annotate variant_apply_recalibration.xml @ 15:01ff8dd37d4d draft default tip

Uploaded
author lz_hust
date Sat, 01 Jun 2019 07:20:41 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
15
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
1 <tool id="gatk2_variant_apply_recalibration" name="Apply Variant Recalibration" version="@VERSION@.1">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
2 <description></description>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
3 <macros>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
4 <import>gatk2_macros.xml</import>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
5 </macros>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
6 <expand macro="requirements" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
7 <expand macro="version_command" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
8 <command interpreter="python">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
9 gatk2_wrapper.py
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
10 --stdout "${output_log}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
11 #for $var_count, $variant in enumerate( $reference_source.input_variants ):
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
12 -d "--input:input_${var_count},%(file_type)s" "${variant}" "${variant.ext}" "input_variants_${var_count}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
13 #end for
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
14 -p '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
15 @JAR_PATH@
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
16 -T "ApplyRecalibration"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
17 \$GATK2_SITE_OPTIONS
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
18
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
19 @THREADS@
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
20
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
21 #if $reference_source.reference_source_selector != "history":
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
22 -R "${reference_source.ref_file.fields.path}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
23 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
24 --recal_file "${reference_source.input_recal}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
25 --tranches_file "${reference_source.input_tranches}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
26 --out "${output_variants}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
27 '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
28
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
29 #include source=$standard_gatk_options#
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
30
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
31 ##start analysis specific options
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
32 -p '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
33 --mode "${mode}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
34
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
35 #for $ignore_filter in $ignore_filters:
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
36 #set $ignore_filter_name = str( $ignore_filter.ignore_filter_type.ignore_filter_type_selector )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
37 #if $ignore_filter_name == "custom":
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
38 #set $ignore_filter_name = str( $ignore_filter.ignore_filter_type.filter_name )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
39 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
40 --ignore_filter "${ignore_filter_name}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
41 #end for
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
42 --ts_filter_level "${ts_filter_level}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
43 '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
44 </command>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
45 <inputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
46 <conditional name="reference_source">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
47 <expand macro="reference_source_selector_param" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
48 <when value="cached">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
49 <expand macro="input_variants" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
50 <param name="input_recal" type="data" format="gatk_recal" label="Variant Recalibration file" help="-recalFile,--recal_file &amp;lt;recal_file&amp;gt;" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
51 <param name="input_tranches" type="data" format="gatk_tranche" label="Variant Tranches file" help="-tranchesFile,--tranches_file &amp;lt;tranches_file&amp;gt;" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
52 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
53 <options from_data_table="gatk2_picard_indexes">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
54 <!-- <filter type="data_meta" key="dbkey" ref="variants[0].input_variants" column="dbkey"/> -->
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
55 </options>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
56 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
57 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
58 </when>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
59 <when value="history"> <!-- FIX ME!!!! -->
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
60 <expand macro="input_variants" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
61 <param name="input_recal" type="data" format="gatk_recal" label="Variant Recalibration file" help="-recalFile,--recal_file &amp;lt;recal_file&amp;gt;" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
62 <param name="input_tranches" type="data" format="gatk_tranche" label="Variant Tranches file" help="-tranchesFile,--tranches_file &amp;lt;tranches_file&amp;gt;" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
63 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
64 </when>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
65 </conditional>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
66
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
67 <expand macro="gatk_param_type_conditional" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
68
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
69 <param name="mode" type="select" label="Recalibration mode" help="-mode,--mode &amp;lt;mode&amp;gt;">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
70 <option value="SNP" selected="True">SNP</option>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
71 <option value="INDEL">INDEL</option>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
72 <option value="BOTH">BOTH</option>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
73 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
74 <repeat name="ignore_filters" title="Ignore Filter" help="-ignoreFilter,--ignore_filter &amp;lt;ignore_filter&amp;gt;">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
75 <conditional name="ignore_filter_type">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
76 <param name="ignore_filter_type_selector" type="select" label="Filter Type">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
77 <option value="HARD_TO_VALIDATE">HARD_TO_VALIDATE</option>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
78 <option value="LowQual" >LowQual</option>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
79 <option value="custom" selected="True">Other</option>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
80 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
81 <when value="custom">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
82 <param name="filter_name" type="text" value="" label="Filter name"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
83 </when>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
84 <when value="HARD_TO_VALIDATE" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
85 <when value="LowQual" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
86 </conditional>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
87 </repeat>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
88 <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 &amp;lt;ts_filter_level&amp;gt;"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
89 </inputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
90 <outputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
91 <data format="vcf" name="output_variants" label="${tool.name} on ${on_string} (Variants File)" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
92 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
93 </outputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
94 <tests>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
95 <!-- ADD TESTS -->
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
96 </tests>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
97 <help>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
98 **What it does**
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
99
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
100 Applies cuts to the input vcf file (by adding filter lines) to achieve the desired novel FDR levels which were specified during VariantRecalibration
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
101
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
102 For more information on using the ApplyRecalibration module, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_variantrecalibration_ApplyRecalibration.html&gt;`_.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
103
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
104 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;`_.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
105
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
106 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
107
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
108 ------
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
109
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
110 **Inputs**
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
111
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
112 GenomeAnalysisTK: ApplyRecalibration accepts a variant input file, a recalibration file and a tranches file.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
113
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
114
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
115 **Outputs**
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
116
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
117 The output is in VCF format.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
118
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
119 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
120
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
121 -------
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
122
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
123 **Settings**::
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
124
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
125
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
126 recal_file The output recal file used by ApplyRecalibration
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
127 tranches_file The input tranches file describing where to cut the data
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
128 out The output filtered, recalibrated VCF file
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
129 ts_filter_level The truth sensitivity level at which to start filtering
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
130 ignore_filter If specified the optimizer will use variants even if the specified filter name is marked in the input VCF file
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
131 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)
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
132
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
133 @CITATION_SECTION@
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
134 </help>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
135 <expand macro="citations" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
136 </tool>