comparison samtools_mpileup.xml @ 0:44a18a94d7a9

Uploaded tool tarball.
author devteam
date Mon, 26 Aug 2013 14:23:36 -0400
parents
children dddde948c3e5
comparison
equal deleted inserted replaced
-1:000000000000 0:44a18a94d7a9
1 <tool id="samtools_mpileup" name="MPileup" version="0.0.1">
2 <description>SNP and indel caller</description>
3 <requirements>
4 <requirement type="package" version="0.1.18">samtools</requirement>
5 </requirements>
6 <command interpreter="python">samtools_wrapper.py
7 -p 'samtools mpileup'
8 --stdout "${output_log}"
9 #if $reference_source.reference_source_selector != "history":
10 -p '-f "${reference_source.ref_file.fields.path}"'
11 #else:
12 -d "-f" "${reference_source.ref_file}" "fa" "reference_input"
13 #end if
14 #for $i, $input_bam in enumerate( $reference_source.input_bams ):
15 -d " " "${input_bam.input_bam}" "${input_bam.input_bam.ext}" "bam_input_${i}"
16 -d "" "${input_bam.input_bam.metadata.bam_index}" "bam_index" "bam_input_${i}" ##hardcode galaxy ext type as bam_index
17 #end for
18 -p '
19 #if str( $advanced_options.advanced_options_selector ) == "advanced":
20 ${advanced_options.skip_anomalous_read_pairs}
21 ${advanced_options.disable_probabilistic_realignment}
22 -C "${advanced_options.coefficient_for_downgrading}"
23 -d "${advanced_options.max_reads_per_bam}"
24 ${advanced_options.extended_BAQ_computation}
25 #if str( $advanced_options.position_list ) != 'None':
26 -l "${advanced_options.position_list}"
27 #end if
28 -q "${advanced_options.minimum_mapping_quality}"
29 -Q "${advanced_options.minimum_base_quality}"
30 #if str( $advanced_options.region_string ):
31 -r "${advanced_options.region_string}"
32 #end if
33 ${advanced_options.output_per_sample_read_depth}
34 ${advanced_options.output_per_sample_strand_bias_p_value}
35 #end if
36 #if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation':
37 ##-g or -u
38 -g
39 -e "${genotype_likelihood_computation_type.gap_extension_sequencing_error_probability}"
40 -h "${genotype_likelihood_computation_type.coefficient_for_modeling_homopolymer_errors}"
41 #if str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'perform_indel_calling':
42 -L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}"
43 #else:
44 -I
45 #end if
46 -o "${genotype_likelihood_computation_type.gap_open_sequencing_error_probability}"
47 #if len( $genotype_likelihood_computation_type.platform_list_repeat ):
48 -P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.platform_list_repeat ] ) }"
49 #end if
50 #end if
51 &gt; "${output_mpileup}"
52 '
53 </command>
54 <inputs>
55 <conditional name="reference_source">
56 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
57 <option value="cached">Locally cached</option>
58 <option value="history">History</option>
59 </param>
60 <when value="cached">
61 <repeat name="input_bams" title="BAM file" min="1">
62 <param name="input_bam" type="data" format="bam" label="BAM file">
63 <validator type="unspecified_build" />
64 <validator type="dataset_metadata_in_data_table" table_name="sam_fa_indexes" metadata_name="dbkey" metadata_column="value" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select -->
65 </param>
66 </repeat>
67 <param name="ref_file" type="select" label="Using reference genome">
68 <options from_data_table="sam_fa_indexes">
69 <!-- <filter type="data_meta" key="dbkey" ref="input_bam" column="value"/> does not yet work in a repeat...-->
70 </options>
71 </param>
72 </when>
73 <when value="history"> <!-- FIX ME!!!! -->
74 <repeat name="input_bams" title="BAM file" min="1">
75 <param name="input_bam" type="data" format="bam" label="BAM file" >
76 <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."/>
77 </param>
78 </repeat>
79 <param name="ref_file" type="data" format="fasta" label="Using reference file" />
80 </when>
81 </conditional>
82
83
84 <conditional name="genotype_likelihood_computation_type">
85 <param name="genotype_likelihood_computation_type_selector" type="select" label="Genotype Likelihood Computation">
86 <option value="perform_genotype_likelihood_computation">Perform genotype likelihood computation</option>
87 <option value="do_not_perform_genotype_likelihood_computation" selected="True">Do not perform genotype likelihood computation</option>
88 </param>
89 <when value="perform_genotype_likelihood_computation">
90 <param name="gap_extension_sequencing_error_probability" type="integer" value="20" label="Phred-scaled gap extension sequencing error probability" />
91 <param name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" label="Coefficient for modeling homopolymer errors." />
92 <conditional name="perform_indel_calling">
93 <param name="perform_indel_calling_selector" type="select" label="Perform INDEL calling">
94 <option value="perform_indel_calling" selected="True">Perform INDEL calling</option>
95 <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option>
96 </param>
97 <when value="perform_indel_calling">
98 <param name="skip_indel_calling_above_sample_depth" type="integer" value="250" label="Skip INDEL calling if the average per-sample depth is above" />
99 </when>
100 <when value="do_not_perform_indel_calling" />
101 </conditional>
102 <param name="gap_open_sequencing_error_probability" type="integer" value="40" label="Phred-scaled gap open sequencing error probability" />
103 <repeat name="platform_list_repeat" title="Platform for INDEL candidates">
104 <param name="platform_entry" type="text" value="" label="Platform to use for INDEL candidates" />
105 </repeat>
106 </when>
107 <when value="do_not_perform_genotype_likelihood_computation">
108 <!-- Do nothing here -->
109 </when>
110 </conditional>
111 <conditional name="advanced_options">
112 <param name="advanced_options_selector" type="select" label="Set advanced options">
113 <option value="basic" selected="True">Basic</option>
114 <option value="advanced">Advanced</option>
115 </param>
116 <when value="advanced">
117 <param name="skip_anomalous_read_pairs" type="boolean" truevalue="-A" falsevalue="" checked="False" label="Do not skip anomalous read pairs in variant calling" />
118 <param name="disable_probabilistic_realignment" type="boolean" truevalue="-B" falsevalue="" checked="False" label=" Disable probabilistic realignment for the computation of base alignment quality (BAQ)" />
119 <param name="coefficient_for_downgrading" type="integer" value="0" label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" />
120 <param name="max_reads_per_bam" type="integer" value="250" label="Max reads per BAM" />
121 <param name="extended_BAQ_computation" type="boolean" truevalue="-E" falsevalue="" checked="False" label="Extended BAQ computation" />
122 <param name="position_list" type="data" format="bed" label="List of regions or sites on which to operate" optional="True" />
123 <param name="minimum_mapping_quality" type="integer" value="0" label="Minimum mapping quality for an alignment to be used" />
124 <param name="minimum_base_quality" type="integer" value="13" label="Minimum base quality for a base to be considered" />
125 <param name="region_string" type="text" value="" label="Only generate pileup in region" />
126 <param name="output_per_sample_read_depth" type="boolean" truevalue="-D" falsevalue="" checked="False" label="Output per-sample read depth" />
127 <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" />
128 </when>
129 <when value="basic" />
130 </conditional>
131 </inputs>
132 <outputs>
133 <data format="pileup" name="output_mpileup" label="${tool.name} on ${on_string}">
134 <change_format>
135 <when input="genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" format="bcf" />
136 </change_format>
137 </data>
138 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
139 </outputs>
140 <tests>
141 <test>
142 <param name="reference_source_selector" value="history" />
143 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
144 <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" />
145 <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" />
146 <param name="advanced_options_selector" value="basic" />
147 <output name="output_mpileup" file="samtools/mpileup/samtools_mpileup_out_1.pileup" />
148 <output name="output_log" file="samtools/mpileup/samtools_mpileup_out_1.log" />
149 </test>
150 <test>
151 <param name="reference_source_selector" value="history" />
152 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
153 <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" />
154 <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" />
155 <param name="gap_extension_sequencing_error_probability" value="20" />
156 <param name="coefficient_for_modeling_homopolymer_errors" value="100" />
157 <param name="perform_indel_calling_selector" value="perform_indel_calling" />
158 <param name="skip_indel_calling_above_sample_depth" value="250" />
159 <param name="gap_open_sequencing_error_probability" value="40" />
160 <param name="platform_list_repeat" value="0" />
161 <param name="advanced_options_selector" value="basic" />
162 <output name="output_mpileup" file="samtools/mpileup/samtools_mpileup_out_2.bcf" />
163 <output name="output_log" file="samtools/mpileup/samtools_mpileup_out_1.log" />
164 </test>
165 </tests>
166 <help>
167 **What it does**
168
169 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.
170
171 ------
172
173 **Settings**::
174
175 Input Options:
176 -6 Assume the quality is in the Illumina 1.3+ encoding.
177 -A Do not skip anomalous read pairs in variant calling.
178 -B Disable probabilistic realignment for the computation of base alignment quality (BAQ). BAQ is the Phred-scaled probability of a read base being misaligned. Applying this option greatly helps to reduce false SNPs caused by misalignments.
179 -b FILE List of input BAM files, one file per line [null]
180 -C INT Coefficient for downgrading mapping quality for reads containing excessive mismatches. Given a read with a phred-scaled probability q of being generated from the mapped position, the new mapping quality is about sqrt((INT-q)/INT)*INT. A zero value disables this functionality; if enabled, the recommended value for BWA is 50. [0]
181 -d INT At a position, read maximally INT reads per input BAM. [250]
182 -E Extended BAQ computation. This option helps sensitivity especially for MNPs, but may hurt specificity a little bit.
183 -f FILE The faidx-indexed reference file in the FASTA format. The file can be optionally compressed by razip. [null]
184 -l FILE BED or position list file containing a list of regions or sites where pileup or BCF should be generated [null]
185 -q INT Minimum mapping quality for an alignment to be used [0]
186 -Q INT Minimum base quality for a base to be considered [13]
187 -r STR Only generate pileup in region STR [all sites]
188 Output Options:
189
190 -D Output per-sample read depth
191 -g Compute genotype likelihoods and output them in the binary call format (BCF).
192 -S Output per-sample Phred-scaled strand bias P-value
193 -u Similar to -g except that the output is uncompressed BCF, which is preferred for piping.
194
195 Options for Genotype Likelihood Computation (for -g or -u):
196
197 -e INT Phred-scaled gap extension sequencing error probability. Reducing INT leads to longer indels. [20]
198 -h INT Coefficient for modeling homopolymer errors. Given an l-long homopolymer run, the sequencing error of an indel of size s is modeled as INT*s/l. [100]
199 -I Do not perform INDEL calling
200 -L INT Skip INDEL calling if the average per-sample depth is above INT. [250]
201 -o INT Phred-scaled gap open sequencing error probability. Reducing INT leads to more indel calls. [40]
202 -P STR Comma dilimited list of platforms (determined by @RG-PL) from which indel candidates are obtained. It is recommended to collect indel candidates from sequencing technologies that have low indel error rate such as ILLUMINA. [all]
203
204 ------
205
206 **Citation**
207
208 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;`_
209
210 If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.*
211
212 </help>
213 </tool>