# HG changeset patch # User enios # Date 1621668958 0 # Node ID d928c656a8f317c9d48e5691402399fd7be09b11 # Parent 11d232ed904c971411cbf16be34b1bc18e3fc8d8 Uploaded diff -r 11d232ed904c -r d928c656a8f3 gffread.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gffread.xml Sat May 22 07:35:58 2021 +0000 @@ -0,0 +1,503 @@ + + Filters and/or converts GFF3/GTF2 records + + 343307676715.dkr.ecr.eu-central-1.amazonaws.com/galaxy:gffread + + + 0.11.6 + + + + + + + + + + + + + + + + + + + + \w+ + + + + + + + + + + + + + + + + + + + + + + + + + 0: + -i $maxintron + #end if + #if $region.region_filter == 'filter': + -r '$region.range' $region.discard_partial + #end if + #if $merging.merge_sel != 'none': + $merging.merge_cmd + #if $merging.merge_options: + #echo ' '.join(str($merging.merge_options).split(',')) + #end if + #end if + #if $chr_replace: + -m '$chr_replace' + #end if + + $full_gff_attribute_preservation + $decode_url + $expose + + ## + ## Although documented, does not appear to be used in the gffread code + ## #if $seq_info: + ## -A -s "$seq_info" + ## #end if + ## + ## outputs + #if $reference_genome.source != 'none': + #if $reference_genome.fa_outputs and str($reference_genome.fa_outputs) != '': + #echo ' ' + ' '.join(str($reference_genome.fa_outputs).split(',')) + #end if + #end if + #if $gffs.gff_fmt != 'none': + #if $gffs.tname: + -t '$gffs.tname' + #end if + #if $gffs.gff_fmt == 'gff': + #if $input.datatype.file_ext == 'gft': + $gffs.ensembl + #end if + $gffs.output_cmd + #elif $gffs.gff_fmt == 'gtf': + $gffs.output_cmd + #end if + #end if +]]> + + + + + + + + + + + + + + + + + + + + + examples:
+ 1000..500000
+ chr1:1000..500000
+ +chr1:1000..500000
+ -chr1:1000..500000 + ]]> + + (([+-])?(\w+:))?\d+\.\.\d+ + + + + + + + + chr_replace is a reference sequence replacement table consisting of 2 columns: "original_ref_ID" "new_ref_ID"
+ It is useful for switching between Ensembl and UCSC naming conventions
+ NOTE: GFF records on reference sequences that are not found among the "original_ref_ID" entries in this file will be filtered out + ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + gffs['gff_fmt'] == 'gff' + + + gffs['gff_fmt'] == 'gtf' + + + 'fa_outputs' in reference_genome and str(reference_genome['fa_outputs']).find('exons.fa') > 0 + + + 'fa_outputs' in reference_genome and str(reference_genome['fa_outputs']).find('cds.fa') > 0 + + + 'fa_outputs' in reference_genome and str(reference_genome['fa_outputs']).find('pep.fa') > 0 + + + 'merge_options' in merging and merging['merge_options'].find('dupinfo') > 0 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + [-g | ][-s ] + [-o ] [-t ] [-r [[]:].. [-R]] + [-CTVNJMKQAFPGUBHZWTOLE] [-w ] [-x ] [-y ] + [-i ] [--bed] [--table ] [--sort-by ] + + Filter, convert or cluster GFF/GTF/BED records, extract the sequence of + transcripts (exon or CDS) and more. + By default (i.e. without -O) only transcripts are processed, discarding any + other non-transcript features. Default output is a simplified GFF3 with only + the basic attributes. + + is a GFF file, use '-' for stdin + + Options: + + -i discard transcripts having an intron larger than + -l discard transcripts shorter than bases + -r only show transcripts overlapping coordinate range .. + (on chromosome/contig , strand if provided) + -R for -r option, discard all transcripts that are not fully + contained within the given range + -U discard single-exon transcripts + -C coding only: discard mRNAs that have no CDS features + --nc non-coding only: discard mRNAs that have CDS features + --ignore-locus : discard locus features and attributes found in the input + -A use the description field from and add it + as the value for a 'descr' attribute to the GFF record + -s is a tab-delimited file providing this info + for each of the mapped sequences: +

+ (useful for -A option with mRNA/EST/protein mappings) + + Sorting: (by default, chromosomes are kept in the order they were found) + --sort-alpha : chromosomes (reference sequences) are sorted alphabetically + --sort-by : sort the reference sequences by the order in which their + names are given in the file + + Misc options: + -F preserve all GFF attributes (for non-exon features) + --keep-exon-attrs : for -F option, do not attempt to reduce redundant + exon/CDS attributes + -G do not keep exon attributes, move them to the transcript feature + (for GFF3 output) + --keep-genes : in transcript-only mode (default), also preserve gene records + --keep-comments: for GFF3 input/output, try to preserve comments + -O process other non-transcript GFF records (by default non-transcript + records are ignored) + -V discard any mRNAs with CDS having in-frame stop codons (requires -g) + -H for -V option, check and adjust the starting CDS phase + if the original phase leads to a translation with an + in-frame stop codon + -B for -V option, single-exon transcripts are also checked on the + opposite strand (requires -g) + -P add transcript level GFF attributes about the coding status of each + transcript, including partialness or in-frame stop codons (requires -g) + --add-hasCDS : add a "hasCDS" attribute with value "true" for transcripts + that have CDS features + --adj-stop stop codon adjustment: enables -P and performs automatic + adjustment of the CDS stop coordinate if premature or downstream + -N discard multi-exon mRNAs that have any intron with a non-canonical + splice site consensus (i.e. not GT-AG, GC-AG or AT-AC) + -J discard any mRNAs that either lack initial START codon + or the terminal STOP codon, or have an in-frame stop codon + (i.e. only print mRNAs with a complete CDS) + --no-pseudo: filter out records matching the 'pseudo' keyword + --in-bed: input should be parsed as BED format (automatic if the input + filename ends with .bed*) + --in-tlf: input GFF-like one-line-per-transcript format without exon/CDS + features (see --tlf option below); automatic if the input + filename ends with .tlf) + + Clustering: + -M/--merge : cluster the input transcripts into loci, discarding + "duplicated" transcripts (those with the same exact introns + and fully contained or equal boundaries) + -d : for -M option, write duplication info to file + --cluster-only: same as -M/--merge but without discarding any of the + "duplicate" transcripts, only create "locus" features + -K for -M option: also discard as redundant the shorter, fully contained + transcripts (intron chains matching a part of the container) + -Q for -M option, no longer require boundary containment when assessing + redundancy (can be combined with -K); only introns have to match for + multi-exon transcripts, and >=80% overlap for single-exon transcripts + -Y for -M option, enforce -Q but also discard overlapping single-exon + transcripts, even on the opposite strand (can be combined with -K) + + Output options: + --force-exons: make sure that the lowest level GFF features are considered + "exon" features + --gene2exon: for single-line genes not parenting any transcripts, add an + exon feature spanning the entire gene (treat it as a transcript) + --t-adopt: try to find a parent gene overlapping/containing a transcript + that does not have any explicit gene Parent + -D decode url encoded characters within attributes + -Z merge very close exons into a single exon (when intron size<4) + -g full path to a multi-fasta file with the genomic sequences + for all input mappings, OR a directory with single-fasta files + (one per genomic sequence, with file names matching sequence names) + -w write a fasta file with spliced exons for each GFF transcript + -x write a fasta file with spliced CDS for each GFF transcript + -y write a protein fasta file with the translation of CDS for each record + -W for -w and -x options, write in the FASTA defline the exon + coordinates projected onto the spliced sequence; + for -y option, write transcript attributes in the FASTA defline + -S for -y option, use '*' instead of '.' as stop codon translation + -L Ensembl GTF to GFF3 conversion (implies -F; should be used with -m) + -m is a name mapping table for converting reference + sequence names, having this 2-column format: + + WARNING: all GFF records on reference sequences whose original IDs + are not found in the 1st column of this table will be discarded! + -t use in the 2nd column of each GFF/GTF output line + -o write the records into instead of stdout + -T main output will be GTF instead of GFF3 + --bed output records in BED format instead of default GFF3 + --tlf output "transcript line format" which is like GFF + but exons, CDS features and related data are stored as GFF + attributes in the transcript feature line, like this: + exoncount=N;exons=;CDSphase=;CDS= + is a comma-delimited list of exon_start-exon_end coordinates; + is CDS_start:CDS_end coordinates or a list like + --table output a simple tab delimited format instead of GFF, with columns + having the values of GFF attributes given in ; special + pseudo-attributes (prefixed by @) are recognized: + @chr, @start, @end, @strand, @numexons, @exons, @cds, @covlen, @cdslen + -v,-E expose (warn about) duplicate transcript IDs and other potential + problems with the given GFF/GTF records +]]> + + + 10.1038/nbt.1621 + + +