Mercurial > repos > devteam > samtools_mpileup

comparison samtools_mpileup.xml @ 3:da0203c3461a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 9c291d7ad7c82e6051fe3e5ddffbe7a5edf6f006
author devteam
date Fri, 11 Sep 2015 14:16:52 -0400
parents 3aa48bcbc599
children 5872c9894a37
comparison
equal deleted inserted replaced
2:3aa48bcbc599 3:da0203c3461a
1 <tool id="samtools_mpileup" name="MPileup" version="0.0.3"> 1 <tool id="samtools_mpileup" name="MPileup" version="2.1">
2 <description>SNP and indel caller</description> 2 <description>call variants</description>
3 <requirements> 3 <macros>
4 <requirement type="package" version="0.1.19">samtools</requirement> 4 <import>macros.xml</import>
5 </requirements> 5 </macros>
6 <command><![CDATA[ 6 <expand macro="requirements" />
7 <expand macro="stdio" />
8 <expand macro="version_command" />
9 <command>
10 <![CDATA[
7 #if $reference_source.reference_source_selector == "history": 11 #if $reference_source.reference_source_selector == "history":
8 ln -s "${reference_source.ref_file}" && samtools faidx `basename "${reference_source.ref_file}"` && samtools mpileup 12 ln -s "${reference_source.ref_file}" && samtools faidx `basename "${reference_source.ref_file}"` && samtools mpileup
9 #else: 13 #else:
10 samtools mpileup 14 samtools mpileup
11 #end if 15 #end if
13 -f "${reference_source.ref_file.fields.path}" 17 -f "${reference_source.ref_file.fields.path}"
14 #else: 18 #else:
15 -f "${reference_source.ref_file}" 19 -f "${reference_source.ref_file}"
16 #end if 20 #end if
17 #for $i, $input_bam in enumerate( $reference_source.input_bams ): 21 #for $i, $input_bam in enumerate( $reference_source.input_bams ):
18 $input_bam.input_bam 22 "${input_bam.input_bam}"
19 #end for 23 #end for
20 #if str( $advanced_options.advanced_options_selector ) == "advanced": 24 #if str( $advanced_options.advanced_options_selector ) == "advanced":
21 #if str( $advanced_options.filter_by_flags.filter_flags ) == "filter": 25 #if str( $advanced_options.filter_by_flags.filter_flags ) == "filter":
22 #if $advanced_options.filter_by_flags.require_flags: 26 #if $advanced_options.filter_by_flags.require_flags:
23 --rf ${sum([int(flag) for flag in str($advanced_options.filter_by_flags.require_flags).split(',')])} 27 --rf ${sum([int(flag) for flag in str($advanced_options.filter_by_flags.require_flags).split(',')])}
27 #end if 31 #end if
28 #end if 32 #end if
29 #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste": 33 #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste":
30 -l "$pasted_regions" 34 -l "$pasted_regions"
31 #elif str( $advanced_options.limit_by_region.limit_by_regions ) == "history" 35 #elif str( $advanced_options.limit_by_region.limit_by_regions ) == "history"
32 -l "$bed_regions" 36 -l "$advanced_options.limit_by_region.bed_regions"
33 #end if 37 #end if
34 #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste": 38 #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste":
35 -G "$excluded_read_groups" 39 -G "$excluded_read_groups"
36 #elif str( $advanced_options.exclude_read_group.exclude_read_groups ) == "history" 40 #elif str( $advanced_options.exclude_read_group.exclude_read_groups ) == "history"
37 -G "$read_groups" 41 -G "$advanced_options.exclude_read_group.read_groups"
38 #end if 42 #end if
39 ${advanced_options.skip_anomalous_read_pairs} 43 ${advanced_options.skip_anomalous_read_pairs}
40 ${advanced_options.disable_probabilistic_realignment} 44 ${advanced_options.disable_probabilistic_realignment}
41 -C "${advanced_options.coefficient_for_downgrading}" 45 -C "${advanced_options.coefficient_for_downgrading}"
42 -d "${advanced_options.max_reads_per_bam}" 46 -d "${advanced_options.max_reads_per_bam}"
43 ${advanced_options.extended_BAQ_computation} 47 ${advanced_options.extended_BAQ_computation}
44 -q "${advanced_options.minimum_mapping_quality}" 48 -q "${advanced_options.minimum_mapping_quality}"
45 -Q "${advanced_options.minimum_base_quality}" 49 -Q "${advanced_options.minimum_base_quality}"
46 #if str( $advanced_options.region_string ): 50 #if str( $advanced_options.region_string ):
47 -r "${advanced_options.region_string}" 51 -r "${advanced_options.region_string}"
48 #end if 52 #end if
49 ${advanced_options.output_per_sample_read_depth} 53
50 ${advanced_options.output_per_sample_strand_bias_p_value}
51 #end if 54 #end if
52 #if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation': 55 #if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation':
53 ##-g or -u 56 ##
54 -g 57
55 -e "${genotype_likelihood_computation_type.gap_extension_sequencing_error_probability}" 58 ${genotype_likelihood_computation_type.output_format}
56 -h "${genotype_likelihood_computation_type.coefficient_for_modeling_homopolymer_errors}" 59 ${genotype_likelihood_computation_type.compressed}
60
61 #if str( $genotype_likelihood_computation_type.output_tags ) != "None":
62 --output-tags "${genotype_likelihood_computation_type.output_tags}"
63 #end if
64
57 #if str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'perform_indel_calling': 65 #if str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'perform_indel_calling':
66 -o "${genotype_likelihood_computation_type.perform_indel_calling.gap_open_sequencing_error_probability}"
67 -e "${genotype_likelihood_computation_type.perform_indel_calling.gap_extension_sequencing_error_probability}"
68 -h "${genotype_likelihood_computation_type.perform_indel_calling.coefficient_for_modeling_homopolymer_errors}"
58 -L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}" 69 -L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}"
59 -m "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_reads_for_indel_candidates}" 70 -m "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_reads_for_indel_candidates}"
71 --open-prob "${genotype_likelihood_computation_type.perform_indel_calling.open_seq_error_probability}"
60 -F "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_read_fraction}" 72 -F "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_read_fraction}"
61 ${genotype_likelihood_computation_type.perform_indel_calling.gapped_read_per_sample} 73 ${genotype_likelihood_computation_type.perform_indel_calling.gapped_read_per_sample}
62 #else: 74 #if len( $genotype_likelihood_computation_type.perform_indel_calling.platform_list_repeat ):
75 -P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.perform_indel_calling.platform_list_repeat ] ) }"
76 #end if
77 #elif str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'do_not_perform_indel_calling':
63 -I 78 -I
64 #end if 79 #end if
65 -o "${genotype_likelihood_computation_type.gap_open_sequencing_error_probability}" 80
66 #if len( $genotype_likelihood_computation_type.platform_list_repeat ): 81
67 -P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.platform_list_repeat ] ) }"
68 #end if
69 #else: 82 #else:
70 ${genotype_likelihood_computation_type.base_position_on_reads} 83 ${genotype_likelihood_computation_type.base_position_on_reads}
71 ${genotype_likelihood_computation_type.output_mapping_quality} 84 ${genotype_likelihood_computation_type.output_mapping_quality}
72 #end if 85 #end if
73 > "$output_mpileup" 2> "$output_log" 86 --output "$output_mpileup" 2> "$output_log"
74 ]]></command> 87 ]]>
75 <stdio> 88 </command>
76 <exit_code range="1:" level="fatal" description="Error" />
77 </stdio>
78 <inputs> 89 <inputs>
79 <conditional name="reference_source"> 90 <conditional name="reference_source">
80 <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> 91 <param label="Choose the source for the reference genome" name="reference_source_selector" type="select">
81 <option value="cached">Locally cached</option> 92 <option value="cached">Use a built-in genome</option>
82 <option value="history">History</option> 93 <option value="history">Use a genome from the history</option>
83 </param> 94 </param>
84 <when value="cached"> 95 <when value="cached">
85 <repeat name="input_bams" title="BAM file" min="1"> 96 <repeat min="1" name="input_bams" title="BAM file">
86 <param name="input_bam" type="data" format="bam" label="BAM file"> 97 <param format="bam" label="BAM file" name="input_bam" type="data">
87 <validator type="unspecified_build" /> 98 <validator type="unspecified_build" />
88 <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." /> <!-- fixme!!! this needs to be a select --> 99 <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" />
89 </param> 100 </param>
90 </repeat> 101 </repeat>
91 <param name="ref_file" type="select" label="Using reference genome"> 102 <param label="Using reference genome" name="ref_file" type="select">
92 <options from_data_table="fasta_indexes" /> 103 <options from_data_table="fasta_indexes" />
93 <!-- <filter type="data_meta" ref="input_bam" key="dbkey" column="1" /> does not yet work in a repeat...-->
94 </param> 104 </param>
95 </when> 105 </when>
96 <when value="history"> 106 <when value="history">
97 <repeat name="input_bams" title="BAM file" min="1"> 107 <repeat min="1" name="input_bams" title="BAM file">
98 <param name="input_bam" type="data" format="bam" label="BAM file"> 108 <param format="bam" label="BAM file" name="input_bam" type="data">
99 <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." /> 109 <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" />
100 </param> 110 </param>
101 </repeat> 111 </repeat>
102 <param name="ref_file" type="data" format="fasta" label="Using reference file" /> 112 <param format="fasta" label="Using reference genome" name="ref_file" type="data" />
103 </when> 113 </when>
104 </conditional> 114 </conditional>
105 <conditional name="genotype_likelihood_computation_type"> 115 <conditional name="genotype_likelihood_computation_type">
106 <param name="genotype_likelihood_computation_type_selector" type="select" label="Genotype Likelihood Computation"> 116 <param label="Genotype Likelihood Computation" name="genotype_likelihood_computation_type_selector" type="select">
107 <option value="perform_genotype_likelihood_computation">Perform genotype likelihood computation</option> 117 <option selected="True" value="perform_genotype_likelihood_computation">Perform genotype likelihood computation (--VCF, --BCF options)</option>
108 <option value="do_not_perform_genotype_likelihood_computation" selected="True">Do not perform genotype likelihood computation</option> 118 <option value="do_not_perform_genotype_likelihood_computation">Do not perform genotype likelihood computation (output pileup)</option>
109 </param> 119 </param>
110 <when value="perform_genotype_likelihood_computation"> 120 <when value="perform_genotype_likelihood_computation">
111 <param name="gap_extension_sequencing_error_probability" type="integer" value="20" label="Phred-scaled gap extension sequencing error probability" /> 121 <param label="Choose the output format" name="output_format" type="select">
112 <param name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" label="Coefficient for modeling homopolymer errors." /> 122 <option value="--VCF">VCF</option>
123 <option value="--BCF">BCF</option>
124 </param>
125 <param checked="False" falsevalue="--uncompressed" label="Compress output" name="compressed" truevalue="" type="boolean" help="--incompressed; default=False"/>
126 <param name="output_tags" optional="True" type="select" multiple="True" display="checkboxes" label="Optional tags to output" help="--output-tags">
127 <option value="DP">DP (Number of high-quality bases)</option>
128 <option value="DPR">DRP (Number of high-quality bases for each observed allele)</option>
129 <option value="DV">DV (Number of high-quality non-reference bases)</option>
130 <option value="DP4">DP4 (Number of high-quality ref-forward, ref-reverse, alt-forward and alt-reverse bases)</option>
131 <option value="INFO/DPR">INFO/DPR (Number of high-quality bases for each observed allele)</option>
132 <option value="SP">SP (Phred-scaled strand bias P-value)</option>
133 </param>
113 <conditional name="perform_indel_calling"> 134 <conditional name="perform_indel_calling">
114 <param name="perform_indel_calling_selector" type="select" label="Perform INDEL calling"> 135 <param label="Perform INDEL calling" name="perform_indel_calling_selector" type="select">
115 <option value="perform_indel_calling" selected="True">Perform INDEL calling</option> 136 <option selected="True" value="perform_indel_calling_def">Perform INDEL calling using default options</option>
137 <option value="perform_indel_calling">Perform INDEL calling and set advanced options</option>
116 <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option> 138 <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option>
117 </param> 139 </param>
140 <when value="perform_indel_calling_def" />
118 <when value="perform_indel_calling"> 141 <when value="perform_indel_calling">
119 <param name="skip_indel_calling_above_sample_depth" type="integer" value="250" label="Skip INDEL calling if the average per-sample depth is above" /> 142 <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"/>
120 <param name="minimum_gapped_reads_for_indel_candidates" type="integer" value="1" label="Minimum gapped reads for indel candidates" /> 143 <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"/>
121 <param name="minimum_gapped_read_fraction" type="float" value="0.002" label="Minimum fraction of gapped reads for candidates" /> 144 <param label="Coefficient for modeling homopolymer errors." name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" help="--tandem-qual; default=100"/>
122 <param name="gapped_read_per_sample" type="boolean" truevalue="-p" falsevalue="" checked="False" label="Apply minimum values on a per-sample basis" /> 145 <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"/>
146 <param label="Minimum gapped reads for indel candidates" name="minimum_gapped_reads_for_indel_candidates" type="integer" value="1" help="--min-ireads; default=1"/>
147 <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"/>
148 <param label="Minimum fraction of gapped reads" name="minimum_gapped_read_fraction" type="float" value="0.002" help="--gap-frac; default=0.002"/>
149 <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"/>
150 <repeat name="platform_list_repeat" title="Platform for INDEL candidates">
151 <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"/>
152 </repeat>
123 </when> 153 </when>
124 <when value="do_not_perform_indel_calling" /> 154 <when value="do_not_perform_indel_calling" />
125 </conditional> 155 </conditional>
126 <param name="gap_open_sequencing_error_probability" type="integer" value="40" label="Phred-scaled gap open sequencing error probability" /> 156
127 <repeat name="platform_list_repeat" title="Platform for INDEL candidates">
128 <param name="platform_entry" type="text" value="" label="Platform to use for INDEL candidates" />
129 </repeat>
130 </when> 157 </when>
131 <when value="do_not_perform_genotype_likelihood_computation"> 158 <when value="do_not_perform_genotype_likelihood_computation">
132 <param name="base_position_on_reads" type="boolean" truevalue="-O" falsevalue="" checked="False" label="Output base positions on reads" /> 159 <param checked="False" falsevalue="" label="Output base positions on reads" name="base_position_on_reads" truevalue="-O" type="boolean" help="--output-BP"/>
133 <param name="output_mapping_quality" type="boolean" truevalue="-s" falsevalue="" checked="False" label="Output mapping quality" /> 160 <param checked="False" falsevalue="" label="Output mapping quality" name="output_mapping_quality" truevalue="-s" type="boolean" help="--output-MQ"/>
134 </when> 161 </when>
135 </conditional> 162 </conditional>
136 <conditional name="advanced_options"> 163 <conditional name="advanced_options">
137 <param name="advanced_options_selector" type="select" label="Set advanced options"> 164 <param label="Set advanced options" name="advanced_options_selector" type="select">
138 <option value="basic" selected="True">Basic</option> 165 <option selected="True" value="basic">Basic</option>
139 <option value="advanced">Advanced</option> 166 <option value="advanced">Advanced</option>
140 </param> 167 </param>
141 <when value="advanced"> 168 <when value="advanced">
142 <conditional name="filter_by_flags"> 169 <conditional name="filter_by_flags">
143 <param name="filter_flags" type="select" label="Set filter by flags"> 170 <param label="Set filter by flags" name="filter_flags" type="select">
144 <option value="nofilter" selected="True">Do not filter</option> 171 <option selected="True" value="nofilter">Do not filter</option>
145 <option value="filter">Filter by flags to exclude or require</option> 172 <option value="filter">Filter by flags to exclude or require</option>
146 </param> 173 </param>
147 <when value="filter"> 174 <when value="filter">
148 <param name="require_flags" type="select" display="checkboxes" multiple="True" label="Require"> 175 <param display="checkboxes" label="Require" multiple="True" name="require_flags" type="select" help="--incl-flags">
149 <option value="1">Read is paired</option> 176 <option value="1">Read is paired</option>
150 <option value="2">Read is mapped in a proper pair</option> 177 <option value="2">Read is mapped in a proper pair</option>
151 <option value="4">The read is unmapped</option> 178 <option value="4">The read is unmapped</option>
152 <option value="8">The mate is unmapped</option> 179 <option value="8">The mate is unmapped</option>
153 <option value="16">Read strand</option> 180 <option value="16">Read strand</option>
156 <option value="128">Read is the second in a pair</option> 183 <option value="128">Read is the second in a pair</option>
157 <option value="256">The alignment or this read is not primary</option> 184 <option value="256">The alignment or this read is not primary</option>
158 <option value="512">The read fails platform/vendor quality checks</option> 185 <option value="512">The read fails platform/vendor quality checks</option>
159 <option value="1024">The read is a PCR or optical duplicate</option> 186 <option value="1024">The read is a PCR or optical duplicate</option>
160 </param> 187 </param>
161 <param name="exclude_flags" type="select" display="checkboxes" multiple="True" label="Exclude"> 188 <param display="checkboxes" label="Exclude" multiple="True" name="exclude_flags" type="select" help="--excl-flags">
162 <option value="1">Read is paired</option> 189 <option value="1">Read is paired</option>
163 <option value="2">Read is mapped in a proper pair</option> 190 <option value="2">Read is mapped in a proper pair</option>
164 <option value="4">The read is unmapped</option> 191 <option value="4">The read is unmapped</option>
165 <option value="8">The mate is unmapped</option> 192 <option value="8">The mate is unmapped</option>
166 <option value="16">Read strand</option> 193 <option value="16">Read strand</option>
173 </param> 200 </param>
174 </when> 201 </when>
175 <when value="nofilter" /> 202 <when value="nofilter" />
176 </conditional> 203 </conditional>
177 <conditional name="limit_by_region"> 204 <conditional name="limit_by_region">
178 <param name="limit_by_regions" type="select" label="Select regions to call"> 205 <param label="Select regions to call" name="limit_by_regions" type="select">
179 <option value="no_limit" selected="True">Do not limit</option> 206 <option selected="True" value="no_limit">Do not limit</option>
180 <option value="history">From an uploaded BED file</option> 207 <option value="history">From an uploaded BED file (--positions)</option>
181 <option value="paste">Paste a list of regions or BED</option> 208 <option value="paste">Paste a list of regions or BED (--region)</option>
182 </param> 209 </param>
183 <when value="history"> 210 <when value="history">
184 <param name="bed_regions" type="data" format="bed" label="BED file"> 211 <param format="bed" label="BED file" name="bed_regions" type="data" help="--positions">
185 <validator type="dataset_ok_validator" /> 212 <validator type="dataset_ok_validator" />
186 </param> 213 </param>
187 </when> 214 </when>
188 <when value="paste"> 215 <when value="paste">
189 <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"/> 216 <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"/>
190 </when> 217 </when>
191 <when value="no_limit" /> 218 <when value="no_limit" />
192 </conditional> 219 </conditional>
193 <conditional name="exclude_read_group"> 220 <conditional name="exclude_read_group">
194 <param name="exclude_read_groups" type="select" label="Select read groups to exclude"> 221 <param label="Select read groups to exclude" name="exclude_read_groups" type="select" help="--exclude-RG">
195 <option value="no_limit" selected="True">Do not exclude</option> 222 <option selected="True" value="no_limit">Do not exclude</option>
196 <option value="history">From an uploaded text file</option> 223 <option value="history">From an uploaded text file</option>
197 <option value="paste">Paste a list of read groups</option> 224 <option value="paste">Paste a list of read groups</option>
198 </param> 225 </param>
199 <when value="history"> 226 <when value="history">
200 <param name="read_groups" type="data" format="txt" label="Text file"> 227 <param format="txt" label="Text file" name="read_groups" type="data">
201 <validator type="dataset_ok_validator" /> 228 <validator type="dataset_ok_validator" />
202 </param> 229 </param>
203 </when> 230 </when>
204 <when value="paste"> 231 <when value="paste">
205 <param name="group_paste" type="text" area="true" size="10x35" label="Read groups" help="Paste a list of read groups"/> 232 <param area="true" help="Paste a list of read groups" label="Read groups" name="group_paste" size="10x35" type="text" />
206 </when> 233 </when>
207 <when value="no_limit" /> 234 <when value="no_limit" />
208 </conditional> 235 </conditional>
209 <param name="skip_anomalous_read_pairs" type="boolean" truevalue="-A" falsevalue="" checked="False" label="Do not skip anomalous read pairs in variant calling" /> 236 <param checked="False" falsevalue="" label="Disable read-pair overlap detection" name="ignore_overlaps" truevalue="-x" type="boolean" help="--ignore-overlaps"/>
210 <param name="disable_probabilistic_realignment" type="boolean" truevalue="-B" falsevalue="" checked="False" label=" Disable probabilistic realignment for the computation of base alignment quality (BAQ)" /> 237 <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"/>
211 <param name="coefficient_for_downgrading" type="integer" value="0" label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" /> 238 <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"/>
212 <param name="max_reads_per_bam" type="integer" value="250" label="Max reads per BAM" /> 239 <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"/>
213 <param name="extended_BAQ_computation" type="boolean" truevalue="-E" falsevalue="" checked="False" label="Extended BAQ computation" /> 240 <param label="Max reads per BAM" max="1024" min="1" name="max_reads_per_bam" type="integer" value="250" help="--max-depth; default=250"/>
214 <param name="minimum_mapping_quality" type="integer" value="0" label="Minimum mapping quality for an alignment to be used" /> 241 <param checked="False" falsevalue="" label="Redo BAQ computation" name="extended_BAQ_computation" truevalue="-E" type="boolean" help="--redo-BAQ; ignore existing BQ tags"/>
215 <param name="minimum_base_quality" type="integer" value="13" label="Minimum base quality for a base to be considered" /> 242 <param label="Minimum mapping quality for an alignment to be used" name="minimum_mapping_quality" type="integer" value="0" help="-min-MQ; default=0"/>
216 <param name="region_string" type="text" value="" label="Only generate pileup in region" /> 243 <param label="Minimum base quality for a base to be considered" name="minimum_base_quality" type="integer" value="13" help="--min-BQ; default=13"/>
217 <param name="output_per_sample_read_depth" type="boolean" truevalue="-D" falsevalue="" checked="False" label="Output per-sample read depth" /> 244 <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" />
218 <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" />
219 </when> 245 </when>
220 <when value="basic" /> 246 <when value="basic" />
221 </conditional> 247 </conditional>
222 </inputs> 248 </inputs>
223 <configfiles>
224 <configfile name="excluded_read_groups">
225 <![CDATA[
226 <%
227 import re
228 %>
229 #set pasted_data = ''
230 #if str( $advanced_options.advanced_options_selector ) == "advanced":
231 #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste":
232 #set regex=re.compile("\\s+")
233 #set pasted_data = '\t'.join( regex.split( str( $advanced_options.exclude_read_group['read_groups'] ) ) )
234 #end if
235 #end if
236 ${pasted_data}
237 ]]>
238 </configfile>
239 <configfile name="pasted_regions">
240 <![CDATA[
241 <%
242 import re
243 %>
244 #set pasted_data = ''
245 #if str( $advanced_options.advanced_options_selector ) == "advanced":
246 #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste":
247 #set regex=re.compile("\\s+")
248 #set pasted_data = '\t'.join( regex.split( str( $advanced_options.limit_by_region['region_paste'] ) ) )
249 #end if
250 #end if
251 ${pasted_data}
252 ]]>
253 </configfile>
254 </configfiles>
255 <outputs> 249 <outputs>
256 <data format="pileup" name="output_mpileup" label="${tool.name} on ${on_string}"> 250 <data format="pileup" label="${tool.name} on ${on_string}" name="output_mpileup">
257 <change_format> 251 <change_format>
258 <when input="genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" format="bcf" /> 252 <when format="bcf" input="genotype_likelihood_computation_type.output_format" value="--BCF" />
253 <when format="vcf" input="genotype_likelihood_computation_type.output_format" value="--VCF" />
259 </change_format> 254 </change_format>
260 </data> 255 </data>
261 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> 256 <data format="txt" label="${tool.name} on ${on_string} (log)" name="output_log" />
262 </outputs> 257 </outputs>
263 <tests> 258 <tests>
264 <test> 259 <test>
265 <param name="reference_source_selector" value="history" /> 260 <param name="reference_source_selector" value="history" />
266 <param name="ref_file" value="phiX.fasta" ftype="fasta" /> 261 <param ftype="fasta" name="ref_file" value="phiX.fasta" />
267 <param name="input_bam" value="samtools_mpileup_in_1.bam" ftype="bam" /> 262 <param ftype="bam" name="input_bam" value="samtools_mpileup_in_1.bam" />
268 <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" /> 263 <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" />
269 <param name="advanced_options_selector" value="basic" /> 264 <param name="advanced_options_selector" value="basic" />
270 <param name="base_position_on_reads" value="true" /> 265 <param name="base_position_on_reads" value="true" />
271 <param name="output_mapping_quality" value="true" /> 266 <param name="output_mapping_quality" value="true" />
272 <output name="output_mpileup" file="samtools_mpileup_out_1.pileup" /> 267 <output file="samtools_mpileup_out_1.pileup" name="output_mpileup" />
273 <output name="output_log" file="samtools_mpileup_out_1.log" /> 268 <output file="samtools_mpileup_out_1.log" name="output_log" />
274 </test> 269 </test>
275 <test> 270 <test>
276 <param name="reference_source_selector" value="history" /> 271 <param name="reference_source_selector" value="history" />
277 <param name="ref_file" value="phiX.fasta" ftype="fasta" /> 272 <param ftype="fasta" name="ref_file" value="phiX.fasta" />
278 <param name="input_bam" value="samtools_mpileup_in_1.bam" ftype="bam" /> 273 <param ftype="bam" name="input_bam" value="phiX.bam" />
279 <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" /> 274 <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" />
280 <param name="gap_extension_sequencing_error_probability" value="20" /> 275 <param name="gap_extension_sequencing_error_probability" value="20" />
281 <param name="coefficient_for_modeling_homopolymer_errors" value="100" /> 276 <param name="coefficient_for_modeling_homopolymer_errors" value="100" />
282 <param name="perform_indel_calling_selector" value="perform_indel_calling" /> 277 <param name="perform_indel_calling_selector" value="perform_indel_calling" />
283 <param name="skip_indel_calling_above_sample_depth" value="250" /> 278 <param name="skip_indel_calling_above_sample_depth" value="250" />
284 <param name="gap_open_sequencing_error_probability" value="40" /> 279 <param name="gap_open_sequencing_error_probability" value="40" />
285 <param name="platform_list_repeat" value="0" /> 280 <param name="platform_list_repeat" value="0" />
286 <param name="advanced_options_selector" value="basic" /> 281 <param name="advanced_options_selector" value="basic" />
287 <output name="output_mpileup" ftype="bcf" file="samtools_mpileup_out_2.bcf" lines_diff="1" /> 282 <param name="genotype_likelihood_computation_type|output_format" value="VCF" />
288 <output name="output_log" file="samtools_mpileup_out_2.log" /> 283 <output file="samtools_mpileup_out_2.vcf" ftype="vcf" lines_diff="8" name="output_mpileup" />
289 </test> 284 <output file="samtools_mpileup_out_2.log" name="output_log" />
290 <test>
291 <param name="reference_source_selector" value="cached" />
292 <param name="input_bam" value="samtools_mpileup_in_3.bam" ftype="bam" dbkey="phiX" />
293 <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" />
294 <param name="gap_extension_sequencing_error_probability" value="20" />
295 <param name="coefficient_for_modeling_homopolymer_errors" value="100" />
296 <param name="perform_indel_calling_selector" value="perform_indel_calling" />
297 <param name="skip_indel_calling_above_sample_depth" value="250" />
298 <param name="gap_open_sequencing_error_probability" value="40" />
299 <param name="platform_list_repeat" value="0" />
300 <param name="advanced_options_selector" value="basic" />
301 <output name="output_mpileup" ftype="bcf" file="samtools_mpileup_out_2.bcf" lines_diff="1" />
302 <output name="output_log" file="samtools_mpileup_out_3.log" />
303 </test>
304 <test>
305 <param name="reference_source_selector" value="cached" />
306 <param name="input_bam" value="samtools_mpileup_in_1.bam" ftype="bam" dbkey="phiX" />
307 <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" />
308 <param name="gap_extension_sequencing_error_probability" value="20" />
309 <param name="coefficient_for_modeling_homopolymer_errors" value="100" />
310 <param name="perform_indel_calling_selector" value="perform_indel_calling" />
311 <param name="skip_indel_calling_above_sample_depth" value="250" />
312 <param name="gap_open_sequencing_error_probability" value="40" />
313 <param name="platform_list_repeat" value="0" />
314 <param name="advanced_options_selector" value="advanced" />
315 <param name="advanced_options|filter_by_flags|filter_flags" value="nofilter" />
316 <param name="advanced_options|limit_by_region|limit_by_regions" value="no_limit" />
317 <param name="advanced_options|coefficient_for_downgrading" value="true" />
318 <param name="advanced_options|max_reads_per_bam" value="200" />
319 <param name="advanced_options|extended_BAQ_computation" value="true" />
320 <param name="advanced_options|minimum_mapping_quality" value="0" />
321 <param name="advanced_options|minimum_base_quality" value="43" />
322 <output name="output_mpileup" ftype="bcf" file="samtools_mpileup_out_4.bcf" lines_diff="1" />
323 <output name="output_log" file="samtools_mpileup_out_4.log" />
324 </test> 285 </test>
325 </tests> 286 </tests>
326 <help> 287 <help>
288 <![CDATA[
327 **What it does** 289 **What it does**
328 290
329 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. 291 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.
330 292
331 ------ 293 ------
332 294
333 .. list-table:: **Input options** 295 **Input options**::
334 :widths: 5 5 40 10 296
335 :header-rows: 1 297 -6, --illumina1.3+ quality is in the Illumina-1.3+ encoding
336 298 -A, --count-orphans do not discard anomalous read pairs
337 * - Flag 299 -b, --bam-list FILE list of input BAM filenames, one per line
338 - Type 300 -B, --no-BAQ disable BAQ (per-Base Alignment Quality)
339 - Description 301 -C, --adjust-MQ INT adjust mapping quality; recommended:50, disable:0 [0]
340 - Default 302 -d, --max-depth INT max per-BAM depth; avoids excessive memory usage [250]
341 * - -6 303 -E, --redo-BAQ recalculate BAQ on the fly, ignore existing BQs
342 - *BOOLEAN* 304 -f, --fasta-ref FILE faidx indexed reference sequence file
343 - assume the quality is in the Illumina-1.3+ encoding 305 -G, --exclude-RG FILE exclude read groups listed in FILE
344 - off 306 -l, --positions FILE skip unlisted positions (chr pos) or regions (BED)
345 * - -A 307 -q, --min-MQ INT skip alignments with mapQ smaller than INT [0]
346 - *BOOLEAN* 308 -Q, --min-BQ INT skip bases with baseQ/BAQ smaller than INT [13]
347 - count anomalous read pairs 309 -r, --region REG region in which pileup is generated
348 - off 310 -R, --ignore-RG ignore RG tags (one BAM = one sample)
349 * - -B 311 --rf, --incl-flags STR|INT required flags: skip reads with mask bits unset []
350 - *BOOLEAN* 312 --ff, --excl-flags STR|INT filter flags: skip reads with mask bits set
351 - disable BAQ computation 313 [UNMAP,SECONDARY,QCFAIL,DUP]
352 - off 314 -x, --ignore-overlaps disable read-pair overlap detection
353 * - -b 315
354 - *FILE* 316 **Output options**::
355 - list of input BAM filenames, one per line 317
356 - *null* 318 -o, --output FILE write output to FILE [standard output]
357 * - -C 319 -g, --BCF generate genotype likelihoods in BCF format
358 - *INT* 320 -v, --VCF generate genotype likelihoods in VCF format
359 - parameter for adjusting mapQ; 0 to disable 321
360 - 0 322 **Output options for mpileup format** (without -g/-v)::
361 * - -d 323
362 - *INT* 324 -O, --output-BP output base positions on reads
363 - max per-BAM depth to avoid excessive memory usage 325 -s, --output-MQ output mapping quality
364 - 250 326
365 * - -E 327 **Output options for genotype likelihoods** (when -g/-v is used)::
366 - *BOOLEAN* 328
367 - recalculate extended BAQ on the fly thus ignoring existing BQs 329 -t, --output-tags LIST optional tags to output: DP,DPR,DV,DP4,INFO/DPR,SP []
368 - off 330 -u, --uncompressed generate uncompressed VCF/BCF output
369 * - -f 331
370 - *FILE* 332 **SNP/INDEL genotype likelihoods options** (effective with -g/-v)::
371 - faidx indexed reference sequence file 333
372 - *null* 334 -e, --ext-prob INT Phred-scaled gap extension seq error probability [20]
373 * - -G 335 -F, --gap-frac FLOAT minimum fraction of gapped reads [0.002]
374 - *FILE* 336 -h, --tandem-qual INT coefficient for homopolymer errors [100]
375 - exclude read groups listed in FILE 337 -I, --skip-indels do not perform indel calling
376 - *null* 338 -L, --max-idepth INT maximum per-sample depth for INDEL calling [250]
377 * - -l 339 -m, --min-ireads INT minimum number gapped reads for indel candidates [1]
378 - *FILE* 340 -o, --open-prob INT Phred-scaled gap open seq error probability [40]
379 - list of positions (chr pos) or regions (BED) 341 -p, --per-sample-mF apply -m and -F per-sample for increased sensitivity
380 - *null* 342 -P, --platforms STR comma separated list of platforms for indels [all]
381 * - -M 343
382 - *INT* 344 **Notes**: Assuming diploid individuals.
383 - cap mapping quality at INT 345 ]]>
384 - 60
385 * - -r
386 - *STR*
387 - region in which pileup is generated
388 - *null*
389 * - -R
390 - *BOOLEAN*
391 - ignore RG tags
392 - off
393 * - -q
394 - *INT*
395 - skip alignments with mapQ smaller than INT
396 - 0
397 * - -Q
398 - *INT*
399 - skip bases with baseQ/BAQ smaller than INT
400 - 13
401 * - --rf
402 - *INT*
403 - required flags: skip reads with mask bits unset
404 - 0
405 * - --ff
406 - *INT*
407 - filter flags: skip reads with mask bits set
408 - 0
409
410 ------
411
412 .. list-table:: **Output options**
413 :widths: 5 5 40 10
414 :header-rows: 1
415
416 * - Flag
417 - Type
418 - Description
419 - Default
420 * - -D
421 - *BOOLEAN*
422 - output per-sample DP in BCF (require -g/-u)
423 - off
424 * - -g
425 - *BOOLEAN*
426 - generate BCF output (genotype likelihoods)
427 - off
428 * - -O
429 - *BOOLEAN*
430 - output base positions on reads (disabled by -g/-u)
431 - off
432 * - -s
433 - *BOOLEAN*
434 - output mapping quality (disabled by -g/-u)
435 - off
436 * - -S
437 - *BOOLEAN*
438 - output per-sample strand bias P-value in BCF (require -g/-u)
439 - off
440 * - -u
441 - *BOOLEAN*
442 - generate uncompressed BCF output
443 - off
444
445 ------
446
447 .. list-table:: **SNP/INDEL genotype likelihoods options (effective with '-g' or '-u')**
448 :widths: 5 5 40 10
449 :header-rows: 1
450
451 * - Flag
452 - Type
453 - Description
454 - Default
455 * - -e
456 - *INT*
457 - Phred-scaled gap extension seq error probability
458 - 20
459 * - -F
460 - *FLOAT*
461 - minimum fraction of gapped reads for candidates
462 - 0.002
463 * - -h
464 - *INT*
465 - coefficient for homopolymer errors
466 - 100
467 * - -I
468 - *BOOLEAN*
469 - do not perform indel calling
470 - off
471 * - -L
472 - *INT*
473 - max per-sample depth for INDEL calling
474 - 250
475 * - -m
476 - *INT*
477 - minimum gapped reads for indel candidates
478 - 1
479 * - -o
480 - *INT*
481 - Phred-scaled gap open sequencing error probability
482 - 40
483 * - -p
484 - *BOOLEAN*
485 - apply -m and -F per-sample to increase sensitivity
486 - off
487 * - -P
488 - *STR*
489 - comma separated list of platforms for indels
490 - all
491
492 ------
493
494 **Citation**
495
496 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;`_
497
498
499 If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.*
500 </help> 346 </help>
347 <configfiles>
348 <configfile name="excluded_read_groups">
349 <![CDATA[
350 #set pasted_data = ''
351 #if str( $advanced_options.advanced_options_selector ) == "advanced":
352 #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste":
353 #set pasted_data = '\t'.join( str( $advanced_options.exclude_read_group['read_groups'] ).split() )
354 #end if
355 #end if
356 ${pasted_data}
357 ]]>
358 </configfile>
359 <configfile name="pasted_regions">
360 <![CDATA[
361 #set pasted_data = ''
362 #if str( $advanced_options.advanced_options_selector ) == "advanced":
363 #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste":
364 #set pasted_data = '\t'.join( str( $advanced_options.limit_by_region['region_paste'] ).split() )
365 #end if
366 #end if
367 ${pasted_data}
368 ]]>
369 </configfile>
370 </configfiles>
371 <expand macro="citations" />
501 </tool> 372 </tool>