Mercurial > repos > iuc > gatk2

comparison print_reads.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_print_reads" name="Print Reads" version="0.0.7">
2 <description>on BAM files</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 "PrintReads"
17 -o "${output_bam}"
18 \$GATK2_SITE_OPTIONS
19
20 ## according to http://www.broadinstitute.org/gatk/guide/article?id=1975
21 --num_cpu_threads_per_data_thread 8
22
23 @THREADS@
24
25 #if $reference_source.reference_source_selector != "history":
26 -R "${reference_source.ref_file.fields.path}"
27 #end if
28 #if str($input_recal) != 'None':
29 --BQSR "${input_recal}"
30 #end if
31 --disable_bam_indexing
32 '
33
34 #include source=$standard_gatk_options#
35
36 #if str( $reference_source.reference_source_selector ) == "history":
37 -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
38 #end if
39 ##end standard gatk options
40
41 ##start analysis specific options
42 #if $analysis_param_type.analysis_param_type_selector == "advanced":
43 -p '
44 #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set":
45 --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}"
46 #end if
47 #if str( $analysis_param_type.default_platform ) != "default":
48 --default_platform "${analysis_param_type.default_platform}"
49 #end if
50 #if str( $analysis_param_type.force_read_group_type.force_read_group_type_selector ) == "set":
51 --force_read_group "${analysis_param_type.force_read_group_type.force_read_group}"
52 #end if
53 #if str( $analysis_param_type.force_platform ) != "default":
54 --force_platform "${analysis_param_type.force_platform}"
55 #end if
56 ${analysis_param_type.exception_if_no_tile}
57 #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set":
58 #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default":
59 --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}"
60 #end if
61 #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default":
62 --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}"
63 #end if
64 #end if
65 ${analysis_param_type.simplify_bam}
66 --preserve_qscores_less_than "${analysis_param_type.preserve_qscores_less_than}"
67 --smoothing "${analysis_param_type.smoothing}"
68 --max_quality_score "${analysis_param_type.max_quality_score}"
69 --window_size_nqs "${analysis_param_type.window_size_nqs}"
70 --homopolymer_nback "${analysis_param_type.homopolymer_nback}"
71 ${analysis_param_type.do_not_write_original_quals}
72 '
73 #end if
74 </command>
75 <inputs>
76 <param name="input_recal" type="data" format="gatk_report" optional="true" label="Covariates table recalibration file"
77 help="The input covariates table file which enables on-the-fly base quality score recalibration (intended for use with BaseRecalibrator files) (-BQSR,--BQSR)" />
78 <conditional name="reference_source">
79 <expand macro="reference_source_selector_param" />
80 <when value="cached">
81 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;">
82 <validator type="unspecified_build" />
83 <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 -->
84 </param>
85 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" >
86 <options from_data_table="gatk2_picard_indexes">
87 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
88 </options>
89 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
90 </param>
91 </when>
92 <when value="history">
93 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;" />
94 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
95 <options>
96 <filter type="data_meta" key="dbkey" ref="input_bam" />
97 </options>
98 </param>
99 </when>
100 </conditional>
101
102 <expand macro="gatk_param_type_conditional" />
103
104
105 <conditional name="analysis_param_type">
106 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
107 <option value="basic" selected="True">Basic</option>
108 <option value="advanced">Advanced</option>
109 </param>
110 <when value="basic">
111 <!-- Do nothing here -->
112 </when>
113 <when value="advanced">
114 <conditional name="default_read_group_type">
115 <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group">
116 <option value="default" selected="True">Don't Set</option>
117 <option value="set">Set</option>
118 </param>
119 <when value="default">
120 <!-- do nothing here -->
121 </when>
122 <when value="set">
123 <param name="default_read_group" type="text" value="Unknown" label="If a read has no read group then default to the provided String"/>
124 </when>
125 </conditional>
126 <param name="default_platform" type="select" label="Set default Platform" help="--default_platform">
127 <option value="default" selected="True">Don't Set</option>
128 <option value="illumina">illumina</option>
129 <option value="454">454</option>
130 <option value="solid">solid</option>
131 </param>
132 <conditional name="force_read_group_type">
133 <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group">
134 <option value="default" selected="True">Don't Force</option>
135 <option value="set">Force</option>
136 </param>
137 <when value="default">
138 <!-- do nothing here -->
139 </when>
140 <when value="set">
141 <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."/>
142 </when>
143 </conditional>
144 <param name="force_platform" type="select" label="Force Platform" help="--force_platform">
145 <option value="default" selected="True">Don't Force</option>
146 <option value="illumina">illumina</option>
147 <option value="454">454</option>
148 <option value="solid">solid</option>
149 </param>
150 <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"/>
151 <conditional name="solid_options_type">
152 <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options">
153 <option value="default" selected="True">Don't Set</option>
154 <option value="set">Set</option>
155 </param>
156 <when value="default">
157 <!-- do nothing here -->
158 </when>
159 <when value="set">
160 <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;">
161 <option value="default" selected="True">Don't set</option>
162 <option value="DO_NOTHING">DO_NOTHING</option>
163 <option value="SET_Q_ZERO">SET_Q_ZERO</option>
164 <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option>
165 <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option>
166 </param>
167 <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;">
168 <option value="default" selected="True">Don't set</option>
169 <option value="THROW_EXCEPTION">THROW_EXCEPTION</option>
170 <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option>
171 <option value="PURGE_READ">PURGE_READ</option>
172 </param>
173 </when>
174 </conditional>
175 <param name="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/>
176 <param name="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate" help="--window_size_nqs"/>
177 <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;" />
178 <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 &amp;lt;preserve_qscores_less_than&amp;gt;"/>
179 <param name="smoothing" type="integer" value="1" label="smoothing" help="-sm,--smoothing &amp;lt;smoothing&amp;gt;"/>
180 <param name="max_quality_score" type="integer" value="50" label="Max quality score" help="-maxQ,--max_quality_score &amp;lt;max_quality_score&amp;gt;"/>
181 <param name="do_not_write_original_quals" type="boolean" checked="False" truevalue="--doNotWriteOriginalQuals" falsevalue="" label="Do Not Write Original Quality tag" help="-noOQs,--doNotWriteOriginalQuals"/>
182 </when>
183 </conditional>
184 </inputs>
185 <outputs>
186 <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (BAM)" />
187 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
188 </outputs>
189 <tests>
190 <test>
191 <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" />
192 <param name="reference_source_selector" value="history" />
193 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
194 <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" />
195 <param name="gatk_param_type_selector" value="basic" />
196 <param name="analysis_param_type_selector" value="basic" />
197 <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" />
198 <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" />
199 </test>
200 </tests>
201 <help>
202 **What it does**
203
204 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.
205
206 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_PrintReads.html&gt;`_.
207
208 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;`_.
209
210 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
211
212 ------
213
214 **Inputs**
215
216 GenomeAnalysisTK: PrintReads accepts an aligned BAM and a recalibration (gatk_report) input files.
217
218
219 **Outputs**
220
221 The output is in BAM format.
222
223
224 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
225
226 -------
227
228 **Settings**::
229
230 default_read_group If a read has no read group then default to the provided String.
231 default_platform If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid.
232 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.
233 force_platform If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid.
234 window_size_nqs The window size used by MinimumNQSCovariate for its calculation
235 homopolymer_nback The number of previous bases to look at in HomopolymerCovariate
236 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
237 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)
238 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)
239 recal_file Filename for the input covariates table recalibration .gatk_report file
240 out The output BAM file
241 bam_compression Compression level to use for writing BAM files
242 disable_bam_indexing Turn off on-the-fly creation of indices for output BAM files.
243 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
244 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 &lt; 5, since base callers use these values to indicate random or bad bases
245 smoothing Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1
246 max_quality_score The integer value at which to cap the quality scores, default=50
247 doNotWriteOriginalQuals If true, we will not write the original quality (OQ) tag for each read
248
249 @CITATION_SECTION@
250 </help>
251 </tool>