annotate base_recalibrator.xml @ 4:e67da4f2c9bf draft

Uploaded
author bgruening
date Sat, 18 Jan 2014 07:00:26 -0500
parents 28b85e2409ce
children b80301676614
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">
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
2 <description>calculates covariates used to recalibrate base quality scores of reads</description>
0
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>
1
c8752e31f496 Uploaded
bgruening
parents: 0
diff changeset
7 <command interpreter="python">
c8752e31f496 Uploaded
bgruening
parents: 0
diff changeset
8 gatk2_wrapper.py
c8752e31f496 Uploaded
bgruening
parents: 0
diff changeset
9 --stdout "${output_log}"
c8752e31f496 Uploaded
bgruening
parents: 0
diff changeset
10 -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
c8752e31f496 Uploaded
bgruening
parents: 0
diff changeset
11 #if str( $reference_source.input_bam.metadata.bam_index ) != "None":
c8752e31f496 Uploaded
bgruening
parents: 0
diff changeset
12 -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
c8752e31f496 Uploaded
bgruening
parents: 0
diff changeset
13 #end if
c8752e31f496 Uploaded
bgruening
parents: 0
diff changeset
14 -p '
c8752e31f496 Uploaded
bgruening
parents: 0
diff changeset
15 @JAR_PATH@
0
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
4
e67da4f2c9bf Uploaded
bgruening
parents: 2
diff changeset
20 --num_cpu_threads_per_data_thread \${GALAXY_SLOTS:-8}
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
21
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
22 ## we set non standards at every run and the user can choose which ones are preferred
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
23 ## in our select box both standard options (ContextCovariate, CycleCovariate) are selected by default
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
24 --no_standard_covs
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
25
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
26 #if $reference_source.reference_source_selector != "history":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
27 -R "${reference_source.ref_file.fields.path}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
28 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
29 #if str($input_recal) != 'None':
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
30 --BQSR "${input_recal}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
31 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
32 --out "${output_recal}"
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 '
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
39
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
40 #set $snp_dataset_provided = False
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
41 #set $rod_binding_names = dict()
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
42 #for $rod_binding in $rod_bind:
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
43 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
44 #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
45 #else
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
46 #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
47 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
48 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'dbsnp':
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
49 #set $snp_dataset_provided = True
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
50 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
51 #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
52 -d "--knownSites:${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[$rod_bind_name]}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
53 #end for
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
54
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
55 #include source=$standard_gatk_options#
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
56
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
57 ##start analysis specific options
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
58 #if $analysis_param_type.analysis_param_type_selector == "advanced":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
59 -p '
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
60 #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
61 --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
62 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
63 #if str( $analysis_param_type.default_platform ) != "default":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
64 --default_platform "${analysis_param_type.default_platform}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
65 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
66 #if str( $analysis_param_type.force_read_group_type.force_read_group_type_selector ) == "set":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
67 --force_read_group "${analysis_param_type.force_read_group_type.force_read_group}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
68 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
69 #if str( $analysis_param_type.force_platform ) != "default":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
70 --force_platform "${analysis_param_type.force_platform}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
71 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
72 ${analysis_param_type.exception_if_no_tile}
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
73 #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
74 #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
75 --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
76 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
77 #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default":
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
78 --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
79 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
80 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
81 --window_size_nqs "${analysis_param_type.window_size_nqs}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
82 --homopolymer_nback "${analysis_param_type.homopolymer_nback}"
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
83 '
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
84 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
85 #if not $snp_dataset_provided:
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
86 -p '--run_without_dbsnp_potentially_ruining_quality'
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
87 #end if
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
88 </command>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
89 <inputs>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
90 <conditional name="reference_source">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
91 <expand macro="reference_source_selector_param" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
92 <when value="cached">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
93 <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
94 <validator type="unspecified_build" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
95 <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
96 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
97 <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
98 <options from_data_table="gatk2_picard_indexes">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
99 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
100 </options>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
101 <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
102 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
103 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
104 <when value="history">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
105 <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
106 <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
107 <options>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
108 <filter type="data_meta" key="dbkey" ref="input_bam" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
109 </options>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
110 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
111 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
112 </conditional>
4
e67da4f2c9bf Uploaded
bgruening
parents: 2
diff changeset
113 <param name="input_recal" type="data" format="gatk_report" optional="true" label="Covariates table recalibration file" help="The input covariates table file which enables on-the-fly base quality score recalibration. Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool. Please be aware that one should only run recalibration with the covariates file created on the same input bam(s) (-BQSR,--BQSR &amp;lt;recal_file&amp;gt;)" />
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
114
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
115 <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
116 <!-- might we want to load the available covariates from an external configuration file, since additional ones can be added to local installs? -->
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
117 <option value="ContextCovariate" selected="true"/>
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
118 <option value="CycleCovariate" selected="true"/>
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
119 <option value="RepeatLengthCovariate" />
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
120 <option value="RepeatUnitCovariate" />
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
121 <option value="RepeatUnitAndLengthCovariate" />
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
122 <!--
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
123 Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
124 be added for the user regardless of whether or not they were specified.
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
125 <option value="QualityScoreCovariate" />
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
126 <option value="ReadGroupCovariate" />
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
127 -->
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
128 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
129
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
130 <repeat name="rod_bind" title="Known Variants" help="Using data sets of known variants (-knownSites,--knownSites &amp;lt;knownSites&amp;gt;)">
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
131 <conditional name="rod_bind_type">
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
132 <param name="rod_bind_type_selector" type="select" label="Variant Type">
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
133 <option value="dbsnp" selected="True">dbSNP</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
134 <option value="snps">SNPs</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
135 <option value="indels">INDELs</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
136 <option value="mask">Mask</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
137 <option value="custom">Custom</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
138 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
139 <when value="dbsnp">
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
140 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
141 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
142 <when value="snps">
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
143 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
144 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
145 <when value="indels">
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
146 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
147 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
148 <when value="mask">
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
149 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
150 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
151 <when value="custom">
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
152 <param name="custom_rod_name" type="text" value="Unknown" label="Customer's variant file"/>
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
153 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
154 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
155 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
156 </repeat>
2
28b85e2409ce Uploaded
bgruening
parents: 1
diff changeset
157
0
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
158 <expand macro="gatk_param_type_conditional" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
159
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
160 <conditional name="analysis_param_type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
161 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
162 <option value="basic" selected="True">Basic</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
163 <option value="advanced">Advanced</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
164 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
165 <when value="basic">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
166 <!-- Do nothing here -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
167 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
168 <when value="advanced">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
169 <conditional name="default_read_group_type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
170 <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
171 <option value="default" selected="True">Don't Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
172 <option value="set">Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
173 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
174 <when value="default">
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="set">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
178 <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
179 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
180 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
181 <param name="default_platform" type="select" label="Set default Platform" help="--default_platform">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
182 <option value="default" selected="True">Don't Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
183 <option value="illumina">illumina</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
184 <option value="454">454</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
185 <option value="solid">solid</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
186 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
187 <conditional name="force_read_group_type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
188 <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
189 <option value="default" selected="True">Don't Force</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
190 <option value="set">Force</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
191 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
192 <when value="default">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
193 <!-- do nothing here -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
194 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
195 <when value="set">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
196 <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
197 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
198 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
199 <param name="force_platform" type="select" label="Force Platform" help="--force_platform">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
200 <option value="default" selected="True">Don't Force</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
201 <option value="illumina">illumina</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
202 <option value="454">454</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
203 <option value="solid">solid</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
204 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
205 <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
206 <conditional name="solid_options_type">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
207 <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
208 <option value="default" selected="True">Don't Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
209 <option value="set">Set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
210 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
211 <when value="default">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
212 <!-- do nothing here -->
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
213 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
214 <when value="set">
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
215 <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
216 <option value="default" selected="True">Don't set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
217 <option value="DO_NOTHING">DO_NOTHING</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
218 <option value="SET_Q_ZERO">SET_Q_ZERO</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
219 <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
220 <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
221 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
222 <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
223 <option value="default" selected="True">Don't set</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
224 <option value="THROW_EXCEPTION">THROW_EXCEPTION</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
225 <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
226 <option value="PURGE_READ">PURGE_READ</option>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
227 </param>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
228 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
229 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
230 <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
231 <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
232 </when>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
233 </conditional>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
234 </inputs>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
235 <outputs>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
236 <data format="gatk_report" name="output_recal" label="${tool.name} on ${on_string} (Covariate File)" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
237 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
238 </outputs>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
239 <tests>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
240 <test>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
241 <param name="reference_source_selector" value="history" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
242 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
243 <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
244 <param name="rod_bind_type_selector" value="dbsnp" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
245 <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
246 <param name="standard_covs" value="True" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
247 <param name="covariates" value="ReadGroupCovariate,HomopolymerCovariate,MinimumNQSCovariate,PositionCovariate" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
248 <param name="gatk_param_type_selector" value="basic" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
249 <param name="analysis_param_type_selector" value="basic" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
250 <output name="output_recal" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
251 <output name="output_log" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.log.contains" compare="contains" />
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
252 </test>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
253 </tests>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
254 <help>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
255 .. class:: warningmark
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
256
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
257 "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
258 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
259
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
260 **What it does**
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
261
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
262 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
263
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
264 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
265
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
266 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
267
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
268 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
269
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
270 ------
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
271
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
272 **Inputs**
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
273
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
274 GenomeAnalysisTK: BaseRecalibrator accepts an aligned BAM input file.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
275
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
276
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
277 **Outputs**
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
278
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
279 The output is in CSV format.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
280
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
281
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
282 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
283
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
284 -------
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
285
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
286 **Settings**::
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
287
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
288
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
289 default_read_group If a read has no read group then default to the provided String.
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
290 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
291 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
292 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
293 window_size_nqs The window size used by MinimumNQSCovariate for its calculation
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
294 homopolymer_nback The number of previous bases to look at in HomopolymerCovariate
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
295 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
296 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
297 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
298 recal_file Filename for the input covariates table recalibration .csv file
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
299 out The output CSV file
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
300 standard_covs Use the standard set of covariates in addition to the ones listed using the -cov argument
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
301 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
302
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
303 @CITATION_SECTION@
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
304 </help>
9ad15075b9fa Uploaded
iuc
parents:
diff changeset
305 </tool>