from the back - - for (1..$ignore) { - my $op = pop @comp_cigar_2; # adjusting composite CIGAR string by removing $ignore operations, here the last value of the array - while ($op eq 'D') { # repeating this for deletions (D) - $op = pop @comp_cigar_2; - } - } + # the start position of reads mapping to the reverse strand is being adjusted further below - } elsif ($strand eq '-') { + } + elsif ($strand eq '-') { ### if the (read 1) strand information is '-', read 1 needs to be trimmed from the back for (1..$ignore) { @@ -1663,11 +2186,35 @@ } # the start position of reads mapping to the reverse strand is being adjusted further below + } + } + + if ($ignore_r2) { + ### Clipping off the first <int> number of bases from the methylation call string as specified with '--ignore_r2 <int>' for read 2 + ### the methylation calls have already been reversed where necessary + $meth_call_2 = substr($meth_call_2,$ignore_r2,length($meth_call_2)-$ignore_r2); + + ### If we are ignoring a part of the sequence we also need to adjust the cigar string accordingly + + if ($strand eq '+') { + + ### if the (read 1) strand information is '+', read 2 needs to be trimmed from the back + + for (1..$ignore_r2) { + my $op = pop @comp_cigar_2; # adjusting composite CIGAR string by removing $ignore operations, here the last value of the array + while ($op eq 'D') { # repeating this for deletions (D) + $op = pop @comp_cigar_2; + } + } + # the start position of reads mapping to the reverse strand is being adjusted further below + } + elsif ($strand eq '-') { + ### if the (read 1) strand information is '-', read 2 needs to be trimmed from the start my $D_count_2 = 0; # counting all deletions that affect the ignored genomic position for read 2, i.e. Deletions and insertions - my $I_count_2 = 0; - - for (1..$ignore) { + my $I_count_2 = 0; + + for (1..$ignore_r2) { my $op = shift @comp_cigar_2; # adjusting composite CIGAR string of read 2 by removing $ignore operations from the start # print "$_ deleted $op\n"; @@ -1681,11 +2228,12 @@ } } - $start_read_2 += $ignore + $D_count_2 - $I_count_2; - # print "start read 2 $start_read_2\t ignore: $ignore\t D count 2: $D_count_2\tI_count 2: $I_count_2\n"; + $start_read_2 += $ignore_r2 + $D_count_2 - $I_count_2; + # print "start read 2 $start_read_2\t ignore R2: $ignore_r2\t D count 2: $D_count_2\tI_count 2: $I_count_2\n"; + } + } - } - + if ($ignore){ ### reconstituting shortened CIGAR string 1 my $new_cigar_1; my $count_1 = 0; @@ -1708,6 +2256,9 @@ $new_cigar_1 .= "$count_1$last_op_1"; # appending the last operation and count $cigar_1 = $new_cigar_1; # print "ignore adjusted CIGAR 1 scalar: $cigar_1\n"; + } + + if ($ignore_r2){ ### reconstituting shortened CIGAR string 2 my $new_cigar_2; @@ -1722,7 +2273,8 @@ } if ($last_op_2 eq $op) { ++$count_2; - } else { + } + else { $new_cigar_2 .= "$count_2$last_op_2"; $last_op_2 = $op; $count_2 = 1; @@ -1730,10 +2282,11 @@ } $new_cigar_2 .= "$count_2$last_op_2"; # appending the last operation and count $cigar_2 = $new_cigar_2; - # print "ignore adjusted CIGAR 2 scalar: $cigar_2\n"; - + # print "ignore_r2 adjusted CIGAR 2 scalar: $cigar_2\n"; } + ### Adjusting CIGAR string and starting position of reads in reverse orientation which we will pass to the extraction subroutine later on + if ($strand eq '+') { ### adjusting the start position for all reads mapping to the reverse strand, in this case read 2 @comp_cigar_2 = reverse@comp_cigar_2; # the CIGAR string needs to be reversed for all reads aligning to the reverse strand, too @@ -1751,7 +2304,8 @@ $end_read_1 = $start_read_1 + $MD_count_1 - 1; $start_read_2 += $MD_count_2 - 1; ## Passing on the start position on the reverse strand - } else { + } + else { ### adjusting the start position for all reads mapping to the reverse strand, in this case read 1 @comp_cigar_1 = reverse@comp_cigar_1; # the CIGAR string needs to be reversed for all reads aligning to the reverse strand, too @@ -1764,23 +2318,22 @@ $end_read_1 = $start_read_1; $start_read_1 += $MD_count_1 - 1; ### Passing on the start position on the reverse strand - } if ($strand eq '+') { - ## we first pass the first read which is in + orientation on the forward strand - print_individual_C_methylation_states_paired_end_files($meth_call_1,$chrom,$start_read_1,$id_1,'+',$index,0,0,$cigar_1); + ## we first pass the first read which is in + orientation on the forward strand; the last value is the read identity + print_individual_C_methylation_states_paired_end_files($meth_call_1,$chrom,$start_read_1,$id_1,'+',$index,0,0,$cigar_1,1); # we next pass the second read which is in - orientation on the reverse strand ### if --no_overlap was specified we also pass the end of read 1. If read 2 starts to overlap with read 1 we can stop extracting methylation calls from read 2 - print_individual_C_methylation_states_paired_end_files($meth_call_2,$chrom,$start_read_2,$id_2,'-',$index,$no_overlap,$end_read_1,$cigar_2); + print_individual_C_methylation_states_paired_end_files($meth_call_2,$chrom,$start_read_2,$id_2,'-',$index,$no_overlap,$end_read_1,$cigar_2,2); } else { ## we first pass the first read which is in - orientation on the reverse strand - print_individual_C_methylation_states_paired_end_files($meth_call_1,$chrom,$start_read_1,$id_1,'-',$index,0,0,$cigar_1); + print_individual_C_methylation_states_paired_end_files($meth_call_1,$chrom,$start_read_1,$id_1,'-',$index,0,0,$cigar_1,1); # we next pass the second read which is in + orientation on the forward strand ### if --no_overlap was specified we also pass the end of read 1. If read 2 starts to overlap with read 1 we will stop extracting methylation calls from read 2 - print_individual_C_methylation_states_paired_end_files($meth_call_2,$chrom,$start_read_2,$id_2,'+',$index,$no_overlap,$end_read_1,$cigar_2); + print_individual_C_methylation_states_paired_end_files($meth_call_2,$chrom,$start_read_2,$id_2,'+',$index,$no_overlap,$end_read_1,$cigar_2,2); } $methylation_call_strings_processed += 2; # paired-end = 2 methylation calls @@ -1791,9 +2344,10 @@ die "Single-end or paired-end reads not specified properly\n"; } - print "\n\nProcessed $line_count lines from $filename in total\n"; - print "Total number of methylation call strings processed: $methylation_call_strings_processed\n\n"; + warn "\n\nProcessed $line_count lines from $filename in total\n"; + warn "Total number of methylation call strings processed: $methylation_call_strings_processed\n\n"; if ($report) { + print REPORT "\n\nProcessed $line_count lines from $filename in total\n"; print REPORT "Total number of methylation call strings processed: $methylation_call_strings_processed\n\n"; } print_splitting_report (); @@ -1934,11 +2488,13 @@ - - sub print_individual_C_methylation_states_paired_end_files{ - my ($meth_call,$chrom,$start,$id,$strand,$filehandle_index,$no_overlap,$end_read_1,$cigar) = @_; + my ($meth_call,$chrom,$start,$id,$strand,$filehandle_index,$no_overlap,$end_read_1,$cigar,$read_identity) = @_; + + ### we will use the read identity for the M-bias plot to discriminate read 1 and read 2 + die "Read identity was neither 1 nor 2: $read_identity\n\n" unless ($read_identity == 1 or $read_identity == 2); + my @methylation_calls = split(//,$meth_call); ################################################################# @@ -1949,6 +2505,8 @@ ### h for not methylated C in CHH context (was converted) ### ### Z for methylated C in CpG context (was protected) ### ### z for not methylated C in CpG context (was converted) ### + ### U for methylated C in Unknown context (was protected) ### + ### u for not methylated C in Unknown context (was converted) ### ################################################################# my $methyl_CHG_count = 0; @@ -1958,13 +2516,13 @@ my $unmethylated_CHH_count = 0; my $unmethylated_CpG_count = 0; - my $pos_offset = 0; # this is only relevant for SAM reads with insertions or deletions my $cigar_offset = 0; # again, this is only relevant for SAM reads containing indels my @comp_cigar; ### Checking whether the CIGAR string is a linear genomic match or whether if requires indel processing if ($cigar =~ /^\d+M$/){ + # this check speeds up the extraction process by up to 60%!!! } else{ # parsing CIGAR string my @len; @@ -1972,6 +2530,7 @@ @len = split (/\D+/,$cigar); # storing the length per operation @ops = split (/\d+/,$cigar); # storing the operation shift @ops; # remove the empty first element + die "CIGAR string contained a non-matching number of lengths and operations\n" unless (scalar @len == scalar @ops); foreach my $index (0..$#len){ @@ -2003,8 +2562,7 @@ ### THIS IS AN OPTIONAL 2-CONTEXT (CpG and non-CpG) SECTION IF --merge_non_CpG was specified if ($merge_non_CpG) { - - if ($no_overlap) { + if ($no_overlap) { # this has to be read 2... ### single-file CpG and non-CpG context output if ($full) { @@ -2025,29 +2583,72 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.'){} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ - die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; + die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n" unless($mbias_only); } } - } elsif ($strand eq '-') { + } + elsif ($strand eq '-') { for my $index (0..$#methylation_calls) { if ($cigar and @comp_cigar){ # only needed for SAM reads with InDels @@ -2061,29 +2662,71 @@ if ($start-$index+$pos_offset <= $end_read_1) { return; } - + if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ - die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; + die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n" unless($mbias_only); } } } else { @@ -2110,24 +2753,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2149,24 +2834,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2194,26 +2921,68 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ - die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; + die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n" unless($mbias_only); } } } elsif ($strand eq '-') { @@ -2228,26 +2997,68 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ - die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; + die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n" unless($mbias_only); } } } else { @@ -2270,24 +3081,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2304,24 +3157,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2357,24 +3252,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2396,24 +3333,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2442,24 +3421,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2481,24 +3502,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2525,24 +3588,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2559,24 +3664,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2600,24 +3747,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2634,24 +3823,66 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CpG}->{$index+1}->{un}++; + } + else{ + $mbias_2{CpG}->{$index+1}->{un}++; + } + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{meth}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{meth}++; + } + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + if ($read_identity == 1){ + $mbias_1{CHH}->{$index+1}->{un}++; + } + else{ + $mbias_2{CHH}->{$index+1}->{un}++; + } } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2797,8 +4028,9 @@ @len = split (/\D+/,$cigar); # storing the length per operation @ops = split (/\d+/,$cigar); # storing the operation shift @ops; # remove the empty first element + # die "CIGAR string contained a non-matching number of lengths and operations: id: $id\nmeth call: $meth_call\nCIGAR: $cigar\n".join(" ",@len)."\n".join(" ",@ops)."\n" unless (scalar @len == scalar @ops); die "CIGAR string contained a non-matching number of lengths and operations\n" unless (scalar @len == scalar @ops); - + foreach my $index (0..$#len){ foreach (1..$len[$index]){ # print "$ops[$index]"; @@ -2814,7 +4046,7 @@ # print "$meth_call\n\n"; # sleep (1); } - + ### adjusting the start position for all reads mapping to the reverse strand if ($strand eq '-') { @@ -2824,7 +4056,7 @@ } unless ($ignore){ ### if --ignore was specified the start position has already been corrected - + if ($cigar){ ### SAM format if ($cigar =~ /^(\d+)M$/){ # linear match $start += $1 - 1; @@ -2861,30 +4093,36 @@ ### not methylated Cs (any context) will receive a reverse (-) orientation if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{un}++; } - elsif ($methylation_calls[$index] eq '.') { - } + elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2905,30 +4143,36 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{other_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{un}++; } - elsif ($methylation_calls[$index] eq '.'){ - } + elsif ($methylation_calls[$index] eq '.'){} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2954,30 +4198,36 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{un}++; } - elsif ($methylation_calls[$index] eq '.') { - } + elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -2997,30 +4247,36 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{meth}++; } elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{other_c}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{un}++; } - elsif ($methylation_calls[$index] eq '.') { - } + elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -3044,29 +4300,41 @@ $cigar_offset += $cigar_mod; $pos_offset += $pos_mod; } - + if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{un}++; + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{un}++; + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ - die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; + die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n" unless($mbias_only); } } } @@ -3084,24 +4352,36 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{CHG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{CHG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{un}++; + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{CpG_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{CpG_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{un}++; + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{CHH_context}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{CHH_context}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -3127,24 +4407,36 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{un}++; + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{un}++; + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start+$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -3164,24 +4456,36 @@ if ($methylation_calls[$index] eq 'X') { $counting{total_meCHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'x') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'x') { $counting{total_unmethylated_CHG_count}++; - print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'Z') { + print {$fhs{$filehandle_index}->{CHG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHG}->{$index+1}->{un}++; + } + elsif ($methylation_calls[$index] eq 'Z') { $counting{total_meCpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'z') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'z') { $counting{total_unmethylated_CpG_count}++; - print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'H') { + print {$fhs{$filehandle_index}->{CpG}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CpG}->{$index+1}->{un}++; + } + elsif ($methylation_calls[$index] eq 'H') { $counting{total_meCHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; - } elsif ($methylation_calls[$index] eq 'h') { + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'+',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{meth}++; + } + elsif ($methylation_calls[$index] eq 'h') { $counting{total_unmethylated_CHH_count}++; - print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n"; + print {$fhs{$filehandle_index}->{CHH}} join ("\t",$id,'-',$chrom,$start-$index+$pos_offset,$methylation_calls[$index]),"\n" unless($mbias_only); + $mbias_1{CHH}->{$index+1}->{un}++; } elsif ($methylation_calls[$index] eq '.') {} + elsif (lc$methylation_calls[$index] eq 'u'){} else{ die "The methylation call string contained the following unrecognised character: $methylation_calls[$index]\n"; } @@ -3195,595 +4499,6 @@ -####################################################################################################################################### -### bismark2bedGaph section - START -####################################################################################################################################### - -### has now been moved to the external script bismark2bedGraph - -# sub process_bedGraph_output{ -# warn "="x64,"\n"; -# warn "Methylation information will now be written into a bedGraph file\n"; -# warn "="x64,"\n\n"; -# sleep (2); - -# ### Closing all filehandles so that the Bismark methtylation extractor output doesn't get truncated due to buffering issues -# foreach my $fh (keys %fhs) { -# if ($fh =~ /^[1230]$/) { -# foreach my $context (keys %{$fhs{$fh}}) { -# close $fhs{$fh}->{$context} or die $!; -# } -# } else { -# close $fhs{$fh} or die $!; -# } -# } - -# ### deciding which files to use for bedGraph conversion -# foreach my $filename (@sorting_files){ -# # warn "$filename\n"; -# if ($filename =~ /\//){ # if files are in a different output folder we extract the filename again -# $filename =~ s/.*\///; # replacing everything up to the last slash in the filename -# # warn "$filename\n"; -# } - -# if ($CX_context){ -# push @bedfiles,$filename; -# } -# else{ ## CpG context only (default) -# if ($filename =~ /^CpG_/){ -# push @bedfiles,$filename; -# } -# else{ -# # skipping CHH or CHG files -# } -# } -# } - -# warn "Using the following files as Input:\n"; -# print join ("\t",@bedfiles),"\n\n"; -# sleep (2); - -# my %temp_fhs; -# my @temp_files; # writing all context files (default CpG only) to these files prior to sorting - -# ### changing to the output directory -# unless ($output_dir eq ''){ # default -# chdir $output_dir or die "Failed to change directory to $output_dir\n"; -# warn "Changed directory to $output_dir\n"; -# } - -# foreach my $infile (@bedfiles) { - -# if ($remove) { -# warn "Now replacing whitespaces in the sequence ID field of the Bismark methylation extractor output $infile prior to bedGraph conversion\n\n"; - -# if ($infile =~ /gz$/){ -# open (READ,"zcat $infile |") or die $!; -# } -# else{ -# open (READ,$infile) or die $!; -# } - -# my $removed_spaces_outfile = $infile; -# $removed_spaces_outfile =~ s/$/.spaces_removed.txt/; - -# open (REM,'>',$output_dir.$removed_spaces_outfile) or die "Couldn't write to file $removed_spaces_outfile: $!\n"; - -# unless ($no_header){ -# $_ = <READ>; ### Bismark version header -# print REM $_; ### Bismark version header -# } - -# while (<READ>) { -# chomp; -# my ($id,$strand,$chr,$pos,$context) = (split (/\t/)); -# $id =~ s/\s+/_/g; -# print REM join ("\t",$id,$strand,$chr,$pos,$context),"\n"; -# } - -# close READ or die $!; -# close REM or die $!; - -# ### changing the infile name to the new file without spaces -# $infile = $removed_spaces_outfile; -# } - -# warn "Now writing methylation information for file $infile to individual files for each chromosome\n"; -# if ($infile =~ /gz$/){ -# open (IN,"zcat $infile |") or die $!; -# } -# else{ -# open (IN,$infile) or die $!; -# } - -# ## always ignoring the version header -# unless ($no_header){ -# $_ = <IN>; ### Bismark version header -# } - -# while (<IN>) { -# chomp; -# my ($chr) = (split (/\t/))[2]; -# # warn "This is the chromosome name before replacing '|' characters:\t$chr\n\n"; -# $chr =~ s/\|/_/g; # replacing pipe ('|') characters in the file names -# # warn "This is the chromosome name AFTER replacing '|' characters:\t$chr\n\n"; - -# unless (exists $temp_fhs{$chr}) { -# open ($temp_fhs{$chr},'>','chr'.$chr.'.meth_extractor.temp') or die "Failed to open filehandle: $!"; -# } -# print {$temp_fhs{$chr}} "$_\n"; -# } - -# warn "Finished writing out individual chromosome files for $infile\n"; -# } -# warn "\n"; - -# @temp_files = <*.meth_extractor.temp>; - -# warn "Collecting temporary chromosome file information...\n"; -# sleep (1); -# warn "processing the following input file(s):\n"; -# warn join ("\n",@temp_files),"\n\n"; -# sleep (1); - -# foreach my $in (@temp_files) { -# if ($sort_size){ -# warn "Sorting input file $in by positions (using -S of '$sort_size')\n"; -# } -# else{ -# warn "Sorting input file $in by positions (using default memory settings)\n"; -# } -# my $sort_dir = $output_dir; -# if ($sort_dir eq ''){ -# $sort_dir = './'; -# } -# open my $ifh, "sort -S $sort_size -T $sort_dir -k3,3 -k4,4n $in |" or die "Input file could not be sorted. $!"; -# # print "Chromosome\tStart Position\tEnd Position\tMethylation Percentage\n"; - -# ############################################# m.a.bentley - moved the variables out of the while loop to hold the current line data { - -# my $name; -# my $meth_state; -# my $chr = ""; -# my $pos = 0; -# my $meth_state2; - -# my $last_pos; -# my $last_chr; - -# ############################################# } - -# while (my $line = <$ifh>) { -# next if $line =~ /^Bismark/; -# chomp $line; - -# ########################################### m.a.bentley - (1) set the last_chr and last_pos variables early in the while loop, before the line split (2) removed unnecessary setting of same variables in if statement { - -# $last_chr = $chr; -# $last_pos = $pos; -# ($name, $meth_state, $chr, $pos, $meth_state2) = split "\t", $line; - -# if (($last_pos ne $pos) || ($last_chr ne $chr)) { -# generate_output($last_chr,$last_pos) if $methylcalls[2] > 0; -# @methylcalls = qw (0 0 0); -# } - -# ############################################# } - -# my $validated = validate_methylation_call($meth_state, $meth_state2); -# unless($validated){ -# warn "Methylation state of sequence ($name) in file ($in) on line $. is inconsistent (meth_state is $meth_state, meth_state2 = $meth_state2)\n"; -# next; -# } -# if ($meth_state eq "+") { -# $methylcalls[0]++; -# $methylcalls[2]++; -# } else { -# $methylcalls[1]++; -# $methylcalls[2]++; -# } -# } - -# ############################################# m.a.bentley - set the last_chr and last_pos variables for the last line in the file (outside the while loop's scope using the method i've implemented) { - -# $last_chr = $chr; -# $last_pos = $pos; -# if ($methylcalls[2] > 0) { -# generate_output($last_chr,$last_pos) if $methylcalls[2] > 0; -# } -# ############################################# } - -# close $ifh or die $!; - -# @methylcalls = qw (0 0 0); # resetting @methylcalls - -# ### deleting temporary files -# my $delete = unlink $in; -# if ($delete) { -# warn "Successfully deleted the temporary input file $in\n\n"; -# } -# else { -# warn "The temporary inputfile $in could not be deleted $!\n\n"; -# } -# } -# } - -# sub generate_output{ -# my $methcount = $methylcalls[0]; -# my $nonmethcount = $methylcalls[1]; -# my $totalcount = $methylcalls[2]; -# my $last_chr = shift; -# my $last_pos = shift; -# croak "Should not be generating output if there's no reads to this region" unless $totalcount > 0; -# croak "Total counts ($totalcount) is not the sum of the methylated ($methcount) and unmethylated ($nonmethcount) counts" if $totalcount != ($methcount + $nonmethcount); - -# ############################################# m.a.bentley - declare a new variable 'bed_pos' to distinguish from bismark positions (-1) - previous scripts modified the last_pos variable earlier in the script leading to problems in meth % calculation { - -# my $bed_pos = $last_pos -1; ### Bismark coordinates are 1 based whereas bedGraph coordinates are 0 based. -# my $meth_percentage; -# ($totalcount >= $coverage_threshold) ? ($meth_percentage = ($methcount/$totalcount) * 100) : ($meth_percentage = undef); -# # $meth_percentage =~ s/(\.\d\d).+$/$1/ unless $meth_percentage =~ /^Below/; -# if (defined $meth_percentage){ -# if ($counts){ -# print OUT "$last_chr\t$bed_pos\t$bed_pos\t$meth_percentage\t$methcount\t$nonmethcount\n"; -# } -# else{ -# print OUT "$last_chr\t$bed_pos\t$bed_pos\t$meth_percentage\n"; -# } -# } -# ############################################# } -# } - -# sub validate_methylation_call{ -# my $meth_state = shift; -# croak "Missing (+/-) methylation call" unless defined $meth_state; -# my $meth_state2 = shift; -# croak "Missing alphabetical methylation call" unless defined $meth_state2; -# my $is_consistent; -# ($meth_state2 =~ /^z/i) ? ($is_consistent = check_CpG_methylation_call($meth_state, $meth_state2)) -# : ($is_consistent = check_nonCpG_methylation_call($meth_state,$meth_state2)); -# return 1 if $is_consistent; -# return 0; -# } - -# sub check_CpG_methylation_call{ -# my $meth1 = shift; -# my $meth2 = shift; -# return 1 if($meth1 eq "+" && $meth2 eq "Z"); -# return 1 if($meth1 eq "-" && $meth2 eq "z"); -# return 0; -# } - -# sub check_nonCpG_methylation_call{ -# my $meth1 = shift; -# my $meth2 = shift; -# return 1 if($meth1 eq "+" && $meth2 eq "C"); -# return 1 if($meth1 eq "+" && $meth2 eq "X"); -# return 1 if($meth1 eq "+" && $meth2 eq "H"); -# return 1 if($meth1 eq "-" && $meth2 eq "c"); -# return 1 if($meth1 eq "-" && $meth2 eq "x"); -# return 1 if($meth1 eq "-" && $meth2 eq "h"); -# return 0; -# } - -####################################################################################################################################### -### bismark2bedGaph section - END -####################################################################################################################################### - - - - - - -# ####################################################################################################################################### -# ### genome-wide cytosine methylation report - START -# ####################################################################################################################################### - -### has now been moved to the external script bedGraph2cytosine - -# sub generate_genome_wide_cytosine_report { - -# warn "="x78,"\n"; -# warn "Methylation information will now be written into a genome-wide cytosine report\n"; -# warn "="x78,"\n\n"; -# sleep (2); - -# ### changing to the output directory again -# unless ($output_dir eq ''){ # default -# chdir $output_dir or die "Failed to change directory to $output_dir\n"; -# # warn "Changed directory to $output_dir\n"; -# } - -# my $in = shift; -# open (IN,$in) or die $!; - -# my $cytosine_out = shift; - -# if ($CX_context){ -# $cytosine_out =~ s/$/genome-wide_CX_report.txt/; -# } -# else{ -# $cytosine_out =~ s/$/genome_wide_CpG_report.txt/; -# } - -# ### note: we are still in the folder: $output_dir, so we do not have to include this into the open commands -# unless ($split_by_chromosome){ ### writing all output to a single file (default) -# open (CYT,'>',$cytosine_out) or die $!; -# warn "Writing genome-wide cytosine report to: $cytosine_out\n"; -# sleep (3); -# } - -# my $last_chr; -# my %chr; # storing reads for one chromosome at a time - -# my $count = 0; -# while (<IN>){ -# chomp; -# ++$count; -# my ($chr,$start,$end,undef,$meth,$nonmeth) = (split /\t/); - -# # defining the first chromosome -# unless (defined $last_chr){ -# $last_chr = $chr; -# # warn "Storing all covered cytosine positions for chromosome: $chr\n"; -# } - -# if ($chr eq $last_chr){ -# $chr{$chr}->{$start}->{meth} = $meth; -# $chr{$chr}->{$start}->{nonmeth} = $nonmeth; -# } -# else{ -# warn "Writing cytosine reports for chromosome $last_chr (stored ",scalar keys %{$chr{$last_chr}}," different covered positions)\n"; - -# if ($split_by_chromosome){ ## writing output to 1 file per chromosome -# my $chromosome_out = $cytosine_out; -# $chromosome_out =~ s/txt$/chr${last_chr}.txt/; -# open (CYT,'>',$chromosome_out) or die $!; -# } - -# while ( $chromosomes{$last_chr} =~ /([CG])/g){ - -# my $tri_nt = ''; -# my $context = ''; -# my $pos = pos$chromosomes{$last_chr}; - -# my $strand; -# my $meth = 0; -# my $nonmeth = 0; - -# if ($1 eq 'C'){ # C on forward strand -# $tri_nt = substr ($chromosomes{$last_chr},($pos-1),3); # positions are 0-based! -# $strand = '+'; -# } -# elsif ($1 eq 'G'){ # C on reverse strand -# $tri_nt = substr ($chromosomes{$last_chr},($pos-3),3); # positions are 0-based! -# $tri_nt = reverse $tri_nt; -# $tri_nt =~ tr/ACTG/TGAC/; -# $strand = '-'; -# } -# next if (length$tri_nt < 3); # trinucleotide sequence could not be extracted - -# if (exists $chr{$last_chr}->{($pos-1)}){ # stored positions are 0-based! -# $meth = $chr{$last_chr}->{$pos-1}->{meth}; -# $nonmeth = $chr{$last_chr}->{$pos-1}->{nonmeth}; -# } - -# ### determining cytosine context -# if ($tri_nt =~ /^CG/){ -# $context = 'CG'; -# } -# elsif ($tri_nt =~ /^C.{1}G$/){ -# $context = 'CHG'; -# } -# elsif ($tri_nt =~ /^C.{2}$/){ -# $context = 'CHH'; -# } -# else{ # if the context can't be determined the positions will not be printed (it will equally not have been reported by Bismark) -# warn "The sequence context could not be determined (found: '$tri_nt'). Skipping.\n"; -# next; -# } - -# if ($CpG_only){ -# if ($tri_nt =~ /^CG/){ # CpG context is the default -# if ($zero){ # zero based coordinates -# $pos -= 1; -# print CYT join ("\t",$last_chr,$pos,$strand,$meth,$nonmeth,$context,$tri_nt),"\n"; -# } -# else{ # default -# print CYT join ("\t",$last_chr,$pos,$strand,$meth,$nonmeth,$context,$tri_nt),"\n"; -# } -# } -# } -# else{ ## all cytosines, specified with --CX -# if ($zero){ # zero based coordinates -# $pos -= 1; -# print CYT join ("\t",$last_chr,$pos,$strand,$meth,$nonmeth,$context,$tri_nt),"\n"; -# } -# else{ # default -# print CYT join ("\t",$last_chr,$pos,$strand,$meth,$nonmeth,$context,$tri_nt),"\n"; -# } -# } -# } - -# %chr = (); # resetting the hash - -# # new first entry -# $last_chr = $chr; -# $chr{$chr}->{$start}->{meth} = $meth; -# $chr{$chr}->{$start}->{nonmeth} = $nonmeth; -# } -# } - -# # Last found chromosome -# warn "Writing cytosine reports for chromosome $last_chr (stored ",scalar keys %{$chr{$last_chr}}," different covered positions)\n"; - -# if ($split_by_chromosome){ ## writing output to 1 file per chromosome -# my $chromosome_out = $cytosine_out; -# $chromosome_out =~ s/txt$/chr${last_chr}.txt/; -# open (CYT,'>',$chromosome_out) or die $!; -# } - -# while ( $chromosomes{$last_chr} =~ /([CG])/g){ - -# my $tri_nt; -# my $context; -# my $pos = pos$chromosomes{$last_chr}; - -# my $strand; -# my $meth = 0; -# my $nonmeth = 0; - -# if ($1 eq 'C'){ # C on forward strand -# $tri_nt = substr ($chromosomes{$last_chr},($pos-1),3); # positions are 0-based! -# $strand = '+'; -# } -# elsif ($1 eq 'G'){ # C on reverse strand -# $tri_nt = substr ($chromosomes{$last_chr},($pos-3),3); # positions are 0-based! -# $tri_nt = reverse $tri_nt; -# $tri_nt =~ tr/ACTG/TGAC/; -# $strand = '-'; -# } - -# if (exists $chr{$last_chr}->{($pos-1)}){ # stored positions are 0-based! -# $meth = $chr{$last_chr}->{$pos-1}->{meth}; -# $nonmeth = $chr{$last_chr}->{$pos-1}->{nonmeth}; -# } - -# next if (length$tri_nt < 3); # trinucleotide sequence could not be extracted - -# ### determining cytosine context -# if ($tri_nt =~ /^CG/){ -# $context = 'CG'; -# } -# elsif ($tri_nt =~ /^C.{1}G$/){ -# $context = 'CHG'; -# } -# elsif ($tri_nt =~ /^C.{2}$/){ -# $context = 'CHH'; -# } -# else{ # if the context can't be determined the positions will not be printed (it will equally not have been reported by Bismark) -# warn "The cytosine context could not be determined (found: '$tri_nt'). Skipping.\n"; -# next; -# } - -# if ($CpG_only){ -# if ($tri_nt =~ /^CG/){ # CpG context is the default -# if ($zero){ # zero-based coordinates -# $pos -= 1; -# print CYT join ("\t",$last_chr,$pos,$strand,$meth,$nonmeth,$context,$tri_nt),"\n"; -# } -# else{ # default -# print CYT join ("\t",$last_chr,$pos,$strand,$meth,$nonmeth,$context,$tri_nt),"\n"; -# } -# } -# } -# else{ ## all cytosines, specified with --CX -# if ($zero){ # zero based coordinates -# $pos -= 1; -# print CYT join ("\t",$last_chr,$pos,$strand,$meth,$nonmeth,$context,$tri_nt),"\n"; -# } -# else{ # default -# print CYT join ("\t",$last_chr,$pos,$strand,$meth,$nonmeth,$context,$tri_nt),"\n"; -# } -# } -# } -# close CYT or die $!; -# } - - -# sub read_genome_into_memory{ - -# ## reading in and storing the specified genome in the %chromosomes hash -# chdir ($genome_folder) or die "Can't move to $genome_folder: $!"; -# warn "Now reading in and storing sequence information of the genome specified in: $genome_folder\n\n"; - -# my @chromosome_filenames = <*.fa>; - -# ### if there aren't any genomic files with the extension .fa we will look for files with the extension .fasta -# unless (@chromosome_filenames){ -# @chromosome_filenames = <*.fasta>; -# } -# unless (@chromosome_filenames){ -# die "The specified genome folder $genome_folder does not contain any sequence files in FastA format (with .fa or .fasta file extensions)\n"; -# } - -# foreach my $chromosome_filename (@chromosome_filenames){ - -# # skipping the tophat entire mouse genome fasta file -# next if ($chromosome_filename eq 'Mus_musculus.NCBIM37.fa'); - -# open (CHR_IN,$chromosome_filename) or die "Failed to read from sequence file $chromosome_filename $!\n"; -# ### first line needs to be a fastA header -# my $first_line = <CHR_IN>; -# chomp $first_line; -# $first_line =~ s/\r//; # removing /r carriage returns - -# ### Extracting chromosome name from the FastA header -# my $chromosome_name = extract_chromosome_name($first_line); - -# my $sequence; -# while (<CHR_IN>){ -# chomp; -# $_ =~ s/\r//; # removing /r carriage returns - -# if ($_ =~ /^>/){ -# ### storing the previous chromosome in the %chromosomes hash, only relevant for Multi-Fasta-Files (MFA) -# if (exists $chromosomes{$chromosome_name}){ -# warn "chr $chromosome_name (",length $sequence ," bp)\n"; -# die "Exiting because chromosome name already exists. Please make sure all chromosomes have a unique name!\n"; -# } -# else { -# if (length($sequence) == 0){ -# warn "Chromosome $chromosome_name in the multi-fasta file $chromosome_filename did not contain any sequence information!\n"; -# } -# warn "chr $chromosome_name (",length $sequence ," bp)\n"; -# $chromosomes{$chromosome_name} = $sequence; -# } -# ### resetting the sequence variable -# $sequence = ''; -# ### setting new chromosome name -# $chromosome_name = extract_chromosome_name($_); -# } -# else{ -# $sequence .= uc$_; -# } -# } - -# if (exists $chromosomes{$chromosome_name}){ -# warn "chr $chromosome_name (",length $sequence ," bp)\t"; -# die "Exiting because chromosome name already exists. Please make sure all chromosomes have a unique name.\n"; -# } -# else{ -# if (length($sequence) == 0){ -# warn "Chromosome $chromosome_name in the file $chromosome_filename did not contain any sequence information!\n"; -# } -# warn "chr $chromosome_name (",length $sequence ," bp)\n"; -# $chromosomes{$chromosome_name} = $sequence; -# } -# } -# warn "\n"; -# chdir $parent_dir or die "Failed to move to directory $parent_dir\n"; -# } - -# sub extract_chromosome_name { -# ## Bowtie extracts the first string after the inition > in the FASTA file, so we are doing this as well -# my $fasta_header = shift; -# if ($fasta_header =~ s/^>//){ -# my ($chromosome_name) = split (/\s+/,$fasta_header); -# return $chromosome_name; -# } -# else{ -# die "The specified chromosome ($fasta_header) file doesn't seem to be in FASTA format as required!\n"; -# } -# } - -# ####################################################################################################################################### -# ### genome-wide cytosine methylation report - END -# ####################################################################################################################################### - - - - sub print_helpfile{ print << 'HOW_TO'; @@ -3797,15 +4512,17 @@ for individual cytosines. This information is found in the methylation call field which can contain the following characters: - ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - ~~~ X for methylated C in CHG context (was protected) ~~~ - ~~~ x for not methylated C CHG (was converted) ~~~ - ~~~ H for methylated C in CHH context (was protected) ~~~ - ~~~ h for not methylated C in CHH context (was converted) ~~~ - ~~~ Z for methylated C in CpG context (was protected) ~~~ - ~~~ z for not methylated C in CpG context (was converted) ~~~ - ~~~ . for any bases not involving cytosines ~~~ - ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + ~~~ X for methylated C in CHG context ~~~ + ~~~ x for not methylated C CHG ~~~ + ~~~ H for methylated C in CHH context ~~~ + ~~~ h for not methylated C in CHH context ~~~ + ~~~ Z for methylated C in CpG context ~~~ + ~~~ z for not methylated C in CpG context ~~~ + ~~~ U for methylated C in Unknown context (CN or CHN ~~~ + ~~~ u for not methylated C in Unknown context (CN or CHN) ~~~ + ~~~ . for any bases not involving cytosines ~~~ + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The methylation extractor outputs result files for cytosines in CpG, CHG and CHH context (this distinction is actually already made in Bismark itself). As the methylation @@ -3839,6 +4556,7 @@ ARGUMENTS: +========== <filenames> A space-separated list of Bismark result files in SAM format from which methylation information is extracted for every cytosine in @@ -3868,12 +4586,21 @@ proportion of the data. This option is highly recommended for paired-end data. ---ignore <int> Ignore the first <int> bp at the 5' end of each read when processing the +--ignore <int> Ignore the first <int> bp from the 5' end of Read 1 when processing the methylation call string. This can remove e.g. a restriction enzyme site - at the start of each read. - ---comprehensive Specifying this option will merge all four possible strand-specific - methylation info into context-dependent output files. The default + at the start of each read or any other source of bias (e.g. PBAT-Seq data). + +--ignore_r2 <int> Ignore the first <int> bp from the 5' end of Read 2 of paired-end sequencing + results only. Since the first couple of bases in Read 2 of BS-Seq experiments + show a severe bias towards non-methylation as a result of end-repairing + sonicated fragments with unmethylated cytosines (see M-bias plot), it is + recommended that the first couple of bp of Read 2 are removed before + starting downstream analysis. Please see the section on M-bias plots in the + Bismark User Guide for more details. + +--comprehensive Specifying this option will merge all four possible strand-specific + methylation info into context-dependent output files. The default + contexts are: - CpG context - CHG context @@ -3904,9 +4631,13 @@ -h/--help Displays this help file and exits. +--mbias_only The methylation extractor will read the entire file but only output the M-bias table and plots as + well as a report (optional) and then quit. Default: OFF. + bedGraph specific options: +========================== --bedGraph After finishing the methylation extraction, the methylation output is written into a sorted bedGraph file that reports the position of a given cytosine and its methylation @@ -3927,12 +4658,6 @@ --remove_spaces Replaces whitespaces in the sequence ID field with underscores to allow sorting. ---counts Adds two additional columns to the output file to enable further calculations: - col 5: number of methylated calls - col 6: number of unmethylated calls - This option is required if '--cytosine_report' is specified (and will be set automatically if - necessary). - --CX/--CX_context The sorted bedGraph output file contains information on every single cytosine that was covered in the experiment irrespective of its sequence context. This applies to both forward and reverse strands. Please be aware that this option may generate large temporary and output files @@ -3945,8 +4670,32 @@ (e.g. --buffer_size 20G). For more information on sort type 'info sort' on a command line. Defaults to 2G. +--scaffolds/--gazillion Users working with unfinished genomes sporting tens or even hundreds of thousands of + scaffolds/contigs/chromosomes frequently encountered errors with pre-sorting reads to + individual chromosome files. These errors were caused by the operating system's limit + of the number of filehandle that can be written to at any one time (typically 1024; to + find out this limit on Linux, type: ulimit -a). + To bypass the limitation of open filehandles, the option --scaffolds does not pre-sort + methylation calls into individual chromosome files. Instead, all input files are + temporarily merged into a single file (unless there is only a single file), and this + file will then be sorted by both chromosome AND position using the Unix sort command. + Please be aware that this option might take a looooong time to complete, depending on + the size of the input files, and the memory you allocate to this process (see --buffer_size). + Nevertheless, it seems to be working. + +--ample_memory Using this option will not sort chromosomal positions using the UNIX 'sort' command, but will + instead use two arrays to sort methylated and unmethylated calls. This may result in a faster + sorting process of very large files, but this comes at the cost of a larger memory footprint + (two arrays of the length of the largest human chromosome 1 (~250M bp) consume around 16GB + of RAM). Due to overheads in creating and looping through these arrays it seems that it will + actually be *slower* for small files (few million alignments), and we are currently testing at + which point it is advisable to use this option. Note that --ample_memory is not compatible + with options '--scaffolds/--gazillion' (as it requires pre-sorted files to begin with). + + Genome-wide cytosine methylation report specific options: +========================================================= --cytosine_report After the conversion to bedGraph has completed, the option '--cytosine_report' produces a genome-wide methylation report for all cytosines in the genome. By default, the output uses 1-based @@ -3983,11 +4732,17 @@ -The bedGraph output (optional) looks like this (tab-delimited): -=============================================================== +The bedGraph output (optional) looks like this (tab-delimited; 0-based start coords, 1-based end coords): +========================================================================================================= + +track type=bedGraph (header line) + <chromosome> <start position> <end position> <methylation percentage> -The bedGraph output with '--counts' specified looks like this (tab-delimited): + + +The coverage output looks like this (tab-delimited, 1-based genomic coords): +============================================================================ <chromosome> <start position> <end position> <methylation percentage> <count methylated> <count non-methylated> @@ -3999,7 +4754,7 @@ -This script was last modified on 21 April 2013. +This script was last modified on 25 November 2013. HOW_TO }
--- a/bismark_methylation_extractor.py Wed Aug 21 05:19:54 2013 -0400 +++ b/bismark_methylation_extractor.py Mon Apr 14 16:43:14 2014 -0400 @@ -27,10 +27,10 @@ # input options parser.add_argument( '--bismark_path', dest='bismark_path', help='Path to the bismark perl scripts' ) - parser.add_argument( '--infile', help='Input file in SAM format.' ) + parser.add_argument( '--infile', help='Input file in SAM or BAM format.' ) parser.add_argument( '--single-end', dest='single_end', action="store_true" ) parser.add_argument( '--paired-end', dest='paired_end', action="store_true" ) - + parser.add_argument( '--report-file', dest='report_file' ) parser.add_argument( '--comprehensive', action="store_true" ) parser.add_argument( '--merge-non-cpg', dest='merge_non_cpg', action="store_true" ) @@ -93,9 +93,15 @@ if args.report_file: additional_opts += ' --report ' - - # Final command: - cmd = cmd % (output_dir, additional_opts, args.infile) + #detect BAM file, use samtools view if it is a bam file + f = open (args.infile, 'rb') + sig = f.read(4) + f.close() + if sig == '\x1f\x8b\x08\x04' : + cmd = cmd % (output_dir, additional_opts, '-') + cmd = 'samtools view %s | %s' % (args.infile, cmd ) + else : + cmd = cmd % (output_dir, additional_opts, args.infile) # Run try:
--- a/bismark_methylation_extractor.xml Wed Aug 21 05:19:54 2013 -0400 +++ b/bismark_methylation_extractor.xml Mon Apr 14 16:43:14 2014 -0400 @@ -1,11 +1,11 @@ -<tool id="bismark_methylation_extractor" name="Bismark" version="0.7.12"> - <!-- Wrapper compatible with Bismark version 0.7.7 --> - <description>methylation extractor</description> +<tool id="bismark_methylation_extractor" name="Bismark Meth. Extractor" version="0.10.1"> + <!-- Wrapper compatible with Bismark version 0.10 --> + <description>Reports on methylation status of reads mapped by Bismark</description> <!--<version_command>bismark_methylation_extractor version</version_command>--> <requirements> <requirement type="set_environment">SCRIPT_PATH</requirement> <requirement type="package" version="0.12.8">bowtie</requirement> - <requirement type="package" version="2.0.0-beta7">bowtie2</requirement> + <requirement type="package" version="2.1.0">bowtie2</requirement> </requirements> <parallelism method="basic"></parallelism> <command interpreter="python"> @@ -81,7 +81,7 @@ </command> <inputs> <!-- Input Parameters --> - <param name="input" type="data" format="sam" label="SAM file from Bismark bisulfid mapper" /> + <param name="input" type="data" format="sam,bam" label="SAM/BAM file from Bismark bisulfite mapper" /> <conditional name="singlePaired"> <param name="sPaired" type="select" label="Is this library mate-paired?"> <option value="single">Single-end</option> @@ -92,7 +92,6 @@ <param name="no_overlap" type="boolean" truevalue="--no-overlap" falsevalue="" checked="False" label="This option avoids scoring overlapping methylation calls twice, in case of overlapping read one and read two" help="" /> </when> </conditional> - <param name="ignore_bps" type="integer" value="0" label="Ignore the first N bp when processing the methylation call string" /> <param name="comprehensive" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Merge all four possible strand-specific methylation info into context-dependent output files" help="" />
--- a/bismark_wrapper.py Wed Aug 21 05:19:54 2013 -0400 +++ b/bismark_wrapper.py Mon Apr 14 16:43:14 2014 -0400 @@ -43,6 +43,7 @@ help='The forward reads file in Sanger FASTQ or FASTA format.' ) parser.add_argument( '-2', '--mate2', dest='mate2', help='The reverse reads file in Sanger FASTQ or FASTA format.' ) + parser.add_argument( '--sort-bam', dest='sort_bam', action="store_true" ) parser.add_argument( '--output-unmapped-reads', dest='output_unmapped_reads', help='Additional output file with unmapped reads (single-end).' ) @@ -176,10 +177,10 @@ #tmp_bismark_dir = tempfile.mkdtemp( dir='/data/0/galaxy_db/tmp/' ) tmp_bismark_dir = tempfile.mkdtemp() output_dir = os.path.join( tmp_bismark_dir, 'results') - cmd = 'bismark %(args)s --bam --temp_dir %(tmp_bismark_dir)s -o %(output_dir)s --quiet %(genome_folder)s %(reads)s' + cmd = 'bismark %(args)s --bam --temp_dir %(tmp_bismark_dir)s --gzip -o %(output_dir)s --quiet %(genome_folder)s %(reads)s' if args.fasta: - # he query input files (specified as mate1,mate2 or singles) are FastA + # the query input files (specified as mate1,mate2 or singles) are FastA cmd = '%s %s' % (cmd, '--fasta') elif args.fastq: cmd = '%s %s' % (cmd, '--fastq') @@ -223,7 +224,7 @@ # alignment options if args.bowtie2: - additional_opts += ' -p %s --bowtie2 ' % args.num_threads + additional_opts += ' -p %s --bowtie2 ' % (int(args.num_threads/2)) #divides by 2 here since bismark will spawn 2 (original top and original bottom) jobs with -p threads each if args.seed_mismatches: additional_opts += ' -N %s ' % args.seed_mismatches if args.seed_len: @@ -327,24 +328,29 @@ bam_files = glob( os.path.join( output_dir, '*.bam') ) if len( bam_files ) > 1: - cmd = 'samtools merge -@ %s -f - %s ' % ( args.num_threads, ' '.join( bam_files ) ) + cmd = 'samtools merge -@ %s -f %s %s ' % ( args.num_threads, tmp_res, ' '.join( bam_files ) ) - p1 = subprocess.Popen( args=shlex.split( cmd ), stdout=subprocess.PIPE ) - proc = subprocess.Popen( ['samtools', 'sort', '-@', str(args.num_threads), '-', tmp_res], stdin=p1.stdout, stdout=tmp_stdout, stderr=tmp_stderr ) - else: - proc = subprocess.Popen( ['samtools', 'sort', '-@', str(args.num_threads), bam_files[0], tmp_res], stdout=tmp_stdout, stderr=tmp_stderr ) + proc = subprocess.Popen( args=shlex.split( cmd ), stdout=subprocess.PIPE ) - returncode = proc.wait() - tmp_stdout.close() - tmp_stderr.close() - if returncode != 0: - raise Exception, open( tmp_stderr.name ).read() + returncode = proc.wait() + tmp_stdout.close() + tmp_stderr.close() + if returncode != 0: + raise Exception, open( tmp_stderr.name ).read() + else: + tmp_res = bam_files[0] - bam_path = "%s.bam" % tmp_res + bam_path = "%s" % tmp_res + if os.path.exists( bam_path ): - shutil.copy( bam_path, args.output ) + if args.sort_bam: + cmd = 'samtools sort -@ %s %s %s' % (args.num_threads, bam_path, args.output) + else: + shutil.copy( bam_path, args.output ) else: stop_err( 'BAM file no found:\n' + str( bam_path ) ) + + # TODO: look for errors in program output. except Exception, e:
--- a/readme.rst Wed Aug 21 05:19:54 2013 -0400 +++ b/readme.rst Mon Apr 14 16:43:14 2014 -0400 @@ -26,6 +26,8 @@ - v0.7.11.1 change default output to BAM, from now on samtools are required - v0.7.11.2 added multi-threading to samtools (samtools > 0.1.19 is required) - v0.7.12 upgrade to bismark 0.7.12 and fix a major slowdown +- v0.7.12.1 define a dependency to samtools 0.1.19 + =============================== Wrapper Licence (MIT/BSD style)
--- a/tool_dependencies.xml Wed Aug 21 05:19:54 2013 -0400 +++ b/tool_dependencies.xml Mon Apr 14 16:43:14 2014 -0400 @@ -1,7 +1,7 @@ <?xml version="1.0"?> <tool_dependency> <package name="samtools" version="0.1.19"> - <repository changeset_revision="cb87eae7fc3e" name="package_samtools_0_1_19" owner="iuc" toolshed="http://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="00e17a794a2e" name="package_samtools_0_1_19" owner="iuc" toolshed="http://toolshed.g2.bx.psu.edu" /> </package> <set_environment version="1.0"> <environment_variable action="set_to" name="SCRIPT_PATH">$REPOSITORY_INSTALL_DIR</environment_variable>