Previous changeset 3:890d97772e2a (2014-01-09) |
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/sam_pileup commit 8301d37348be25a038b3c63b049b1178d05f5003" |
modified:
sam_pileup.xml |
removed:
sam_pileup.py tool_dependencies.xml |
b |
diff -r 890d97772e2a -r a3b4ad6858ff sam_pileup.py --- a/sam_pileup.py Thu Jan 09 14:28:39 2014 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
[ |
@@ -1,146 +0,0 @@ -#!/usr/bin/env python - -""" -Creates a pileup file from a bam file and a reference. - -usage: %prog [options] - -p, --input1=p: bam file - -o, --output1=o: Output pileup - -R, --ref=R: Reference file type - -n, --ownFile=n: User-supplied fasta reference file - -b, --bamIndex=b: BAM index file - -g, --index=g: Path of the indexed reference genome - -s, --lastCol=s: Print the mapping quality as the last column - -i, --indels=i: Only output lines containing indels - -M, --mapCap=M: Cap mapping quality - -c, --consensus=c: Call the consensus sequence using MAQ consensu model - -T, --theta=T: Theta paramter (error dependency coefficient) - -N, --hapNum=N: Number of haplotypes in sample - -r, --fraction=r: Expected fraction of differences between a pair of haplotypes - -I, --phredProb=I: Phred probability of an indel in sequencing/prep - -""" - -import os, shutil, subprocess, sys, tempfile -from galaxy import eggs -import pkg_resources; pkg_resources.require( "bx-python" ) -from bx.cookbook import doc_optparse - -def stop_err( msg ): - sys.stderr.write( '%s\n' % msg ) - sys.exit() - -def __main__(): - #Parse Command Line - options, args = doc_optparse.parse( __doc__ ) - # output version # of tool - try: - tmp = tempfile.NamedTemporaryFile().name - tmp_stdout = open( tmp, 'wb' ) - proc = subprocess.Popen( args='samtools 2>&1', shell=True, stdout=tmp_stdout ) - tmp_stdout.close() - returncode = proc.wait() - stdout = None - for line in open( tmp_stdout.name, 'rb' ): - if line.lower().find( 'version' ) >= 0: - stdout = line.strip() - break - if stdout: - sys.stdout.write( 'Samtools %s\n' % stdout ) - else: - raise Exception - except: - sys.stdout.write( 'Could not determine Samtools version\n' ) - #prepare file names - tmpDir = tempfile.mkdtemp() - tmpf0 = tempfile.NamedTemporaryFile( dir=tmpDir ) - tmpf0_name = tmpf0.name - tmpf0.close() - tmpf0bam_name = '%s.bam' % tmpf0_name - tmpf0bambai_name = '%s.bam.bai' % tmpf0_name - tmpf1 = tempfile.NamedTemporaryFile( dir=tmpDir ) - tmpf1_name = tmpf1.name - tmpf1.close() - #link bam and bam index to working directory (can't move because need to leave original) - os.symlink( options.input1, tmpf0bam_name ) - os.symlink( options.bamIndex, tmpf0bambai_name ) - #get parameters for pileup command - if options.lastCol == 'yes': - lastCol = '-s' - else: - lastCol = '' - if options.indels == 'yes': - indels = '-i' - else: - indels = '' - opts = '%s %s -M %s' % ( lastCol, indels, options.mapCap ) - if options.consensus == 'yes': - opts += ' -c -T %s -N %s -r %s -I %s' % ( options.theta, options.hapNum, options.fraction, options.phredProb ) - #prepare basic pileup command - cmd = 'samtools pileup %s -f %s %s > %s' - try: - # have to nest try-except in try-finally to handle 2.4 - try: - #index reference if necessary and prepare pileup command - if options.ref == 'indexed': - if not os.path.exists( "%s.fai" % options.index ): - raise Exception, "Indexed genome %s not present, request it by reporting this error." % options.index - cmd = cmd % ( opts, options.index, tmpf0bam_name, options.output1 ) - elif options.ref == 'history': - os.symlink( options.ownFile, tmpf1_name ) - cmdIndex = 'samtools faidx %s' % ( tmpf1_name ) - tmp = tempfile.NamedTemporaryFile( dir=tmpDir ).name - tmp_stderr = open( tmp, 'wb' ) - proc = subprocess.Popen( args=cmdIndex, shell=True, cwd=tmpDir, stderr=tmp_stderr.fileno() ) - returncode = proc.wait() - tmp_stderr.close() - # get stderr, allowing for case where it's very large - tmp_stderr = open( tmp, 'rb' ) - stderr = '' - buffsize = 1048576 - try: - while True: - stderr += tmp_stderr.read( buffsize ) - if not stderr or len( stderr ) % buffsize != 0: - break - except OverflowError: - pass - tmp_stderr.close() - #did index succeed? - if returncode != 0: - raise Exception, 'Error creating index file\n' + stderr - cmd = cmd % ( opts, tmpf1_name, tmpf0bam_name, options.output1 ) - #perform pileup command - tmp = tempfile.NamedTemporaryFile( dir=tmpDir ).name - tmp_stderr = open( tmp, 'wb' ) - proc = subprocess.Popen( args=cmd, shell=True, cwd=tmpDir, stderr=tmp_stderr.fileno() ) - returncode = proc.wait() - tmp_stderr.close() - #did it succeed? - # get stderr, allowing for case where it's very large - tmp_stderr = open( tmp, 'rb' ) - stderr = '' - buffsize = 1048576 - try: - while True: - stderr += tmp_stderr.read( buffsize ) - if not stderr or len( stderr ) % buffsize != 0: - break - except OverflowError: - pass - tmp_stderr.close() - if returncode != 0: - raise Exception, stderr - except Exception, e: - stop_err( 'Error running Samtools pileup tool\n' + str( e ) ) - finally: - #clean up temp files - if os.path.exists( tmpDir ): - shutil.rmtree( tmpDir ) - # check that there are results in the output file - if os.path.getsize( options.output1 ) > 0: - sys.stdout.write( 'Converted BAM to pileup' ) - else: - stop_err( 'The output file is empty. Your input file may have had no matches, or there may be an error with your input file or settings.' ) - -if __name__ == "__main__" : __main__() |
b |
diff -r 890d97772e2a -r a3b4ad6858ff sam_pileup.xml --- a/sam_pileup.xml Thu Jan 09 14:28:39 2014 -0500 +++ b/sam_pileup.xml Thu Feb 06 07:11:33 2020 -0500 |
[ |
b'@@ -1,124 +1,126 @@\n-<tool id="sam_pileup" name="Generate pileup" version="1.1.2">\n- <description>from BAM dataset</description>\n- <requirements>\n- <requirement type="package" version="0.1.16">samtools</requirement>\n- </requirements>\n- <command interpreter="python">\n- sam_pileup.py\n- --input1=$input1\n- --output=$output1\n- --ref=$refOrHistory.reference\n- #if $refOrHistory.reference == "history":\n- --ownFile=$refOrHistory.ownFile\n- #else:\n- --index=${refOrHistory.index.fields.path}\n- #end if\n- --bamIndex=${input1.metadata.bam_index}\n- --lastCol=$lastCol\n- --indels=$indels\n- --mapCap=$mapCap\n- --consensus=$c.consensus\n- #if $c.consensus == "yes":\n- --theta=$c.theta\n- --hapNum=$c.hapNum\n- --fraction=$c.fraction\n- --phredProb=$c.phredProb\n- #else:\n- --theta="None"\n- --hapNum="None"\n- --fraction="None"\n- --phredProb="None"\n- #end if\n- </command>\n- <inputs>\n- <conditional name="refOrHistory">\n- <param name="reference" type="select" label="Will you select a reference genome from your history or use a built-in index?">\n- <option value="indexed">Use a built-in index</option>\n- <option value="history">Use one from the history</option>\n- </param>\n- <when value="indexed">\n- <param name="input1" type="data" format="bam" label="Select the BAM file to generate the pileup file for">\n- <validator type="unspecified_build" />\n- <validator type="dataset_metadata_in_data_table" table_name="fasta_indexes" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." />\n-\n- </param>\n- <param name="index" type="select" label="Using reference genome">\n- <options from_data_table="fasta_indexes">\n- <filter type="data_meta" ref="input1" key="dbkey" column="1" />\n- <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" />\n- </options>\n+<tool id="sam_pileup" name="Generate pileup" version="1.1.3" profile="16.04">\n+ <description>from BAM dataset</description>\n+ <requirements>\n+ <requirement type="package" version="0.1.16">samtools</requirement>\n+ </requirements>\n+ <command><![CDATA[\n+ln -s \'$input1\' input1.bam &&\n+ln -s \'${input1.metadata.bam_index}\' \'input1.bam.bai\' &&\n+#if $refOrHistory.reference == \'history\':\n+ ln -s \'$refOrHistory.ownFile\' reference.fasta &&\n+ samtools faidx reference.fasta &&\n+#end if\n+samtools pileup\n+#if $lastCol == \'yes\':\n+ -s\n+#end if\n+#if $indels == \'yes\':\n+ -i\n+#end if\n+-M $mapCap\n+#if $c.consensus == \'yes\':\n+ -c\n+ -T $c.theta\n+ -N $c.hapNum\n+ -r $c.fraction\n+ -I $c.phredProb\n+#end if\n+-f\n+#if $refOrHistory.reference == \'indexed\':\n+ \'${refOrHistory.index.fields.path}\'\n+#else:\n+ reference.fasta\n+#end if\n+input1.bam\n+> \'$output1\'\n+ ]]></command>\n+ <inputs>\n+ <conditional name="refOrHistory">\n+ <param name="reference" type="select" label="Will you select a reference genome from your history or use a built-in index?">\n+ <option value="indexed">Use a built-in index</option>\n+ <option value="history">Use one from the history</option>\n+ </param>\n+ <when value="indexed">\n+ <param name="input1" type="data" format="bam" label="Select the BAM file to generate the pileup file for">\n+ <validator type="unspecified_build" />\n+ <validator type="dataset_metadata_in_data_table" table_name="fasta_indexes" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." />\n+ </param>\n+ <param name="index" type="select" label="Using reference genome">\n+ <options from_data_table="fasta_inde'..b'>\n+ <param name="hapNum" argument="-N" type="integer" value="2" label="Number of haplotypes in the sample" help="Greater than or equal to 2" />\n+ <param name="fraction" argument="-r" type="float" value="0.001" label="Expected fraction of differences between a pair of haplotypes" />\n+ <param name="phredProb" argument="-I" type="integer" value="40" label="Phred probability of an indel in sequencing/prep" />\n+ </when>\n+ </conditional>\n+ </inputs>\n+ <outputs>\n+ <data name="output1" format="tabular" label="${tool.name} on ${on_string}: converted pileup" />\n+ </outputs>\n+ <tests>\n+ <test>\n+ <!--\n+ Bam to pileup command:\n+ samtools faidx chr_m.fasta\n+ samtools pileup -M 60 -f chr_m.fasta test-data/sam_pileup_in1.bam > sam_pileup_out1.pileup\n+ chr_m.fasta is the prefix of the index\n+ -->\n+ <param name="reference" value="history" />\n+ <param name="input1" value="sam_pileup_in1.bam" ftype="bam" />\n+ <param name="ownFile" value="chr_m.fasta" ftype="fasta" dbkey="equCab2" />\n+ <param name="lastCol" value="no" />\n+ <param name="indels" value="no" />\n+ <param name="mapCap" value="60" />\n+ <param name="consensus" value="no" />\n+ <output name="output1" file="sam_pileup_out1.pileup" />\n+ </test>\n+ <!--\n+ <test>\n+ Bam to pileup command:\n+ samtools pileup -M 60 -c -T 0.85 -N 2 -r 0.001 -I 40 -f chr_m.fasta test-data/sam_pileup_in1.bam > sam_pileup_out2.pileup\n+ chr_m.fasta is the prefix of the index\n+ <param name="reference" value="indexed" />\n+ <param name="input1" value="sam_pileup_in1.bam" ftype="bam" dbkey="equCab2" />\n+ <param name="index" value="chr_m" />\n+ <param name="lastCol" value="no" />\n+ <param name="indels" value="no" />\n+ <param name="mapCap" value="60" />\n+ <param name="consensus" value="yes" />\n+ <param name="theta" value="0.85" />\n+ <param name="hapNum" value="2" />\n+ <param name="fraction" value="0.001" />\n+ <param name="phredProb" value="40" />\n+ <output name="output1" file="sam_pileup_out2.pileup" />\n+ </test>\n+ -->\n+ </tests>\n+ <help><![CDATA[\n **What it does**\n \n Uses SAMTools_\' pileup command to produce a pileup dataset from a provided BAM dataset. It generates two types of pileup datasets depending on the specified options. If *Call consensus according to MAQ model?* option is set to **No**, the tool produces simple pileup. If the option is set to **Yes**, a ten column pileup dataset with consensus is generated. Both types of datasets are briefly summarized below.\n@@ -141,7 +143,7 @@\n chrM 413 G 4 ..t, IIIH\n chrM 414 C 4 ...a III2\n chrM 415 C 4 TTTt III7\n- \n+\n where::\n \n Column Definition\n@@ -152,7 +154,7 @@\n 4 Coverage (# reads aligning over that position)\n 5 Bases within reads where (see Galaxy wiki for more info)\n 6 Quality values (phred33 scale, see Galaxy wiki for more)\n- \n+\n **Ten column pileup**\n \n The `ten-column` (consensus_) pileup incorporates additional consensus information generated with *-c* option of *samtools pileup* command::\n@@ -182,15 +184,8 @@\n \n \n .. _consensus: http://samtools.sourceforge.net/cns0.shtml\n-\n-------\n-\n-**Citation**\n-\n-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>`_\n-\n-\n- </help>\n+ ]]></help>\n+ <citations>\n+ <citation type="doi">10.1093/bioinformatics/btp352</citation>\n+ </citations>\n </tool>\n-\n-\n' |
b |
diff -r 890d97772e2a -r a3b4ad6858ff tool_dependencies.xml --- a/tool_dependencies.xml Thu Jan 09 14:28:39 2014 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
@@ -1,6 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="samtools" version="0.1.16"> - <repository changeset_revision="75367f13eb3c" name="package_samtools_0_1_16" owner="devteam" toolshed="http://toolshed.g2.bx.psu.edu" /> - </package> -</tool_dependency> |