Mercurial > repos > jbrayet > samtools_1_2_docker

comparison samtools_mpileup.xml @ 7:2f69634a480e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jbrayet
date Wed, 25 Nov 2015 03:22:57 -0500
parents
children
comparison
equal deleted inserted replaced
6:fdf2125c9f02 7:2f69634a480e
1 <tool id="samtools_mpileup" name="MPileup" version="2.1.1">
2 <description>call variants</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements" />
7 <expand macro="stdio" />
8 <expand macro="version_command" />
9 <command>
10 <![CDATA[
11 #if $reference_source.reference_source_selector == "history":
12 ln -s "${reference_source.ref_file}" && samtools faidx `basename "${reference_source.ref_file}"` && samtools mpileup
13 #else:
14 samtools mpileup
15 #end if
16 #if $reference_source.reference_source_selector != "history":
17 -f "${reference_source.ref_file.fields.path}"
18 #else:
19 -f "${reference_source.ref_file}"
20 #end if
21 #for $bam in $reference_source.input_bam:
22 "${bam}"
23 #end for
24 #if str( $advanced_options.advanced_options_selector ) == "advanced":
25 #if str( $advanced_options.filter_by_flags.filter_flags ) == "filter":
26 #if $advanced_options.filter_by_flags.require_flags:
27 --rf ${sum([int(flag) for flag in str($advanced_options.filter_by_flags.require_flags).split(',')])}
28 #end if
29 #if $advanced_options.filter_by_flags.exclude_flags:
30 --ff ${sum([int(flag) for flag in str($advanced_options.filter_by_flags.exclude_flags).split(',')])}
31 #end if
32 #end if
33 #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste":
34 -l "$pasted_regions"
35 #elif str( $advanced_options.limit_by_region.limit_by_regions ) == "history"
36 -l "$advanced_options.limit_by_region.bed_regions"
37 #end if
38 #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste":
39 -G "$excluded_read_groups"
40 #elif str( $advanced_options.exclude_read_group.exclude_read_groups ) == "history"
41 -G "$advanced_options.exclude_read_group.read_groups"
42 #end if
43 ${advanced_options.skip_anomalous_read_pairs}
44 ${advanced_options.disable_probabilistic_realignment}
45 -C "${advanced_options.coefficient_for_downgrading}"
46 -d "${advanced_options.max_reads_per_bam}"
47 ${advanced_options.extended_BAQ_computation}
48 -q "${advanced_options.minimum_mapping_quality}"
49 -Q "${advanced_options.minimum_base_quality}"
50 #if str( $advanced_options.region_string ):
51 -r "${advanced_options.region_string}"
52 #end if
53
54 #end if
55 #if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation':
56 ##
57
58 ${genotype_likelihood_computation_type.output_format}
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
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}"
69 -L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}"
70 -m "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_reads_for_indel_candidates}"
71 --open-prob "${genotype_likelihood_computation_type.perform_indel_calling.open_seq_error_probability}"
72 -F "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_read_fraction}"
73 ${genotype_likelihood_computation_type.perform_indel_calling.gapped_read_per_sample}
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':
78 -I
79 #end if
80
81
82 #else:
83 ${genotype_likelihood_computation_type.base_position_on_reads}
84 ${genotype_likelihood_computation_type.output_mapping_quality}
85 #end if
86 --output "$output_mpileup" 2> "$output_log"
87 ]]>
88 </command>
89 <inputs>
90 <conditional name="reference_source">
91 <param label="Choose the source for the reference genome" name="reference_source_selector" type="select">
92 <option value="cached">Use a built-in genome</option>
93 <option value="history">Use a genome from the history</option>
94 </param>
95 <when value="cached">
96 <param format="bam" label="BAM file(s)" name="input_bam" type="data" min="1" multiple="True">
97 <validator type="unspecified_build" />
98 <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" />
99 </param>
100 <param label="Using reference genome" name="ref_file" type="select">
101 <options from_data_table="fasta_indexes" />
102 </param>
103 </when>
104 <when value="history">
105 <param format="bam" label="BAM file(s)" name="input_bam" type="data" min="1" multiple="True">
106 <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" />
107 </param>
108 <param format="fasta" label="Using reference genome" name="ref_file" type="data" />
109 </when>
110 </conditional>
111 <conditional name="genotype_likelihood_computation_type">
112 <param label="Genotype Likelihood Computation" name="genotype_likelihood_computation_type_selector" type="select">
113 <option selected="True" value="perform_genotype_likelihood_computation">Perform genotype likelihood computation (--VCF, --BCF options)</option>
114 <option value="do_not_perform_genotype_likelihood_computation">Do not perform genotype likelihood computation (output pileup)</option>
115 </param>
116 <when value="perform_genotype_likelihood_computation">
117 <param label="Choose the output format" name="output_format" type="select">
118 <option value="--VCF">VCF</option>
119 <option value="--BCF">BCF</option>
120 </param>
121 <param checked="False" falsevalue="--uncompressed" label="Compress output" name="compressed" truevalue="" type="boolean" help="--incompressed; default=False"/>
122 <param name="output_tags" optional="True" type="select" multiple="True" display="checkboxes" label="Optional tags to output" help="--output-tags">
123 <option value="DP">DP (Number of high-quality bases)</option>
124 <option value="DPR">DRP (Number of high-quality bases for each observed allele)</option>
125 <option value="DV">DV (Number of high-quality non-reference bases)</option>
126 <option value="DP4">DP4 (Number of high-quality ref-forward, ref-reverse, alt-forward and alt-reverse bases)</option>
127 <option value="INFO/DPR">INFO/DPR (Number of high-quality bases for each observed allele)</option>
128 <option value="SP">SP (Phred-scaled strand bias P-value)</option>
129 </param>
130 <conditional name="perform_indel_calling">
131 <param label="Perform INDEL calling" name="perform_indel_calling_selector" type="select">
132 <option selected="True" value="perform_indel_calling_def">Perform INDEL calling using default options</option>
133 <option value="perform_indel_calling">Perform INDEL calling and set advanced options</option>
134 <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option>
135 </param>
136 <when value="perform_indel_calling_def" />
137 <when value="perform_indel_calling">
138 <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"/>
139 <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"/>
140 <param label="Coefficient for modeling homopolymer errors." name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" help="--tandem-qual; default=100"/>
141 <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"/>
142 <param label="Minimum gapped reads for indel candidates" name="minimum_gapped_reads_for_indel_candidates" type="integer" value="1" help="--min-ireads; default=1"/>
143 <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"/>
144 <param label="Minimum fraction of gapped reads" name="minimum_gapped_read_fraction" type="float" value="0.002" help="--gap-frac; default=0.002"/>
145 <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"/>
146 <repeat name="platform_list_repeat" title="Platform for INDEL candidates">
147 <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"/>
148 </repeat>
149 </when>
150 <when value="do_not_perform_indel_calling" />
151 </conditional>
152
153 </when>
154 <when value="do_not_perform_genotype_likelihood_computation">
155 <param checked="False" falsevalue="" label="Output base positions on reads" name="base_position_on_reads" truevalue="-O" type="boolean" help="--output-BP"/>
156 <param checked="False" falsevalue="" label="Output mapping quality" name="output_mapping_quality" truevalue="-s" type="boolean" help="--output-MQ"/>
157 </when>
158 </conditional>
159 <conditional name="advanced_options">
160 <param label="Set advanced options" name="advanced_options_selector" type="select">
161 <option selected="True" value="basic">Basic</option>
162 <option value="advanced">Advanced</option>
163 </param>
164 <when value="advanced">
165 <conditional name="filter_by_flags">
166 <param label="Set filter by flags" name="filter_flags" type="select">
167 <option selected="True" value="nofilter">Do not filter</option>
168 <option value="filter">Filter by flags to exclude or require</option>
169 </param>
170 <when value="filter">
171 <param display="checkboxes" label="Require" multiple="True" name="require_flags" type="select" help="--incl-flags">
172 <option value="1">Read is paired</option>
173 <option value="2">Read is mapped in a proper pair</option>
174 <option value="4">The read is unmapped</option>
175 <option value="8">The mate is unmapped</option>
176 <option value="16">Read strand</option>
177 <option value="32">Mate strand</option>
178 <option value="64">Read is the first in a pair</option>
179 <option value="128">Read is the second in a pair</option>
180 <option value="256">The alignment or this read is not primary</option>
181 <option value="512">The read fails platform/vendor quality checks</option>
182 <option value="1024">The read is a PCR or optical duplicate</option>
183 </param>
184 <param display="checkboxes" label="Exclude" multiple="True" name="exclude_flags" type="select" help="--excl-flags">
185 <option value="1">Read is paired</option>
186 <option value="2">Read is mapped in a proper pair</option>
187 <option value="4">The read is unmapped</option>
188 <option value="8">The mate is unmapped</option>
189 <option value="16">Read strand</option>
190 <option value="32">Mate strand</option>
191 <option value="64">Read is the first in a pair</option>
192 <option value="128">Read is the second in a pair</option>
193 <option value="256">The alignment or this read is not primary</option>
194 <option value="512">The read fails platform/vendor quality checks</option>
195 <option value="1024">The read is a PCR or optical duplicate</option>
196 </param>
197 </when>
198 <when value="nofilter" />
199 </conditional>
200 <conditional name="limit_by_region">
201 <param label="Select regions to call" name="limit_by_regions" type="select">
202 <option selected="True" value="no_limit">Do not limit</option>
203 <option value="history">From an uploaded BED file (--positions)</option>
204 <option value="paste">Paste a list of regions or BED (--region)</option>
205 </param>
206 <when value="history">
207 <param format="bed" label="BED file" name="bed_regions" type="data" help="--positions">
208 <validator type="dataset_ok_validator" />
209 </param>
210 </when>
211 <when value="paste">
212 <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"/>
213 </when>
214 <when value="no_limit" />
215 </conditional>
216 <conditional name="exclude_read_group">
217 <param label="Select read groups to exclude" name="exclude_read_groups" type="select" help="--exclude-RG">
218 <option selected="True" value="no_limit">Do not exclude</option>
219 <option value="history">From an uploaded text file</option>
220 <option value="paste">Paste a list of read groups</option>
221 </param>
222 <when value="history">
223 <param format="txt" label="Text file" name="read_groups" type="data">
224 <validator type="dataset_ok_validator" />
225 </param>
226 </when>
227 <when value="paste">
228 <param area="true" help="Paste a list of read groups" label="Read groups" name="group_paste" size="10x35" type="text" />
229 </when>
230 <when value="no_limit" />
231 </conditional>
232 <param checked="False" falsevalue="" label="Disable read-pair overlap detection" name="ignore_overlaps" truevalue="-x" type="boolean" help="--ignore-overlaps"/>
233 <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"/>
234 <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"/>
235 <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"/>
236 <param label="Max reads per BAM" max="1024" min="1" name="max_reads_per_bam" type="integer" value="250" help="--max-depth; default=250"/>
237 <param checked="False" falsevalue="" label="Redo BAQ computation" name="extended_BAQ_computation" truevalue="-E" type="boolean" help="--redo-BAQ; ignore existing BQ tags"/>
238 <param label="Minimum mapping quality for an alignment to be used" name="minimum_mapping_quality" type="integer" value="0" help="-min-MQ; default=0"/>
239 <param label="Minimum base quality for a base to be considered" name="minimum_base_quality" type="integer" value="13" help="--min-BQ; default=13"/>
240 <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" />
241 </when>
242 <when value="basic" />
243 </conditional>
244 </inputs>
245 <outputs>
246 <data format="pileup" label="${tool.name} on ${on_string}" name="output_mpileup">
247 <change_format>
248 <when format="bcf" input="genotype_likelihood_computation_type.output_format" value="--BCF" />
249 <when format="vcf" input="genotype_likelihood_computation_type.output_format" value="--VCF" />
250 </change_format>
251 </data>
252 <data format="txt" label="${tool.name} on ${on_string} (log)" name="output_log" />
253 </outputs>
254 <tests>
255 <test>
256 <param name="reference_source_selector" value="history" />
257 <param ftype="fasta" name="ref_file" value="phiX.fasta" />
258 <param ftype="bam" name="input_bam" value="samtools_mpileup_in_1.bam" />
259 <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" />
260 <param name="advanced_options_selector" value="basic" />
261 <param name="base_position_on_reads" value="true" />
262 <param name="output_mapping_quality" value="true" />
263 <output file="samtools_mpileup_out_1.pileup" name="output_mpileup" />
264 <output file="samtools_mpileup_out_1.log" name="output_log" />
265 </test>
266 <test>
267 <param name="reference_source_selector" value="history" />
268 <param ftype="fasta" name="ref_file" value="phiX.fasta" />
269 <param ftype="bam" name="input_bam" value="phiX.bam" />
270 <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" />
271 <param name="gap_extension_sequencing_error_probability" value="20" />
272 <param name="coefficient_for_modeling_homopolymer_errors" value="100" />
273 <param name="perform_indel_calling_selector" value="perform_indel_calling" />
274 <param name="skip_indel_calling_above_sample_depth" value="250" />
275 <param name="gap_open_sequencing_error_probability" value="40" />
276 <param name="platform_list_repeat" value="0" />
277 <param name="advanced_options_selector" value="basic" />
278 <param name="genotype_likelihood_computation_type|output_format" value="VCF" />
279 <output file="samtools_mpileup_out_2.vcf" ftype="vcf" lines_diff="8" name="output_mpileup" />
280 <output file="samtools_mpileup_out_2.log" name="output_log" />
281 </test>
282 </tests>
283 <help>
284 <![CDATA[
285 **What it does**
286
287 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.
288
289 ------
290
291 **Input options**::
292
293 -6, --illumina1.3+ quality is in the Illumina-1.3+ encoding
294 -A, --count-orphans do not discard anomalous read pairs
295 -b, --bam-list FILE list of input BAM filenames, one per line
296 -B, --no-BAQ disable BAQ (per-Base Alignment Quality)
297 -C, --adjust-MQ INT adjust mapping quality; recommended:50, disable:0 [0]
298 -d, --max-depth INT max per-BAM depth; avoids excessive memory usage [250]
299 -E, --redo-BAQ recalculate BAQ on the fly, ignore existing BQs
300 -f, --fasta-ref FILE faidx indexed reference sequence file
301 -G, --exclude-RG FILE exclude read groups listed in FILE
302 -l, --positions FILE skip unlisted positions (chr pos) or regions (BED)
303 -q, --min-MQ INT skip alignments with mapQ smaller than INT [0]
304 -Q, --min-BQ INT skip bases with baseQ/BAQ smaller than INT [13]
305 -r, --region REG region in which pileup is generated
306 -R, --ignore-RG ignore RG tags (one BAM = one sample)
307 --rf, --incl-flags STR|INT required flags: skip reads with mask bits unset []
308 --ff, --excl-flags STR|INT filter flags: skip reads with mask bits set
309 [UNMAP,SECONDARY,QCFAIL,DUP]
310 -x, --ignore-overlaps disable read-pair overlap detection
311
312 **Output options**::
313
314 -o, --output FILE write output to FILE [standard output]
315 -g, --BCF generate genotype likelihoods in BCF format
316 -v, --VCF generate genotype likelihoods in VCF format
317
318 **Output options for mpileup format** (without -g/-v)::
319
320 -O, --output-BP output base positions on reads
321 -s, --output-MQ output mapping quality
322
323 **Output options for genotype likelihoods** (when -g/-v is used)::
324
325 -t, --output-tags LIST optional tags to output: DP,DPR,DV,DP4,INFO/DPR,SP []
326 -u, --uncompressed generate uncompressed VCF/BCF output
327
328 **SNP/INDEL genotype likelihoods options** (effective with -g/-v)::
329
330 -e, --ext-prob INT Phred-scaled gap extension seq error probability [20]
331 -F, --gap-frac FLOAT minimum fraction of gapped reads [0.002]
332 -h, --tandem-qual INT coefficient for homopolymer errors [100]
333 -I, --skip-indels do not perform indel calling
334 -L, --max-idepth INT maximum per-sample depth for INDEL calling [250]
335 -m, --min-ireads INT minimum number gapped reads for indel candidates [1]
336 -o, --open-prob INT Phred-scaled gap open seq error probability [40]
337 -p, --per-sample-mF apply -m and -F per-sample for increased sensitivity
338 -P, --platforms STR comma separated list of platforms for indels [all]
339
340 **Notes**: Assuming diploid individuals.
341 ]]>
342 </help>
343 <configfiles>
344 <configfile name="excluded_read_groups">
345 <![CDATA[
346 #set pasted_data = ''
347 #if str( $advanced_options.advanced_options_selector ) == "advanced":
348 #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste":
349 #set pasted_data = '\t'.join( str( $advanced_options.exclude_read_group['read_groups'] ).split() )
350 #end if
351 #end if
352 ${pasted_data}
353 ]]>
354 </configfile>
355 <configfile name="pasted_regions">
356 <![CDATA[
357 #set pasted_data = ''
358 #if str( $advanced_options.advanced_options_selector ) == "advanced":
359 #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste":
360 #set pasted_data = '\t'.join( str( $advanced_options.limit_by_region['region_paste'] ).split() )
361 #end if
362 #end if
363 ${pasted_data}
364 ]]>
365 </configfile>
366 </configfiles>
367 <expand macro="citations" />
368 </tool>