Add SAMTools mpileup.

This commit is contained in:
Daniel Blankenberg
2011-11-21 16:30:34 -05:00
parent f84f482659
commit 8986dc2c81
5 changed files with 330 additions and 0 deletions
+1
View File
@@ -159,6 +159,7 @@
<converter file="vcf_to_summary_tree_converter.xml" target_datatype="summary_tree"/>
<display file="igv/vcf.xml" />
</datatype>
<datatype extension="bcf" type="galaxy.datatypes.binary:Binary" subclass="True"/>
<datatype extension="wsf" type="galaxy.datatypes.wsf:SnpFile" display_in_upload="true"/>
<datatype extension="velvet" type="galaxy.datatypes.assembly:Velvet" display_in_upload="false"/>
<datatype extension="wig" type="galaxy.datatypes.interval:Wiggle" display_in_upload="true">
+1
View File
@@ -371,6 +371,7 @@
<tool file="samtools/sam_to_bam.xml" />
<tool file="samtools/bam_to_sam.xml" />
<tool file="samtools/sam_merge.xml" />
<tool file="samtools/samtools_mpileup.xml" />
<tool file="samtools/sam_pileup.xml" />
<tool file="samtools/pileup_parser.xml" />
<tool file="samtools/pileup_interval.xml" />
+5
View File
@@ -65,6 +65,11 @@
<columns>value, name, path</columns>
<file path="tool-data/perm_color_index.loc" />
</table>
<!-- Location of SAMTools indexes and other files -->
<table name="sam_fa_indexes" comment_char="#">
<columns>line_type, value, path</columns>
<file path="tool-data/sam_fa_indices.loc" />
</table>
<!-- Location of Picard dict file and other files -->
<table name="picard_indexes" comment_char="#">
<columns>value, dbkey, name, path</columns>
+213
View File
@@ -0,0 +1,213 @@
<tool id="samtools_mpileup" name="MPileup" version="0.0.1">
<description>SNP and indel caller</description>
<requirements>
<requirement type="package">samtools</requirement>
</requirements>
<command interpreter="python">samtools_wrapper.py
-p 'samtools mpileup'
--stdout "${output_log}"
#if $reference_source.reference_source_selector != "history":
-p '-f "${reference_source.ref_file.fields.path}"'
#else:
-d "-f" "${reference_source.ref_file}" "fa" "reference_input"
#end if
#for $i, $input_bam in enumerate( $reference_source.input_bams ):
-d " " "${input_bam.input_bam}" "${input_bam.input_bam.ext}" "bam_input_${i}"
-d "" "${input_bam.input_bam.metadata.bam_index}" "bam_index" "bam_input_${i}" ##hardcode galaxy ext type as bam_index
#end for
-p '
#if str( $advanced_options.advanced_options_selector ) == "advanced":
${advanced_options.skip_anomalous_read_pairs}
${advanced_options.disable_probabilistic_realignment}
-C "${advanced_options.coefficient_for_downgrading}"
-d "${advanced_options.max_reads_per_bam}"
${advanced_options.extended_BAQ_computation}
#if str( $advanced_options.position_list ) != 'None':
-l "${advanced_options.position_list}"
#end if
-q "${advanced_options.minimum_mapping_quality}"
-Q "${advanced_options.minimum_base_quality}"
#if str( $advanced_options.region_string ):
-r "${advanced_options.region_string}"
#end if
${advanced_options.output_per_sample_read_depth}
${advanced_options.output_per_sample_strand_bias_p_value}
#end if
#if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation':
##-g or -u
-g
-e "${genotype_likelihood_computation_type.gap_extension_sequencing_error_probability}"
-h "${genotype_likelihood_computation_type.coefficient_for_modeling_homopolymer_errors}"
#if str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'perform_indel_calling':
-L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}"
#else:
-I
#end if
-o "${genotype_likelihood_computation_type.gap_open_sequencing_error_probability}"
#if len( $genotype_likelihood_computation_type.platform_list_repeat ):
-P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.platform_list_repeat ] ) }"
#end if
#end if
&gt; "${output_mpileup}"
'
</command>
<inputs>
<conditional name="reference_source">
<param name="reference_source_selector" type="select" label="Choose the source for the reference list">
<option value="cached">Locally cached</option>
<option value="history">History</option>
</param>
<when value="cached">
<repeat name="input_bams" title="BAM file" min="1">
<param name="input_bam" type="data" format="bam" label="BAM file">
<validator type="unspecified_build" />
<validator type="dataset_metadata_in_data_table" table_name="sam_fa_indexes" metadata_name="dbkey" metadata_column="value" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select -->
</param>
</repeat>
<param name="ref_file" type="select" label="Using reference genome">
<options from_data_table="sam_fa_indexes">
<!-- <filter type="data_meta" key="dbkey" ref="input_bam" column="value"/> does not yet work in a repeat...-->
</options>
</param>
</when>
<when value="history"> <!-- FIX ME!!!! -->
<repeat name="input_bams" title="BAM file" min="1">
<param name="input_bam" type="data" format="bam" label="BAM file" >
<validator type="metadata" check="bam_index" message="Metadata missing, click the pencil icon in the history item and use the auto-detect feature to correct this issue."/>
</param>
</repeat>
<param name="ref_file" type="data" format="fasta" label="Using reference file" />
</when>
</conditional>
<conditional name="genotype_likelihood_computation_type">
<param name="genotype_likelihood_computation_type_selector" type="select" label="Genotype Likelihood Computation">
<option value="perform_genotype_likelihood_computation">Perform genotype likelihood computation</option>
<option value="do_not_perform_genotype_likelihood_computation" selected="True">Do not perform genotype likelihood computation</option>
</param>
<when value="perform_genotype_likelihood_computation">
<param name="gap_extension_sequencing_error_probability" type="integer" value="20" label="Phred-scaled gap extension sequencing error probability" />
<param name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" label="Coefficient for modeling homopolymer errors." />
<conditional name="perform_indel_calling">
<param name="perform_indel_calling_selector" type="select" label="Perform INDEL calling">
<option value="perform_indel_calling" selected="True">Perform INDEL calling</option>
<option value="do_not_perform_indel_calling">Do not perform INDEL calling</option>
</param>
<when value="perform_indel_calling">
<param name="skip_indel_calling_above_sample_depth" type="integer" value="250" label="Skip INDEL calling if the average per-sample depth is above" />
</when>
<when value="do_no_perform_indel_calling" />
</conditional>
<param name="gap_open_sequencing_error_probability" type="integer" value="40" label="Phred-scaled gap open sequencing error probability" />
<repeat name="platform_list_repeat" title="Platform for INDEL candidates">
<param name="platform_entry" type="text" value="" label="Platform to use for INDEL candidates" />
</repeat>
</when>
<when value="do_not_perform_genotype_likelihood_computation">
<!-- Do nothing here -->
</when>
</conditional>
<conditional name="advanced_options">
<param name="advanced_options_selector" type="select" label="Set advanced options">
<option value="basic" selected="True">Basic</option>
<option value="advanced">Advanced</option>
</param>
<when value="advanced">
<param name="skip_anomalous_read_pairs" type="boolean" truevalue="-A" falsevalue="" checked="False" label="Do not skip anomalous read pairs in variant calling" />
<param name="disable_probabilistic_realignment" type="boolean" truevalue="-B" falsevalue="" checked="False" label=" Disable probabilistic realignment for the computation of base alignment quality (BAQ)" />
<param name="coefficient_for_downgrading" type="integer" value="0" label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" />
<param name="max_reads_per_bam" type="integer" value="250" label="Max reads per BAM" />
<param name="extended_BAQ_computation" type="boolean" truevalue="-E" falsevalue="" checked="False" label="Extended BAQ computation" />
<param name="position_list" type="data" format="bed" label="List of regions or sites on which to operate" optional="True" />
<param name="minimum_mapping_quality" type="integer" value="0" label="Minimum mapping quality for an alignment to be used" />
<param name="minimum_base_quality" type="integer" value="13" label="Minimum base quality for a base to be considered" />
<param name="region_string" type="text" value="" label="Only generate pileup in region" />
<param name="output_per_sample_read_depth" type="boolean" truevalue="-D" falsevalue="" checked="False" label="Output per-sample read depth" />
<param name="output_per_sample_strand_bias_p_value" type="boolean" truevalue="-S" falsevalue="" checked="False" label="Output per-sample Phred-scaled strand bias P-value" />
</when>
<when value="basic" />
</conditional>
</inputs>
<outputs>
<data format="pileup" name="output_mpileup" label="${tool.name} on ${on_string}">
<change_format>
<when input="genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" format="bcf" />
</change_format>
</data>
<data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
</outputs>
<tests>
<test>
<param name="reference_source_selector" value="history" />
<param name="ref_file" value="phiX.fasta" ftype="fasta" />
<param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" />
<param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" />
<param name="advanced_options_selector" value="basic" />
<output name="output_mpileup" file="samtools/mpileup/samtools_mpileup_out_1.pileup" />
<output name="output_log" file="samtools/mpileup/samtools_mpileup_out_1.log" />
</test>
<test>
<param name="reference_source_selector" value="history" />
<param name="ref_file" value="phiX.fasta" ftype="fasta" />
<param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" />
<param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" />
<param name="gap_extension_sequencing_error_probability" value="20" />
<param name="coefficient_for_modeling_homopolymer_errors" value="100" />
<param name="perform_indel_calling_selector" value="perform_indel_calling" />
<param name="skip_indel_calling_above_sample_depth" value="250" />
<param name="gap_open_sequencing_error_probability" value="40" />
<param name="platform_list_repeat" value="0" />
<param name="advanced_options_selector" value="basic" />
<output name="output_mpileup" file="samtools/mpileup/samtools_mpileup_out_2.bcf" />
<output name="output_log" file="samtools/mpileup/samtools_mpileup_out_1.log" />
</test>
</tests>
<help>
**What it does**
Generate BCF or pileup for one or multiple BAM files. Alignment records are grouped by sample identifiers in @RG header lines. If sample identifiers are absent, each input file is regarded as one sample.
------
**Settings**::
Input Options:
-6 Assume the quality is in the Illumina 1.3+ encoding.
-A Do not skip anomalous read pairs in variant calling.
-B Disable probabilistic realignment for the computation of base alignment quality (BAQ). BAQ is the Phred-scaled probability of a read base being misaligned. Applying this option greatly helps to reduce false SNPs caused by misalignments.
-b FILE List of input BAM files, one file per line [null]
-C INT Coefficient for downgrading mapping quality for reads containing excessive mismatches. Given a read with a phred-scaled probability q of being generated from the mapped position, the new mapping quality is about sqrt((INT-q)/INT)*INT. A zero value disables this functionality; if enabled, the recommended value for BWA is 50. [0]
-d INT At a position, read maximally INT reads per input BAM. [250]
-E Extended BAQ computation. This option helps sensitivity especially for MNPs, but may hurt specificity a little bit.
-f FILE The faidx-indexed reference file in the FASTA format. The file can be optionally compressed by razip. [null]
-l FILE BED or position list file containing a list of regions or sites where pileup or BCF should be generated [null]
-q INT Minimum mapping quality for an alignment to be used [0]
-Q INT Minimum base quality for a base to be considered [13]
-r STR Only generate pileup in region STR [all sites]
Output Options:
-D Output per-sample read depth
-g Compute genotype likelihoods and output them in the binary call format (BCF).
-S Output per-sample Phred-scaled strand bias P-value
-u Similar to -g except that the output is uncompressed BCF, which is preferred for piping.
Options for Genotype Likelihood Computation (for -g or -u):
-e INT Phred-scaled gap extension sequencing error probability. Reducing INT leads to longer indels. [20]
-h INT Coefficient for modeling homopolymer errors. Given an l-long homopolymer run, the sequencing error of an indel of size s is modeled as INT*s/l. [100]
-I Do not perform INDEL calling
-L INT Skip INDEL calling if the average per-sample depth is above INT. [250]
-o INT Phred-scaled gap open sequencing error probability. Reducing INT leads to more indel calls. [40]
-P STR Comma dilimited list of platforms (determined by @RG-PL) from which indel candidates are obtained. It is recommended to collect indel candidates from sequencing technologies that have low indel error rate such as ILLUMINA. [all]
------
**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. &lt;http://www.ncbi.nlm.nih.gov/pubmed/19505943&gt;`_
If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.*
</help>
</tool>
+110
View File
@@ -0,0 +1,110 @@
#!/usr/bin/env python
#Dan Blankenberg
"""
A wrapper script for running SAMTools commands.
"""
import sys, optparse, os, tempfile, subprocess, shutil
from string import Template
GALAXY_EXT_TO_SAMTOOLS_EXT = { 'bam_index':'bam.bai', } #items not listed here will use the galaxy extension as-is
GALAXY_EXT_TO_SAMTOOLS_FILE_TYPE = GALAXY_EXT_TO_SAMTOOLS_EXT #for now, these are the same, but could be different if needed
DEFAULT_SAMTOOLS_PREFIX = "SAMTools_file"
CHUNK_SIZE = 2**20 #1mb
def cleanup_before_exit( tmp_dir ):
if tmp_dir and os.path.exists( tmp_dir ):
shutil.rmtree( tmp_dir )
def SAMTOOLS_filename_from_galaxy( galaxy_filename, galaxy_ext, target_dir = None, prefix = None ):
suffix = GALAXY_EXT_TO_SAMTOOLS_EXT.get( galaxy_ext, galaxy_ext )
if prefix is None:
prefix = DEFAULT_SAMTOOLS_PREFIX
if target_dir is None:
target_dir = os.getcwd()
SAMTools_filename = os.path.join( target_dir, "%s.%s" % ( prefix, suffix ) )
os.symlink( galaxy_filename, SAMTools_filename )
return SAMTools_filename
def SAMTOOLS_filetype_argument_substitution( argument, galaxy_ext ):
return argument % dict( file_type = GALAXY_EXT_TO_SAMTOOLS_FILE_TYPE.get( galaxy_ext, galaxy_ext ) )
def open_file_from_option( filename, mode = 'rb' ):
if filename:
return open( filename, mode = mode )
return None
def html_report_from_directory( html_out, dir ):
html_out.write( '<html>\n<head>\n<title>Galaxy - SAMTOOLS Output</title>\n</head>\n<body>\n<p/>\n<ul>\n' )
for fname in sorted( os.listdir( dir ) ):
html_out.write( '<li><a href="%s">%s</a></li>\n' % ( fname, fname ) )
html_out.write( '</ul>\n</body>\n</html>\n' )
def __main__():
#Parse Command Line
parser = optparse.OptionParser()
parser.add_option( '-p', '--pass_through', dest='pass_through_options', action='append', type="string", help='These options are passed through directly to SAMTOOLS, without any modification.' )
parser.add_option( '-d', '--dataset', dest='datasets', action='append', type="string", nargs=4, help='"-argument" "original_filename" "galaxy_filetype" "name_prefix"' )
parser.add_option( '', '--stdout', dest='stdout', action='store', type="string", default=None, help='If specified, the output of stdout will be written to this file.' )
parser.add_option( '', '--stderr', dest='stderr', action='store', type="string", default=None, help='If specified, the output of stderr will be written to this file.' )
parser.add_option( '', '--html_report_from_directory', dest='html_report_from_directory', action='append', type="string", nargs=2, help='"Target HTML File" "Directory"')
(options, args) = parser.parse_args()
tmp_dir = tempfile.mkdtemp( prefix='tmp-SAMTOOLS-' )
#set up stdout and stderr output options
stdout = open_file_from_option( options.stdout, mode = 'wb' )
stderr = open_file_from_option( options.stderr, mode = 'wb' )
#if no stderr file is specified, we'll use our own
if stderr is None:
stderr = tempfile.NamedTemporaryFile( prefix="SAMTOOLS-stderr-", dir=tmp_dir )
if options.pass_through_options:
cmd = ' '.join( options.pass_through_options )
else:
cmd = ''
return_code = None
if options.datasets:
for ( dataset_arg, filename, galaxy_ext, prefix ) in options.datasets:
SAMTools_filename = SAMTOOLS_filename_from_galaxy( filename, galaxy_ext, target_dir = tmp_dir, prefix = prefix )
if dataset_arg:
if '>' in cmd:
cmd = cmd.replace( '>', ' %s "%s" >' % ( SAMTOOLS_filetype_argument_substitution( dataset_arg, galaxy_ext ), SAMTools_filename ), 1 )
else:
cmd = '%s %s "%s"' % ( cmd, SAMTOOLS_filetype_argument_substitution( dataset_arg, galaxy_ext ), SAMTools_filename )
#auto index fasta files:
if galaxy_ext == 'fa':
index_cmd = 'samtools faidx %s' % ( SAMTools_filename )
proc = subprocess.Popen( args=index_cmd, stdout=stdout, stderr=stderr, shell=True, cwd=tmp_dir )
return_code = proc.wait()
if return_code:
break
if return_code is None or not return_code:
proc = subprocess.Popen( args=cmd, stdout=stdout, stderr=stderr, shell=True, cwd=tmp_dir )
return_code = proc.wait()
if return_code:
stderr_target = sys.stderr
else:
if stdout:
stderr_target = stdout
else:
stderr_target = sys.stdout
stderr.flush()
stderr.seek(0)
while True:
chunk = stderr.read( CHUNK_SIZE )
if chunk:
stderr_target.write( chunk )
else:
break
stderr.close()
#generate html reports
if options.html_report_from_directory:
for ( html_filename, html_dir ) in options.html_report_from_directory:
html_report_from_directory( open( html_filename, 'wb' ), html_dir )
cleanup_before_exit( tmp_dir )
if __name__=="__main__": __main__()