Mercurial > repos > iuc > gatk2

comparison base_recalibrator.xml @ 0:340633249b3d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bgruening
date Mon, 02 Dec 2013 06:18:36 -0500
parents
children 8bcc13094767
comparison
equal deleted inserted replaced
-1:000000000000 0:340633249b3d
1 <tool id="gatk2_base_recalibrator" name="Base Recalibrator" version="0.0.7">
2 <description>calculates covariates used to recalibrate base quality scores of reads</description>
3 <expand macro="requirements" />
4 <macros>
5 <import>gatk2_macros.xml</import>
6 </macros>
7 <command interpreter="python">
8 gatk2_wrapper.py
9 --stdout "${output_log}"
10 -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
11 #if str( $reference_source.input_bam.metadata.bam_index ) != "None":
12 -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
13 #end if
14 -p '
15 @JAR_PATH@
16 -T "BaseRecalibrator"
17 \$GATK2_SITE_OPTIONS
18
19 ## according to http://www.broadinstitute.org/gatk/guide/article?id=1975
20 --num_cpu_threads_per_data_thread 8
21
22 @THREADS@
23 ## we set non standards at every run and the user can choose which ones are preferred
24 ## in our select box both standard options (ContextCovariate, CycleCovariate) are selected by default
25 --no_standard_covs
26
27 #if $reference_source.reference_source_selector != "history":
28 -R "${reference_source.ref_file.fields.path}"
29 #end if
30 #if str($input_recal) != 'None':
31 --BQSR "${input_recal}"
32 #end if
33 --out "${output_recal}"
34 #if str( $covariates ) != "None":
35 #for $cov in str( $covariates ).split( ',' ):
36 -cov "${cov}"
37 #end for
38 #end if
39 '
40
41 #set $snp_dataset_provided = False
42 #set $rod_binding_names = dict()
43 #for $rod_binding in $rod_bind:
44 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
45 #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
46 #else
47 #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
48 #end if
49 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'dbsnp':
50 #set $snp_dataset_provided = True
51 #end if
52 #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
53 -d "--knownSites:${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[$rod_bind_name]}"
54 #end for
55
56 #include source=$standard_gatk_options#
57
58 ##start analysis specific options
59 #if $analysis_param_type.analysis_param_type_selector == "advanced":
60 -p '
61 #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set":
62 --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}"
63 #end if
64 #if str( $analysis_param_type.default_platform ) != "default":
65 --default_platform "${analysis_param_type.default_platform}"
66 #end if
67 #if str( $analysis_param_type.force_read_group_type.force_read_group_type_selector ) == "set":
68 --force_read_group "${analysis_param_type.force_read_group_type.force_read_group}"
69 #end if
70 #if str( $analysis_param_type.force_platform ) != "default":
71 --force_platform "${analysis_param_type.force_platform}"
72 #end if
73 ${analysis_param_type.exception_if_no_tile}
74 #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set":
75 #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default":
76 --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}"
77 #end if
78 #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default":
79 --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}"
80 #end if
81 #end if
82 --window_size_nqs "${analysis_param_type.window_size_nqs}"
83 --homopolymer_nback "${analysis_param_type.homopolymer_nback}"
84 '
85 #end if
86 #if not $snp_dataset_provided:
87 -p '--run_without_dbsnp_potentially_ruining_quality'
88 #end if
89 </command>
90 <inputs>
91 <conditional name="reference_source">
92 <expand macro="reference_source_selector_param" />
93 <when value="cached">
94 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;">
95 <validator type="unspecified_build" />
96 <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 -->
97 </param>
98 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" >
99 <options from_data_table="gatk2_picard_indexes">
100 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
101 </options>
102 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
103 </param>
104 </when>
105 <when value="history">
106 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;" />
107 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
108 <options>
109 <filter type="data_meta" key="dbkey" ref="input_bam" />
110 </options>
111 </param>
112 </when>
113 </conditional>
114 <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;" >
115 <help>The input covariates table file which enables on-the-fly base quality score recalibration.
116 Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool.
117 Please be aware that one should only run recalibration with the covariates file created on the same input bam(s).
118 </help>
119 </param>
120
121 <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;" >
122 <!-- might we want to load the available covariates from an external configuration file, since additional ones can be added to local installs? -->
123 <option value="ContextCovariate" selected="true"/>
124 <option value="CycleCovariate" selected="true"/>
125 <option value="RepeatLengthCovariate" />
126 <option value="RepeatUnitCovariate" />
127 <option value="RepeatUnitAndLengthCovariate" />
128 <!--
129 Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will
130 be added for the user regardless of whether or not they were specified.
131 <option value="QualityScoreCovariate" />
132 <option value="ReadGroupCovariate" />
133 -->
134 </param>
135
136 <repeat name="rod_bind" title="Known Variants" help="Using data sets of known variants (-knownSites,--knownSites &amp;lt;knownSites&amp;gt;)">
137 <conditional name="rod_bind_type">
138 <param name="rod_bind_type_selector" type="select" label="Variant Type">
139 <option value="dbsnp" selected="True">dbSNP</option>
140 <option value="snps">SNPs</option>
141 <option value="indels">INDELs</option>
142 <option value="mask">Mask</option>
143 <option value="custom">Custom</option>
144 </param>
145 <when value="dbsnp">
146 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
147 </when>
148 <when value="snps">
149 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
150 </when>
151 <when value="indels">
152 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
153 </when>
154 <when value="mask">
155 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
156 </when>
157 <when value="custom">
158 <param name="custom_rod_name" type="text" value="Unknown" label="Customer's variant file"/>
159 <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" />
160 </when>
161 </conditional>
162 </repeat>
163
164 <expand macro="gatk_param_type_conditional" />
165
166 <conditional name="analysis_param_type">
167 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
168 <option value="basic" selected="True">Basic</option>
169 <option value="advanced">Advanced</option>
170 </param>
171 <when value="basic">
172 <!-- Do nothing here -->
173 </when>
174 <when value="advanced">
175 <conditional name="default_read_group_type">
176 <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group">
177 <option value="default" selected="True">Don't Set</option>
178 <option value="set">Set</option>
179 </param>
180 <when value="default">
181 <!-- do nothing here -->
182 </when>
183 <when value="set">
184 <param name="default_read_group" type="text" value="Unknown" label="If a read has no read group then default to the provided String"/>
185 </when>
186 </conditional>
187 <param name="default_platform" type="select" label="Set default Platform" help="--default_platform">
188 <option value="default" selected="True">Don't Set</option>
189 <option value="illumina">illumina</option>
190 <option value="454">454</option>
191 <option value="solid">solid</option>
192 </param>
193 <conditional name="force_read_group_type">
194 <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group">
195 <option value="default" selected="True">Don't Force</option>
196 <option value="set">Force</option>
197 </param>
198 <when value="default">
199 <!-- do nothing here -->
200 </when>
201 <when value="set">
202 <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."/>
203 </when>
204 </conditional>
205 <param name="force_platform" type="select" label="Force Platform" help="--force_platform">
206 <option value="default" selected="True">Don't Force</option>
207 <option value="illumina">illumina</option>
208 <option value="454">454</option>
209 <option value="solid">solid</option>
210 </param>
211 <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"/>
212 <conditional name="solid_options_type">
213 <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options">
214 <option value="default" selected="True">Don't Set</option>
215 <option value="set">Set</option>
216 </param>
217 <when value="default">
218 <!-- do nothing here -->
219 </when>
220 <when value="set">
221 <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;">
222 <option value="default" selected="True">Don't set</option>
223 <option value="DO_NOTHING">DO_NOTHING</option>
224 <option value="SET_Q_ZERO">SET_Q_ZERO</option>
225 <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option>
226 <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option>
227 </param>
228 <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;">
229 <option value="default" selected="True">Don't set</option>
230 <option value="THROW_EXCEPTION">THROW_EXCEPTION</option>
231 <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option>
232 <option value="PURGE_READ">PURGE_READ</option>
233 </param>
234 </when>
235 </conditional>
236 <param name="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate" help="window_size_nqs"/>
237 <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;" />
238 </when>
239 </conditional>
240 </inputs>
241 <outputs>
242 <data format="gatk_report" name="output_recal" label="${tool.name} on ${on_string} (Covariate File)" />
243 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
244 </outputs>
245 <tests>
246 <test>
247 <param name="reference_source_selector" value="history" />
248 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
249 <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" />
250 <param name="rod_bind_type_selector" value="dbsnp" />
251 <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
252 <param name="standard_covs" value="True" />
253 <param name="covariates" value="ReadGroupCovariate,HomopolymerCovariate,MinimumNQSCovariate,PositionCovariate" />
254 <param name="gatk_param_type_selector" value="basic" />
255 <param name="analysis_param_type_selector" value="basic" />
256 <output name="output_recal" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" />
257 <output name="output_log" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.log.contains" compare="contains" />
258 </test>
259 </tests>
260 <help>
261 .. class:: warningmark
262
263 "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."
264 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.
265
266 **What it does**
267
268 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.
269
270 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;`_.
271
272 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;`_.
273
274 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
275
276 ------
277
278 **Inputs**
279
280 GenomeAnalysisTK: BaseRecalibrator accepts an aligned BAM input file.
281
282
283 **Outputs**
284
285 The output is in CSV format.
286
287
288 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
289
290 -------
291
292 **Settings**::
293
294
295 default_read_group If a read has no read group then default to the provided String.
296 default_platform If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid.
297 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.
298 force_platform If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid.
299 window_size_nqs The window size used by MinimumNQSCovariate for its calculation
300 homopolymer_nback The number of previous bases to look at in HomopolymerCovariate
301 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
302 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)
303 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)
304 recal_file Filename for the input covariates table recalibration .csv file
305 out The output CSV file
306 standard_covs Use the standard set of covariates in addition to the ones listed using the -cov argument
307 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.
308
309 @CITATION_SECTION@
310 </help>
311 </tool>