| Next changeset 1:5f3ea90dc6ae (2022-08-15) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_ampliconclip commit 4596e7b08744df85b48d106cf4d44ebdd90dd554 |
|
added:
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 |
| b |
| diff -r 000000000000 -r a941babb9268 macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Mon Jun 27 20:07:59 2022 +0000 |
| [ |
| b'@@ -0,0 +1,256 @@\n+<macros>\n+ <xml name="requirements">\n+ <requirements>\n+ <requirement type="package" version="@TOOL_VERSION@">samtools</requirement>\n+ <yield/>\n+ </requirements>\n+ </xml>\n+ <token name="@TOOL_VERSION@">1.13</token>\n+ <token name="@PROFILE@">20.05</token>\n+ <token name="@FLAGS@"><![CDATA[\n+ #set $flags = 0\n+ #if $filter\n+ #set $flags = sum(map(int, str($filter).split(\',\')))\n+ #end if\n+ ]]></token>\n+ <token name="@PREPARE_IDX@"><![CDATA[\n+ ##prepare input and indices\n+ ln -s \'$input\' infile &&\n+ #if $input.is_of_type(\'bam\'):\n+ #if str( $input.metadata.bam_index ) != "None":\n+ ln -s \'${input.metadata.bam_index}\' infile.bai &&\n+ #else:\n+ samtools index infile infile.bai &&\n+ #end if\n+ #elif $input.is_of_type(\'cram\'):\n+ #if str( $input.metadata.cram_index ) != "None":\n+ ln -s \'${input.metadata.cram_index}\' infile.crai &&\n+ #else:\n+ samtools index infile infile.crai &&\n+ #end if\n+ #end if\n+ ]]></token>\n+ <token name="@PREPARE_IDX_MULTIPLE@"><![CDATA[\n+ ##prepare input and indices\n+ #for $i, $bam in enumerate( $input_bams ):\n+ ln -s \'$bam\' \'${i}\' &&\n+ #if $bam.is_of_type(\'bam\'):\n+ #if str( $bam.metadata.bam_index ) != "None":\n+ ln -s \'${bam.metadata.bam_index}\' \'${i}.bai\' &&\n+ #else:\n+ samtools index \'${i}\' \'${i}.bai\' &&\n+ #end if\n+ #elif $bam.is_of_type(\'cram\'):\n+ #if str( $bam.metadata.cram_index ) != "None":\n+ ln -s \'${bam.metadata.cram_index}\' \'${i}.crai\' &&\n+ #else:\n+ samtools index \'${i}\' \'${i}.crai\' &&\n+ #end if\n+ #end if\n+ #end for\n+ ]]></token>\n+ <token name="@PREPARE_FASTA_IDX@"><![CDATA[\n+ ## Make the user-selected reference genome, if any, accessible through\n+ ## a shell variable $reffa, index the reference if necessary, and make\n+ ## the fai-index file available through a shell variable $reffai.\n+\n+ ## For a cached genome simply sets the shell variables to point to the\n+ ## genome file and its precalculated index.\n+ ## For a genome from the user\'s history, if that genome is a plain\n+ ## fasta file, the code creates a symlink in the pwd, creates the fai\n+ ## index file next to it, then sets the shell variables to point to the\n+ ## symlink and its index.\n+ ## For a fasta.gz dataset from the user\'s history, it tries the same,\n+ ## but this will only succeed if the file got compressed with bgzip.\n+ ## For a regular gzipped file samtools faidx will fail, in which case\n+ ## the code falls back to decompressing to plain fasta before\n+ ## reattempting the indexing.\n+ ## Indexing of a bgzipped file produces a regular fai index file *and*\n+ ## a compressed gzi file. The former is identical to the fai index of\n+ ## the uncompressed fasta.\n+\n+ ## If the user has not selected a reference (it\'s an optional parameter\n+ ## in some samtools wrappers), a cheetah boolean use_ref is set to\n+ ## False to encode that fact.\n+\n+ #set use_ref=True\n+ #if $addref_cond.addref_select == "history":\n+ #if $addref_cond.ref.is_of_type(\'fasta\'):\n+ reffa="reference.fa" &&\n+ ln -s \'${addref_cond.ref}\' \\$reffa &&\n+ samtools faidx \\$reffa &&\n+ #else:\n+ reffa="reference.fa.gz" &&\n+ ln -s \'${addref_cond.ref}\' \\$reffa &&\n+ {\n+ samtools faidx \\$reffa ||\n+ {\n+ echo "Failed to index compressed reference. Trying decompressed ..." 1>&2 &&\n+ '..b'ed="@S1024@">Read is a PCR or optical duplicate</option>\n+ <option value="2048" selected="@S2048@">Alignment is supplementary</option>\n+ </xml>\n+\n+ <!-- region specification macros and tokens for tools that allow the specification\n+ of region by bed file / space separated list of regions -->\n+ <token name="@REGIONS_FILE@"><![CDATA[\n+ #if $cond_region.select_region == \'tab\':\n+ -t \'$cond_region.targetregions\'\n+ #end if\n+ ]]></token>\n+ <token name="@REGIONS_MANUAL@"><![CDATA[\n+ #if $cond_region.select_region == \'text\':\n+ #for $i, $x in enumerate($cond_region.regions_repeat):\n+ \'${x.region}\'\n+ #end for\n+ #end if\n+ ]]></token>\n+ <xml name="regions_macro">\n+ <conditional name="cond_region">\n+ <param name="select_region" type="select" label="Filter by regions" help="restricts output to only those alignments which overlap the specified region(s)">\n+ <option value="no" selected="True">No</option>\n+ <option value="text">Manualy specify regions</option>\n+ <option value="tab">Regions from tabular file</option>\n+ </param>\n+ <when value="no"/>\n+ <when value="text">\n+ <repeat name="regions_repeat" min="1" default="1" title="Regions">\n+ <param name="region" type="text" label="region" help="format chr:from-to">\n+ <validator type="regex" message="Required format: CHR[:FROM[-TO]]; where CHR: string containing any character except quotes, whitespace and colon; FROM and TO: any integer">^[^\\s\'\\":]+(:\\d+(-\\d+){0,1}){0,1}$</validator>\n+ </param>\n+ </repeat>\n+ </when>\n+ <when value="tab">\n+ <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)" />\n+ </when>\n+ </conditional>\n+ </xml>\n+\n+ <xml name="citations">\n+ <citations>\n+ <citation type="bibtex">\n+ @misc{SAM_def,\n+ title={Definition of SAM/BAM format},\n+ url = {https://samtools.github.io/hts-specs/},}\n+ </citation>\n+ <citation type="doi">10.1093/bioinformatics/btp352</citation>\n+ <citation type="doi">10.1093/bioinformatics/btr076</citation>\n+ <citation type="doi">10.1093/bioinformatics/btr509</citation>\n+ <citation type="bibtex">\n+ @misc{Danecek_et_al,\n+ Author={Danecek, P., Schiffels, S., Durbin, R.},\n+ title={Multiallelic calling model in bcftools (-m)},\n+ url = {http://samtools.github.io/bcftools/call-m.pdf},}\n+ </citation>\n+ <citation type="bibtex">\n+ @misc{Durbin_VCQC,\n+ Author={Durbin, R.},\n+ title={Segregation based metric for variant call QC},\n+ url = {http://samtools.github.io/bcftools/rd-SegBias.pdf},}\n+ </citation>\n+ <citation type="bibtex">\n+ @misc{Li_SamMath,\n+ Author={Li, H.},\n+ title={Mathematical Notes on SAMtools Algorithms},\n+ url = {http://www.broadinstitute.org/gatk/media/docs/Samtools.pdf},}\n+ </citation>\n+ <citation type="bibtex">\n+ @misc{SamTools_github,\n+ title={SAMTools GitHub page},\n+ url = {https://github.com/samtools/samtools},}\n+ </citation>\n+ </citations>\n+ </xml>\n+ <xml name="version_command">\n+ <version_command><![CDATA[samtools 2>&1 | grep Version]]></version_command>\n+ </xml>\n+ <xml name="stdio">\n+ <stdio>\n+ <exit_code range="1:" level="fatal" description="Error" />\n+ </stdio>\n+ </xml>\n+</macros>\n' |
| b |
| diff -r 000000000000 -r a941babb9268 samtools_ampliconclip.xml --- /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> |
| b |
| diff -r 000000000000 -r a941babb9268 test-data/eboVir3.1.bed --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/eboVir3.1.bed Mon Jun 27 20:07:59 2022 +0000 |
| b |
| @@ -0,0 +1,3 @@ +eboVir3 500 1500 1 0 - +eboVir3 1500 2000 2 0 + +eboVir3 1500 3000 3 0 - |
| b |
| diff -r 000000000000 -r a941babb9268 test-data/eboVir3.bam |
| b |
| Binary file test-data/eboVir3.bam has changed |
| b |
| diff -r 000000000000 -r a941babb9268 test-data/eboVir3.clipped.bam |
| b |
| Binary file test-data/eboVir3.clipped.bam has changed |
| b |
| diff -r 000000000000 -r a941babb9268 test-data/eboVir3.clipped.strand.bam |
| b |
| Binary file test-data/eboVir3.clipped.strand.bam has changed |
| b |
| diff -r 000000000000 -r a941babb9268 test-data/eboVir3.clipped.strand_gt30.bam |
| b |
| Binary file test-data/eboVir3.clipped.strand_gt30.bam has changed |
| b |
| diff -r 000000000000 -r a941babb9268 test-data/eboVir3.hardclipped.bam |
| b |
| Binary file test-data/eboVir3.hardclipped.bam has changed |
| b |
| diff -r 000000000000 -r a941babb9268 test-data/rebuild_output_bams.sh --- /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 |
| b |
| @@ -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 |