Mercurial > repos > devteam > samtools_mpileup
changeset 8:583abf29fc8e draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_mpileup commit 411130b45dc30f7f24f41cdeec5e148c5d8faf40
| author | iuc |
|---|---|
| date | Tue, 09 May 2017 11:17:20 -0400 |
| parents | bfc4517aa037 |
| children | fa7ad9b89f4a |
| files | macros.xml samtools_mpileup.xml test-data/samtools/mpileup/samtools_mpileup_out_1.log test-data/samtools/mpileup/samtools_mpileup_out_1.pileup test-data/samtools/mpileup/samtools_mpileup_out_2.bcf test-data/samtools_mpileup_out_1.log test-data/samtools_mpileup_out_1.pileup test-data/samtools_mpileup_out_2.log test-data/samtools_mpileup_out_2.vcf test-data/samtools_mpileup_out_3.log test-data/samtools_mpileup_out_3.pileup test-data/samtools_mpileup_out_4.log tool_dependencies.xml |
| diffstat | 13 files changed, 216 insertions(+), 284 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Wed Nov 11 12:53:32 2015 -0500 +++ b/macros.xml Tue May 09 11:17:20 2017 -0400 @@ -1,16 +1,17 @@ <macros> <xml name="requirements"> <requirements> - <requirement type="package" version="1.2">samtools</requirement> + <requirement type="package" version="1.3.1">samtools</requirement> <yield/> </requirements> </xml> + <token name="@TOOL_VERSION@">1.3.1</token> <xml name="citations"> <citations> <citation type="bibtex"> @misc{SAM_def, title={Definition of SAM/BAM format}, - url = {https://samtools.github.io/hts-specs/SAMv1.pdf},} + url = {https://samtools.github.io/hts-specs/},} </citation> <citation type="doi">10.1093/bioinformatics/btp352</citation> <citation type="doi">10.1093/bioinformatics/btr076</citation> @@ -41,7 +42,7 @@ </citations> </xml> <xml name="version_command"> - <version_command>samtools --version | head -n 1 | awk '{ print $2 }'</version_command> + <version_command><![CDATA[samtools 2>&1 | grep Version]]></version_command> </xml> <xml name="stdio"> <stdio> @@ -64,7 +65,5 @@ 5. Click **Save** The medatada will be re-detected and you will be able to see the list of reference sequences in the "**Select references (chromosomes and contigs) you would like to restrict bam to**" drop-down. - </token> - </macros>
--- a/samtools_mpileup.xml Wed Nov 11 12:53:32 2015 -0500 +++ b/samtools_mpileup.xml Tue May 09 11:17:20 2017 -0400 @@ -1,25 +1,30 @@ -<tool id="samtools_mpileup" name="MPileup" version="2.1.1"> - <description>call variants</description> +<tool id="samtools_mpileup" name="MPileup" version="2.1.3"> + <description>multi-way pileup of variants</description> <macros> <import>macros.xml</import> </macros> <expand macro="requirements" /> <expand macro="stdio" /> <expand macro="version_command" /> - <command> - <![CDATA[ + <command><![CDATA[ + #for $bam_count, $input_bam in enumerate( $reference_source.input_bam ): + ln -s '${input_bam}' 'localbam_${bam_count}.bam' && + ln -s '${input_bam.metadata.bam_index}' 'localbam_${bam_count}.bam.bai' && + #end for + #if $reference_source.reference_source_selector == "history": - ln -s "${reference_source.ref_file}" && samtools faidx `basename "${reference_source.ref_file}"` && samtools mpileup - #else: - samtools mpileup + ln -s '${reference_source.ref_file}' && + samtools faidx `basename '${reference_source.ref_file}'` && #end if + + samtools mpileup #if $reference_source.reference_source_selector != "history": - -f "${reference_source.ref_file.fields.path}" + -f '${reference_source.ref_file.fields.path}' #else: - -f "${reference_source.ref_file}" + -f '${reference_source.ref_file}' #end if - #for $bam in $reference_source.input_bam: - "${bam}" + #for $bam_count, $input_bam in enumerate( $reference_source.input_bam ): + localbam_${bam_count}.bam #end for #if str( $advanced_options.advanced_options_selector ) == "advanced": #if str( $advanced_options.filter_by_flags.filter_flags ) == "filter": @@ -31,95 +36,110 @@ #end if #end if #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste": - -l "$pasted_regions" + -l '$pasted_regions' #elif str( $advanced_options.limit_by_region.limit_by_regions ) == "history" - -l "$advanced_options.limit_by_region.bed_regions" + -l '$advanced_options.limit_by_region.bed_regions' #end if #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste": - -G "$excluded_read_groups" + -G '$excluded_read_groups' #elif str( $advanced_options.exclude_read_group.exclude_read_groups ) == "history" - -G "$advanced_options.exclude_read_group.read_groups" + -G '$advanced_options.exclude_read_group.read_groups' #end if ${advanced_options.skip_anomalous_read_pairs} ${advanced_options.disable_probabilistic_realignment} - -C "${advanced_options.coefficient_for_downgrading}" - -d "${advanced_options.max_reads_per_bam}" + -C ${advanced_options.coefficient_for_downgrading} + -d ${advanced_options.max_reads_per_bam} ${advanced_options.extended_BAQ_computation} - -q "${advanced_options.minimum_mapping_quality}" - -Q "${advanced_options.minimum_base_quality}" + -q ${advanced_options.minimum_mapping_quality} + -Q ${advanced_options.minimum_base_quality} #if str( $advanced_options.region_string ): - -r "${advanced_options.region_string}" + -r '${advanced_options.region_string}' #end if - #end if #if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation': - ## - ${genotype_likelihood_computation_type.output_format} ${genotype_likelihood_computation_type.compressed} #if str( $genotype_likelihood_computation_type.output_tags ) != "None": - --output-tags "${genotype_likelihood_computation_type.output_tags}" + --output-tags '${genotype_likelihood_computation_type.output_tags}' #end if #if str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'perform_indel_calling': - -o "${genotype_likelihood_computation_type.perform_indel_calling.gap_open_sequencing_error_probability}" - -e "${genotype_likelihood_computation_type.perform_indel_calling.gap_extension_sequencing_error_probability}" - -h "${genotype_likelihood_computation_type.perform_indel_calling.coefficient_for_modeling_homopolymer_errors}" - -L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}" - -m "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_reads_for_indel_candidates}" - --open-prob "${genotype_likelihood_computation_type.perform_indel_calling.open_seq_error_probability}" - -F "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_read_fraction}" + --open-prob ${genotype_likelihood_computation_type.perform_indel_calling.gap_open_sequencing_error_probability} + -e ${genotype_likelihood_computation_type.perform_indel_calling.gap_extension_sequencing_error_probability} + -h ${genotype_likelihood_computation_type.perform_indel_calling.coefficient_for_modeling_homopolymer_errors} + -L ${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth} + -m ${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_reads_for_indel_candidates} + -F ${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_read_fraction} ${genotype_likelihood_computation_type.perform_indel_calling.gapped_read_per_sample} #if len( $genotype_likelihood_computation_type.perform_indel_calling.platform_list_repeat ): - -P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.perform_indel_calling.platform_list_repeat ] ) }" + -P '${ ",".join( str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.perform_indel_calling.platform_list_repeat ) }' #end if #elif str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'do_not_perform_indel_calling': -I #end if - - #else: ${genotype_likelihood_computation_type.base_position_on_reads} ${genotype_likelihood_computation_type.output_mapping_quality} #end if - --output "$output_mpileup" 2> "$output_log" - ]]> - </command> + --output '$output_mpileup' + ]]></command> + + <configfiles> + <configfile name="excluded_read_groups"><![CDATA[ +#set pasted_data = '' +#if str( $advanced_options.advanced_options_selector ) == "advanced": + #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste": + #set pasted_data = '\t'.join( str( $advanced_options.exclude_read_group['read_groups'] ).split() ) + #end if +#end if +${pasted_data} + ]]></configfile> + <configfile name="pasted_regions"><![CDATA[ +#set pasted_data = '' +#if str( $advanced_options.advanced_options_selector ) == "advanced": + #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste": + #set pasted_data = '\t'.join( str( $advanced_options.limit_by_region['region_paste'] ).split() ) + #end if +#end if +${pasted_data} + ]]></configfile> + </configfiles> + <inputs> <conditional name="reference_source"> - <param label="Choose the source for the reference genome" name="reference_source_selector" type="select"> + <param name="reference_source_selector" type="select" label="Choose the source for the reference genome"> <option value="cached">Use a built-in genome</option> <option value="history">Use a genome from the history</option> </param> <when value="cached"> - <param format="bam" label="BAM file(s)" name="input_bam" type="data" min="1" multiple="True"> + <param name="input_bam" type="data" format="bam" multiple="True" min="1" label="BAM file(s)"> <validator type="unspecified_build" /> <validator message="Sequences are not currently available for the specified build." metadata_column="1" metadata_name="dbkey" table_name="fasta_indexes" type="dataset_metadata_in_data_table" /> </param> - <param label="Using reference genome" name="ref_file" type="select"> + <param name="ref_file" type="select" label="Using reference genome"> <options from_data_table="fasta_indexes" /> </param> </when> <when value="history"> - <param format="bam" label="BAM file(s)" name="input_bam" type="data" min="1" multiple="True"> + <param name="input_bam" type="data" format="bam" multiple="True" min="1" label="BAM file(s)"> <validator check="bam_index" message="Metadata missing, click the pencil icon in the history item and use the auto-detect feature to correct this issue." type="metadata" /> </param> - <param format="fasta" label="Using reference genome" name="ref_file" type="data" /> + <param name="ref_file" type="data" format="fasta" label="Using reference genome" /> </when> </conditional> <conditional name="genotype_likelihood_computation_type"> - <param label="Genotype Likelihood Computation" name="genotype_likelihood_computation_type_selector" type="select"> + <param name="genotype_likelihood_computation_type_selector" type="select" label="Genotype Likelihood Computation"> <option selected="True" value="perform_genotype_likelihood_computation">Perform genotype likelihood computation (--VCF, --BCF options)</option> <option value="do_not_perform_genotype_likelihood_computation">Do not perform genotype likelihood computation (output pileup)</option> </param> <when value="perform_genotype_likelihood_computation"> - <param label="Choose the output format" name="output_format" type="select"> + <param name="output_format" type="select" label="Choose the output format"> <option value="--VCF">VCF</option> <option value="--BCF">BCF</option> </param> - <param checked="False" falsevalue="--uncompressed" label="Compress output" name="compressed" truevalue="" type="boolean" help="--incompressed; default=False"/> - <param name="output_tags" optional="True" type="select" multiple="True" display="checkboxes" label="Optional tags to output" help="--output-tags"> + <param name="compressed" argument="--uncompressed" type="boolean" truevalue="" falsevalue="--uncompressed" checked="False" label="Compress output" /> + <param name="output_tags" argument="--output-tags" type="select" optional="True" multiple="True" display="checkboxes" label="Optional tags to output"> <option value="DP">DP (Number of high-quality bases)</option> <option value="DPR">DRP (Number of high-quality bases for each observed allele)</option> <option value="DV">DV (Number of high-quality non-reference bases)</option> @@ -128,23 +148,22 @@ <option value="SP">SP (Phred-scaled strand bias P-value)</option> </param> <conditional name="perform_indel_calling"> - <param label="Perform INDEL calling" name="perform_indel_calling_selector" type="select"> + <param name="perform_indel_calling_selector" type="select" label="Perform INDEL calling"> <option selected="True" value="perform_indel_calling_def">Perform INDEL calling using default options</option> <option value="perform_indel_calling">Perform INDEL calling and set advanced options</option> - <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option> + <option value="do_not_perform_indel_calling">Do not perform INDEL calling (-I)</option> </param> <when value="perform_indel_calling_def" /> <when value="perform_indel_calling"> - <param label="Phred-scaled gap open sequencing error probability" name="gap_open_sequencing_error_probability" type="integer" value="40" help="--open-prob; Reducing this value leads to more indel calls; default=40"/> - <param label="Phred-scaled gap extension sequencing error probability" name="gap_extension_sequencing_error_probability" type="integer" value="20" help="--ext-prob; Reducing this value leads to longer indels. default=20"/> - <param label="Coefficient for modeling homopolymer errors." name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" help="--tandem-qual; default=100"/> - <param label="Skip INDEL calling if the average per-sample depth is above" name="skip_indel_calling_above_sample_depth" type="integer" value="250" help="--max-idepth; default=250"/> - <param label="Minimum gapped reads for indel candidates" name="minimum_gapped_reads_for_indel_candidates" type="integer" value="1" help="--min-ireads; default=1"/> - <param label="Phred-scaled gap open sequencing error probability" name="open_seq_error_probability" type="integer" value="40" help="--open-prob; Reducing this value leads to more indel calls; default=40"/> - <param label="Minimum fraction of gapped reads" name="minimum_gapped_read_fraction" type="float" value="0.002" help="--gap-frac; default=0.002"/> - <param checked="False" falsevalue="" label="Apply --min-ireads and --gap-frac values on a per-sample basis" name="gapped_read_per_sample" truevalue="-p" type="boolean" help="--per-sample-mF; by default both options are applied to reads pooled from all samples"/> - <repeat name="platform_list_repeat" title="Platform for INDEL candidates"> - <param label="Platform to use for INDEL candidates" name="platform_entry" type="text" value="" help="It is recommended to collect indel candidates from sequencing technologies that have low indel error rate such as ILLUMINA"/> + <param name="gap_open_sequencing_error_probability" argument="--open-prob" type="integer" value="40" label="Phred-scaled gap open sequencing error probability" help="Reducing this value leads to more indel calls" /> + <param name="gap_extension_sequencing_error_probability" argument="--ext-prob" type="integer" value="20" label="Phred-scaled gap extension sequencing error probability" help="Reducing this value leads to longer indels" /> + <param name="coefficient_for_modeling_homopolymer_errors" argument="--tandem-qual" type="integer" value="100" label="Coefficient for modeling homopolymer errors" /> + <param name="skip_indel_calling_above_sample_depth" argument="--max-idepth" type="integer" value="250" label="Skip INDEL calling if the average per-sample depth is above" /> + <param name="minimum_gapped_reads_for_indel_candidates" argument="--min-ireads" type="integer" value="1" label="Minimum gapped reads for indel candidates" /> + <param name="minimum_gapped_read_fraction" argument="--gap-frac" type="float" value="0.002" label="Minimum fraction of gapped reads" /> + <param name="gapped_read_per_sample" argument="--per-sample-mF" type="boolean" truevalue="-p" falsevalue="" checked="False" label="Apply --min-ireads and --gap-frac values on a per-sample basis" help="By default both options are applied to reads pooled from all samples"/> + <repeat name="platform_list_repeat" title="Platform for INDEL candidates" help="--platforms"> + <param name="platform_entry" type="text" value="" label="Platform to use for INDEL candidates" help="It is recommended to collect indel candidates from sequencing technologies that have low indel error rate such as ILLUMINA"/> </repeat> </when> <when value="do_not_perform_indel_calling" /> @@ -152,23 +171,24 @@ </when> <when value="do_not_perform_genotype_likelihood_computation"> - <param checked="False" falsevalue="" label="Output base positions on reads" name="base_position_on_reads" truevalue="-O" type="boolean" help="--output-BP"/> - <param checked="False" falsevalue="" label="Output mapping quality" name="output_mapping_quality" truevalue="-s" type="boolean" help="--output-MQ"/> + <param name="base_position_on_reads" argument="--output-BP" type="boolean" truevalue="-O" falsevalue="" checked="False" label="Output base positions on reads" /> + <param name="output_mapping_quality" argument="--output-MQ" type="boolean" truevalue="-s" falsevalue="" checked="False" label="Output mapping quality" /> </when> </conditional> <conditional name="advanced_options"> - <param label="Set advanced options" name="advanced_options_selector" type="select"> + <param name="advanced_options_selector" type="select" label="Set advanced options"> <option selected="True" value="basic">Basic</option> <option value="advanced">Advanced</option> </param> + <when value="basic" /> <when value="advanced"> <conditional name="filter_by_flags"> - <param label="Set filter by flags" name="filter_flags" type="select"> + <param name="filter_flags" type="select" label="Set filter by flags"> <option selected="True" value="nofilter">Do not filter</option> <option value="filter">Filter by flags to exclude or require</option> </param> <when value="filter"> - <param display="checkboxes" label="Require" multiple="True" name="require_flags" type="select" help="--incl-flags"> + <param name="require_flags" argument="--incl-flags" type="select" multiple="True" display="checkboxes" 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> @@ -181,7 +201,7 @@ <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 display="checkboxes" label="Exclude" multiple="True" name="exclude_flags" type="select" help="--excl-flags"> + <param name="exclude_flags" argument="--excl-flags" type="select" multiple="True" display="checkboxes" 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> @@ -198,75 +218,72 @@ <when value="nofilter" /> </conditional> <conditional name="limit_by_region"> - <param label="Select regions to call" name="limit_by_regions" type="select"> + <param name="limit_by_regions" argument="--positions" type="select" label="Select regions to call"> <option selected="True" value="no_limit">Do not limit</option> - <option value="history">From an uploaded BED file (--positions)</option> - <option value="paste">Paste a list of regions or BED (--region)</option> + <option value="history">From a BED file</option> + <option value="paste">Paste a list of regions or BED</option> </param> <when value="history"> - <param format="bed" label="BED file" name="bed_regions" type="data" help="--positions"> + <param name="bed_regions" type="data" format="bed" label="BED file"> <validator type="dataset_ok_validator" /> </param> </when> <when value="paste"> - <param area="true" help="Paste a list of regions in BED format or as a list of chromosomes and positions" label="Regions" name="region_paste" size="10x35" type="text"/> + <param name="region_paste" type="text" area="true" size="10x35" label="Regions" help="Paste a list of regions in BED format or as a list of chromosomes and positions" /> </when> <when value="no_limit" /> </conditional> <conditional name="exclude_read_group"> - <param label="Select read groups to exclude" name="exclude_read_groups" type="select" help="--exclude-RG"> + <param name="exclude_read_groups" argument="--exclude-RG" type="select" label="Select read groups to exclude"> <option selected="True" value="no_limit">Do not exclude</option> - <option value="history">From an uploaded text file</option> + <option value="history">From a text file</option> <option value="paste">Paste a list of read groups</option> </param> <when value="history"> - <param format="txt" label="Text file" name="read_groups" type="data"> + <param name="read_groups" type="data" format="txt" label="Text file"> <validator type="dataset_ok_validator" /> </param> </when> <when value="paste"> - <param area="true" help="Paste a list of read groups" label="Read groups" name="group_paste" size="10x35" type="text" /> + <param name="group_paste" type="text" area="true" size="10x35" label="Read groups" help="Paste a list of read groups" /> </when> <when value="no_limit" /> </conditional> - <param checked="False" falsevalue="" label="Disable read-pair overlap detection" name="ignore_overlaps" truevalue="-x" type="boolean" help="--ignore-overlaps"/> - <param checked="False" falsevalue="" label="Do not skip anomalous read pairs in variant calling" name="skip_anomalous_read_pairs" truevalue="-A" type="boolean" help="--count-orphans"/> - <param checked="False" falsevalue="" label="Disable probabilistic realignment for the computation of base alignment quality (BAQ)" name="disable_probabilistic_realignment" truevalue="-B" type="boolean" help="--no-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"/> - <param label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" name="coefficient_for_downgrading" type="integer" value="0" help="--adjust-MQ; 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. default=0"/> - <param label="Max reads per BAM" max="1024" min="1" name="max_reads_per_bam" type="integer" value="250" help="--max-depth; default=250"/> - <param checked="False" falsevalue="" label="Redo BAQ computation" name="extended_BAQ_computation" truevalue="-E" type="boolean" help="--redo-BAQ; ignore existing BQ tags"/> - <param label="Minimum mapping quality for an alignment to be used" name="minimum_mapping_quality" type="integer" value="0" help="-min-MQ; default=0"/> - <param label="Minimum base quality for a base to be considered" name="minimum_base_quality" type="integer" value="13" help="--min-BQ; default=13"/> - <param label="Only generate pileup in region" name="region_string" type="text" value="" help="--region; If used in conjunction with --positions, then considers the intersection of the two requests. Defaults to all sites" /> + <param name="ignore_overlaps" argument="--ignore-overlaps" type="boolean" truevalue="-x" falsevalue="" checked="False" label="Disable read-pair overlap detection" /> + <param name="skip_anomalous_read_pairs" argument="--count-orphans" type="boolean" truevalue="-A" falsevalue="" checked="False" label="Do not skip anomalous read pairs in variant calling" /> + <param name="disable_probabilistic_realignment" argument="--no-BAQ" type="boolean" truevalue="-B" falsevalue="" checked="False" label="Disable probabilistic realignment for the computation of base alignment quality (BAQ)" help="BAQ is the Phred-scaled probability of a read base being misaligned. Applying this option greatly helps to reduce false SNPs caused by misalignments" /> + <param name="coefficient_for_downgrading" argument="--adjust-MQ" type="integer" value="0" label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" help="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" /> + <param name="max_reads_per_bam" argument="--max-depth" type="integer" max="1024" min="1" value="250" label="Max reads per BAM" /> + <param name="extended_BAQ_computation" argument="--redo-BAQ" type="boolean" truevalue="-E" falsevalue="" checked="False" label="Redo BAQ computation" help="Ignore existing BQ tags" /> + <param name="minimum_mapping_quality" argument="--min-MQ" type="integer" value="0" label="Minimum mapping quality for an alignment to be used" /> + <param name="minimum_base_quality" argument="--min-BQ" type="integer" value="13" label="Minimum base quality for a base to be considered" /> + <param name="region_string" argument="--region" type="text" value="" label="Only generate pileup in region" help="If used in conjunction with --positions, then considers the intersection of the two requests. Defaults to all sites" /> </when> - <when value="basic" /> </conditional> </inputs> <outputs> - <data format="pileup" label="${tool.name} on ${on_string}" name="output_mpileup"> + <data name="output_mpileup" format="pileup" label="${tool.name} on ${on_string}"> <change_format> <when format="bcf" input="genotype_likelihood_computation_type.output_format" value="--BCF" /> <when format="vcf" input="genotype_likelihood_computation_type.output_format" value="--VCF" /> </change_format> </data> - <data format="txt" label="${tool.name} on ${on_string} (log)" name="output_log" /> </outputs> <tests> <test> <param name="reference_source_selector" value="history" /> - <param ftype="fasta" name="ref_file" value="phiX.fasta" /> - <param ftype="bam" name="input_bam" value="samtools_mpileup_in_1.bam" /> + <param name="ref_file" ftype="fasta" value="phiX.fasta" /> + <param name="input_bam" ftype="bam" value="samtools_mpileup_in_1.bam" /> <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" /> <param name="advanced_options_selector" value="basic" /> <param name="base_position_on_reads" value="true" /> <param name="output_mapping_quality" value="true" /> - <output file="samtools_mpileup_out_1.pileup" name="output_mpileup" /> - <output file="samtools_mpileup_out_1.log" name="output_log" /> + <output name="output_mpileup" file="samtools_mpileup_out_1.pileup" /> </test> <test> <param name="reference_source_selector" value="history" /> - <param ftype="fasta" name="ref_file" value="phiX.fasta" /> - <param ftype="bam" name="input_bam" value="phiX.bam" /> + <param name="ref_file" ftype="fasta" value="phiX.fasta" /> + <param name="input_bam" ftype="bam" value="phiX.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" /> @@ -276,93 +293,27 @@ <param name="platform_list_repeat" value="0" /> <param name="advanced_options_selector" value="basic" /> <param name="genotype_likelihood_computation_type|output_format" value="VCF" /> - <output file="samtools_mpileup_out_2.vcf" ftype="vcf" lines_diff="8" name="output_mpileup" /> - <output file="samtools_mpileup_out_2.log" name="output_log" /> + <output name="output_mpileup" file="samtools_mpileup_out_2.vcf" ftype="vcf" lines_diff="8" /> + </test> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" ftype="fasta" value="phiX.fasta" /> + <param name="input_bam" ftype="bam" value="samtools_mpileup_in_1.bam" /> + <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" /> + <param name="advanced_options_selector" value="advanced" /> + <param name="minimum_base_quality" value="0" /><!-- most reads have ultra low quality resuling in empty columns --> + <param name="base_position_on_reads" value="true" /> + <param name="output_mapping_quality" value="true" /> + <output name="output_mpileup" file="samtools_mpileup_out_3.pileup" /> </test> </tests> - <help> -<![CDATA[ + <help><![CDATA[ **What it does** -Report variants 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. - ------- - -**Input options**:: - - -6, --illumina1.3+ quality is in the Illumina-1.3+ encoding - -A, --count-orphans do not discard anomalous read pairs - -b, --bam-list FILE list of input BAM filenames, one per line - -B, --no-BAQ disable BAQ (per-Base Alignment Quality) - -C, --adjust-MQ INT adjust mapping quality; recommended:50, disable:0 [0] - -d, --max-depth INT max per-BAM depth; avoids excessive memory usage [250] - -E, --redo-BAQ recalculate BAQ on the fly, ignore existing BQs - -f, --fasta-ref FILE faidx indexed reference sequence file - -G, --exclude-RG FILE exclude read groups listed in FILE - -l, --positions FILE skip unlisted positions (chr pos) or regions (BED) - -q, --min-MQ INT skip alignments with mapQ smaller than INT [0] - -Q, --min-BQ INT skip bases with baseQ/BAQ smaller than INT [13] - -r, --region REG region in which pileup is generated - -R, --ignore-RG ignore RG tags (one BAM = one sample) - --rf, --incl-flags STR|INT required flags: skip reads with mask bits unset [] - --ff, --excl-flags STR|INT filter flags: skip reads with mask bits set - [UNMAP,SECONDARY,QCFAIL,DUP] - -x, --ignore-overlaps disable read-pair overlap detection - -**Output options**:: - - -o, --output FILE write output to FILE [standard output] - -g, --BCF generate genotype likelihoods in BCF format - -v, --VCF generate genotype likelihoods in VCF format - -**Output options for mpileup format** (without -g/-v):: - - -O, --output-BP output base positions on reads - -s, --output-MQ output mapping quality - -**Output options for genotype likelihoods** (when -g/-v is used):: - - -t, --output-tags LIST optional tags to output: DP,DPR,DV,DP4,INFO/DPR,SP [] - -u, --uncompressed generate uncompressed VCF/BCF output - -**SNP/INDEL genotype likelihoods options** (effective with -g/-v):: - - -e, --ext-prob INT Phred-scaled gap extension seq error probability [20] - -F, --gap-frac FLOAT minimum fraction of gapped reads [0.002] - -h, --tandem-qual INT coefficient for homopolymer errors [100] - -I, --skip-indels do not perform indel calling - -L, --max-idepth INT maximum per-sample depth for INDEL calling [250] - -m, --min-ireads INT minimum number gapped reads for indel candidates [1] - -o, --open-prob INT Phred-scaled gap open seq error probability [40] - -p, --per-sample-mF apply -m and -F per-sample for increased sensitivity - -P, --platforms STR comma separated list of platforms for indels [all] +Report variants 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. **Notes**: Assuming diploid individuals. -]]> - </help> - <configfiles> - <configfile name="excluded_read_groups"> -<![CDATA[ -#set pasted_data = '' -#if str( $advanced_options.advanced_options_selector ) == "advanced": - #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste": - #set pasted_data = '\t'.join( str( $advanced_options.exclude_read_group['read_groups'] ).split() ) - #end if -#end if -${pasted_data} -]]> - </configfile> - <configfile name="pasted_regions"> -<![CDATA[ -#set pasted_data = '' -#if str( $advanced_options.advanced_options_selector ) == "advanced": - #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste": - #set pasted_data = '\t'.join( str( $advanced_options.limit_by_region['region_paste'] ).split() ) - #end if -#end if -${pasted_data} -]]> - </configfile> - </configfiles> + ]]></help> <expand macro="citations" /> </tool>
--- a/test-data/samtools/mpileup/samtools_mpileup_out_1.log Wed Nov 11 12:53:32 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,2 +0,0 @@ -[mpileup] 1 samples in 1 input files -<mpileup> Set max per-file depth to 8000
--- a/test-data/samtools/mpileup/samtools_mpileup_out_1.pileup Wed Nov 11 12:53:32 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,43 +0,0 @@ -phiX174 1411 A 1 ^P. $ -phiX174 1412 G 3 .^D.^F. "$$ -phiX174 1413 C 5 ...^D.^F. """$$ -phiX174 1414 G 6 .....^F. #####$ -phiX174 1415 C 7 ......^F. %%%%%%& -phiX174 1416 C 8 .......^F. $$$$$$$$ -phiX174 1417 G 9 ........^F. "#######$ -phiX174 1418 T 10 .........^F. """""""""$ -phiX174 1419 G 10 .......... """""'&'%$ -phiX174 1420 G 10 .......... """""""""" -phiX174 1421 A 10 .......... """""""""" -phiX174 1422 T 10 .......... """""""""" -phiX174 1423 G 10 .......... """""""""# -phiX174 1424 C 10 ..A.AAAAAA %""""""""" -phiX174 1425 C 10 .......... $$$""""""" -phiX174 1426 T 10 .......... #####""""" -phiX174 1427 G 10 .......... ######"""" -phiX174 1428 A 10 .......... """""""""" -phiX174 1429 C 10 .......... ((((((&("" -phiX174 1430 C 10 .......... $$$$$$$$$" -phiX174 1431 G 10 .......... ########## -phiX174 1432 T 10 .......... """""""""" -phiX174 1433 A 10 .......... ########## -phiX174 1434 C 10 .......... ((((((&(%$ -phiX174 1435 C 10 .......... $$$$$$$$$$ -phiX174 1436 G 10 .......... ########## -phiX174 1437 A 10 .......... """""""""! -phiX174 1438 G 10 .......... """""####! -phiX174 1439 G 10 .......... """""""""! -phiX174 1440 C 10 .......... """""""""! -phiX174 1441 T 10 .......... """"""""#! -phiX174 1442 A 10 .......... $$$%%%&&%! -phiX174 1443 A 10 .-1C.-1C..-1C...... """""""""! -phiX174 1444 C 10 **.*...... &%"!"""""! -phiX174 1445 C 10 .......... &%&!%%%&%! -phiX174 1446 C 10 .......... """!"""""! -phiX174 1447 T 10 .$..$....... #"#!"""""! -phiX174 1448 A 8 .$..$..... #!#%%$$! -phiX174 1449 A 6 .$.$.... !""""! -phiX174 1450 T 4 .$... """! -phiX174 1451 G 3 .$.. #"! -phiX174 1452 A 2 .$. "! -phiX174 1453 G 1 .$ !
--- a/test-data/samtools_mpileup_out_1.log Wed Nov 11 12:53:32 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,3 +0,0 @@ -[fai_load] build FASTA index. -[mpileup] 1 samples in 1 input files -<mpileup> Set max per-file depth to 8000
--- a/test-data/samtools_mpileup_out_1.pileup Wed Nov 11 12:53:32 2015 -0500 +++ b/test-data/samtools_mpileup_out_1.pileup Tue May 09 11:17:20 2017 -0400 @@ -1,43 +1,43 @@ -phiX174 1411 A 0 1 -phiX174 1412 G 0 2,1,1 -phiX174 1413 C 0 3,2,2,1,1 -phiX174 1414 G 0 4,3,3,2,2,1 -phiX174 1415 C 0 5,4,4,3,3,2,1 -phiX174 1416 C 0 6,5,5,4,4,3,2,1 -phiX174 1417 G 0 7,6,6,5,5,4,3,2,1 -phiX174 1418 T 0 8,7,7,6,6,5,4,3,2,1 -phiX174 1419 G 0 9,8,8,7,7,6,5,4,3,2 -phiX174 1420 G 0 10,9,9,8,8,7,6,5,4,3 -phiX174 1421 A 0 11,10,10,9,9,8,7,6,5,4 -phiX174 1422 T 0 12,11,11,10,10,9,8,7,6,5 -phiX174 1423 G 0 13,12,12,11,11,10,9,8,7,6 -phiX174 1424 C 0 14,13,13,12,12,11,10,9,8,7 -phiX174 1425 C 0 15,14,14,13,13,12,11,10,9,8 -phiX174 1426 T 0 16,15,15,14,14,13,12,11,10,9 -phiX174 1427 G 0 17,16,16,15,15,14,13,12,11,10 -phiX174 1428 A 0 18,17,17,16,16,15,14,13,12,11 -phiX174 1429 C 0 19,18,18,17,17,16,15,14,13,12 -phiX174 1430 C 0 20,19,19,18,18,17,16,15,14,13 -phiX174 1431 G 0 21,20,20,19,19,18,17,16,15,14 -phiX174 1432 T 0 22,21,21,20,20,19,18,17,16,15 -phiX174 1433 A 0 23,22,22,21,21,20,19,18,17,16 -phiX174 1434 C 0 24,23,23,22,22,21,20,19,18,17 -phiX174 1435 C 0 25,24,24,23,23,22,21,20,19,18 -phiX174 1436 G 0 26,25,25,24,24,23,22,21,20,19 -phiX174 1437 A 0 27,26,26,25,25,24,23,22,21,20 -phiX174 1438 G 0 28,27,27,26,26,25,24,23,22,21 -phiX174 1439 G 0 29,28,28,27,27,26,25,24,23,22 -phiX174 1440 C 0 30,29,29,28,28,27,26,25,24,23 -phiX174 1441 T 0 31,30,30,29,29,28,27,26,25,24 -phiX174 1442 A 0 32,31,31,30,30,29,28,27,26,25 -phiX174 1443 A 0 33,32,32,31,31,30,29,28,27,26 -phiX174 1444 C 0 34,33,33,32,32,31,30,29,28,27 -phiX174 1445 C 0 34,33,34,32,33,32,31,30,29,28 -phiX174 1446 C 0 35,34,35,33,34,33,32,31,30,29 -phiX174 1447 T 0 36,35,36,34,35,34,33,32,31,30 -phiX174 1448 A 0 36,35,36,35,34,33,32,31 -phiX174 1449 A 0 36,36,35,34,33,32 -phiX174 1450 T 0 36,35,34,33 -phiX174 1451 G 0 36,35,34 -phiX174 1452 A 0 36,35 -phiX174 1453 G 0 36 +phiX174 1411 A 0 +phiX174 1412 G 0 +phiX174 1413 C 0 +phiX174 1414 G 0 +phiX174 1415 C 0 +phiX174 1416 C 0 +phiX174 1417 G 0 +phiX174 1418 T 0 +phiX174 1419 G 0 +phiX174 1420 G 0 +phiX174 1421 A 0 +phiX174 1422 T 0 +phiX174 1423 G 0 +phiX174 1424 C 0 +phiX174 1425 C 0 +phiX174 1426 T 0 +phiX174 1427 G 0 +phiX174 1428 A 0 +phiX174 1429 C 0 +phiX174 1430 C 0 +phiX174 1431 G 0 +phiX174 1432 T 0 +phiX174 1433 A 0 +phiX174 1434 C 0 +phiX174 1435 C 0 +phiX174 1436 G 0 +phiX174 1437 A 0 +phiX174 1438 G 0 +phiX174 1439 G 0 +phiX174 1440 C 0 +phiX174 1441 T 0 +phiX174 1442 A 0 +phiX174 1443 A 0 +phiX174 1444 C 0 +phiX174 1445 C 0 +phiX174 1446 C 0 +phiX174 1447 T 0 +phiX174 1448 A 0 +phiX174 1449 A 0 +phiX174 1450 T 0 +phiX174 1451 G 0 +phiX174 1452 A 0 +phiX174 1453 G 0
--- a/test-data/samtools_mpileup_out_2.log Wed Nov 11 12:53:32 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,3 +0,0 @@ -[fai_load] build FASTA index. -[mpileup] 1 samples in 1 input files -<mpileup> Set max per-file depth to 8000
--- a/test-data/samtools_mpileup_out_2.vcf Wed Nov 11 12:53:32 2015 -0500 +++ b/test-data/samtools_mpileup_out_2.vcf Tue May 09 11:17:20 2017 -0400 @@ -4,7 +4,7 @@ ##samtoolsCommand=samtools mpileup --VCF --uncompressed -f /tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_735.dat -g -e 20 -h 100 -L 250 -m 1 --open-prob 40 -F 0.002 -e 40 --output /tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_736.dat /tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_734.dat ##reference=file:///tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_735.dat ##contig=<ID=phiX174,length=5386> -##ALT=<ID=X,Description="Represents allele(s) other than observed."> +##ALT=<ID=*,Description="Represents allele(s) other than observed."> ##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL."> ##INFO=<ID=IDV,Number=1,Type=Integer,Description="Maximum number of reads supporting an indel"> ##INFO=<ID=IMF,Number=1,Type=Float,Description="Maximum fraction of reads supporting an indel"> @@ -19,4 +19,4 @@ ##INFO=<ID=I16,Number=16,Type=Float,Description="Auxiliary tag used for calling, see description of bcf_callret1_t in bam2bcf.h"> ##INFO=<ID=QS,Number=R,Type=Float,Description="Auxiliary tag used for calling"> ##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods"> -#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT /tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_734.dat +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT localbam_0.bam
--- a/test-data/samtools_mpileup_out_3.log Wed Nov 11 12:53:32 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,2 +0,0 @@ -[mpileup] 1 samples in 1 input files -<mpileup> Set max per-file depth to 8000
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/samtools_mpileup_out_3.pileup Tue May 09 11:17:20 2017 -0400 @@ -0,0 +1,43 @@ +phiX174 1411 A 1 ^P. $ P 1 +phiX174 1412 G 3 .^D.^F. "$$ PDF 2,1,1 +phiX174 1413 C 5 ...^D.^F. """$$ PDFDF 3,2,2,1,1 +phiX174 1414 G 6 .....^F. #####$ PDFDFF 4,3,3,2,2,1 +phiX174 1415 C 7 ......^F. %%%%%%& PDFDFFF 5,4,4,3,3,2,1 +phiX174 1416 C 8 .......^F. $$$$$$$$ PDFDFFFF 6,5,5,4,4,3,2,1 +phiX174 1417 G 9 ........^F. "#######$ PDFDFFFFF 7,6,6,5,5,4,3,2,1 +phiX174 1418 T 10 .........^F. """""""""$ PDFDFFFFFF 8,7,7,6,6,5,4,3,2,1 +phiX174 1419 G 10 .......... """""'&'%$ PDFDFFFFFF 9,8,8,7,7,6,5,4,3,2 +phiX174 1420 G 10 .......... """""""""" PDFDFFFFFF 10,9,9,8,8,7,6,5,4,3 +phiX174 1421 A 10 .......... """""""""" PDFDFFFFFF 11,10,10,9,9,8,7,6,5,4 +phiX174 1422 T 10 .......... """""""""" PDFDFFFFFF 12,11,11,10,10,9,8,7,6,5 +phiX174 1423 G 10 .......... """""""""# PDFDFFFFFF 13,12,12,11,11,10,9,8,7,6 +phiX174 1424 C 10 ..A.AAAAAA %""""""""" PDFDFFFFFF 14,13,13,12,12,11,10,9,8,7 +phiX174 1425 C 10 .......... $$$""""""" PDFDFFFFFF 15,14,14,13,13,12,11,10,9,8 +phiX174 1426 T 10 .......... #####""""" PDFDFFFFFF 16,15,15,14,14,13,12,11,10,9 +phiX174 1427 G 10 .......... ######"""" PDFDFFFFFF 17,16,16,15,15,14,13,12,11,10 +phiX174 1428 A 10 .......... """""""""" PDFDFFFFFF 18,17,17,16,16,15,14,13,12,11 +phiX174 1429 C 10 .......... ((((((&("" PDFDFFFFFF 19,18,18,17,17,16,15,14,13,12 +phiX174 1430 C 10 .......... $$$$$$$$$" PDFDFFFFFF 20,19,19,18,18,17,16,15,14,13 +phiX174 1431 G 10 .......... ########## PDFDFFFFFF 21,20,20,19,19,18,17,16,15,14 +phiX174 1432 T 10 .......... """""""""" PDFDFFFFFF 22,21,21,20,20,19,18,17,16,15 +phiX174 1433 A 10 .......... ########## PDFDFFFFFF 23,22,22,21,21,20,19,18,17,16 +phiX174 1434 C 10 .......... ((((((&(%$ PDFDFFFFFF 24,23,23,22,22,21,20,19,18,17 +phiX174 1435 C 10 .......... $$$$$$$$$$ PDFDFFFFFF 25,24,24,23,23,22,21,20,19,18 +phiX174 1436 G 10 .......... ########## PDFDFFFFFF 26,25,25,24,24,23,22,21,20,19 +phiX174 1437 A 10 .......... """""""""! PDFDFFFFFF 27,26,26,25,25,24,23,22,21,20 +phiX174 1438 G 10 .......... """""####! PDFDFFFFFF 28,27,27,26,26,25,24,23,22,21 +phiX174 1439 G 10 .......... """""""""! PDFDFFFFFF 29,28,28,27,27,26,25,24,23,22 +phiX174 1440 C 10 .......... """""""""! PDFDFFFFFF 30,29,29,28,28,27,26,25,24,23 +phiX174 1441 T 10 .......... """"""""#! PDFDFFFFFF 31,30,30,29,29,28,27,26,25,24 +phiX174 1442 A 10 .......... $$$%%%&&%! PDFDFFFFFF 32,31,31,30,30,29,28,27,26,25 +phiX174 1443 A 10 .-1C.-1C..-1C...... """""""""! PDFDFFFFFF 33,32,32,31,31,30,29,28,27,26 +phiX174 1444 C 10 **.*...... !!"!"""""! PDFDFFFFFF 34,33,33,32,32,31,30,29,28,27 +phiX174 1445 C 10 .......... !!&!%%%&%! PDFDFFFFFF 34,33,34,32,33,32,31,30,29,28 +phiX174 1446 C 10 .......... !!"!"""""! PDFDFFFFFF 35,34,35,33,34,33,32,31,30,29 +phiX174 1447 T 10 .$..$....... !!#!"""""! PDFDFFFFFF 36,35,36,34,35,34,33,32,31,30 +phiX174 1448 A 8 .$..$..... !!#%%$$! DDFFFFFF 36,35,36,35,34,33,32,31 +phiX174 1449 A 6 .$.$.... !""""! DFFFFF 36,36,35,34,33,32 +phiX174 1450 T 4 .$... """! FFFF 36,35,34,33 +phiX174 1451 G 3 .$.. #"! FFF 36,35,34 +phiX174 1452 A 2 .$. "! FF 36,35 +phiX174 1453 G 1 .$ ! F 36
--- a/test-data/samtools_mpileup_out_4.log Wed Nov 11 12:53:32 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,2 +0,0 @@ -[mpileup] 1 samples in 1 input files -<mpileup> Set max per-file depth to 8000
--- a/tool_dependencies.xml Wed Nov 11 12:53:32 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,6 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="samtools" version="1.2"> - <repository changeset_revision="f6ae3ba3f3c1" name="package_samtools_1_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> -</tool_dependency>