Mercurial > repos > devteam > indel_realigner

comparison indel_realigner.xml @ 0:bb0beda6cf83 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author devteam
date Tue, 01 Apr 2014 10:48:26 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:bb0beda6cf83
1 <tool id="gatk_indel_realigner" name="Indel Realigner" version="0.0.6">
2 <description>- perform local realignment</description>
3 <requirements>
4 <requirement type="package" version="1.4">gatk</requirement>
5 <requirement type="package" version="0.1.18">samtools</requirement>
6 </requirements>
7 <macros>
8 <import>gatk_macros.xml</import>
9 </macros>
10 <command interpreter="python">gatk_wrapper.py
11 --max_jvm_heap_fraction "1"
12 --stdout "${output_log}"
13 -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
14 #if str( $reference_source.input_bam.metadata.bam_index ) != "None":
15 -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
16 #end if
17 -p 'java
18 -jar "\$JAVA_JAR_PATH/GenomeAnalysisTK.jar"
19 -T "IndelRealigner"
20 -o "${output_bam}"
21 -et "NO_ET" ##ET no phone home
22 ##--num_threads 4 ##hard coded, for now
23 ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
24 #if $reference_source.reference_source_selector != "history":
25 -R "${reference_source.ref_file.fields.path}"
26 #end if
27 -LOD "${lod_threshold}"
28 ${knowns_only}
29 '
30
31 #set $rod_binding_names = dict()
32 #for $rod_binding in $rod_bind:
33 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
34 #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
35 #else
36 #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
37 #end if
38 #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
39 -d "-known:${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[$rod_bind_name]}"
40 #end for
41
42 #include source=$standard_gatk_options#
43 ##start analysis specific options
44 -d "-targetIntervals" "${target_intervals}" "${target_intervals.ext}" "gatk_target_intervals"
45 -p '
46 --disable_bam_indexing
47 '
48 #if $analysis_param_type.analysis_param_type_selector == "advanced":
49 -p '
50 --entropyThreshold "${analysis_param_type.entropy_threshold}"
51 ${analysis_param_type.simplify_bam}
52 --consensusDeterminationModel "${analysis_param_type.consensus_determination_model}"
53 --maxIsizeForMovement "${analysis_param_type.max_insert_size_for_movement}"
54 --maxPositionalMoveAllowed "${analysis_param_type.max_positional_move_allowed}"
55 --maxConsensuses "${analysis_param_type.max_consensuses}"
56 --maxReadsForConsensuses "${analysis_param_type.max_reads_for_consensuses}"
57 --maxReadsForRealignment "${analysis_param_type.max_reads_for_realignment}"
58 ${analysis_param_type.no_original_alignment_tags}
59 '
60 #end if
61 </command>
62 <inputs>
63
64 <conditional name="reference_source">
65 <expand macro="reference_source_selector_param" />
66 <when value="cached">
67 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;">
68 <validator type="unspecified_build" />
69 <validator type="dataset_metadata_in_data_table" table_name="gatk_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 -->
70 </param>
71 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" >
72 <options from_data_table="gatk_picard_indexes">
73 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
74 </options>
75 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
76 </param>
77 </when>
78 <when value="history">
79 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;" />
80 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
81 <options>
82 <filter type="data_meta" key="dbkey" ref="input_bam" />
83 </options>
84 </param>
85 </when>
86 </conditional>
87 <param name="target_intervals" type="data" format="gatk_interval,bed,picard_interval_list" label="Restrict realignment to provided intervals" help="-targetIntervals,--targetIntervals &amp;lt;targetIntervals&amp;gt;" />
88 <repeat name="rod_bind" title="Binding for reference-ordered data" help="-known,--knownAlleles &amp;lt;knownAlleles&amp;gt;">
89 <conditional name="rod_bind_type">
90 <param name="rod_bind_type_selector" type="select" label="Binding Type">
91 <option value="dbsnp" selected="True">dbSNP</option>
92 <option value="snps">SNPs</option>
93 <option value="indels">INDELs</option>
94 <option value="custom">Custom</option>
95 </param>
96 <when value="dbsnp">
97 <param name="input_rod" type="data" format="vcf" label="ROD file" />
98 </when>
99 <when value="snps">
100 <param name="input_rod" type="data" format="vcf" label="ROD file" />
101 </when>
102 <when value="indels">
103 <param name="input_rod" type="data" format="vcf" label="ROD file" />
104 </when>
105 <when value="custom">
106 <param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/>
107 <param name="input_rod" type="data" format="vcf" label="ROD file" />
108 </when>
109 </conditional>
110 </repeat>
111 <param name="lod_threshold" type="float" value="5.0" label="LOD threshold above which the realigner will proceed to realign" help="-LOD,--LODThresholdForCleaning &amp;lt;LODThresholdForCleaning&amp;gt;" />
112 <param name="knowns_only" type="boolean" checked="False" truevalue="-knownsOnly" falsevalue="" label="Use only known indels provided as RODs" help="-knownsOnly"/>
113
114 <expand macro="gatk_param_type_conditional" />
115
116 <expand macro="analysis_type_conditional">
117
118 <param name="entropy_threshold" type="float" value="0.15" label="percentage of mismatching base quality scores at a position to be considered having high entropy" help="-entropy,--entropyThreshold &amp;lt;entropyThreshold&amp;gt;" />
119 <param name="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/>
120 <param name="consensus_determination_model" type="select" label="Consensus Determination Model" help="-model,--consensusDeterminationModel &amp;lt;consensusDeterminationModel&amp;gt;">
121 <option value="KNOWNS_ONLY">KNOWNS_ONLY</option>
122 <option value="USE_READS" selected="True">USE_READS</option>
123 <option value="USE_SW">USE_SW</option>
124 </param>
125 <param name="max_insert_size_for_movement" type="integer" value="3000" label="Maximum insert size of read pairs that we attempt to realign" help="-maxIsize,--maxIsizeForMovement &amp;lt;maxIsizeForMovement&amp;gt;" />
126 <param name="max_positional_move_allowed" type="integer" value="200" label="Maximum positional move in basepairs that a read can be adjusted during realignment" help="-maxPosMove,--maxPositionalMoveAllowed &amp;lt;maxPositionalMoveAllowed&amp;gt;" />
127 <param name="max_consensuses" type="integer" value="30" label="Max alternate consensuses to try" help="-maxConsensuses,--maxConsensuses &amp;lt;maxConsensuses&amp;gt;" />
128 <param name="max_reads_for_consensuses" type="integer" value="120" label="Max reads (chosen randomly) used for finding the potential alternate consensuses" help="-greedy,--maxReadsForConsensuses &amp;lt;maxReadsForConsensuses&amp;gt;" />
129 <param name="max_reads_for_realignment" type="integer" value="20000" label="Max reads allowed at an interval for realignment" help="-maxReads,--maxReadsForRealignment &amp;lt;maxReadsForRealignment&amp;gt;" />
130 <param name="no_original_alignment_tags" type="boolean" checked="False" truevalue="--noOriginalAlignmentTags" falsevalue="" label="Don't output the original cigar or alignment start tags for each realigned read in the output bam" help="-noTags,--noOriginalAlignmentTags"/>
131 </expand>
132 </inputs>
133 <outputs>
134 <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (BAM)" />
135 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
136 </outputs>
137 <tests>
138 <test>
139 <param name="reference_source_selector" value="history" />
140 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
141 <param name="target_intervals" value="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.gatk_interval" ftype="gatk_interval" />
142 <param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" />
143 <param name="rod_bind_type_selector" value="snps" />
144 <param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" />
145 <param name="lod_threshold" value="5.0" />
146 <param name="knowns_only" />
147 <param name="gatk_param_type_selector" value="basic" />
148 <param name="analysis_param_type_selector" value="advanced" />
149 <param name="entropy_threshold" value="0.15" />
150 <param name="simplify_bam" />
151 <param name="consensus_determination_model" value="USE_SW" />
152 <param name="max_insert_size_for_movement" value="3000" />
153 <param name="max_positional_move_allowed" value="200" />
154 <param name="max_consensuses" value="30" />
155 <param name="max_reads_for_consensuses" value="120" />
156 <param name="max_reads_for_realignment" value="20000" />
157 <param name="no_original_alignment_tags" />
158 <output name="output_bam" file="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" lines_diff="2" />
159 <output name="output_log" file="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.log.contains" compare="contains" />
160 </test>
161 </tests>
162 <help>
163 **What it does**
164
165 Performs local realignment of reads based on misalignments due to the presence of indels. Unlike most mappers, this walker uses the full alignment context to determine whether an appropriate alternate reference (i.e. indel) exists and updates SAMRecords accordingly.
166
167 For more information on local realignment around indels using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Local_realignment_around_indels&gt;`_.
168
169 To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
170
171 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
172
173 ------
174
175 **Inputs**
176
177 GenomeAnalysisTK: IndelRealigner accepts an aligned BAM and a list of intervals to realign as input files.
178
179
180 **Outputs**
181
182 The output is in the BAM format.
183
184
185 Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
186
187 -------
188
189 **Settings**::
190
191 targetIntervals intervals file output from RealignerTargetCreator
192 LODThresholdForCleaning LOD threshold above which the cleaner will clean
193 entropyThreshold percentage of mismatches at a locus to be considered having high entropy
194 out Output bam
195 bam_compression Compression level to use for writing BAM files
196 disable_bam_indexing Turn off on-the-fly creation of indices for output BAM files.
197 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
198 useOnlyKnownIndels Don't run 'Smith-Waterman' to generate alternate consenses; use only known indels provided as RODs for constructing the alternate references.
199 maxReadsInMemory max reads allowed to be kept in memory at a time by the SAMFileWriter. Keep it low to minimize memory consumption (but the tool may skip realignment on regions with too much coverage. If it is too low, it may generate errors during realignment); keep it high to maximize realignment (but make sure to give Java enough memory).
200 maxIsizeForMovement maximum insert size of read pairs that we attempt to realign
201 maxPositionalMoveAllowed maximum positional move in basepairs that a read can be adjusted during realignment
202 maxConsensuses max alternate consensuses to try (necessary to improve performance in deep coverage)
203 maxReadsForConsensuses max reads used for finding the alternate consensuses (necessary to improve performance in deep coverage)
204 maxReadsForRealignment max reads allowed at an interval for realignment; if this value is exceeded, realignment is not attempted and the reads are passed to the output file(s) as-is
205 noOriginalAlignmentTags Don't output the original cigar or alignment start tags for each realigned read in the output bam.
206
207 @CITATION_SECTION@
208 </help>
209 </tool>