Mercurial > repos > jjohnson > gatk2
annotate print_reads.xml @ 35:a29c7d7d962d draft
Fix default read filter screening
author | Jim Johnson <jj@umn.edu> |
---|---|
date | Fri, 01 Mar 2013 07:52:02 -0600 |
parents | b99c25b0ad4d |
children | 14d47237bb0a |
rev | line source |
---|---|
34 | 1 <tool id="gatk2_print_reads" name="Print Reads" version="0.0.7"> |
0 | 2 <description>on BAM files</description> |
3 <requirements> | |
18
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
6
diff
changeset
|
4 <requirement type="package" version="2.3">gatk</requirement> |
0 | 5 <requirement type="package" version="0.1.18">samtools</requirement> |
6 </requirements> | |
7 <command interpreter="python">gatk2_wrapper.py | |
8 --max_jvm_heap_fraction "1" | |
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 'java | |
15 -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" | |
16 -T "PrintReads" | |
17 -o "${output_bam}" | |
18 \$GATK2_SITE_OPTIONS | |
28
6ef8eb568700
Move GATK tool_dependency to a repository dependency, use 2 env vars: GATK2_NUM_THREADS and GATK2_NUM_CPU_THREADS for site threading values
Jim Johnson <jj@umn.edu>
parents:
18
diff
changeset
|
19 \$GATK2_NUM_CPU_THREADS |
0 | 20 ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home |
21 ##--num_threads 4 ##not supported yet | |
22 ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout | |
23 #if $reference_source.reference_source_selector != "history": | |
24 -R "${reference_source.ref_file.fields.path}" | |
25 #end if | |
18
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
6
diff
changeset
|
26 #if str($input_recal) != 'None': |
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
6
diff
changeset
|
27 --BQSR "${input_recal}" |
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
6
diff
changeset
|
28 #end if |
0 | 29 --disable_bam_indexing |
30 ' | |
31 ##start standard gatk options | |
32 #if $gatk_param_type.gatk_param_type_selector == "advanced": | |
33 #for $pedigree in $gatk_param_type.pedigree: | |
34 -p '--pedigree "${pedigree.pedigree_file}"' | |
35 #end for | |
36 #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: | |
37 -p '--pedigreeString "${pedigree_string.pedigree_string}"' | |
38 #end for | |
39 -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' | |
35 | 40 #set default_read_filters = ['MalformedRead'] |
0 | 41 #for $read_filter in $gatk_param_type.read_filter: |
33
76f8ca47b810
Omit --read_filter param included by default
Jim Johnson <jj@umn.edu>
parents:
28
diff
changeset
|
42 -p ' |
35 | 43 #if $read_filter.read_filter_type.read_filter_type_selector not in $default_read_filters: |
33
76f8ca47b810
Omit --read_filter param included by default
Jim Johnson <jj@umn.edu>
parents:
28
diff
changeset
|
44 --read_filter "${read_filter.read_filter_type.read_filter_type_selector}" |
76f8ca47b810
Omit --read_filter param included by default
Jim Johnson <jj@umn.edu>
parents:
28
diff
changeset
|
45 #end_if |
0 | 46 #for $name, $param in $read_filter.read_filter_type.iteritems(): |
47 #if $name not in [ "__current_case__", "read_filter_type_selector" ]: | |
48 #if hasattr( $param.input, 'truevalue' ): | |
49 ${param} | |
50 #else: | |
51 --${name} "${param}" | |
52 #end if | |
53 #end if | |
54 #end for | |
55 ' | |
56 #end for | |
57 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ): | |
58 -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}" | |
59 #end for | |
60 | |
61 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ): | |
62 -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" | |
63 #end for | |
64 | |
65 -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' | |
66 | |
67 -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' | |
68 #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": | |
69 -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"' | |
70 #end if | |
71 -p ' | |
72 --baq "${gatk_param_type.baq}" | |
73 --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}" | |
74 ${gatk_param_type.use_original_qualities} | |
75 --defaultBaseQualities "${gatk_param_type.default_base_qualities}" | |
76 --validation_strictness "${gatk_param_type.validation_strictness}" | |
77 --interval_merging "${gatk_param_type.interval_merging}" | |
78 ${gatk_param_type.disable_experimental_low_memory_sharding} | |
18
7533db8dfb5b
Update tool_dependencies to GATK v 2.3
Jim Johnson <jj@umn.edu>
parents:
6
diff
changeset
|
79 ${gatk_param_type.fix_misencoded_quality_scores} |
0 | 80 ${gatk_param_type.non_deterministic_random_seed} |
81 ' | |
82 #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): | |
83 #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file": | |
84 -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}" | |
85 #else | |
86 -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"' | |
87 #end if | |
88 #end for | |
89 #end if | |
90 | |
91 #if str( $reference_source.reference_source_selector ) == "history": | |
92 -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input" | |
93 #end if | |
94 ##end standard gatk options | |
95 | |
96 ##start analysis specific options | |
97 #if $analysis_param_type.analysis_param_type_selector == "advanced": | |
98 -p ' | |
99 #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set": | |
100 --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}" | |
101 #end if | |
102 #if str( $analysis_param_type.default_platform ) != "default": | |
103 --default_platform "${analysis_param_type.default_platform}" | |
104 #end if | |
105 #if str( $analysis_param_type.force_read_group_type.force_read_group_type_selector ) == "set": | |
106 --force_read_group "${analysis_param_type.force_read_group_type.force_read_group}" | |
107 #end if | |
108 #if str( $analysis_param_type.force_platform ) != "default": | |
109 --force_platform "${analysis_param_type.force_platform}" | |
110 #end if | |
111 ${analysis_param_type.exception_if_no_tile} | |
112 #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set": | |
113 #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default": | |
114 --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}" | |
115 #end if | |
116 #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default": | |
117 --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}" | |
118 #end if | |
119 #end if | |
120 ${analysis_param_type.simplify_bam} | |
121 --preserve_qscores_less_than "${analysis_param_type.preserve_qscores_less_than}" | |
122 --smoothing "${analysis_param_type.smoothing}" | |
123 --max_quality_score "${analysis_param_type.max_quality_score}" | |
124 --window_size_nqs "${analysis_param_type.window_size_nqs}" | |
125 --homopolymer_nback "${analysis_param_type.homopolymer_nback}" | |
126 ${analysis_param_type.do_not_write_original_quals} | |
127 ' | |
128 #end if | |
129 </command> | |
130 <inputs> | |
6 | 131 <param name="input_recal" type="data" format="csv" optional="true" label="Covariates table recalibration file" help="-BQSR,--BQSR &lt;recal_file&gt;" /> |
0 | 132 <conditional name="reference_source"> |
133 <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> | |
134 <option value="cached">Locally cached</option> | |
135 <option value="history">History</option> | |
136 </param> | |
137 <when value="cached"> | |
138 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &lt;input_file&gt;"> | |
139 <validator type="unspecified_build" /> | |
140 <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 --> | |
141 </param> | |
142 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &lt;reference_sequence&gt;" > | |
143 <options from_data_table="gatk2_picard_indexes"> | |
144 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> | |
145 </options> | |
146 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> | |
147 </param> | |
148 </when> | |
149 <when value="history"> | |
150 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &lt;input_file&gt;" /> | |
151 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;"> | |
152 <options> | |
153 <filter type="data_meta" key="dbkey" ref="input_bam" /> | |
154 </options> | |
155 </param> | |
156 </when> | |
157 </conditional> | |
158 | |
159 <conditional name="gatk_param_type"> | |
160 <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options"> | |
161 <option value="basic" selected="True">Basic</option> | |
162 <option value="advanced">Advanced</option> | |
163 </param> | |
164 <when value="basic"> | |
165 <!-- Do nothing here --> | |
166 </when> | |
167 <when value="advanced"> | |
168 <repeat name="pedigree" title="Pedigree file" help="-ped,--pedigree &lt;pedigree&gt;"> | |
169 <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples"/> | |
170 </repeat> | |
171 <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &lt;pedigreeString&gt;"> | |
172 <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/> | |
173 </repeat> | |
174 <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information" help="-pedValidationType,--pedigreeValidationType &lt;pedigreeValidationType&gt;"> | |
175 <option value="STRICT" selected="True">STRICT</option> | |
176 <option value="SILENT">SILENT</option> | |
177 </param> | |
178 <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &lt;read_filter&gt;"> | |
179 <conditional name="read_filter_type"> | |
180 <param name="read_filter_type_selector" type="select" label="Read Filter Type"> | |
181 <option value="BadCigar">BadCigar</option> | |
182 <option value="BadMate">BadMate</option> | |
183 <option value="DuplicateRead">DuplicateRead</option> | |
184 <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option> | |
185 <option value="MalformedRead">MalformedRead</option> | |
186 <option value="MappingQuality">MappingQuality</option> | |
187 <option value="MappingQualityUnavailable">MappingQualityUnavailable</option> | |
188 <option value="MappingQualityZero">MappingQualityZero</option> | |
189 <option value="MateSameStrand">MateSameStrand</option> | |
190 <option value="MaxInsertSize">MaxInsertSize</option> | |
191 <option value="MaxReadLength" selected="True">MaxReadLength</option> | |
192 <option value="MissingReadGroup">MissingReadGroup</option> | |
193 <option value="NoOriginalQualityScores">NoOriginalQualityScores</option> | |
194 <option value="NotPrimaryAlignment">NotPrimaryAlignment</option> | |
195 <option value="Platform454">Platform454</option> | |
196 <option value="Platform">Platform</option> | |
197 <option value="PlatformUnit">PlatformUnit</option> | |
198 <option value="ReadGroupBlackList">ReadGroupBlackList</option> | |
199 <option value="ReadName">ReadName</option> | |
200 <option value="ReadStrand">ReadStrand</option> | |
201 <option value="ReassignMappingQuality">ReassignMappingQuality</option> | |
202 <option value="Sample">Sample</option> | |
203 <option value="SingleReadGroup">SingleReadGroup</option> | |
204 <option value="UnmappedRead">UnmappedRead</option> | |
205 </param> | |
206 <when value="BadCigar"> | |
207 <!-- no extra options --> | |
208 </when> | |
209 <when value="BadMate"> | |
210 <!-- no extra options --> | |
211 </when> | |
212 <when value="DuplicateRead"> | |
213 <!-- no extra options --> | |
214 </when> | |
215 <when value="FailsVendorQualityCheck"> | |
216 <!-- no extra options --> | |
217 </when> | |
218 <when value="MalformedRead"> | |
35 | 219 <param name="filter_mismatching_base_and_quals" type="boolean" truevalue="--filter_mismatching_base_and_quals" falsevalue="" checked="false" label="filter out the reads with mismatching number of bases and base qualities" help="filter out the mismatch reads instead of quitting with an error"/> |
0 | 220 </when> |
221 <when value="MappingQuality"> | |
222 <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/> | |
223 </when> | |
224 <when value="MappingQualityUnavailable"> | |
225 <!-- no extra options --> | |
226 </when> | |
227 <when value="MappingQualityZero"> | |
228 <!-- no extra options --> | |
229 </when> | |
230 <when value="MateSameStrand"> | |
231 <!-- no extra options --> | |
232 </when> | |
233 <when value="MaxInsertSize"> | |
234 <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/> | |
235 </when> | |
236 <when value="MaxReadLength"> | |
237 <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/> | |
238 </when> | |
239 <when value="MissingReadGroup"> | |
240 <!-- no extra options --> | |
241 </when> | |
242 <when value="NoOriginalQualityScores"> | |
243 <!-- no extra options --> | |
244 </when> | |
245 <when value="NotPrimaryAlignment"> | |
246 <!-- no extra options --> | |
247 </when> | |
248 <when value="Platform454"> | |
249 <!-- no extra options --> | |
250 </when> | |
251 <when value="Platform"> | |
252 <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/> | |
253 </when> | |
254 <when value="PlatformUnit"> | |
255 <!-- no extra options --> | |
256 </when> | |
257 <when value="ReadGroupBlackList"> | |
258 <!-- no extra options --> | |
259 </when> | |
260 <when value="ReadName"> | |
261 <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/> | |
262 </when> | |
263 <when value="ReadStrand"> | |
264 <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/> | |
265 </when> | |
266 <when value="ReassignMappingQuality"> | |
267 <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/> | |
268 </when> | |
269 <when value="Sample"> | |
270 <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/> | |
271 </when> | |
272 <when value="SingleReadGroup"> | |
273 <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/> | |
274 </when> | |
275 <when value="UnmappedRead"> | |
276 <!-- no extra options --> | |
277 </when> | |
278 </conditional> | |
279 </repeat> | |
280 <repeat name="input_interval_repeat" title="Operate on Genomic intervals" help="-L,--intervals &lt;intervals&gt;"> | |
281 <param name="input_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" /> | |
282 </repeat> | |
283 <repeat name="input_exclude_interval_repeat" title="Exclude Genomic intervals" help="-XL,--excludeIntervals &lt;excludeIntervals&gt;"> | |
284 <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" /> | |
285 </repeat> | |
286 | |
287 <param name="interval_set_rule" type="select" label="Interval set rule" help="-isr,--interval_set_rule &lt;interval_set_rule&gt;"> | |
288 <option value="UNION" selected="True">UNION</option> | |
289 <option value="INTERSECTION">INTERSECTION</option> | |
290 </param> | |
291 | |
292 <conditional name="downsampling_type"> | |
293 <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;"> | |
294 <option value="NONE" selected="True">NONE</option> | |
295 <option value="ALL_READS">ALL_READS</option> | |
296 <option value="BY_SAMPLE">BY_SAMPLE</option> | |
297 </param> | |
298 <when value="NONE"> | |
299 <!-- no more options here --> | |
300 </when> | |
301 <when value="ALL_READS"> | |
302 <conditional name="downsample_to_type"> | |
303 <param name="downsample_to_type_selector" type="select" label="Downsample method"> | |
304 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option> | |
305 <option value="downsample_to_coverage">Downsample by Coverage</option> | |
306 </param> | |
307 <when value="downsample_to_fraction"> | |
308 <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;"/> | |
309 </when> | |
310 <when value="downsample_to_coverage"> | |
311 <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;"/> | |
312 </when> | |
313 </conditional> | |
314 </when> | |
315 <when value="BY_SAMPLE"> | |
316 <conditional name="downsample_to_type"> | |
317 <param name="downsample_to_type_selector" type="select" label="Downsample method"> | |
318 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option> | |
319 <option value="downsample_to_coverage">Downsample by Coverage</option> | |
320 </param> | |
321 <when value="downsample_to_fraction"> | |
322 <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;"/> | |
323 </when> | |
324 <when value="downsample_to_coverage"> | |
325 <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;"/> | |
326 </when> | |
327 </conditional> | |
328 </when> | |
329 </conditional> | |
330 <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine" help="-baq,--baq &lt;baq&gt;"> | |
331 <option value="OFF" selected="True">OFF</option> | |
332 <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option> | |
333 <option value="RECALCULATE">RECALCULATE</option> | |
334 </param> | |
335 <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;" /> | |
336 <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" help="-OQ,--useOriginalQualities" /> | |
337 <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;"/> | |
338 <param name="validation_strictness" type="select" label="How strict should we be with validation" help="-S,--validation_strictness &lt;validation_strictness&gt;"> | |
339 <option value="STRICT" selected="True">STRICT</option> | |
340 <option value="LENIENT">LENIENT</option> | |
341 <option value="SILENT">SILENT</option> | |
342 <!-- <option value="DEFAULT_STRINGENCY">DEFAULT_STRINGENCY</option> listed in docs, but not valid value...--> | |
343 </param> | |
344 <param name="interval_merging" type="select" label="Interval merging rule" help="-im,--interval_merging &lt;interval_merging&gt;"> | |
345 <option value="ALL" selected="True">ALL</option> | |
346 <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option> | |
347 </param> | |
348 | |
349 <repeat name="read_group_black_list_repeat" title="Read group black list" help="-rgbl,--read_group_black_list &lt;read_group_black_list&gt;"> | |
350 <conditional name="read_group_black_list_type"> | |
351 <param name="read_group_black_list_type_selector" type="select" label="Type of reads read group black list"> | |
352 <option value="file" selected="True">Filters in file</option> | |
353 <option value="text">Specify filters as a string</option> | |
354 </param> | |
355 <when value="file"> | |
356 <param name="read_group_black_list" type="data" format="txt" label="Read group black list file" /> | |
357 </when> | |
358 <when value="text"> | |
359 <param name="read_group_black_list" type="text" value="tag:string" label="Read group black list tag:string" /> | |
360 </when> | |
361 </conditional> | |
362 </repeat> | |
363 | |
364 <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"/> | |
365 <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:
6
diff
changeset
|
366 <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 | 367 |
368 </when> | |
369 </conditional> | |
370 | |
371 | |
372 <conditional name="analysis_param_type"> | |
373 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> | |
374 <option value="basic" selected="True">Basic</option> | |
375 <option value="advanced">Advanced</option> | |
376 </param> | |
377 <when value="basic"> | |
378 <!-- Do nothing here --> | |
379 </when> | |
380 <when value="advanced"> | |
381 <conditional name="default_read_group_type"> | |
382 <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group"> | |
383 <option value="default" selected="True">Don't Set</option> | |
384 <option value="set">Set</option> | |
385 </param> | |
386 <when value="default"> | |
387 <!-- do nothing here --> | |
388 </when> | |
389 <when value="set"> | |
390 <param name="default_read_group" type="text" value="Unknown" label="If a read has no read group then default to the provided String"/> | |
391 </when> | |
392 </conditional> | |
393 <param name="default_platform" type="select" label="Set default Platform" help="--default_platform"> | |
394 <option value="default" selected="True">Don't Set</option> | |
395 <option value="illumina">illumina</option> | |
396 <option value="454">454</option> | |
397 <option value="solid">solid</option> | |
398 </param> | |
399 <conditional name="force_read_group_type"> | |
400 <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group"> | |
401 <option value="default" selected="True">Don't Force</option> | |
402 <option value="set">Force</option> | |
403 </param> | |
404 <when value="default"> | |
405 <!-- do nothing here --> | |
406 </when> | |
407 <when value="set"> | |
408 <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."/> | |
409 </when> | |
410 </conditional> | |
411 <param name="force_platform" type="select" label="Force Platform" help="--force_platform"> | |
412 <option value="default" selected="True">Don't Force</option> | |
413 <option value="illumina">illumina</option> | |
414 <option value="454">454</option> | |
415 <option value="solid">solid</option> | |
416 </param> | |
417 <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"/> | |
418 <conditional name="solid_options_type"> | |
419 <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options"> | |
420 <option value="default" selected="True">Don't Set</option> | |
421 <option value="set">Set</option> | |
422 </param> | |
423 <when value="default"> | |
424 <!-- do nothing here --> | |
425 </when> | |
426 <when value="set"> | |
427 <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 &lt;solid_recal_mode&gt;"> | |
428 <option value="default" selected="True">Don't set</option> | |
429 <option value="DO_NOTHING">DO_NOTHING</option> | |
430 <option value="SET_Q_ZERO">SET_Q_ZERO</option> | |
431 <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option> | |
432 <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option> | |
433 </param> | |
434 <param name="solid_nocall_strategy" type="select" label="Behavior of the recalibrator when it encounters no calls" help="-solid_nocall_strategy,--solid_nocall_strategy &lt;solid_nocall_strategy&gt;"> | |
435 <option value="default" selected="True">Don't set</option> | |
436 <option value="THROW_EXCEPTION">THROW_EXCEPTION</option> | |
437 <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option> | |
438 <option value="PURGE_READ">PURGE_READ</option> | |
439 </param> | |
440 </when> | |
441 </conditional> | |
442 <param name="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/> | |
443 <param name="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate" help="--window_size_nqs"/> | |
444 <param name="homopolymer_nback" type="integer" value="7" label="Number of previous bases to look at in HomopolymerCovariate" help="-nback,--homopolymer_nback &lt;homopolymer_nback&gt;" /> | |
445 <param name="preserve_qscores_less_than" type="integer" value="5" label="Bases with quality scores less than this threshold won't be recalibrated" help="-pQ,--preserve_qscores_less_than &lt;preserve_qscores_less_than&gt;"/> | |
446 <param name="smoothing" type="integer" value="1" label="smoothing" help="-sm,--smoothing &lt;smoothing&gt;"/> | |
447 <param name="max_quality_score" type="integer" value="50" label="Max quality score" help="-maxQ,--max_quality_score &lt;max_quality_score&gt;"/> | |
448 <param name="do_not_write_original_quals" type="boolean" checked="False" truevalue="--doNotWriteOriginalQuals" falsevalue="" label="Do Not Write Original Quality tag" help="-noOQs,--doNotWriteOriginalQuals"/> | |
449 </when> | |
450 </conditional> | |
451 </inputs> | |
452 <outputs> | |
453 <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (BAM)" /> | |
454 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> | |
455 </outputs> | |
456 <tests> | |
457 <test> | |
458 <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" /> | |
459 <param name="reference_source_selector" value="history" /> | |
460 <param name="ref_file" value="phiX.fasta" ftype="fasta" /> | |
461 <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" /> | |
462 <param name="gatk_param_type_selector" value="basic" /> | |
463 <param name="analysis_param_type_selector" value="basic" /> | |
464 <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" /> | |
465 <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" /> | |
466 </test> | |
467 </tests> | |
468 <help> | |
469 **What it does** | |
470 | |
471 This walker is designed to work as the second pass in a two-pass processing step, doing a by-read traversal. For each base in each read this walker calculates various user-specified covariates (such as read group, reported quality score, cycle, and dinuc) Using these values as a key in a large hashmap the walker calculates an empirical base quality score and overwrites the quality score currently in the read. This walker then outputs a new bam file with these updated (recalibrated) reads. Note: This walker expects as input the recalibration table file generated previously by CovariateCounterWalker. Note: This walker is designed to be used in conjunction with CovariateCounterWalker. | |
472 | |
473 For more information on base quality score recalibration using the GATK, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_PrintReads.html>`_. | |
474 | |
475 To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gatk/guide/topic?name=best-practices>`_. | |
476 | |
477 If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gatk/guide/topic?name=faqs>`_. | |
478 | |
479 ------ | |
480 | |
481 **Inputs** | |
482 | |
483 GenomeAnalysisTK: PrintReads accepts an aligned BAM and a recalibration CSV input files. | |
484 | |
485 | |
486 **Outputs** | |
487 | |
488 The output is in BAM format. | |
489 | |
490 | |
491 Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. | |
492 | |
493 ------- | |
494 | |
495 **Settings**:: | |
496 | |
497 default_read_group If a read has no read group then default to the provided String. | |
498 default_platform If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid. | |
499 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. | |
500 force_platform If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid. | |
501 window_size_nqs The window size used by MinimumNQSCovariate for its calculation | |
502 homopolymer_nback The number of previous bases to look at in HomopolymerCovariate | |
503 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 | |
504 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) | |
505 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) | |
506 recal_file Filename for the input covariates table recalibration .csv file | |
507 out The output BAM file | |
508 bam_compression Compression level to use for writing BAM files | |
509 disable_bam_indexing Turn off on-the-fly creation of indices for output BAM files. | |
510 simplifyBAM If provided, output BAM files will be simplified to include just key reads for downstream variation discovery analyses (removing duplicates, PF-, non-primary reads), as well stripping all extended tags from the kept reads except the read group identifier | |
511 preserve_qscores_less_than Bases with quality scores less than this threshold won't be recalibrated, default=5. In general it's unsafe to change qualities scores below < 5, since base callers use these values to indicate random or bad bases | |
512 smoothing Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1 | |
513 max_quality_score The integer value at which to cap the quality scores, default=50 | |
514 doNotWriteOriginalQuals If true, we will not write the original quality (OQ) tag for each read | |
515 | |
516 ------ | |
517 | |
518 **Citation** | |
519 | |
520 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>`_ | |
521 | |
522 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>`_ | |
523 | |
524 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>`_ | |
525 | |
526 </help> | |
527 </tool> |