Mercurial > repos > iuc > samtools_ampliconclip
changeset 0:a941babb9268 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_ampliconclip commit 4596e7b08744df85b48d106cf4d44ebdd90dd554
| author | iuc |
|---|---|
| date | Mon, 27 Jun 2022 20:07:59 +0000 |
| parents | |
| children | 5f3ea90dc6ae |
| files | macros.xml samtools_ampliconclip.xml test-data/eboVir3.1.bed test-data/eboVir3.bam test-data/eboVir3.clipped.bam test-data/eboVir3.clipped.strand.bam test-data/eboVir3.clipped.strand_gt30.bam test-data/eboVir3.hardclipped.bam test-data/rebuild_output_bams.sh |
| diffstat | 9 files changed, 346 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Mon Jun 27 20:07:59 2022 +0000 @@ -0,0 +1,256 @@ +<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[ + ## Make the user-selected reference genome, if any, accessible through + ## a shell variable $reffa, index the reference if necessary, and make + ## the fai-index file available through a shell variable $reffai. + + ## For a cached genome simply sets the shell variables to point to the + ## genome file and its precalculated index. + ## For a genome from the user's history, if that genome is a plain + ## fasta file, the code creates a symlink in the pwd, creates the fai + ## index file next to it, then sets the shell variables to point to the + ## symlink and its index. + ## For a fasta.gz dataset from the user's history, it tries the same, + ## but this will only succeed if the file got compressed with bgzip. + ## For a regular gzipped file samtools faidx will fail, in which case + ## the code falls back to decompressing to plain fasta before + ## reattempting the indexing. + ## Indexing of a bgzipped file produces a regular fai index file *and* + ## a compressed gzi file. The former is identical to the fai index of + ## the uncompressed fasta. + + ## If the user has not selected a reference (it's an optional parameter + ## in some samtools wrappers), a cheetah boolean use_ref is set to + ## False to encode that fact. + + #set use_ref=True + #if $addref_cond.addref_select == "history": + #if $addref_cond.ref.is_of_type('fasta'): + reffa="reference.fa" && + ln -s '${addref_cond.ref}' \$reffa && + samtools faidx \$reffa && + #else: + reffa="reference.fa.gz" && + ln -s '${addref_cond.ref}' \$reffa && + { + samtools faidx \$reffa || + { + echo "Failed to index compressed reference. Trying decompressed ..." 1>&2 && + gzip -dc \$reffa > reference.fa && + reffa="reference.fa" && + samtools faidx \$reffa; + } + } && + #end if + reffai=\$reffa.fai && + #elif $addref_cond.addref_select == "cached": + ## in case of cached the absolute path is used which allows to read + ## a cram file without specifying the reference + reffa='${addref_cond.ref.fields.path}' && + reffai=\$reffa.fai && + #else + #set use_ref=False + #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_ampliconclip.xml Mon Jun 27 20:07:59 2022 +0000 @@ -0,0 +1,83 @@ +<tool id="samtools_ampliconclip" name="Samtools ampliconclip" version="@TOOL_VERSION@" profile="@PROFILE@"> + <description>clip primer bases from bam files</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <expand macro="version_command"/> + <command><![CDATA[ + @ADDTHREADS@ + samtools ampliconclip + $hard_clip_mode + #if $min_length: + --fail-len $min_length + #end if + --tolerance $tolerance + $strand + -b '${input_bed}' + -u + $both_ends + $no_excluded + -@ \$addthreads + '${input_bam}' + | samtools collate -@ \$addthreads -O -u - + | samtools fixmate -@ \$addthreads -u - - + | samtools sort -@ \$addthreads -m \${GALAXY_MEMORY_MB:-768}M -T "\${TMPDIR:-.}" -o '${output_bam}' + ]]></command> + <inputs> + <param name="input_bed" type="data" format="bed" label="Genetic intervals (in BED format)" /> + <param name="input_bam" type="data" format="bam" label="BAM file" /> + <param name="hard_clip_mode" argument="--hard-clip" type="boolean" checked="false" truevalue="--hard-clip" falsevalue="--soft-clip" label="hard clip" help="hard clip (remove bases), unchekced = default soft-clipping" /> + <param name="strand" argument="--strand" type="boolean" checked="false" truevalue="--strand" falsevalue="" label="only clip reads that match bed file strand annotation" /> + <param name="both_ends" argument="--both-ends" type="boolean" checked="false" truevalue="--both-ends" falsevalue="" label="clip both ends of reads (false = 5' only)" /> + <param name="no_excluded" argument="--no-excluded" type="boolean" checked="false" truevalue="--no-excluded" falsevalue="" label="don't write excluded reads to output (default = write all)" /> + <param name="min_length" argument="--fail-len" type="integer" min="0" optional="true" label="Min Read length" help="mark reads QCFAIL at this length or shorter after clipping" /> + <param name="tolerance" argument="--tolerance" type="integer" value="5" min="0" label="Tolerance" help="match region within this number of bases, default 5." /> + + </inputs> + <outputs> + <data name="output_bam" format="bam" /> + </outputs> + <tests> + <!-- 1) --> + <test> + <param name="input_bed" value="eboVir3.1.bed" ftype="bed" /> + <param name="input_bam" value="eboVir3.bam" ftype="bam" /> + <output name="output_bam" file="eboVir3.clipped.bam" ftype="bam" lines_diff="22" /> + </test> + <!-- 2) testing strand --> + <test> + <param name="input_bed" value="eboVir3.1.bed" ftype="bed" /> + <param name="input_bam" value="eboVir3.bam" ftype="bam" /> + <param name="strand" value="--strand" /> + <output name="output_bam" file="eboVir3.clipped.strand.bam" ftype="bam" lines_diff="16" /> + </test> + <!-- 3) testing hard clip--> + <test> + <param name="input_bed" value="eboVir3.1.bed" ftype="bed" /> + <param name="input_bam" value="eboVir3.bam" ftype="bam" /> + <param name="hard_clip_mode" value="--hard-clip" /> + <output name="output_bam" file="eboVir3.hardclipped.bam" ftype="bam" lines_diff="14" /> + </test> + <!-- 4) testing strand and min length--> + <test> + <param name="input_bed" value="eboVir3.1.bed" ftype="bed" /> + <param name="input_bam" value="eboVir3.bam" ftype="bam" /> + <param name="min_length" value="30" /> + <param name="strand" value="--strand" /> + <param name="tolerance" value="6" /> + <param name="both_ends" value="--both-ends" /> + <param name="no_excluded" value="--no-excluded" /> + <output name="output_bam" file="eboVir3.clipped.strand_gt30.bam" ftype="bam" lines_diff="13" /> + </test> + + </tests> + <help> +**What it does** + Clips read alignments where they match BED file defined regions (e.g. for amplicon sequencing). + + samtools ampliconclip -b [INPUT BED] [INPUT BAM1] -o [OUTPUT] + </help> + <expand macro="citations"/> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/eboVir3.1.bed Mon Jun 27 20:07:59 2022 +0000 @@ -0,0 +1,3 @@ +eboVir3 500 1500 1 0 - +eboVir3 1500 2000 2 0 + +eboVir3 1500 3000 3 0 -
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/rebuild_output_bams.sh Mon Jun 27 20:07:59 2022 +0000 @@ -0,0 +1,4 @@ +samtools ampliconclip -b eboVir3.1.bed eboVir3.bam | samtools collate -@ 0 -O -u - | samtools fixmate -@ 0 -u - - | samtools sort -o eboVir3.clipped.bam +samtools ampliconclip --strand -b eboVir3.1.bed eboVir3.bam | samtools collate -@ 0 -O -u - | samtools fixmate -@ 0 -u - - | samtools sort -o eboVir3.clipped.strand.bam +samtools ampliconclip --hard-clip -b eboVir3.1.bed eboVir3.bam | samtools collate -@ 0 -O -u - | samtools fixmate -@ 0 -u - - | samtools sort -o eboVir3.hardclipped.bam +samtools ampliconclip --both-ends --no-excluded --strand --fail-len 30 -b eboVir3.1.bed eboVir3.bam | samtools collate -@ 0 -O -u - | samtools fixmate -@ 0 -u - - | samtools sort -o eboVir3.clipped.strand_gt30.bam