annotate base_recalibrator.xml @ 0:9ad15075b9fa draft

Uploaded
author iuc
date Mon, 25 Nov 2013 14:23:47 -0500
parents
children c8752e31f496
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
1 <tool id="gatk2_base_recalibrator" name="Base Recalibrator" version="0.0.7">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
2 <description>on BAM files</description>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
3 <expand macro="requirements" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
4 <macros>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
5 <import>gatk2_macros.xml</import>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
6 </macros>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
7 <command interpreter="python">gatk2_wrapper.py
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
8 ##--max_jvm_heap_fraction "1"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
9 --stdout "${output_log}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
10 -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
11 #if str( $reference_source.input_bam.metadata.bam_index ) != "None":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
12 -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
13 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
14 -p '
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
15 @JAR_PATH@
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
16 -T "BaseRecalibrator"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
17 \$GATK2_SITE_OPTIONS
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
18
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
19 ## according to http://www.broadinstitute.org/gatk/guide/article?id=1975
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
20 --num_cpu_threads_per_data_thread 8
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
21
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
22 @THREADS@
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
23
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
24 ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
25 #if $reference_source.reference_source_selector != "history":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
26 -R "${reference_source.ref_file.fields.path}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
27 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
28 #if str($input_recal) != 'None':
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
29 --BQSR "${input_recal}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
30 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
31 --out "${output_recal}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
32 ${standard_covs}
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
33 #if str( $covariates ) != "None":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
34 #for $cov in str( $covariates ).split( ',' ):
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
35 -cov "${cov}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
36 #end for
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
37 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
38 #if $plot_pdf:
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
39 --plot_pdf_file $output_pdf
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
40 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
41 '
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
42
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
43 #set $snp_dataset_provided = False
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
44 #set $rod_binding_names = dict()
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
45 #for $rod_binding in $rod_bind:
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
46 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
47 #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
48 #else
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
49 #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
50 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
51 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'dbsnp':
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
52 #set $snp_dataset_provided = True
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
53 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
54 #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
55 -d "--knownSites:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
56 #end for
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
57
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
58 #include source=$standard_gatk_options#
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
59
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
60 ##start analysis specific options
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
61 #if $analysis_param_type.analysis_param_type_selector == "advanced":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
62 -p '
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
63 #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
64 --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
65 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
66 #if str( $analysis_param_type.default_platform ) != "default":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
67 --default_platform "${analysis_param_type.default_platform}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
68 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
69 #if str( $analysis_param_type.force_read_group_type.force_read_group_type_selector ) == "set":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
70 --force_read_group "${analysis_param_type.force_read_group_type.force_read_group}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
71 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
72 #if str( $analysis_param_type.force_platform ) != "default":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
73 --force_platform "${analysis_param_type.force_platform}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
74 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
75 ${analysis_param_type.exception_if_no_tile}
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
76 #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
77 #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
78 --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
79 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
80 #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
81 --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
82 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
83 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
84 --window_size_nqs "${analysis_param_type.window_size_nqs}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
85 --homopolymer_nback "${analysis_param_type.homopolymer_nback}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
86 '
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
87 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
88 #if not $snp_dataset_provided:
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
89 -p '--run_without_dbsnp_potentially_ruining_quality'
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
90 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
91 </command>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
92 <inputs>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
93 <conditional name="reference_source">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
94 <expand macro="reference_source_selector_param" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
95 <when value="cached">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
96 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
97 <validator type="unspecified_build" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
98 <validator type="dataset_metadata_in_data_table" table_name="gatk2_picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
99 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
100 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" >
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
101 <options from_data_table="gatk2_picard_indexes">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
102 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
103 </options>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
104 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
105 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
106 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
107 <when value="history">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
108 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
109 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
110 <options>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
111 <filter type="data_meta" key="dbkey" ref="input_bam" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
112 </options>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
113 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
114 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
115 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
116 <param name="input_recal" type="data" format="gatk_report" optional="true" label="Covariates table recalibration file" help="-BQSR,--BQSR &amp;lt;recal_file&amp;gt;" >
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
117 <help>The input covariates table file which enables on-the-fly base quality score recalibration.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
118 Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
119 Please be aware that one should only run recalibration with the covariates file created on the same input bam(s).
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
120 </help>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
121 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
122 <param name="standard_covs" type="boolean" truevalue="" falsevalue="--no_standard_covs" checked="false" label="Do not use the standard set of covariates in addition to the ones selected" help="--no_standard_covs/-noStandard" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
123 <param name="covariates" type="select" multiple="True" display="checkboxes" label="Covariates to be used in the recalibration" help="-cov,--covariate &amp;lt;covariate&amp;gt;" >
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
124 <!-- might we want to load the available covariates from an external configuration file, since additional ones can be added to local installs? -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
125 <option value="ReadGroupCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
126 <option value="QualityScoreCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
127 <option value="CycleCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
128 <option value="ContextCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
129 <!-- covariates below were pulled from list option -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
130 <option value="HomopolymerCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
131 <option value="GCContentCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
132 <option value="MappingQualityCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
133 <option value="MinimumNQSCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
134 <option value="PositionCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
135 <option value="PrimerRoundCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
136 <option value="TileCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
137 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
138
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
139 <repeat name="rod_bind" title="Binding for reference-ordered data" help="-knownSites,--knownSites &amp;lt;knownSites&amp;gt;">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
140 <conditional name="rod_bind_type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
141 <param name="rod_bind_type_selector" type="select" label="Binding Type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
142 <option value="dbsnp" selected="True">dbSNP</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
143 <option value="snps">SNPs</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
144 <option value="indels">INDELs</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
145 <option value="mask">Mask</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
146 <option value="custom">Custom</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
147 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
148 <when value="dbsnp">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
149 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
150 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
151 <when value="snps">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
152 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
153 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
154 <when value="indels">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
155 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
156 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
157 <when value="mask">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
158 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
159 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
160 <when value="custom">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
161 <param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
162 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
163 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
164 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
165 </repeat>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
166 <param name="plot_pdf" type="boolean" truevalue="--plot_pdf_file" falsevalue="" checked="False" label="Output recalibration plots pdf"/>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
167 <expand macro="gatk_param_type_conditional" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
168
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
169 <conditional name="analysis_param_type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
170 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
171 <option value="basic" selected="True">Basic</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
172 <option value="advanced">Advanced</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
173 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
174 <when value="basic">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
175 <!-- Do nothing here -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
176 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
177 <when value="advanced">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
178 <conditional name="default_read_group_type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
179 <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
180 <option value="default" selected="True">Don't Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
181 <option value="set">Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
182 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
183 <when value="default">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
184 <!-- do nothing here -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
185 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
186 <when value="set">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
187 <param name="default_read_group" type="text" value="Unknown" label="If a read has no read group then default to the provided String"/>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
188 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
189 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
190 <param name="default_platform" type="select" label="Set default Platform" help="--default_platform">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
191 <option value="default" selected="True">Don't Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
192 <option value="illumina">illumina</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
193 <option value="454">454</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
194 <option value="solid">solid</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
195 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
196 <conditional name="force_read_group_type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
197 <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
198 <option value="default" selected="True">Don't Force</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
199 <option value="set">Force</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
200 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
201 <when value="default">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
202 <!-- do nothing here -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
203 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
204 <when value="set">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
205 <param name="force_read_group" type="text" value="Unknown" label="If provided, the read group ID of EVERY read will be forced to be the provided String."/>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
206 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
207 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
208 <param name="force_platform" type="select" label="Force Platform" help="--force_platform">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
209 <option value="default" selected="True">Don't Force</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
210 <option value="illumina">illumina</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
211 <option value="454">454</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
212 <option value="solid">solid</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
213 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
214 <param name="exception_if_no_tile" type="boolean" checked="False" truevalue="--exception_if_no_tile" falsevalue="" label="Throw an exception when no tile can be found" help="--exception_if_no_tile"/>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
215 <conditional name="solid_options_type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
216 <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
217 <option value="default" selected="True">Don't Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
218 <option value="set">Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
219 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
220 <when value="default">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
221 <!-- do nothing here -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
222 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
223 <when value="set">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
224 <param name="solid_recal_mode" type="select" label="How should we recalibrate solid bases in which the reference was inserted" help="-sMode,--solid_recal_mode &amp;lt;solid_recal_mode&amp;gt;">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
225 <option value="default" selected="True">Don't set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
226 <option value="DO_NOTHING">DO_NOTHING</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
227 <option value="SET_Q_ZERO">SET_Q_ZERO</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
228 <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
229 <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
230 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
231 <param name="solid_nocall_strategy" type="select" label="Behavior of the recalibrator when it encounters no calls" help="-solid_nocall_strategy,--solid_nocall_strategy &amp;lt;solid_nocall_strategy&amp;gt;">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
232 <option value="default" selected="True">Don't set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
233 <option value="THROW_EXCEPTION">THROW_EXCEPTION</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
234 <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
235 <option value="PURGE_READ">PURGE_READ</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
236 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
237 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
238 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
239 <param name="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate" help="window_size_nqs"/>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
240 <param name="homopolymer_nback" type="integer" value="7" label="number of previous bases to look at in HomopolymerCovariate" help="-nback,--homopolymer_nback &amp;lt;homopolymer_nback&amp;gt;" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
241 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
242 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
243 </inputs>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
244 <outputs>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
245 <data format="gatk_report" name="output_recal" label="${tool.name} on ${on_string} (Covariate File)" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
246 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
247 <data format="pdf" name="output_pdf" label="${tool.name} on ${on_string} (plot_pdf_file)">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
248 <filter>plot_pdf == True</filter>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
249 </data>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
250 </outputs>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
251 <tests>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
252 <test>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
253 <param name="reference_source_selector" value="history" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
254 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
255 <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
256 <param name="rod_bind_type_selector" value="dbsnp" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
257 <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
258 <param name="standard_covs" value="True" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
259 <param name="covariates" value="ReadGroupCovariate,HomopolymerCovariate,MinimumNQSCovariate,PositionCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
260 <param name="gatk_param_type_selector" value="basic" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
261 <param name="analysis_param_type_selector" value="basic" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
262 <output name="output_recal" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
263 <output name="output_log" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.log.contains" compare="contains" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
264 </test>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
265 </tests>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
266 <help>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
267 .. class:: warningmark
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
268
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
269 "This calculation is critically dependent on being able to skip over known variant sites. Please provide a dbSNP ROD or a VCF file containing known sites of genetic variation."
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
270 However, if you do not provide this file, the '--run_without_dbsnp_potentially_ruining_quality' flag will be automatically used, and the command will be allowed to run.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
271
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
272 **What it does**
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
273
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
274 This walker is designed to work as the first pass in a two-pass processing step. It does a by-locus traversal operating only at sites that are not in dbSNP. We assume that all reference mismatches we see are therefore errors and indicative of poor base quality. This walker generates tables based on various user-specified covariates (such as read group, reported quality score, cycle, and dinucleotide) Since there is a large amount of data one can then calculate an empirical probability of error given the particular covariates seen at this site, where p(error) = num mismatches / num observations The output file is a CSV list of (the several covariate values, num observations, num mismatches, empirical quality score) The first non-comment line of the output file gives the name of the covariates that were used for this calculation. Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will be added for the user regardless of whether or not they were specified Note: This walker is designed to be used in conjunction with TableRecalibrationWalker.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
275
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
276 For more information on base quality score recalibration using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_bqsr_BaseRecalibrator.html&gt;`_.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
277
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
278 To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gatk/guide/topic?name=best-practices&gt;`_.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
279
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
280 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
281
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
282 ------
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
283
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
284 **Inputs**
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
285
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
286 GenomeAnalysisTK: BaseRecalibrator accepts an aligned BAM input file.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
287
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
288
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
289 **Outputs**
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
290
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
291 The output is in CSV format.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
292
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
293
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
294 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
295
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
296 -------
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
297
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
298 **Settings**::
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
299
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
300
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
301 default_read_group If a read has no read group then default to the provided String.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
302 default_platform If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
303 force_read_group If provided, the read group ID of EVERY read will be forced to be the provided String. This is useful to collapse all data into a single read group.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
304 force_platform If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
305 window_size_nqs The window size used by MinimumNQSCovariate for its calculation
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
306 homopolymer_nback The number of previous bases to look at in HomopolymerCovariate
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
307 exception_if_no_tile If provided, TileCovariate will throw an exception when no tile can be found. The default behavior is to use tile = -1
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
308 solid_recal_mode How should we recalibrate solid bases in whichthe reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS (DO_NOTHING|SET_Q_ZERO|SET_Q_ZERO_BASE_N|REMOVE_REF_BIAS)
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
309 solid_nocall_strategy Defines the behavior of the recalibrator when it encounters no calls in the color space. Options = THROW_EXCEPTION, LEAVE_READ_UNRECALIBRATED, or PURGE_READ (THROW_EXCEPTION|LEAVE_READ_UNRECALIBRATED|PURGE_READ)
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
310 recal_file Filename for the input covariates table recalibration .csv file
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
311 out The output CSV file
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
312 standard_covs Use the standard set of covariates in addition to the ones listed using the -cov argument
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
313 run_without_dbsnp_potentially_ruining_quality If specified, allows the recalibrator to be used without a dbsnp rod. Very unsafe and for expert users only.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
314
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
315 @CITATION_SECTION@
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
316 </help>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
317 </tool>