|
2
|
1 <tool id="samtools_mpileup" name="MPileup" version="0.0.3">
|
|
|
2 <description>SNP and indel caller</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="0.1.19">samtools</requirement>
|
|
|
5 </requirements>
|
|
|
6 <command><![CDATA[
|
|
|
7 #if $reference_source.reference_source_selector == "history":
|
|
|
8 ln -s "${reference_source.ref_file}" && samtools faidx `basename "${reference_source.ref_file}"` && samtools mpileup
|
|
|
9 #else:
|
|
|
10 samtools mpileup
|
|
|
11 #end if
|
|
0
|
12 #if $reference_source.reference_source_selector != "history":
|
|
2
|
13 -f "${reference_source.ref_file.fields.path}"
|
|
0
|
14 #else:
|
|
2
|
15 -f "${reference_source.ref_file}"
|
|
0
|
16 #end if
|
|
|
17 #for $i, $input_bam in enumerate( $reference_source.input_bams ):
|
|
2
|
18 $input_bam.input_bam
|
|
0
|
19 #end for
|
|
|
20 #if str( $advanced_options.advanced_options_selector ) == "advanced":
|
|
2
|
21 #if str( $advanced_options.filter_by_flags.filter_flags ) == "filter":
|
|
|
22 #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(',')])}
|
|
|
24 #end if
|
|
|
25 #if $advanced_options.filter_by_flags.exclude_flags:
|
|
|
26 --ff ${sum([int(flag) for flag in str($advanced_options.filter_by_flags.exclude_flags).split(',')])}
|
|
|
27 #end if
|
|
|
28 #end if
|
|
|
29 #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste":
|
|
|
30 -l "$pasted_regions"
|
|
|
31 #elif str( $advanced_options.limit_by_region.limit_by_regions ) == "history"
|
|
|
32 -l "$bed_regions"
|
|
|
33 #end if
|
|
|
34 #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste":
|
|
|
35 -G "$excluded_read_groups"
|
|
|
36 #elif str( $advanced_options.exclude_read_group.exclude_read_groups ) == "history"
|
|
|
37 -G "$read_groups"
|
|
|
38 #end if
|
|
|
39 ${advanced_options.skip_anomalous_read_pairs}
|
|
0
|
40 ${advanced_options.disable_probabilistic_realignment}
|
|
|
41 -C "${advanced_options.coefficient_for_downgrading}"
|
|
|
42 -d "${advanced_options.max_reads_per_bam}"
|
|
|
43 ${advanced_options.extended_BAQ_computation}
|
|
|
44 -q "${advanced_options.minimum_mapping_quality}"
|
|
|
45 -Q "${advanced_options.minimum_base_quality}"
|
|
|
46 #if str( $advanced_options.region_string ):
|
|
|
47 -r "${advanced_options.region_string}"
|
|
|
48 #end if
|
|
|
49 ${advanced_options.output_per_sample_read_depth}
|
|
|
50 ${advanced_options.output_per_sample_strand_bias_p_value}
|
|
|
51 #end if
|
|
|
52 #if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation':
|
|
|
53 ##-g or -u
|
|
|
54 -g
|
|
|
55 -e "${genotype_likelihood_computation_type.gap_extension_sequencing_error_probability}"
|
|
|
56 -h "${genotype_likelihood_computation_type.coefficient_for_modeling_homopolymer_errors}"
|
|
|
57 #if str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'perform_indel_calling':
|
|
|
58 -L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}"
|
|
2
|
59 -m "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_reads_for_indel_candidates}"
|
|
|
60 -F "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_read_fraction}"
|
|
|
61 ${genotype_likelihood_computation_type.perform_indel_calling.gapped_read_per_sample}
|
|
0
|
62 #else:
|
|
|
63 -I
|
|
|
64 #end if
|
|
|
65 -o "${genotype_likelihood_computation_type.gap_open_sequencing_error_probability}"
|
|
|
66 #if len( $genotype_likelihood_computation_type.platform_list_repeat ):
|
|
|
67 -P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.platform_list_repeat ] ) }"
|
|
|
68 #end if
|
|
2
|
69 #else:
|
|
|
70 ${genotype_likelihood_computation_type.base_position_on_reads}
|
|
|
71 ${genotype_likelihood_computation_type.output_mapping_quality}
|
|
0
|
72 #end if
|
|
2
|
73 > "$output_mpileup" 2> "$output_log"
|
|
|
74 ]]></command>
|
|
|
75 <stdio>
|
|
|
76 <exit_code range="1:" level="fatal" description="Error" />
|
|
|
77 </stdio>
|
|
|
78 <inputs>
|
|
|
79 <conditional name="reference_source">
|
|
|
80 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
|
|
|
81 <option value="cached">Locally cached</option>
|
|
|
82 <option value="history">History</option>
|
|
0
|
83 </param>
|
|
2
|
84 <when value="cached">
|
|
|
85 <repeat name="input_bams" title="BAM file" min="1">
|
|
|
86 <param name="input_bam" type="data" format="bam" label="BAM file">
|
|
|
87 <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 -->
|
|
|
89 </param>
|
|
|
90 </repeat>
|
|
|
91 <param name="ref_file" type="select" label="Using reference genome">
|
|
|
92 <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>
|
|
|
95 </when>
|
|
|
96 <when value="history">
|
|
|
97 <repeat name="input_bams" title="BAM file" min="1">
|
|
|
98 <param name="input_bam" type="data" format="bam" label="BAM file">
|
|
|
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." />
|
|
|
100 </param>
|
|
|
101 </repeat>
|
|
|
102 <param name="ref_file" type="data" format="fasta" label="Using reference file" />
|
|
|
103 </when>
|
|
|
104 </conditional>
|
|
|
105 <conditional name="genotype_likelihood_computation_type">
|
|
|
106 <param name="genotype_likelihood_computation_type_selector" type="select" label="Genotype Likelihood Computation">
|
|
|
107 <option value="perform_genotype_likelihood_computation">Perform genotype likelihood computation</option>
|
|
|
108 <option value="do_not_perform_genotype_likelihood_computation" selected="True">Do not perform genotype likelihood computation</option>
|
|
|
109 </param>
|
|
|
110 <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" />
|
|
|
112 <param name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" label="Coefficient for modeling homopolymer errors." />
|
|
|
113 <conditional name="perform_indel_calling">
|
|
|
114 <param name="perform_indel_calling_selector" type="select" label="Perform INDEL calling">
|
|
|
115 <option value="perform_indel_calling" selected="True">Perform INDEL calling</option>
|
|
|
116 <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option>
|
|
|
117 </param>
|
|
|
118 <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" />
|
|
|
120 <param name="minimum_gapped_reads_for_indel_candidates" type="integer" value="1" label="Minimum gapped reads for indel candidates" />
|
|
|
121 <param name="minimum_gapped_read_fraction" type="float" value="0.002" label="Minimum fraction of gapped reads for candidates" />
|
|
|
122 <param name="gapped_read_per_sample" type="boolean" truevalue="-p" falsevalue="" checked="False" label="Apply minimum values on a per-sample basis" />
|
|
|
123 </when>
|
|
|
124 <when value="do_not_perform_indel_calling" />
|
|
|
125 </conditional>
|
|
|
126 <param name="gap_open_sequencing_error_probability" type="integer" value="40" label="Phred-scaled gap open sequencing error probability" />
|
|
|
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>
|
|
|
131 <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" />
|
|
|
133 <param name="output_mapping_quality" type="boolean" truevalue="-s" falsevalue="" checked="False" label="Output mapping quality" />
|
|
0
|
134 </when>
|
|
2
|
135 </conditional>
|
|
|
136 <conditional name="advanced_options">
|
|
|
137 <param name="advanced_options_selector" type="select" label="Set advanced options">
|
|
|
138 <option value="basic" selected="True">Basic</option>
|
|
|
139 <option value="advanced">Advanced</option>
|
|
|
140 </param>
|
|
|
141 <when value="advanced">
|
|
|
142 <conditional name="filter_by_flags">
|
|
|
143 <param name="filter_flags" type="select" label="Set filter by flags">
|
|
|
144 <option value="nofilter" selected="True">Do not filter</option>
|
|
|
145 <option value="filter">Filter by flags to exclude or require</option>
|
|
|
146 </param>
|
|
|
147 <when value="filter">
|
|
|
148 <param name="require_flags" type="select" display="checkboxes" multiple="True" label="Require">
|
|
|
149 <option value="1">Read is paired</option>
|
|
|
150 <option value="2">Read is mapped in a proper pair</option>
|
|
|
151 <option value="4">The read is unmapped</option>
|
|
|
152 <option value="8">The mate is unmapped</option>
|
|
|
153 <option value="16">Read strand</option>
|
|
|
154 <option value="32">Mate strand</option>
|
|
|
155 <option value="64">Read is the first in a pair</option>
|
|
|
156 <option value="128">Read is the second in a pair</option>
|
|
|
157 <option value="256">The alignment or this read is not primary</option>
|
|
|
158 <option value="512">The read fails platform/vendor quality checks</option>
|
|
|
159 <option value="1024">The read is a PCR or optical duplicate</option>
|
|
|
160 </param>
|
|
|
161 <param name="exclude_flags" type="select" display="checkboxes" multiple="True" label="Exclude">
|
|
|
162 <option value="1">Read is paired</option>
|
|
|
163 <option value="2">Read is mapped in a proper pair</option>
|
|
|
164 <option value="4">The read is unmapped</option>
|
|
|
165 <option value="8">The mate is unmapped</option>
|
|
|
166 <option value="16">Read strand</option>
|
|
|
167 <option value="32">Mate strand</option>
|
|
|
168 <option value="64">Read is the first in a pair</option>
|
|
|
169 <option value="128">Read is the second in a pair</option>
|
|
|
170 <option value="256">The alignment or this read is not primary</option>
|
|
|
171 <option value="512">The read fails platform/vendor quality checks</option>
|
|
|
172 <option value="1024">The read is a PCR or optical duplicate</option>
|
|
|
173 </param>
|
|
|
174 </when>
|
|
|
175 <when value="nofilter" />
|
|
|
176 </conditional>
|
|
|
177 <conditional name="limit_by_region">
|
|
|
178 <param name="limit_by_regions" type="select" label="Select regions to call">
|
|
|
179 <option value="no_limit" selected="True">Do not limit</option>
|
|
|
180 <option value="history">From an uploaded BED file</option>
|
|
|
181 <option value="paste">Paste a list of regions or BED</option>
|
|
|
182 </param>
|
|
|
183 <when value="history">
|
|
|
184 <param name="bed_regions" type="data" format="bed" label="BED file">
|
|
|
185 <validator type="dataset_ok_validator" />
|
|
|
186 </param>
|
|
|
187 </when>
|
|
|
188 <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"/>
|
|
|
190 </when>
|
|
|
191 <when value="no_limit" />
|
|
|
192 </conditional>
|
|
|
193 <conditional name="exclude_read_group">
|
|
|
194 <param name="exclude_read_groups" type="select" label="Select read groups to exclude">
|
|
|
195 <option value="no_limit" selected="True">Do not exclude</option>
|
|
|
196 <option value="history">From an uploaded text file</option>
|
|
|
197 <option value="paste">Paste a list of read groups</option>
|
|
|
198 </param>
|
|
|
199 <when value="history">
|
|
|
200 <param name="read_groups" type="data" format="txt" label="Text file">
|
|
|
201 <validator type="dataset_ok_validator" />
|
|
|
202 </param>
|
|
|
203 </when>
|
|
|
204 <when value="paste">
|
|
|
205 <param name="group_paste" type="text" area="true" size="10x35" label="Read groups" help="Paste a list of read groups"/>
|
|
|
206 </when>
|
|
|
207 <when value="no_limit" />
|
|
|
208 </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" />
|
|
|
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)" />
|
|
|
211 <param name="coefficient_for_downgrading" type="integer" value="0" label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" />
|
|
|
212 <param name="max_reads_per_bam" type="integer" value="250" label="Max reads per BAM" />
|
|
|
213 <param name="extended_BAQ_computation" type="boolean" truevalue="-E" falsevalue="" checked="False" label="Extended BAQ computation" />
|
|
|
214 <param name="minimum_mapping_quality" type="integer" value="0" label="Minimum mapping quality for an alignment to be used" />
|
|
|
215 <param name="minimum_base_quality" type="integer" value="13" label="Minimum base quality for a base to be considered" />
|
|
|
216 <param name="region_string" type="text" value="" label="Only generate pileup in region" />
|
|
|
217 <param name="output_per_sample_read_depth" type="boolean" truevalue="-D" falsevalue="" checked="False" label="Output per-sample read depth" />
|
|
|
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>
|
|
|
220 <when value="basic" />
|
|
|
221 </conditional>
|
|
|
222 </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 ${pasted_data}
|
|
|
252 ]]>
|
|
|
253 </configfile>
|
|
|
254 </configfiles>
|
|
|
255 <outputs>
|
|
|
256 <data format="pileup" name="output_mpileup" label="${tool.name} on ${on_string}">
|
|
|
257 <change_format>
|
|
|
258 <when input="genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" format="bcf" />
|
|
|
259 </change_format>
|
|
|
260 </data>
|
|
|
261 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
|
|
|
262 </outputs>
|
|
|
263 <tests>
|
|
|
264 <test>
|
|
|
265 <param name="reference_source_selector" value="history" />
|
|
|
266 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
|
|
|
267 <param name="input_bam" value="samtools_mpileup_in_1.bam" ftype="bam" />
|
|
|
268 <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" />
|
|
|
269 <param name="advanced_options_selector" value="basic" />
|
|
|
270 <param name="base_position_on_reads" value="true" />
|
|
|
271 <param name="output_mapping_quality" value="true" />
|
|
|
272 <output name="output_mpileup" file="samtools_mpileup_out_1.pileup" />
|
|
|
273 <output name="output_log" file="samtools_mpileup_out_1.log" />
|
|
|
274 </test>
|
|
|
275 <test>
|
|
|
276 <param name="reference_source_selector" value="history" />
|
|
|
277 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
|
|
|
278 <param name="input_bam" value="samtools_mpileup_in_1.bam" ftype="bam" />
|
|
|
279 <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" />
|
|
|
280 <param name="gap_extension_sequencing_error_probability" value="20" />
|
|
|
281 <param name="coefficient_for_modeling_homopolymer_errors" value="100" />
|
|
|
282 <param name="perform_indel_calling_selector" value="perform_indel_calling" />
|
|
|
283 <param name="skip_indel_calling_above_sample_depth" value="250" />
|
|
|
284 <param name="gap_open_sequencing_error_probability" value="40" />
|
|
|
285 <param name="platform_list_repeat" value="0" />
|
|
|
286 <param name="advanced_options_selector" value="basic" />
|
|
|
287 <output name="output_mpileup" ftype="bcf" file="samtools_mpileup_out_2.bcf" lines_diff="1" />
|
|
|
288 <output name="output_log" file="samtools_mpileup_out_2.log" />
|
|
|
289 </test>
|
|
|
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>
|
|
|
325 </tests>
|
|
|
326 <help>
|
|
0
|
327 **What it does**
|
|
|
328
|
|
|
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.
|
|
|
330
|
|
|
331 ------
|
|
|
332
|
|
2
|
333 .. list-table:: **Input options**
|
|
|
334 :widths: 5 5 40 10
|
|
|
335 :header-rows: 1
|
|
|
336
|
|
|
337 * - Flag
|
|
|
338 - Type
|
|
|
339 - Description
|
|
|
340 - Default
|
|
|
341 * - -6
|
|
|
342 - *BOOLEAN*
|
|
|
343 - assume the quality is in the Illumina-1.3+ encoding
|
|
|
344 - off
|
|
|
345 * - -A
|
|
|
346 - *BOOLEAN*
|
|
|
347 - count anomalous read pairs
|
|
|
348 - off
|
|
|
349 * - -B
|
|
|
350 - *BOOLEAN*
|
|
|
351 - disable BAQ computation
|
|
|
352 - off
|
|
|
353 * - -b
|
|
|
354 - *FILE*
|
|
|
355 - list of input BAM filenames, one per line
|
|
|
356 - *null*
|
|
|
357 * - -C
|
|
|
358 - *INT*
|
|
|
359 - parameter for adjusting mapQ; 0 to disable
|
|
|
360 - 0
|
|
|
361 * - -d
|
|
|
362 - *INT*
|
|
|
363 - max per-BAM depth to avoid excessive memory usage
|
|
|
364 - 250
|
|
|
365 * - -E
|
|
|
366 - *BOOLEAN*
|
|
|
367 - recalculate extended BAQ on the fly thus ignoring existing BQs
|
|
|
368 - off
|
|
|
369 * - -f
|
|
|
370 - *FILE*
|
|
|
371 - faidx indexed reference sequence file
|
|
|
372 - *null*
|
|
|
373 * - -G
|
|
|
374 - *FILE*
|
|
|
375 - exclude read groups listed in FILE
|
|
|
376 - *null*
|
|
|
377 * - -l
|
|
|
378 - *FILE*
|
|
|
379 - list of positions (chr pos) or regions (BED)
|
|
|
380 - *null*
|
|
|
381 * - -M
|
|
|
382 - *INT*
|
|
|
383 - cap mapping quality at INT
|
|
|
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 ------
|
|
0
|
411
|
|
2
|
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
|
|
0
|
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. <http://www.ncbi.nlm.nih.gov/pubmed/19505943>`_
|
|
|
497
|
|
2
|
498
|
|
0
|
499 If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.*
|
|
2
|
500 </help>
|
|
|
501 </tool> |
