annotate realigner_target_creator.xml @ 1:f760c0de8e3a draft

Uploaded
author bgruening
date Mon, 02 Dec 2013 10:36:02 -0500
parents 340633249b3d
children f244b8209eb8
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
340633249b3d Uploaded
bgruening
parents:
diff changeset
1 <tool id="gatk2_realigner_target_creator" name="Realigner Target Creator" version="0.0.7">
340633249b3d Uploaded
bgruening
parents:
diff changeset
2 <description>for use in local realignment</description>
340633249b3d Uploaded
bgruening
parents:
diff changeset
3 <expand macro="requirements" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
4 <macros>
340633249b3d Uploaded
bgruening
parents:
diff changeset
5 <import>gatk2_macros.xml</import>
340633249b3d Uploaded
bgruening
parents:
diff changeset
6 </macros>
340633249b3d Uploaded
bgruening
parents:
diff changeset
7 <command interpreter="python">
340633249b3d Uploaded
bgruening
parents:
diff changeset
8 gatk2_wrapper.py
340633249b3d Uploaded
bgruening
parents:
diff changeset
9 --stdout "${output_log}"
340633249b3d Uploaded
bgruening
parents:
diff changeset
10 -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
340633249b3d Uploaded
bgruening
parents:
diff changeset
11 #if str( $reference_source.input_bam.metadata.bam_index ) != "None":
340633249b3d Uploaded
bgruening
parents:
diff changeset
12 -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
340633249b3d Uploaded
bgruening
parents:
diff changeset
13 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
14 -p '
340633249b3d Uploaded
bgruening
parents:
diff changeset
15 @JAR_PATH@
340633249b3d Uploaded
bgruening
parents:
diff changeset
16 -T "RealignerTargetCreator"
340633249b3d Uploaded
bgruening
parents:
diff changeset
17 -o "${output_interval}"
340633249b3d Uploaded
bgruening
parents:
diff changeset
18
340633249b3d Uploaded
bgruening
parents:
diff changeset
19 \$GATK2_SITE_OPTIONS
340633249b3d Uploaded
bgruening
parents:
diff changeset
20
340633249b3d Uploaded
bgruening
parents:
diff changeset
21 ## according to http://www.broadinstitute.org/gatk/guide/article?id=1975
340633249b3d Uploaded
bgruening
parents:
diff changeset
22 --num_cpu_threads_per_data_thread 1
340633249b3d Uploaded
bgruening
parents:
diff changeset
23
340633249b3d Uploaded
bgruening
parents:
diff changeset
24 @THREADS@
340633249b3d Uploaded
bgruening
parents:
diff changeset
25
340633249b3d Uploaded
bgruening
parents:
diff changeset
26 #if $reference_source.reference_source_selector != "history":
340633249b3d Uploaded
bgruening
parents:
diff changeset
27 -R "${reference_source.ref_file.fields.path}"
340633249b3d Uploaded
bgruening
parents:
diff changeset
28 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
29 '
340633249b3d Uploaded
bgruening
parents:
diff changeset
30 #set $rod_binding_names = dict()
340633249b3d Uploaded
bgruening
parents:
diff changeset
31 #for $rod_binding in $rod_bind:
340633249b3d Uploaded
bgruening
parents:
diff changeset
32 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
340633249b3d Uploaded
bgruening
parents:
diff changeset
33 #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
340633249b3d Uploaded
bgruening
parents:
diff changeset
34 #else
340633249b3d Uploaded
bgruening
parents:
diff changeset
35 #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
340633249b3d Uploaded
bgruening
parents:
diff changeset
36 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
37 #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
340633249b3d Uploaded
bgruening
parents:
diff changeset
38 -d "-known:${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[$rod_bind_name]}"
340633249b3d Uploaded
bgruening
parents:
diff changeset
39 #end for
340633249b3d Uploaded
bgruening
parents:
diff changeset
40
340633249b3d Uploaded
bgruening
parents:
diff changeset
41 #include source=$standard_gatk_options#
340633249b3d Uploaded
bgruening
parents:
diff changeset
42 ##start analysis specific options
340633249b3d Uploaded
bgruening
parents:
diff changeset
43 #if $analysis_param_type.analysis_param_type_selector == "advanced":
340633249b3d Uploaded
bgruening
parents:
diff changeset
44 -p '
340633249b3d Uploaded
bgruening
parents:
diff changeset
45 --minReadsAtLocus "${analysis_param_type.minReadsAtLocus}"
340633249b3d Uploaded
bgruening
parents:
diff changeset
46 --windowSize "${analysis_param_type.windowSize}"
340633249b3d Uploaded
bgruening
parents:
diff changeset
47 --mismatchFraction "${analysis_param_type.mismatchFraction}"
340633249b3d Uploaded
bgruening
parents:
diff changeset
48 --maxIntervalSize "${analysis_param_type.maxIntervalSize}"
340633249b3d Uploaded
bgruening
parents:
diff changeset
49 '
340633249b3d Uploaded
bgruening
parents:
diff changeset
50 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
51 </command>
340633249b3d Uploaded
bgruening
parents:
diff changeset
52 <inputs>
340633249b3d Uploaded
bgruening
parents:
diff changeset
53 <conditional name="reference_source">
340633249b3d Uploaded
bgruening
parents:
diff changeset
54 <expand macro="reference_source_selector_param" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
55 <when value="cached">
340633249b3d Uploaded
bgruening
parents:
diff changeset
56 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;">
340633249b3d Uploaded
bgruening
parents:
diff changeset
57 <validator type="unspecified_build" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
58 <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 -->
340633249b3d Uploaded
bgruening
parents:
diff changeset
59 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
60 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" >
340633249b3d Uploaded
bgruening
parents:
diff changeset
61 <options from_data_table="gatk2_picard_indexes">
340633249b3d Uploaded
bgruening
parents:
diff changeset
62 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
63 </options>
340633249b3d Uploaded
bgruening
parents:
diff changeset
64 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
65 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
66 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
67 <when value="history">
340633249b3d Uploaded
bgruening
parents:
diff changeset
68 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
69 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
340633249b3d Uploaded
bgruening
parents:
diff changeset
70 <options>
340633249b3d Uploaded
bgruening
parents:
diff changeset
71 <filter type="data_meta" key="dbkey" ref="input_bam" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
72 </options>
340633249b3d Uploaded
bgruening
parents:
diff changeset
73 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
74 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
75 </conditional>
340633249b3d Uploaded
bgruening
parents:
diff changeset
76
340633249b3d Uploaded
bgruening
parents:
diff changeset
77 <repeat name="rod_bind" title="Known Variants" help="Using data sets of known variants (-known,--known &amp;lt;known&amp;gt;)">
340633249b3d Uploaded
bgruening
parents:
diff changeset
78 <conditional name="rod_bind_type">
340633249b3d Uploaded
bgruening
parents:
diff changeset
79 <param name="rod_bind_type_selector" type="select" label="Variant Type">
340633249b3d Uploaded
bgruening
parents:
diff changeset
80 <option value="dbsnp" selected="True">dbSNP</option>
340633249b3d Uploaded
bgruening
parents:
diff changeset
81 <option value="snps">SNPs</option>
340633249b3d Uploaded
bgruening
parents:
diff changeset
82 <option value="indels">INDELs</option>
340633249b3d Uploaded
bgruening
parents:
diff changeset
83 <option value="custom">Custom</option>
340633249b3d Uploaded
bgruening
parents:
diff changeset
84 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
85 <when value="dbsnp">
340633249b3d Uploaded
bgruening
parents:
diff changeset
86 <param name="input_rod" type="data" format="vcf" label="Variant file (VCF format)" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
87 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
88 <when value="snps">
340633249b3d Uploaded
bgruening
parents:
diff changeset
89 <param name="input_rod" type="data" format="vcf" label="Variant file (VCF format)" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
90 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
91 <when value="indels">
340633249b3d Uploaded
bgruening
parents:
diff changeset
92 <param name="input_rod" type="data" format="vcf" label="Variant file (VCF format)" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
93 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
94 <when value="custom">
340633249b3d Uploaded
bgruening
parents:
diff changeset
95 <param name="custom_rod_name" type="text" value="Unknown" label="Customer's variant file" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
96 <param name="input_rod" type="data" format="vcf" label="Variant file (VCF format)" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
97 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
98 </conditional>
340633249b3d Uploaded
bgruening
parents:
diff changeset
99 </repeat>
340633249b3d Uploaded
bgruening
parents:
diff changeset
100
340633249b3d Uploaded
bgruening
parents:
diff changeset
101 <expand macro="gatk_param_type_conditional" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
102
340633249b3d Uploaded
bgruening
parents:
diff changeset
103 <expand macro="analysis_type_conditional">
340633249b3d Uploaded
bgruening
parents:
diff changeset
104 <param name="windowSize" type="integer" value="10" label="Window size for calculating entropy or SNP clusters (windowSize)" help="-window,--windowSize &amp;lt;windowSize&amp;gt;" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
105 <param name="mismatchFraction" type="float" value="0.15" label="Fraction of base qualities needing to mismatch for a position to have high entropy (mismatchFraction)" help="to disable set to &lt;= 0 or &gt; 1 (-mismatch,--mismatchFraction &amp;lt;mismatchFraction&amp;gt;)"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
106 <param name="minReadsAtLocus" type="integer" value="4" label="Minimum reads at a locus to enable using the entropy calculation (minReadsAtLocus)" help="-minReads,--minReadsAtLocus &amp;lt;minReadsAtLocus&amp;gt;" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
107 <param name="maxIntervalSize" type="integer" value="500" label="Maximum interval size" help="-maxInterval,--maxIntervalSize &amp;lt;maxIntervalSize&amp;gt;" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
108 </expand>
340633249b3d Uploaded
bgruening
parents:
diff changeset
109 </inputs>
340633249b3d Uploaded
bgruening
parents:
diff changeset
110 <outputs>
340633249b3d Uploaded
bgruening
parents:
diff changeset
111 <data format="gatk_interval" name="output_interval" label="${tool.name} on ${on_string} (GATK intervals)" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
112 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
113 </outputs>
340633249b3d Uploaded
bgruening
parents:
diff changeset
114 <tests>
340633249b3d Uploaded
bgruening
parents:
diff changeset
115 <test>
340633249b3d Uploaded
bgruening
parents:
diff changeset
116 <param name="reference_source_selector" value="history" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
117 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
118 <param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
119 <param name="rod_bind_type_selector" value="dbsnp" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
120 <param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
121 <param name="gatk_param_type_selector" value="basic" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
122 <param name="analysis_param_type_selector" value="advanced" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
123 <param name="windowSize" value="10" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
124 <param name="mismatchFraction" value="0.15" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
125 <param name="minReadsAtLocus" value="4" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
126 <param name="maxIntervalSize" value="500" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
127 <output name="output_interval" file="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.gatk_interval" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
128 <output name="output_log" file="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.log.contains" compare="contains"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
129 </test>
340633249b3d Uploaded
bgruening
parents:
diff changeset
130 </tests>
340633249b3d Uploaded
bgruening
parents:
diff changeset
131 <help>
340633249b3d Uploaded
bgruening
parents:
diff changeset
132 **What it does**
340633249b3d Uploaded
bgruening
parents:
diff changeset
133
340633249b3d Uploaded
bgruening
parents:
diff changeset
134 Emits intervals for the Local Indel Realigner to target for cleaning. Ignores 454 reads, MQ0 reads, and reads with consecutive indel operators in the CIGAR string.
340633249b3d Uploaded
bgruening
parents:
diff changeset
135
340633249b3d Uploaded
bgruening
parents:
diff changeset
136 For more information on local realignment around indels using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_indels_RealignerTargetCreator.html&gt;`_.
340633249b3d Uploaded
bgruening
parents:
diff changeset
137
340633249b3d Uploaded
bgruening
parents:
diff changeset
138 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;`_.
340633249b3d Uploaded
bgruening
parents:
diff changeset
139
340633249b3d Uploaded
bgruening
parents:
diff changeset
140 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
340633249b3d Uploaded
bgruening
parents:
diff changeset
141
340633249b3d Uploaded
bgruening
parents:
diff changeset
142 ------
340633249b3d Uploaded
bgruening
parents:
diff changeset
143
340633249b3d Uploaded
bgruening
parents:
diff changeset
144 **Inputs**
340633249b3d Uploaded
bgruening
parents:
diff changeset
145
340633249b3d Uploaded
bgruening
parents:
diff changeset
146 GenomeAnalysisTK: RealignerTargetCreator accepts an aligned BAM input file.
340633249b3d Uploaded
bgruening
parents:
diff changeset
147
340633249b3d Uploaded
bgruening
parents:
diff changeset
148
340633249b3d Uploaded
bgruening
parents:
diff changeset
149 **Outputs**
340633249b3d Uploaded
bgruening
parents:
diff changeset
150
340633249b3d Uploaded
bgruening
parents:
diff changeset
151 The output is in GATK Interval format.
340633249b3d Uploaded
bgruening
parents:
diff changeset
152
340633249b3d Uploaded
bgruening
parents:
diff changeset
153
340633249b3d Uploaded
bgruening
parents:
diff changeset
154 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
340633249b3d Uploaded
bgruening
parents:
diff changeset
155
340633249b3d Uploaded
bgruening
parents:
diff changeset
156 -------
340633249b3d Uploaded
bgruening
parents:
diff changeset
157
340633249b3d Uploaded
bgruening
parents:
diff changeset
158 **Settings**::
340633249b3d Uploaded
bgruening
parents:
diff changeset
159
340633249b3d Uploaded
bgruening
parents:
diff changeset
160 windowSize window size for calculating entropy or SNP clusters
340633249b3d Uploaded
bgruening
parents:
diff changeset
161 mismatchFraction fraction of base qualities needing to mismatch for a position to have high entropy; to disable set to &lt;= 0 or &gt; 1
340633249b3d Uploaded
bgruening
parents:
diff changeset
162 minReadsAtLocus minimum reads at a locus to enable using the entropy calculation
340633249b3d Uploaded
bgruening
parents:
diff changeset
163 maxIntervalSize maximum interval size
340633249b3d Uploaded
bgruening
parents:
diff changeset
164
340633249b3d Uploaded
bgruening
parents:
diff changeset
165 @CITATION_SECTION@
340633249b3d Uploaded
bgruening
parents:
diff changeset
166 </help>
340633249b3d Uploaded
bgruening
parents:
diff changeset
167 </tool>