Mercurial > repos > jjohnson > gatk2
annotate variant_apply_recalibration.xml @ 23:2f9bf8bf42b7 draft
Replace covariate DinucCovariate with ContextCovariate
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Fri, 28 Dec 2012 12:34:05 -0600 |
| parents | 7533db8dfb5b |
| children | 6ef8eb568700 |
| rev | line source |
|---|---|
|
18
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
1 <tool id="gatk2_variant_apply_recalibration" name="Apply Variant Recalibration" version="0.0.5"> |
| 0 | 2 <description></description> |
| 3 <requirements> | |
|
18
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
4 <requirement type="package" version="2.3">gatk</requirement> |
| 0 | 5 </requirements> |
| 6 <command interpreter="python">gatk2_wrapper.py | |
| 7 --max_jvm_heap_fraction "1" | |
| 8 --stdout "${output_log}" | |
| 9 #for $var_count, $variant in enumerate( $reference_source.variants ): | |
| 10 -d "--input:input_${var_count},%(file_type)s" "${variant.input_variants}" "${variant.input_variants.ext}" "input_variants_${var_count}" | |
| 11 #end for | |
| 12 -p 'java | |
| 13 -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" | |
| 14 -T "ApplyRecalibration" | |
| 15 \$GATK2_SITE_OPTIONS | |
|
18
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
16 \$GATK2_THREAD_OPTIONS |
| 0 | 17 ##--num_threads 4 ##hard coded, for now |
| 18 ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home | |
| 19 #if $reference_source.reference_source_selector != "history": | |
| 20 -R "${reference_source.ref_file.fields.path}" | |
| 21 #end if | |
| 22 --recal_file "${reference_source.input_recal}" | |
| 23 --tranches_file "${reference_source.input_tranches}" | |
| 24 --out "${output_variants}" | |
| 25 ' | |
| 26 | |
| 27 ##start standard gatk options | |
| 28 #if $gatk_param_type.gatk_param_type_selector == "advanced": | |
| 29 #for $pedigree in $gatk_param_type.pedigree: | |
| 30 -p '--pedigree "${pedigree.pedigree_file}"' | |
| 31 #end for | |
| 32 #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: | |
| 33 -p '--pedigreeString "${pedigree_string.pedigree_string}"' | |
| 34 #end for | |
| 35 -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' | |
| 36 #for $read_filter in $gatk_param_type.read_filter: | |
| 37 -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" | |
| 38 ###raise Exception( str( dir( $read_filter ) ) ) | |
| 39 #for $name, $param in $read_filter.read_filter_type.iteritems(): | |
| 40 #if $name not in [ "__current_case__", "read_filter_type_selector" ]: | |
| 41 #if hasattr( $param.input, 'truevalue' ): | |
| 42 ${param} | |
| 43 #else: | |
| 44 --${name} "${param}" | |
| 45 #end if | |
| 46 #end if | |
| 47 #end for | |
| 48 ' | |
| 49 #end for | |
| 50 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ): | |
| 51 -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}" | |
| 52 #end for | |
| 53 | |
| 54 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ): | |
| 55 -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" | |
| 56 #end for | |
| 57 | |
| 58 -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' | |
| 59 | |
| 60 -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' | |
| 61 #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": | |
| 62 -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"' | |
| 63 #end if | |
| 64 -p ' | |
| 65 --baq "${gatk_param_type.baq}" | |
| 66 --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}" | |
| 67 ${gatk_param_type.use_original_qualities} | |
| 68 --defaultBaseQualities "${gatk_param_type.default_base_qualities}" | |
| 69 --validation_strictness "${gatk_param_type.validation_strictness}" | |
| 70 --interval_merging "${gatk_param_type.interval_merging}" | |
| 71 ${gatk_param_type.disable_experimental_low_memory_sharding} | |
|
18
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
72 ${gatk_param_type.fix_misencoded_quality_scores} |
| 0 | 73 ${gatk_param_type.non_deterministic_random_seed} |
| 74 ' | |
| 75 #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): | |
| 76 #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file": | |
| 77 -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}" | |
| 78 #else | |
| 79 -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"' | |
| 80 #end if | |
| 81 #end for | |
| 82 #end if | |
| 83 | |
| 84 #if str( $reference_source.reference_source_selector ) == "history": | |
| 85 -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input" | |
| 86 #end if | |
| 87 ##end standard gatk options | |
| 88 | |
| 89 ##start analysis specific options | |
| 90 -p ' | |
| 91 --mode "${mode}" | |
| 92 | |
| 93 #for $ignore_filter in $ignore_filters: | |
| 94 #set $ignore_filter_name = str( $ignore_filter.ignore_filter_type.ignore_filter_type_selector ) | |
| 95 #if $ignore_filter_name == "custom": | |
| 96 #set $ignore_filter_name = str( $ignore_filter.ignore_filter_type.filter_name ) | |
| 97 #end if | |
| 98 --ignore_filter "${ignore_filter_name}" | |
| 99 #end for | |
| 100 --ts_filter_level "${ts_filter_level}" | |
| 101 ' | |
| 102 </command> | |
| 103 <inputs> | |
| 104 <conditional name="reference_source"> | |
| 105 <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> | |
| 106 <option value="cached">Locally cached</option> | |
| 107 <option value="history">History</option> | |
| 108 </param> | |
| 109 <when value="cached"> | |
| 110 <repeat name="variants" title="Variant" min="1" help="-input,--input &lt;input&gt;"> | |
| 111 <param name="input_variants" type="data" format="vcf" label="Variant file to annotate"/> | |
| 112 </repeat> | |
| 113 <param name="input_recal" type="data" format="gatk_recal" label="Variant Recalibration file" help="-recalFile,--recal_file &lt;recal_file&gt;" /> | |
| 114 <param name="input_tranches" type="data" format="gatk_tranche" label="Variant Tranches file" help="-tranchesFile,--tranches_file &lt;tranches_file&gt;" /> | |
| 115 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &lt;reference_sequence&gt;"> | |
| 116 <options from_data_table="gatk2_picard_indexes"> | |
| 117 <!-- <filter type="data_meta" key="dbkey" ref="variants[0].input_variants" column="dbkey"/> --> | |
| 118 </options> | |
| 119 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> | |
| 120 </param> | |
| 121 </when> | |
| 122 <when value="history"> <!-- FIX ME!!!! --> | |
| 123 <repeat name="variants" title="Variant" min="1" help="-input,--input &lt;input&gt;"> | |
| 124 <param name="input_variants" type="data" format="vcf" label="Variant file to annotate" /> | |
| 125 </repeat> | |
| 126 <param name="input_recal" type="data" format="gatk_recal" label="Variant Recalibration file" help="-recalFile,--recal_file &lt;recal_file&gt;" /> | |
| 127 <param name="input_tranches" type="data" format="gatk_tranche" label="Variant Tranches file" help="-tranchesFile,--tranches_file &lt;tranches_file&gt;" /> | |
| 128 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;" /> | |
| 129 </when> | |
| 130 </conditional> | |
| 131 | |
| 132 <conditional name="gatk_param_type"> | |
| 133 <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options"> | |
| 134 <option value="basic" selected="True">Basic</option> | |
| 135 <option value="advanced">Advanced</option> | |
| 136 </param> | |
| 137 <when value="basic"> | |
| 138 <!-- Do nothing here --> | |
| 139 </when> | |
| 140 <when value="advanced"> | |
| 141 <repeat name="pedigree" title="Pedigree file" help="-ped,--pedigree &lt;pedigree&gt;"> | |
| 142 <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples"/> | |
| 143 </repeat> | |
| 144 <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &lt;pedigreeString&gt;"> | |
| 145 <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/> | |
| 146 </repeat> | |
| 147 <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information" help="-pedValidationType,--pedigreeValidationType &lt;pedigreeValidationType&gt;"> | |
| 148 <option value="STRICT" selected="True">STRICT</option> | |
| 149 <option value="SILENT">SILENT</option> | |
| 150 </param> | |
| 151 <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &lt;read_filter&gt;"> | |
| 152 <conditional name="read_filter_type"> | |
| 153 <param name="read_filter_type_selector" type="select" label="Read Filter Type"> | |
| 154 <option value="BadCigar">BadCigar</option> | |
| 155 <option value="BadMate">BadMate</option> | |
| 156 <option value="DuplicateRead">DuplicateRead</option> | |
| 157 <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option> | |
| 158 <option value="MalformedRead">MalformedRead</option> | |
| 159 <option value="MappingQuality">MappingQuality</option> | |
| 160 <option value="MappingQualityUnavailable">MappingQualityUnavailable</option> | |
| 161 <option value="MappingQualityZero">MappingQualityZero</option> | |
| 162 <option value="MateSameStrand">MateSameStrand</option> | |
| 163 <option value="MaxInsertSize">MaxInsertSize</option> | |
| 164 <option value="MaxReadLength" selected="True">MaxReadLength</option> | |
| 165 <option value="MissingReadGroup">MissingReadGroup</option> | |
| 166 <option value="NoOriginalQualityScores">NoOriginalQualityScores</option> | |
| 167 <option value="NotPrimaryAlignment">NotPrimaryAlignment</option> | |
| 168 <option value="Platform454">Platform454</option> | |
| 169 <option value="Platform">Platform</option> | |
| 170 <option value="PlatformUnit">PlatformUnit</option> | |
| 171 <option value="ReadGroupBlackList">ReadGroupBlackList</option> | |
| 172 <option value="ReadName">ReadName</option> | |
| 173 <option value="ReadStrand">ReadStrand</option> | |
| 174 <option value="ReassignMappingQuality">ReassignMappingQuality</option> | |
| 175 <option value="Sample">Sample</option> | |
| 176 <option value="SingleReadGroup">SingleReadGroup</option> | |
| 177 <option value="UnmappedRead">UnmappedRead</option> | |
| 178 </param> | |
| 179 <when value="BadCigar"> | |
| 180 <!-- no extra options --> | |
| 181 </when> | |
| 182 <when value="BadMate"> | |
| 183 <!-- no extra options --> | |
| 184 </when> | |
| 185 <when value="DuplicateRead"> | |
| 186 <!-- no extra options --> | |
| 187 </when> | |
| 188 <when value="FailsVendorQualityCheck"> | |
| 189 <!-- no extra options --> | |
| 190 </when> | |
| 191 <when value="MalformedRead"> | |
| 192 <!-- no extra options --> | |
| 193 </when> | |
| 194 <when value="MappingQuality"> | |
| 195 <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/> | |
| 196 </when> | |
| 197 <when value="MappingQualityUnavailable"> | |
| 198 <!-- no extra options --> | |
| 199 </when> | |
| 200 <when value="MappingQualityZero"> | |
| 201 <!-- no extra options --> | |
| 202 </when> | |
| 203 <when value="MateSameStrand"> | |
| 204 <!-- no extra options --> | |
| 205 </when> | |
| 206 <when value="MaxInsertSize"> | |
| 207 <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/> | |
| 208 </when> | |
| 209 <when value="MaxReadLength"> | |
| 210 <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/> | |
| 211 </when> | |
| 212 <when value="MissingReadGroup"> | |
| 213 <!-- no extra options --> | |
| 214 </when> | |
| 215 <when value="NoOriginalQualityScores"> | |
| 216 <!-- no extra options --> | |
| 217 </when> | |
| 218 <when value="NotPrimaryAlignment"> | |
| 219 <!-- no extra options --> | |
| 220 </when> | |
| 221 <when value="Platform454"> | |
| 222 <!-- no extra options --> | |
| 223 </when> | |
| 224 <when value="Platform"> | |
| 225 <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/> | |
| 226 </when> | |
| 227 <when value="PlatformUnit"> | |
| 228 <!-- no extra options --> | |
| 229 </when> | |
| 230 <when value="ReadGroupBlackList"> | |
| 231 <!-- no extra options --> | |
| 232 </when> | |
| 233 <when value="ReadName"> | |
| 234 <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/> | |
| 235 </when> | |
| 236 <when value="ReadStrand"> | |
| 237 <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/> | |
| 238 </when> | |
| 239 <when value="ReassignMappingQuality"> | |
| 240 <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/> | |
| 241 </when> | |
| 242 <when value="Sample"> | |
| 243 <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/> | |
| 244 </when> | |
| 245 <when value="SingleReadGroup"> | |
| 246 <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/> | |
| 247 </when> | |
| 248 <when value="UnmappedRead"> | |
| 249 <!-- no extra options --> | |
| 250 </when> | |
| 251 </conditional> | |
| 252 </repeat> | |
| 253 <repeat name="input_interval_repeat" title="Operate on Genomic intervals" help="-L,--intervals &lt;intervals&gt;"> | |
| 254 <param name="input_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" /> | |
| 255 </repeat> | |
| 256 <repeat name="input_exclude_interval_repeat" title="Exclude Genomic intervals" help="-XL,--excludeIntervals &lt;excludeIntervals&gt;"> | |
| 257 <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" /> | |
| 258 </repeat> | |
| 259 | |
| 260 <param name="interval_set_rule" type="select" label="Interval set rule" help="-isr,--interval_set_rule &lt;interval_set_rule&gt;"> | |
| 261 <option value="UNION" selected="True">UNION</option> | |
| 262 <option value="INTERSECTION">INTERSECTION</option> | |
| 263 </param> | |
| 264 | |
| 265 <conditional name="downsampling_type"> | |
| 266 <param name="downsampling_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="-dt,--downsampling_type &lt;downsampling_type&gt;"> | |
| 267 <option value="NONE" selected="True">NONE</option> | |
| 268 <option value="ALL_READS">ALL_READS</option> | |
| 269 <option value="BY_SAMPLE">BY_SAMPLE</option> | |
| 270 </param> | |
| 271 <when value="NONE"> | |
| 272 <!-- no more options here --> | |
| 273 </when> | |
| 274 <when value="ALL_READS"> | |
| 275 <conditional name="downsample_to_type"> | |
| 276 <param name="downsample_to_type_selector" type="select" label="Downsample method"> | |
| 277 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option> | |
| 278 <option value="downsample_to_coverage">Downsample by Coverage</option> | |
| 279 </param> | |
| 280 <when value="downsample_to_fraction"> | |
| 281 <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &lt;downsample_to_fraction&gt;"/> | |
| 282 </when> | |
| 283 <when value="downsample_to_coverage"> | |
| 284 <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &lt;downsample_to_coverage&gt;"/> | |
| 285 </when> | |
| 286 </conditional> | |
| 287 </when> | |
| 288 <when value="BY_SAMPLE"> | |
| 289 <conditional name="downsample_to_type"> | |
| 290 <param name="downsample_to_type_selector" type="select" label="Downsample method"> | |
| 291 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option> | |
| 292 <option value="downsample_to_coverage">Downsample by Coverage</option> | |
| 293 </param> | |
| 294 <when value="downsample_to_fraction"> | |
| 295 <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &lt;downsample_to_fraction&gt;"/> | |
| 296 </when> | |
| 297 <when value="downsample_to_coverage"> | |
| 298 <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &lt;downsample_to_coverage&gt;"/> | |
| 299 </when> | |
| 300 </conditional> | |
| 301 </when> | |
| 302 </conditional> | |
| 303 <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine" help="-baq,--baq &lt;baq&gt;"> | |
| 304 <option value="OFF" selected="True">OFF</option> | |
| 305 <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option> | |
| 306 <option value="RECALCULATE">RECALCULATE</option> | |
| 307 </param> | |
| 308 <param name="baq_gap_open_penalty" type="float" label="BAQ gap open penalty (Phred Scaled)" value="40" help="Default value is 40. 30 is perhaps better for whole genome call sets. -baqGOP,--baqGapOpenPenalty &lt;baqGapOpenPenalty&gt;" /> | |
| 309 <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" help="-OQ,--useOriginalQualities" /> | |
| 310 <param name="default_base_qualities" type="integer" label="Value to be used for all base quality scores, when some are missing" value="-1" help="-DBQ,--defaultBaseQualities &lt;defaultBaseQualities&gt;"/> | |
| 311 <param name="validation_strictness" type="select" label="How strict should we be with validation" help="-S,--validation_strictness &lt;validation_strictness&gt;"> | |
| 312 <option value="STRICT" selected="True">STRICT</option> | |
| 313 <option value="LENIENT">LENIENT</option> | |
| 314 <option value="SILENT">SILENT</option> | |
| 315 <!-- <option value="DEFAULT_STRINGENCY">DEFAULT_STRINGENCY</option> listed in docs, but not valid value...--> | |
| 316 </param> | |
| 317 <param name="interval_merging" type="select" label="Interval merging rule" help="-im,--interval_merging &lt;interval_merging&gt;"> | |
| 318 <option value="ALL" selected="True">ALL</option> | |
| 319 <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option> | |
| 320 </param> | |
| 321 | |
| 322 <repeat name="read_group_black_list_repeat" title="Read group black list" help="-rgbl,--read_group_black_list &lt;read_group_black_list&gt;"> | |
| 323 <conditional name="read_group_black_list_type"> | |
| 324 <param name="read_group_black_list_type_selector" type="select" label="Type of reads read group black list"> | |
| 325 <option value="file" selected="True">Filters in file</option> | |
| 326 <option value="text">Specify filters as a string</option> | |
| 327 </param> | |
| 328 <when value="file"> | |
| 329 <param name="read_group_black_list" type="data" format="txt" label="Read group black list file" /> | |
| 330 </when> | |
| 331 <when value="text"> | |
| 332 <param name="read_group_black_list" type="text" value="tag:string" label="Read group black list tag:string" /> | |
| 333 </when> | |
| 334 </conditional> | |
| 335 </repeat> | |
| 336 | |
| 337 <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> | |
| 338 <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> | |
|
18
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
339 <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> |
| 0 | 340 |
| 341 </when> | |
| 342 </conditional> | |
| 343 | |
| 344 <param name="mode" type="select" label="Recalibration mode" help="-mode,--mode &lt;mode&gt;"> | |
| 345 <option value="SNP" selected="True">SNP</option> | |
| 346 <option value="INDEL">INDEL</option> | |
| 347 <option value="BOTH">BOTH</option> | |
| 348 </param> | |
| 349 <repeat name="ignore_filters" title="Ignore Filter" help="-ignoreFilter,--ignore_filter &lt;ignore_filter&gt;"> | |
| 350 <conditional name="ignore_filter_type"> | |
| 351 <param name="ignore_filter_type_selector" type="select" label="Filter Type"> | |
| 352 <option value="HARD_TO_VALIDATE">HARD_TO_VALIDATE</option> | |
| 353 <option value="LowQual" >LowQual</option> | |
| 354 <option value="custom" selected="True">Other</option> | |
| 355 </param> | |
| 356 <when value="custom"> | |
| 357 <param name="filter_name" type="text" value="" label="Filter name"/> | |
| 358 </when> | |
| 359 <when value="HARD_TO_VALIDATE" /> | |
| 360 <when value="LowQual" /> | |
| 361 </conditional> | |
| 362 </repeat> | |
| 363 <param name="ts_filter_level" type="float" label="truth sensitivity level at which to start filtering, used here to indicate filtered variants in plots" value="99.0" help="-ts_filter_level,--ts_filter_level &lt;ts_filter_level&gt;"/> | |
| 364 </inputs> | |
| 365 <outputs> | |
| 366 <data format="vcf" name="output_variants" label="${tool.name} on ${on_string} (Variants File)" /> | |
| 367 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> | |
| 368 </outputs> | |
| 369 <tests> | |
| 370 <!-- ADD TESTS --> | |
| 371 </tests> | |
| 372 <help> | |
| 373 **What it does** | |
| 374 | |
| 375 Applies cuts to the input vcf file (by adding filter lines) to achieve the desired novel FDR levels which were specified during VariantRecalibration | |
| 376 | |
| 377 For more information on using the ApplyRecalibration module, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_variantrecalibration_ApplyRecalibration.html>`_. | |
| 378 | |
| 379 To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gatk/guide/topic?name=best-practices>`_. | |
| 380 | |
| 381 If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gatk/guide/topic?name=faqs>`_. | |
| 382 | |
| 383 ------ | |
| 384 | |
| 385 **Inputs** | |
| 386 | |
| 387 GenomeAnalysisTK: ApplyRecalibration accepts a variant input file, a recalibration file and a tranches file. | |
| 388 | |
| 389 | |
| 390 **Outputs** | |
| 391 | |
| 392 The output is in VCF format. | |
| 393 | |
| 394 Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. | |
| 395 | |
| 396 ------- | |
| 397 | |
| 398 **Settings**:: | |
| 399 | |
| 400 | |
| 401 recal_file The output recal file used by ApplyRecalibration | |
| 402 tranches_file The input tranches file describing where to cut the data | |
| 403 out The output filtered, recalibrated VCF file | |
| 404 ts_filter_level The truth sensitivity level at which to start filtering | |
| 405 ignore_filter If specified the optimizer will use variants even if the specified filter name is marked in the input VCF file | |
| 406 mode Recalibration mode to employ: 1.) SNP for recalibrating only SNPs (emitting indels untouched in the output VCF); 2.) INDEL for indels; and 3.) BOTH for recalibrating both SNPs and indels simultaneously. (SNP|INDEL|BOTH) | |
| 407 | |
| 408 ------ | |
| 409 | |
| 410 **Citation** | |
| 411 | |
| 412 For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. <http://www.ncbi.nlm.nih.gov/pubmed/21478889>`_ | |
| 413 | |
| 414 Please also site `McKenna A, Hanna M, Banks E, Sivachenko A, Cibulskis K, Kernytsky A, Garimella K, Altshuler D, Gabriel S, Daly M, DePristo MA (2010). The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data. Genome Res. 20:1297-303. Epub 2010 Jul 19. <http://www.ncbi.nlm.nih.gov/pubmed/20644199>`_ | |
| 415 | |
| 416 If you use this tool in Galaxy, please cite `Blankenberg D, Von Kuster G, Coraor N, Ananda G, Lazarus R, Mangan M, Nekrutenko A, Taylor J. Galaxy: a web-based genome analysis tool for experimentalists. Curr Protoc Mol Biol. 2010 Jan;Chapter 19:Unit 19.10.1-21. <http://www.ncbi.nlm.nih.gov/pubmed/20069535>`_ | |
| 417 | |
| 418 </help> | |
| 419 </tool> |