Mercurial > repos > iuc > samtools_coverage
changeset 0:90f2dd176d80 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/sam_to_bam commit 4d0362c336f67d05086298ab4980c1d922d71c6e"
| author | iuc |
|---|---|
| date | Tue, 28 Sep 2021 15:10:16 +0000 |
| parents | |
| children | ae36fab06bc2 |
| files | macros.xml samtools_coverage.xml test-data/results_1.tabular test-data/results_2.txt test-data/results_3.txt test-data/test_1.bam test-data/test_2.bam |
| diffstat | 4 files changed, 349 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Tue Sep 28 15:10:16 2021 +0000 @@ -0,0 +1,223 @@ +<macros> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">samtools</requirement> + <yield/> + </requirements> + </xml> + <token name="@TOOL_VERSION@">1.13</token> + <token name="@PROFILE@">20.05</token> + <token name="@FLAGS@"><![CDATA[ + #set $flags = 0 + #if $filter + #set $flags = sum(map(int, str($filter).split(','))) + #end if + ]]></token> + <token name="@PREPARE_IDX@"><![CDATA[ + ##prepare input and indices + ln -s '$input' infile && + #if $input.is_of_type('bam'): + #if str( $input.metadata.bam_index ) != "None": + ln -s '${input.metadata.bam_index}' infile.bai && + #else: + samtools index infile infile.bai && + #end if + #elif $input.is_of_type('cram'): + #if str( $input.metadata.cram_index ) != "None": + ln -s '${input.metadata.cram_index}' infile.crai && + #else: + samtools index infile infile.crai && + #end if + #end if + ]]></token> + <token name="@PREPARE_IDX_MULTIPLE@"><![CDATA[ + ##prepare input and indices + #for $i, $bam in enumerate( $input_bams ): + ln -s '$bam' '${i}' && + #if $bam.is_of_type('bam'): + #if str( $bam.metadata.bam_index ) != "None": + ln -s '${bam.metadata.bam_index}' '${i}.bai' && + #else: + samtools index '${i}' '${i}.bai' && + #end if + #elif $bam.is_of_type('cram'): + #if str( $bam.metadata.cram_index ) != "None": + ln -s '${bam.metadata.cram_index}' '${i}.crai' && + #else: + samtools index '${i}' '${i}.crai' && + #end if + #end if + #end for + ]]></token> + <token name="@PREPARE_FASTA_IDX@"><![CDATA[ + ##checks for reference data ($addref_cond.addref_select=="history" or =="cached") + ##and sets the -t/-T parameters accordingly: + ##- in case of history a symbolic link is used because samtools (view) will generate + ## the index which might not be possible in the directory containing the fasta file + ##- in case of cached the absolute path is used which allows to read the cram file + ## without specifying the reference + #if $addref_cond.addref_select == "history": + ln -s '${addref_cond.ref}' reference.fa && + samtools faidx reference.fa && + #set reffa="reference.fa" + #set reffai="reference.fa.fai" + #elif $addref_cond.addref_select == "cached": + #set reffa=str($addref_cond.ref.fields.path) + #set reffai=str($addref_cond.ref.fields.path)+".fai" + #else + #set reffa=None + #set reffai=None + #end if + ]]></token> + + <xml name="optional_reference"> + <conditional name="addref_cond"> + <param name="addref_select" type="select" label="Use a reference sequence"> + <help>@HELP@</help> + <option value="no">No</option> + <option value="history">Use a genome/index from the history</option> + <option value="cached">Use a built-in genome</option> + </param> + <when value="no"/> + <when value="history"> + <param name="ref" argument="@ARGUMENT@" type="data" format="fasta,fasta.gz" label="Reference"/> + </when> + <when value="cached"> + <param name="ref" argument="@ARGUMENT@" type="select" label="Reference"> + <options from_data_table="fasta_indexes"> + <filter type="data_meta" ref="input" key="dbkey" column="dbkey"/> + </options> + <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset"/> + </param> + </when> + </conditional> + </xml> + <xml name="mandatory_reference" token_help="" token_argument=""> + <conditional name="addref_cond"> + <param name="addref_select" type="select" label="Use a reference sequence"> + <help>@HELP@</help> + <option value="history">Use a genome/index from the history</option> + <option value="cached">Use a built-in genome</option> + </param> + <when value="history"> + <param name="ref" argument="@ARGUMENT@" type="data" format="fasta,fasta.gz" label="Reference"/> + </when> + <when value="cached"> + <param name="ref" argument="@ARGUMENT@" type="select" label="Reference"> + <options from_data_table="fasta_indexes"> + <filter type="data_meta" ref="input" key="dbkey" column="dbkey"/> + <validator message="No reference genome is available for the build associated with the selected input dataset" type="no_options" /> + </options> + </param> + </when> + </conditional> + </xml> + + + <token name="@ADDTHREADS@"><![CDATA[ + ##compute the number of ADDITIONAL threads to be used by samtools (-@) + addthreads=\${GALAXY_SLOTS:-1} && (( addthreads-- )) && + ]]></token> + <token name="@ADDMEMORY@"><![CDATA[ + ##compute the number of memory available to samtools sort (-m) + ##use only 75% of available: https://github.com/samtools/samtools/issues/831 + addmemory=\${GALAXY_MEMORY_MB_PER_SLOT:-768} && + ((addmemory=addmemory*75/100)) && + ]]></token> + <xml name="seed_input"> + <param name="seed" type="integer" optional="True" label="Seed for random number generator" help="If empty a random seed is used." /> + </xml> + <xml name="flag_options" token_s1="false" token_s2="false" token_s4="false" token_s8="false" token_s16="false" token_s32="false" token_s64="false" token_s128="false" token_s256="false" token_s512="false" token_s1024="false" token_s2048="false"> + <option value="1" selected="@S1@">Read is paired</option> + <option value="2" selected="@S2@">Read is mapped in a proper pair</option> + <option value="4" selected="@S4@">Read is unmapped</option> + <option value="8" selected="@S8@">Mate is unmapped</option> + <option value="16" selected="@S16@">Read is mapped to the reverse strand of the reference</option> + <option value="32" selected="@S32@">Mate is mapped to the reverse strand of the reference</option> + <option value="64" selected="@S64@">Read is the first in a pair</option> + <option value="128" selected="@S128@">Read is the second in a pair</option> + <option value="256" selected="@S256@">Alignment of the read is not primary</option> + <option value="512" selected="@S512@">Read fails platform/vendor quality checks</option> + <option value="1024" selected="@S1024@">Read is a PCR or optical duplicate</option> + <option value="2048" selected="@S2048@">Alignment is supplementary</option> + </xml> + + <!-- region specification macros and tokens for tools that allow the specification + of region by bed file / space separated list of regions --> + <token name="@REGIONS_FILE@"><![CDATA[ + #if $cond_region.select_region == 'tab': + -t '$cond_region.targetregions' + #end if + ]]></token> + <token name="@REGIONS_MANUAL@"><![CDATA[ + #if $cond_region.select_region == 'text': + #for $i, $x in enumerate($cond_region.regions_repeat): + '${x.region}' + #end for + #end if + ]]></token> + <xml name="regions_macro"> + <conditional name="cond_region"> + <param name="select_region" type="select" label="Filter by regions" help="restricts output to only those alignments which overlap the specified region(s)"> + <option value="no" selected="True">No</option> + <option value="text">Manualy specify regions</option> + <option value="tab">Regions from tabular file</option> + </param> + <when value="no"/> + <when value="text"> + <repeat name="regions_repeat" min="1" default="1" title="Regions"> + <param name="region" type="text" label="region" help="format chr:from-to"> + <validator type="regex" message="Required format: CHR[:FROM[-TO]]; where CHR: string containing any character except quotes, whitespace and colon; FROM and TO: any integer">^[^\s'\":]+(:\d+(-\d+){0,1}){0,1}$</validator> + </param> + </repeat> + </when> + <when value="tab"> + <param name="targetregions" argument="-t/--target-regions" type="data" format="tabular" label="Target regions file" help="Do stats in these regions only. Tab-delimited file chr,from,to (1-based, inclusive)" /> + </when> + </conditional> + </xml> + + <xml name="citations"> + <citations> + <citation type="bibtex"> + @misc{SAM_def, + title={Definition of SAM/BAM format}, + url = {https://samtools.github.io/hts-specs/},} + </citation> + <citation type="doi">10.1093/bioinformatics/btp352</citation> + <citation type="doi">10.1093/bioinformatics/btr076</citation> + <citation type="doi">10.1093/bioinformatics/btr509</citation> + <citation type="bibtex"> + @misc{Danecek_et_al, + Author={Danecek, P., Schiffels, S., Durbin, R.}, + title={Multiallelic calling model in bcftools (-m)}, + url = {http://samtools.github.io/bcftools/call-m.pdf},} + </citation> + <citation type="bibtex"> + @misc{Durbin_VCQC, + Author={Durbin, R.}, + title={Segregation based metric for variant call QC}, + url = {http://samtools.github.io/bcftools/rd-SegBias.pdf},} + </citation> + <citation type="bibtex"> + @misc{Li_SamMath, + Author={Li, H.}, + title={Mathematical Notes on SAMtools Algorithms}, + url = {http://www.broadinstitute.org/gatk/media/docs/Samtools.pdf},} + </citation> + <citation type="bibtex"> + @misc{SamTools_github, + title={SAMTools GitHub page}, + url = {https://github.com/samtools/samtools},} + </citation> + </citations> + </xml> + <xml name="version_command"> + <version_command><![CDATA[samtools 2>&1 | grep Version]]></version_command> + </xml> + <xml name="stdio"> + <stdio> + <exit_code range="1:" level="fatal" description="Error" /> + </stdio> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/samtools_coverage.xml Tue Sep 28 15:10:16 2021 +0000 @@ -0,0 +1,126 @@ +<tool id="samtools_coverage" name="Samtools coverage" version="@TOOL_VERSION@" profile="@PROFILE@"> + <description>computes the depth at each position or region</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <expand macro="version_command"/> + <command><![CDATA[ + @PREPARE_IDX@ + samtools coverage + + #if $condition_input.input_pooling == "Yes": + ${ ' '.join( [ "'%s'" % $x for $x in $condition_input.input] ) } + #else + '$condition_input.input' + #end if + + -l $additional_options.min_read_length + -q $additional_options.min_mq + -Q $additional_options.min_bq + + #set $filter = $additional_options.required_flags + @FLAGS@ + -rf $flags + + #set $filter = $additional_options.skipped_flags + @FLAGS@ + -ff $flags + + #if $condition_histogram.histogram_select == "yes" + -m + -w $condition_histogram.n_bins + #if $condition_histogram.region != "": + -r '$condition_histogram.region' + #end if + #end if + + -o '$output' + ]]></command> + <inputs> + <conditional name="condition_input"> + <param name="input_pooling" type="select" label="Are you pooling bam files?" help="Calculate the coverage for multiple bam files" > + <option value="No" selected="True">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" > + <param name="input" type="data" format="bam" multiple="true" label="BAM file"/> + </when> + <when value="Yes"> + <param name="input" type="data" format="bam" multiple="true" label="BAM files to be pooled"/> + </when> + </conditional> + + <section name="additional_options" title="Additional Options" expanded="true"> + <param name="min_read_length" argument="-l" type="integer" min="0" value="0" label="Minimum read length" help="Ignore reads shorter than INT base pairs (Default = 0)" /> + <param name="min_mq" argument="-q" type="integer" min="0" value="0" label="Minimum mapping quality" help="Minimum mapping quality for an alignment to be used (Default = 0)" /> + <param name="min_bq" argument="-Q" type="integer" min="0" value="0" label="Minimum base quality" help="Minimum base quality for a base to be considered (Default = 0)" /> + + <param name="required_flags" argument="--rf" type="select" multiple="True" label="Require that these flags are set"> + <expand macro="flag_options" /> + </param> + + <param name="skipped_flags" argument="--ff" type="select" multiple="True" label="Exclude reads with any of the following flags set"> + <expand macro="flag_options" s4="true" s256="true" s512="true" s1024="true"/> + </param> + </section> + + <conditional name="condition_histogram"> + <param name="histogram_select" argument="-m" type="select" label="Histogram" help="Show histogram instead of tabular output"> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> + </param> + <when value="yes"> + <param name="n_bins" argument="-w" type="integer" min="1" value="100" label="Number of bins in histogram" help="Number of bins in histogram" /> + <param name="region" argument="-r" type="text" value="" label="Show specified region" help="Show specified region. Format: chr:start-end." /> + </when> + <when value="no" /> + </conditional> + </inputs> + + <outputs> + <data name="output" format="tabular" from_work_dir="outfile" label="${tool.name} on ${on_string}" /> + </outputs> + + <tests> + <test> + <param name="input" value="test_1.bam" ftype="bam" /> + <output name="output" file="results_1.tabular" ftype="tabular" /> + </test> + <test> + <param name="input" value="test_1.bam" ftype="bam" /> + <param name="histogram_select" value="yes" /> + <param name="n_bins" value="50" /> + <output name="output" file="results_2.txt" ftype="tabular" /> + </test> + <test> + <param name="input_pooling" value="Yes" /> + <param name="input" value="test_1.bam,test_2.bam" ftype="bam" /> + <param name="histogram_select" value="yes" /> + <param name="n_bins" value="100" /> + <output name="output" file="results_3.txt" ftype="tabular" /> + </test> + </tests> + <help><![CDATA[ +**What it does** + +This tool runs the ``samtools coverage`` command. + +Computes the depth at each position or region and draws an ASCII-art histogram or tabulated text. If you select to pool the bam files, then it calculates coverage for the combined files. + +The tabulated form uses the following headings: + +- rname Reference name / chromosome +- startpos Start position +- endpos End position (or sequence length) +- numreads Number reads aligned to the region (after filtering) +- covbases Number of covered bases with depth >= 1 +- coverage Proportion of covered bases [0..1] +- meandepth Mean depth of coverage +- meanbaseq Mean baseQ in covered region +- meanmapq Mean mapQ of selected reads + + ]]></help> + <expand macro="citations"/> +</tool>