Mercurial > repos > devteam > samtools_stats
diff samtools_stats.xml @ 0:cd6eb75c9819 draft
Uploaded initial tool definition.
| author | devteam |
|---|---|
| date | Mon, 20 Oct 2014 14:56:49 -0400 |
| parents | |
| children | cc56fc603e53 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/samtools_stats.xml Mon Oct 20 14:56:49 2014 -0400 @@ -0,0 +1,227 @@ +<tool id="samtools_stats" name="Generate statistics" version="1.0.0"> + <description>for a BAM or SAM file</description> + <requirements> + <requirement type="package" version="1.1">samtools</requirement> + </requirements> + <version_command>samtools --version | head -n 1 | awk '{ print $2 }'</version_command> + <command><![CDATA[ + #if $use_reference.use_ref_selector == "yes": + #if $use_reference.reference_source.reference_source_selector == "history": + ln -s "${use_reference.reference_source.ref_file}" && samtools faidx `basename "${use_reference.reference_source.ref_file}"` && samtools stats + #else: + samtools stats + #end if + #else: + samtools stats + #end if + "${input_file}" + --coverage ${coverage_min},${coverage_max},${coverage_step} + ${remove_dups} + #if str( $filter_by_flags.filter_flags ) == "filter": + #if $filter_by_flags.require_flags: + --required-flag ${sum([int(flag) for flag in str($filter_by_flags.require_flags).split(',')])} + #end if + #if $filter_by_flags.exclude_flags: + --filtering-flag ${sum([int(flag) for flag in str($filter_by_flags.exclude_flags).split(',')])} + #end if + #end if + --GC-depth ${gc_depth} + --insert-size ${insert_size} + #if str($read_length) != "0": + --read-length "${read_length}" + #end if + --most-inserts ${most_inserts} + --trim-quality ${trim_quality} + #if $use_reference.use_ref_selector == "yes": + #if $use_reference.reference_source.reference_source_selector != "history": + --ref-seq "${use_reference.reference_source.ref_file.fields.path}" + #else: + --ref-seq "${use_reference.reference_source.ref_file}" + #end if + #end if + > "${output}" + #if $split_output.split_output_selector == "yes": + #set outputs_to_split = str($split_output.generate_tables).split(',') + && mkdir split && echo ${split_output.generate_tables} && + #if 'sn' in $outputs_to_split: + grep -q ^SN "${output}" ; if [ $? = 0 ] ; then grep ^SN "${output}" | cut -f 2- > "split/Summary numbers.tab" ; fi && + #end if + #if 'ffq' in $outputs_to_split: + grep -q ^FFQ "${output}" ; if [ $? = 0 ] ; then grep ^FFQ "${output}" | cut -f 2- > "split/First Fragment Qualities.tab" ; fi && + #end if + #if 'lfq' in $outputs_to_split: + grep -q ^LFQ "${output}" ; if [ $? = 0 ] ; then grep ^LFQ "${output}" | cut -f 2- > "split/Last Fragment Qualities.tab" ; fi && + #end if + #if 'mpc' in $outputs_to_split: + grep -q ^MPC "${output}" ; if [ $? = 0 ] ; then grep ^MPC "${output}" | cut -f 2- > "split/Mismatches per cycle.tab" ; fi && + #end if + #if 'gcf' in $outputs_to_split: + grep -q ^GCF "${output}" ; if [ $? = 0 ] ; then grep ^GCF "${output}" | cut -f 2- > "split/GC Content of first fragments.tab" ; fi && + #end if + #if 'gcl' in $outputs_to_split: + grep -q ^GCL "${output}" ; if [ $? = 0 ] ; then grep ^GCL "${output}" | cut -f 2- > "split/GC Content of last fragments.tab" ; fi && + #end if + #if 'gcc' in $outputs_to_split: + grep -q ^GCC "${output}" ; if [ $? = 0 ] ; then grep ^GCC "${output}" | cut -f 2- > "split/ACGT content per cycle.tab" ; fi && + #end if + #if 'is' in $outputs_to_split: + grep -q ^IS "${output}" ; if [ $? = 0 ] ; then grep ^IS "${output}" | cut -f 2- > "split/Insert sizes.tab" ; fi && + #end if + #if 'rl' in $outputs_to_split: + grep -q ^RL "${output}" ; if [ $? = 0 ] ; then grep ^RL "${output}" | cut -f 2- > "split/Read lengths.tab" ; fi && + #end if + #if 'id' in $outputs_to_split: + grep -q ^ID "${output}" ; if [ $? = 0 ] ; then grep ^ID "${output}" | cut -f 2- > "split/Indel distribution.tab" ; fi && + #end if + #if 'ic' in $outputs_to_split: + grep -q ^IC "${output}" ; if [ $? = 0 ] ; then grep ^IC "${output}" | cut -f 2- > "split/Indels per cycle.tab" ; fi && + #end if + #if 'cov' in $outputs_to_split: + grep -q ^COV "${output}" ; if [ $? = 0 ] ; then grep ^COV "${output}" | cut -f 2- > "split/Coverage distribution.tab" ; fi && + #end if + #if 'gcd' in $outputs_to_split: + grep -q ^GCD "${output}" ; if [ $? = 0 ] ; then grep ^GCD "${output}" | cut -f 2- > "split/GC depth.tab" ; fi + #end if + #end if + ]]></command> + <stdio> + <exit_code range="1:" level="fatal" description="Error" /> + </stdio> + <inputs> + <param name="input_file" type="data" format="sam,bam" label="BAM file" /> + <param name="coverage_min" type="integer" value="1" label="Minimum coverage" /> + <param name="coverage_max" type="integer" value="1000" label="Maximum coverage" /> + <param name="coverage_step" type="integer" value="1" label="Coverage step" /> + <param name="remove_dups" type="boolean" truevalue="--remove-dups" falsevalue="" checked="False" label="Exclude reads marked as duplicates" /> + <conditional name="split_output"> + <param name="split_output_selector" type="select" label="Output"> + <option value="no" selected="True">Output to a summary file</option> + <option value="yes">Extract separate statistics</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="generate_tables" type="select" display="checkboxes" multiple="True" label="Statistics to extract"> + <option value="sn">Summary numbers</option> + <option value="ffq">First Fragment Qualities</option> + <option value="lfq">Last Fragment Qualities</option> + <option value="mpc">Mismatches per cycle</option> + <option value="gcf">GC Content of first fragments</option> + <option value="gcl">GC Content of last fragments</option> + <option value="gcc">ACGT content per cycle</option> + <option value="is">Insert sizes</option> + <option value="rl">Read lengths</option> + <option value="id">Indel distribution</option> + <option value="ic">Indels per cycle</option> + <option value="cov">Coverage distribution</option> + <option value="gcd">GC depth</option> + </param> + </when> + </conditional> + <conditional name="filter_by_flags"> + <param name="filter_flags" type="select" label="Set filter by flags"> + <option value="nofilter" selected="True">Do not filter</option> + <option value="filter">Filter by flags to exclude or require</option> + </param> + <when value="filter"> + <param name="require_flags" type="select" display="checkboxes" multiple="True" label="Require"> + <option value="1">Read is paired</option> + <option value="2">Read is mapped in a proper pair</option> + <option value="4">The read is unmapped</option> + <option value="8">The mate is unmapped</option> + <option value="16">Read strand</option> + <option value="32">Mate strand</option> + <option value="64">Read is the first in a pair</option> + <option value="128">Read is the second in a pair</option> + <option value="256">The alignment or this read is not primary</option> + <option value="512">The read fails platform/vendor quality checks</option> + <option value="1024">The read is a PCR or optical duplicate</option> + </param> + <param name="exclude_flags" type="select" display="checkboxes" multiple="True" label="Exclude"> + <option value="1">Read is paired</option> + <option value="2">Read is mapped in a proper pair</option> + <option value="4">The read is unmapped</option> + <option value="8">The mate is unmapped</option> + <option value="16">Read strand</option> + <option value="32">Mate strand</option> + <option value="64">Read is the first in a pair</option> + <option value="128">Read is the second in a pair</option> + <option value="256">The alignment or this read is not primary</option> + <option value="512">The read fails platform/vendor quality checks</option> + <option value="1024">The read is a PCR or optical duplicate</option> + </param> + </when> + <when value="nofilter" /> + </conditional> + <param name="gc_depth" type="float" value="2000" label="GC-depth bin size" /> + <param name="insert_size" type="integer" value="8000" label="Maximum insert size" /> + <param name="read_group" type="text" optional="true" label="Limit to a specific read group name" /> + <param name="read_length" type="integer" value="0" optional="true" label="Minimum read length to generate statistics for" /> + <param name="most_inserts" type="float" value="0.99" label="Report only the main part of inserts" /> + <param name="trim_quality" type="integer" value="0" label="BWA trim parameter" /> + <conditional name="use_reference"> + <param name="use_ref_selector" type="select" label="Use reference sequence"> + <option value="yes">Use reference</option> + <option value="no">Do not use reference</option> + </param> + <when value="yes"> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Choose a reference sequence for GC depth"> + <option value="cached">Locally cached</option> + <option value="history">History</option> + </param> + <when value="cached"> + <param name="ref_file" type="select" label="Using genome"> + <options from_data_table="fasta_indexes" /> + <filter type="data_meta" ref="input_file" key="dbkey" column="1" /> + </param> + </when> + <when value="history"> + <param name="ref_file" type="data" format="fasta" label="Using file" /> + </when> + </conditional> + </when> + <when value="no" /> + </conditional> + </inputs> + <outputs> + <data format="tabular" name="output" label="${tool.name} on ${on_string}"> + <discover_datasets pattern="(?P<designation>.+)\.tab" ext="tabular" visible="true" directory="split" /> + </data> + </outputs> + <tests> + <test> + <param name="input_file" value="phiX.bam" ftype="bam" /> + <param name="use_ref_selector" value="no" /> + <output name="output" file="samtools_stats_out1.tab" ftype="tabular" lines_diff="2" /> + </test> + <test> + <param name="input_file" value="phiX.bam" ftype="bam" /> + <param name="use_ref_selector" value="no" /> + <param name="split_output_selector" value="yes" /> + <param name="generate_tables" value="sn,gcf,gcl,gcc,cov,gcd" /> + <output name="output" file="samtools_stats_out2.tab" lines_diff="2"> + <discovered_dataset designation="Summary numbers" ftype="tabular" file="samtools_stats_out2/sn.tab" /> + <discovered_dataset designation="GC Content of first fragments" ftype="tabular" file="samtools_stats_out2/gcf.tab" /> + <discovered_dataset designation="GC Content of last fragments" ftype="tabular" file="samtools_stats_out2/gcl.tab" /> + <discovered_dataset designation="ACGT content per cycle" ftype="tabular" file="samtools_stats_out2/gcc.tab" /> + <discovered_dataset designation="Coverage distribution" ftype="tabular" file="samtools_stats_out2/cov.tab" /> + <discovered_dataset designation="GC depth" ftype="tabular" file="samtools_stats_out2/gcd.tab" /> + </output> + </test> + </tests> + <help> +**What it does** + +This tool runs the ``samtools stats`` command in the SAMtools toolkit. + +Collects statistics from BAM files. The output can be visualized using plot-bamstats. + +**Citation** + +For the underlying tool, please cite `Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, Marth G, Abecasis G, Durbin R; 1000 Genome Project Data Processing Subgroup. The Sequence Alignment/Map format and SAMtools. Bioinformatics. 2009 Aug 15;25(16):2078-9. <http://www.ncbi.nlm.nih.gov/pubmed/19505943>`_ + + +If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.* + </help> +</tool> +