Mercurial > repos > devteam > bowtie2
diff bowtie2_wrapper.xml @ 15:43d12513224b draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bowtie2 commit cf554b9b69c32acb484c34fdc60384fa49c7c482
| author | iuc |
|---|---|
| date | Thu, 01 Jun 2017 06:47:03 -0400 |
| parents | 937aa69e715f |
| children | 8ccbdbe9a695 |
line wrap: on
line diff
--- a/bowtie2_wrapper.xml Wed Apr 12 17:09:42 2017 -0400 +++ b/bowtie2_wrapper.xml Thu Jun 01 06:47:03 2017 -0400 @@ -1,10 +1,10 @@ -<tool id="bowtie2" name="Bowtie2" version="2.3.0.1" profile="17.01"> +<tool id="bowtie2" name="Bowtie2" version="2.3.2.1" profile="17.01"> <description>- map reads against reference genome</description> <macros> - <import>read_group_macros.xml</import> + <import>bowtie2_macros.xml</import> </macros> <requirements> - <requirement type="package" version="2.3.0">bowtie2</requirement> + <requirement type="package" version="2.3.2">bowtie2</requirement> <requirement type="package" version="1.3.1">samtools</requirement> </requirements> <version_command>bowtie2 --version</version_command> @@ -66,6 +66,18 @@ #set read2 = "input_r.fastq" #end if ln -s '${library.input_1.reverse}' ${read2} && + + #else if str($library.type) == 'paired_interleaved': + #if $library.input_1.is_of_type("fastq.gz", "fastqsanger.gz"): + #set read1 = "input_il.fastq.gz" + #set compressed = "GZ" + #else if $library.input_1.is_of_type("fastq.bz2", "fastqsanger.bz2"): + #set read1 = "input_il.fastq.bz2" + #set compressed = "BZ2" + #else: + #set read1 = "input_il.fastq" + #end if + ln -s '${library.input_1}' ${read1} && #else: #if $library.input_1.is_of_type("fastq.gz", "fastqsanger.gz"): #set read1 = "input_f.fastq.gz" @@ -110,6 +122,27 @@ --al '${output_aligned_reads_l}' #end if #end if + + #elif str( $library.type ) == "paired_interleaved": + --interleaved '${read1}' + #if str( $library.unaligned_file ) == "true": + #if $compressed == "GZ": + --un-gz '${output_unaligned_reads_l}' + #else if $compressed == "BZ2": + --un-bz2 '${output_unaligned_reads_l}' + #else: + --un '${output_unaligned_reads_l}' + #end if + #end if + #if str( $library.aligned_file ) == "true": + #if $compressed == "GZ": + --al-gz '${output_aligned_reads_l}' + #else if $compressed == "BZ2": + --al-bz2 '${output_aligned_reads_l}' + #else: + --al '${output_aligned_reads_l}' + #end if + #end if #else: -1 '${read1}' -2 '${read2}' @@ -273,69 +306,36 @@ <option value="single">Single-end</option> <option value="paired">Paired-end</option> <option value="paired_collection">Paired-end Dataset Collection</option> + <option value="paired_interleaved">Paired-end data from single interleaved dataset</option> </param> <when value="single"> <param name="input_1" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data" label="FASTQ file" help="Must be of datatype "fastqsanger"" /> - <param name="unaligned_file" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write unaligned reads (in fastq format) to separate file(s)" help="--un/--un-conc (possibly with -gz or -bz2); This triggers --un parameter for single reads and --un-conc for paired reads" /> - <param name="aligned_file" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write aligned reads (in fastq format) to separate file(s)" help="--al/--al-conc (possibly with -gz or -bz2); This triggers --al parameter for single reads and --al-conc for paired reads" /> + + <expand macro="align_unalign" /> + </when> <when value="paired"> <param name="input_1" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data" label="FASTQ file #1" help="Must be of datatype "fastqsanger"" /> <param name="input_2" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data" label="FASTQ file #2" help="Must be of datatype "fastqsanger"" /> - <param name="unaligned_file" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write unaligned reads (in fastq format) to separate file(s)" help="--un/--un-conc (possibly with -gz or -bz2); This triggers --un parameter for single reads and --un-conc for paired reads" /> - <param name="aligned_file" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write aligned reads (in fastq format) to separate file(s)" help="--al/--al-conc (possibly with -gz or -bz2); This triggers --al parameter for single reads and --al-conc for paired reads" /> - <conditional name="paired_options"> - <param name="paired_options_selector" type="select" label="Do you want to set paired-end options?" help="See "Alignment Options" section of Help below for information"> - <option value="no" selected="True">No</option> - <option value="yes">Yes</option> - </param> - <when value="yes"> - <param name="I" type="integer" value="0" min="0" label="Set the minimum fragment length for valid paired-end alignments" help="-I/--minins; E.g. if `-I 60` is specified and a paired-end alignment consists of two 20-bp alignments in the appropriate orientation with a 20-bp gap between them, that alignment is considered valid (as long as `-X` is also satisfied). A 19-bp gap would not be valid in that case. If trimming options `-3` or `-5` are also used, the `-I` constraint is applied with respect to the untrimmed mates. The larger the difference between `-I` and `-X`, the slower Bowtie 2 will run. This is because larger differences bewteen `-I` and `-X` require that Bowtie 2 scan a larger window to determine if a concordant alignment exists. For typical fragment length ranges (200 to 400 nucleotides), Bowtie 2 is very efficient. Default=0"/> - <param name="X" type="integer" value="500" min="0" label="Set the maximum fragment length for valid paired-end alignments" help="-X/--maxins; E.g. if `-X 100` is specified and a paired-end alignment consists of two 20-bp alignments in the proper orientation with a 60-bp gap between them, that alignment is considered valid (as long as `-I` is also satisfied). A 61-bp gap would not be valid in that case. If trimming options `-3` or `-5` are also used, the `-X` constraint is applied with respect to the untrimmed mates, not the trimmed mates; Default=500"/> - <param name="fr_rf_ff" type="select" display="radio" label="Select the upstream/downstream mate orientations for a valid paired-end alignment against the forward reference strand" help="--fr, --rf, or --ff; E.g., if `--fr` is specified and there is a candidate paired-end alignment where mate 1 appears upstream of the reverse complement of mate 2 and the fragment length constraints (`-I` and `-X`) are met, that alignment is valid. Also, if mate 2 appears upstream of the reverse complement of mate 1 and all other constraints are met, that too is valid. `--rf` likewise requires that an upstream mate1 be reverse-complemented and a downstream mate2 be forward-oriented. `--ff` requires both an upstream mate 1 and a downstream mate 2 to be forward-oriented; Default=--fr (appropriate for Illumina's Paired-end Sequencing Assay)"> - <option value="--fr" selected="True">--fr</option> - <option value="--rf">--rf</option> - <option value="--ff">--ff</option> - </param> - <param name="no_mixed" type="boolean" truevalue="--no-mixed" falsevalue="" checked="False" label="Disable no-mixed behavior" help="--no-mixed; By default, when `bowtie2` cannot find a concordant or discordant alignment for a pair, it then tries to find alignments for the individual mates; default=False"/> - <param name="no_discordant" type="boolean" truevalue="--no-discordant" falsevalue="" checked="False" label="Disable no-discordant behavior" help="--no-discordant; By default, `bowtie2` looks for discordant alignments if it cannot find any concordant alignments. A discordant alignment is an alignment where both mates align uniquely, but that does not satisfy the paired-end constraints (`--fr`/`--rf`/`--ff`, `-I`, `-X`); default=False"/> - <param name="dovetail" type="boolean" truevalue="--dovetail" falsevalue="" checked="False" label="Allow mate dovetailing" help="--dovetail; If the mates `dovetail`, that is if one mate alignment extends past the beginning of the other such that the wrong mate begins upstream, consider that to be concordant. Default=False"/> - <param name="no_contain" type="boolean" truevalue="--no-contain" falsevalue="" checked="False" label="Disallow one mate alignment to contain another" help="--no-contain; If one mate alignment contains the other, consider that to be non-concordant. Default=False"/> - <param name="no_overlap" type="boolean" truevalue="--no-overlap" falsevalue="" checked="False" label="Disallow mate alignments to overlap" help="--no-overlap; If one mate alignment overlaps the other at all, consider that to be non-concordant. Default=False"/> - </when> - <when value="no"> - <!-- do nothing --> - </when> - </conditional> + + <expand macro="align_unalign" /> + <expand macro="paired_end_options" /> + </when> <when value="paired_collection"> <param name="input_1" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data_collection" collection_type="paired" label="FASTQ Paired Dataset" help="Must be of datatype "fastqsanger"" /> - <param name="unaligned_file" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write unaligned reads (in fastq format) to separate file(s)" help="--un/--un-conc (possibly with -gz or -bz2); This triggers --un parameter for single reads and --un-conc for paired reads" /> - <param name="aligned_file" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write aligned reads (in fastq format) to separate file(s)" help="--al/--al-conc (possibly with -gz or -bz2); This triggers --al parameter for single reads and --al-conc for paired reads" /> - <conditional name="paired_options"> - <param name="paired_options_selector" type="select" label="Do you want to set paired-end options?" help="See "Alignment Options" section of Help below for information"> - <option value="no" selected="True">No</option> - <option value="yes">Yes</option> - </param> - <when value="yes"> - <param name="I" type="integer" value="0" min="0" label="Set the minimum fragment length for valid paired-end alignments" help="-I/--minins; E.g. if `-I 60` is specified and a paired-end alignment consists of two 20-bp alignments in the appropriate orientation with a 20-bp gap between them, that alignment is considered valid (as long as `-X` is also satisfied). A 19-bp gap would not be valid in that case. If trimming options `-3` or `-5` are also used, the `-I` constraint is applied with respect to the untrimmed mates. The larger the difference between `-I` and `-X`, the slower Bowtie 2 will run. This is because larger differences bewteen `-I` and `-X` require that Bowtie 2 scan a larger window to determine if a concordant alignment exists. For typical fragment length ranges (200 to 400 nucleotides), Bowtie 2 is very efficient. Default=0"/> - <param name="X" type="integer" value="500" min="0" label="Set the maximum fragment length for valid paired-end alignments" help="-X/--maxins; E.g. if `-X 100` is specified and a paired-end alignment consists of two 20-bp alignments in the proper orientation with a 60-bp gap between them, that alignment is considered valid (as long as `-I` is also satisfied). A 61-bp gap would not be valid in that case. If trimming options `-3` or `-5` are also used, the `-X` constraint is applied with respect to the untrimmed mates, not the trimmed mates; Default=500"/> - <param name="fr_rf_ff" type="select" display="radio" label="Select the upstream/downstream mate orientations for a valid paired-end alignment against the forward reference strand" help="--fr, --rf, or --ff; E.g., if `--fr` is specified and there is a candidate paired-end alignment where mate 1 appears upstream of the reverse complement of mate 2 and the fragment length constraints (`-I` and `-X`) are met, that alignment is valid. Also, if mate 2 appears upstream of the reverse complement of mate 1 and all other constraints are met, that too is valid. `--rf` likewise requires that an upstream mate1 be reverse-complemented and a downstream mate2 be forward-oriented. `--ff` requires both an upstream mate 1 and a downstream mate 2 to be forward-oriented; Default=--fr (appropriate for Illumina's Paired-end Sequencing Assay)"> - <option value="--fr" selected="True">--fr</option> - <option value="--rf">--rf</option> - <option value="--ff">--ff</option> - </param> - <param name="no_mixed" type="boolean" truevalue="--no-mixed" falsevalue="" checked="False" label="Disable no-mixed behavior" help="--no-mixed; By default, when `bowtie2` cannot find a concordant or discordant alignment for a pair, it then tries to find alignments for the individual mates; default=False"/> - <param name="no_discordant" type="boolean" truevalue="--no-discordant" falsevalue="" checked="False" label="Disable no-discordant behavior" help="--no-discordant; By default, `bowtie2` looks for discordant alignments if it cannot find any concordant alignments. A discordant alignment is an alignment where both mates align uniquely, but that does not satisfy the paired-end constraints (`--fr`/`--rf`/`--ff`, `-I`, `-X`); default=False"/> - <param name="dovetail" type="boolean" truevalue="--dovetail" falsevalue="" checked="False" label="Allow mate dovetailing" help="--dovetail; If the mates `dovetail`, that is if one mate alignment extends past the beginning of the other such that the wrong mate begins upstream, consider that to be concordant. Default=False"/> - <param name="no_contain" type="boolean" truevalue="--no-contain" falsevalue="" checked="False" label="Disallow one mate alignment to contain another" help="--no-contain; If one mate alignment contains the other, consider that to be non-concordant. Default=False"/> - <param name="no_overlap" type="boolean" truevalue="--no-overlap" falsevalue="" checked="False" label="Disallow mate alignments to overlap" help="--no-overlap; If one mate alignment overlaps the other at all, consider that to be non-concordant. Default=False"/> - </when> - <when value="no"> - <!-- do nothing --> - </when> - </conditional> + + <expand macro="align_unalign" /> + <expand macro="paired_end_options" /> + + </when> + <when value="paired_interleaved"> + <param name="input_1" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data" label="Interleaved FASTQ file" help="Must be of datatype "fastqsanger". --interleaved"/> + + <expand macro="align_unalign" /> + <expand macro="paired_end_options" /> + </when> </conditional> @@ -648,7 +648,6 @@ <test> <!-- basic test on single paired default run --> <param name="type" value="paired"/> - <param name="selection" value="no"/> <param name="paired_options_selector" value="no"/> <param name="unaligned_file" value="false"/> <param name="analysis_type_selector" value="simple"/> @@ -661,7 +660,6 @@ <test> <!-- basic test on single paired default run --> <param name="type" value="paired"/> - <param name="selection" value="no"/> <param name="paired_options_selector" value="no"/> <param name="unaligned_file" value="false"/> <param name="analysis_type_selector" value="simple"/> @@ -677,7 +675,6 @@ <test> <!-- basic test on single paired default run with stats--> <param name="type" value="paired"/> - <param name="selection" value="no"/> <param name="paired_options_selector" value="no"/> <param name="unaligned_file" value="false"/> <param name="analysis_type_selector" value="simple"/> @@ -687,12 +684,29 @@ <param name="own_file" value="bowtie2-ref.fasta" /> <param name="save_mapping_stats" value="true" /> <output name="output" file="bowtie2-test1.bam" ftype="bam" lines_diff="2"/> - <output name="mapping_stats" file="bowtie2-stats.out" ftype="txt"/> + <output name="mapping_stats"> + <assert_contents> + <has_text text="of these" /> + </assert_contents> + </output> + </test> + <test> + <!-- basic test on interleaved paired default run --> + <param name="type" value="paired_interleaved"/> + <!-- <param name="paired_options_selector" value="no"/> --> + <param name="unaligned_file" value="false"/> + <param name="analysis_type_selector" value="simple"/> + <param name="rg_selector" value="set"/> + <param name="ID" value="rg1"/> + <param name="PL" value="CAPILLARY"/> + <param name="source" value="history" /> + <param name="input_1" value="bowtie2-fq_il.fq" ftype="fastqsanger"/> + <param name="own_file" value="bowtie2-ref.fasta" /> + <output name="output" file="bowtie2-test_il.bam" ftype="bam" lines_diff="2"/> </test> <test> <!-- test fastqsanger.gz input --> <param name="type" value="paired"/> - <param name="selection" value="no"/> <param name="paired_options_selector" value="no"/> <param name="unaligned_file" value="false"/> <param name="analysis_type_selector" value="simple"/> @@ -705,7 +719,6 @@ <test> <!-- test fastqsanger.bz2 input --> <param name="type" value="paired"/> - <param name="selection" value="no"/> <param name="paired_options_selector" value="no"/> <param name="unaligned_file" value="false"/> <param name="analysis_type_selector" value="simple"/> @@ -754,12 +767,15 @@ **Inputs** -Bowtie 2 accepts files in Sanger FASTQ format (single or pair-end). Use the FASTQ Groomer to prepare your files. +Bowtie 2 accepts files in Sanger FASTQ format (single or paired-end). Paired-end data can represented as two individual (forward and reverse) datasets, as well as a single interleaved dataset (see an example at the end of the help section). ------ **Input options**:: + --interleaved + Reads interleaved FASTQ files where the first two records (8 lines) represent a mate pair. + -s/--skip <int> Skip (i.e. do not align) the first `<int>` reads or pairs in the input. @@ -1137,6 +1153,57 @@ but might be more appropriate in situations where the input consists of many identical reads. +----- + + +**Paired-end (and mate-pair) data in fastq format** + +Paired end datasets can be represented as two individual datasets: + +First dataset:: + + @1/1 + AGGGATGTGTTAGGGTTAGGGTTAGGGTTAGGGTTAGGGTTAGGGTTA + + + EGGEGGGDFGEEEAEECGDEGGFEEGEFGBEEDDECFEFDD@CDD<ED + @2/1 + AGGGATGTGTTAGGGTTAGGGTTAGGGTTAGGGTTAGGGTTAGGGTTA + + + HHHHHHEGFHEEFEEHEEHHGGEGGGGEFGFGGGGHHHHFBEEEEEFG + +Second dataset:: + + @1/2 + CCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAAC + + + GHHHDFDFGFGEGFBGEGGEGEGGGHGFGHFHFHHHHHHHEF?EFEFF + @2/2 + CCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAAC + + + HHHHHHHHHHHHHGHHHHHHGHHHHHHHHHHHFHHHFHHHHHHHHHHH + +Or a single *interleaved* dataset:: + + @1/1 + AGGGATGTGTTAGGGTTAGGGTTAGGGTTAGGGTTAGGGTTAGGGTTA + + + EGGEGGGDFGEEEAEECGDEGGFEEGEFGBEEDDECFEFDD@CDD<ED + @1/2 + CCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAAC + + + GHHHDFDFGFGEGFBGEGGEGEGGGHGFGHFHFHHHHHHHEF?EFEFF + @2/1 + AGGGATGTGTTAGGGTTAGGGTTAGGGTTAGGGTTAGGGTTAGGGTTA + + + HHHHHHEGFHEEFEEHEEHHGGEGGGGEFGFGGGGHHHHFBEEEEEFG + @2/2 + CCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAAC + + + HHHHHHHHHHHHHGHHHHHHGHHHHHHHHHHHFHHHFHHHHHHHHHHH + + + + ]]></help> <citations> <citation type="doi">10.1186/gb-2009-10-3-r25</citation>