annotate reduce_reads.xml @ 0:340633249b3d draft

Uploaded
author bgruening
date Mon, 02 Dec 2013 06:18:36 -0500
parents
children 8bcc13094767
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
340633249b3d Uploaded
bgruening
parents:
diff changeset
1 <tool id="gatk2_reduce_reads" name="Reduce Reads" version="0.0.7">
340633249b3d Uploaded
bgruening
parents:
diff changeset
2 <description>in BAM files</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 "ReduceReads"
340633249b3d Uploaded
bgruening
parents:
diff changeset
17 -o "${output_bam}"
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 #if str($input_recal) != 'None':
340633249b3d Uploaded
bgruening
parents:
diff changeset
30 --BQSR "${input_recal}"
340633249b3d Uploaded
bgruening
parents:
diff changeset
31 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
32 --disable_bam_indexing
340633249b3d Uploaded
bgruening
parents:
diff changeset
33 '
340633249b3d Uploaded
bgruening
parents:
diff changeset
34 #include source=$standard_gatk_options#
340633249b3d Uploaded
bgruening
parents:
diff changeset
35
340633249b3d Uploaded
bgruening
parents:
diff changeset
36 ##start analysis specific options
340633249b3d Uploaded
bgruening
parents:
diff changeset
37 #if $analysis_param_type.analysis_param_type_selector == "advanced":
340633249b3d Uploaded
bgruening
parents:
diff changeset
38 -p '
340633249b3d Uploaded
bgruening
parents:
diff changeset
39 #if $analysis_param_type.context_size.__str__.strip() != '':
340633249b3d Uploaded
bgruening
parents:
diff changeset
40 --context_size $analysis_param_type.context_size
340633249b3d Uploaded
bgruening
parents:
diff changeset
41 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
42 #if $analysis_param_type.downsample_coverage.__str__.strip() != '':
340633249b3d Uploaded
bgruening
parents:
diff changeset
43 --downsample_coverage $analysis_param_type.downsample_coverage
340633249b3d Uploaded
bgruening
parents:
diff changeset
44 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
45 #if $analysis_param_type.minimum_del_proportion_to_trigger_variant.__str__.strip() != '':
340633249b3d Uploaded
bgruening
parents:
diff changeset
46 --minimum_del_proportion_to_trigger_variant $analysis_param_type.minimum_del_proportion_to_trigger_variant
340633249b3d Uploaded
bgruening
parents:
diff changeset
47 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
48 #if $analysis_param_type.minimum_mapping_quality.__str__.strip() != '':
340633249b3d Uploaded
bgruening
parents:
diff changeset
49 --minimum_mapping_quality $analysis_param_type.minimum_mapping_quality
340633249b3d Uploaded
bgruening
parents:
diff changeset
50 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
51 #if $analysis_param_type.minimum_tail_qualities.__str__.strip() != '':
340633249b3d Uploaded
bgruening
parents:
diff changeset
52 --minimum_tail_qualities $analysis_param_type.minimum_tail_qualities
340633249b3d Uploaded
bgruening
parents:
diff changeset
53 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
54 #if $analysis_param_type.minimum_base_quality_to_consider.__str__.strip() != '':
340633249b3d Uploaded
bgruening
parents:
diff changeset
55 --minimum_base_quality_to_consider $analysis_param_type.minimum_base_quality_to_consider
340633249b3d Uploaded
bgruening
parents:
diff changeset
56 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
57 #if $analysis_param_type.minimum_alt_proportion_to_trigger_variant.__str__.strip() != '':
340633249b3d Uploaded
bgruening
parents:
diff changeset
58 --minimum_alt_proportion_to_trigger_variant $analysis_param_type.minimum_alt_proportion_to_trigger_variant
340633249b3d Uploaded
bgruening
parents:
diff changeset
59 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
60 $analysis_param_type.allow_polyploid_reduction
340633249b3d Uploaded
bgruening
parents:
diff changeset
61 $analysis_param_type.dont_compress_read_names
340633249b3d Uploaded
bgruening
parents:
diff changeset
62 $analysis_param_type.dont_hardclip_low_qual_tails
340633249b3d Uploaded
bgruening
parents:
diff changeset
63 $analysis_param_type.dont_simplify_reads
340633249b3d Uploaded
bgruening
parents:
diff changeset
64 $analysis_param_type.dont_use_softclipped_bases
340633249b3d Uploaded
bgruening
parents:
diff changeset
65 $analysis_param_type.hard_clip_to_interval
340633249b3d Uploaded
bgruening
parents:
diff changeset
66 $analysis_param_type.dont_hardclip_adaptor_sequences
340633249b3d Uploaded
bgruening
parents:
diff changeset
67 '
340633249b3d Uploaded
bgruening
parents:
diff changeset
68 #end if
340633249b3d Uploaded
bgruening
parents:
diff changeset
69 </command>
340633249b3d Uploaded
bgruening
parents:
diff changeset
70 <inputs>
340633249b3d Uploaded
bgruening
parents:
diff changeset
71 <param name="input_recal" type="data" format="csv" optional="true" label="Covariates table recalibration file" help="-BQSR,--BQSR &amp;lt;recal_file&amp;gt;" >
340633249b3d Uploaded
bgruening
parents:
diff changeset
72 <help>The input covariates table file which enables on-the-fly base quality score recalibration.
340633249b3d Uploaded
bgruening
parents:
diff changeset
73 Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool.
340633249b3d Uploaded
bgruening
parents:
diff changeset
74 Please be aware that one should only run recalibration with the covariates file created on the same input bam(s).
340633249b3d Uploaded
bgruening
parents:
diff changeset
75 </help>
340633249b3d Uploaded
bgruening
parents:
diff changeset
76 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
77 <conditional name="reference_source">
340633249b3d Uploaded
bgruening
parents:
diff changeset
78 <expand macro="reference_source_selector_param" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
79 <when value="cached">
340633249b3d Uploaded
bgruening
parents:
diff changeset
80 <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
81 <validator type="unspecified_build" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
82 <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
83 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
84 <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
85 <options from_data_table="gatk2_picard_indexes">
340633249b3d Uploaded
bgruening
parents:
diff changeset
86 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
87 </options>
340633249b3d Uploaded
bgruening
parents:
diff changeset
88 <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
89 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
90 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
91 <when value="history">
340633249b3d Uploaded
bgruening
parents:
diff changeset
92 <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
93 <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
94 <options>
340633249b3d Uploaded
bgruening
parents:
diff changeset
95 <filter type="data_meta" key="dbkey" ref="input_bam" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
96 </options>
340633249b3d Uploaded
bgruening
parents:
diff changeset
97 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
98 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
99 </conditional>
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 <conditional name="analysis_param_type">
340633249b3d Uploaded
bgruening
parents:
diff changeset
104 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
340633249b3d Uploaded
bgruening
parents:
diff changeset
105 <option value="basic" selected="True">Basic</option>
340633249b3d Uploaded
bgruening
parents:
diff changeset
106 <option value="advanced">Advanced</option>
340633249b3d Uploaded
bgruening
parents:
diff changeset
107 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
108 <when value="basic">
340633249b3d Uploaded
bgruening
parents:
diff changeset
109 <!-- Do nothing here -->
340633249b3d Uploaded
bgruening
parents:
diff changeset
110 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
111 <when value="advanced">
340633249b3d Uploaded
bgruening
parents:
diff changeset
112 <param name="allow_polyploid_reduction" type="boolean" checked="False" truevalue="-polyploid" falsevalue="" label="Allow polyploid-based reduction" help="--allow_polyploid_reduction / -polyploid Allow the experimental polyploid-based reduction capabilities"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
113 <param name="context_size" type="integer" value="10" optional="true" label="context_size" help="The number of bases to keep around mismatches (potential variation)">
340633249b3d Uploaded
bgruening
parents:
diff changeset
114 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
115 <param name="dont_compress_read_names" type="boolean" checked="False" truevalue="-nocmp_names" falsevalue="" label="Do not compress read names." help="--dont_compress_read_names / -nocmp_names By default, ReduceReads will compress read names to numbers and guarantee uniqueness and reads with similar name will still have similar compressed names. Note: If you scatter/gather there is no guarantee that read name uniqueness will be maintained -- in this case we recommend not compressing."/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
116 <param name="dont_hardclip_low_qual_tails" type="boolean" checked="False" truevalue="-noclip_tail" falsevalue="" label="Do not hard clip the low quality tails of the reads" help="--dont_hardclip_low_qual_tails / -noclip_tail This option overrides the argument of minimum tail quality"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
117
340633249b3d Uploaded
bgruening
parents:
diff changeset
118 <param name="dont_simplify_reads" type="boolean" checked="False" truevalue="-nosimplify" falsevalue="" label="Do not simplify read" help="--dont_simplify_reads / -nosimplify Do not simplify read (strip away all extra information of the read -- anything other than bases, quals and read group)."/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
119 <param name="dont_use_softclipped_bases" type="boolean" checked="False" truevalue="-no_soft" falsevalue="" label="Do not use high quality soft-clipped bases" help="--dont_use_softclipped_bases / -no_soft Do not use high quality soft-clipped bases. By default, ReduceReads will hard clip away any low quality soft clipped base left by the aligner and use the high quality soft clipped bases in it's traversal algorithm to identify variant regions. The minimum quality for soft clipped bases is the same as the minimum base quality to consider (minqual)"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
120 <param name="downsample_coverage" type="integer" value="250" optional="true" label="Downsample the coverage of a variable region" help="Downsamples the coverage of a variable region approximately (guarantees the minimum to be equal to this). A value of 0 turns downsampling off.">
340633249b3d Uploaded
bgruening
parents:
diff changeset
121 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
122 <param name="hard_clip_to_interval" type="boolean" checked="False" truevalue="-clip_int" falsevalue="" label="Hard clip all incoming reads" help="--hard_clip_to_interval / -clip_int Optionally hard clip all incoming reads to the desired intervals. The hard clips will happen exactly at the interval border."/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
123 <param name="minimum_del_proportion_to_trigger_variant" type="float" value="0.05" optional="true" label="Minimum proportion of indels in a site to trigger a variant region" help="--minimum_del_proportion_to_trigger_variant / -mindel Minimum proportion of indels in a site to trigger a variant region. Anything below this will be considered consensus. ">
340633249b3d Uploaded
bgruening
parents:
diff changeset
124 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
125 <param name="minimum_mapping_quality" type="integer" value="20" optional="true" label="Minimum mapping quality for consensus read" help="--minimum_mapping_quality / -minmap The minimum mapping quality to be considered for the consensus synthetic read. Reads that have mapping quality below this threshold will not be counted towards consensus, but are still counted towards variable regions.">
340633249b3d Uploaded
bgruening
parents:
diff changeset
126 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
127 <param name="minimum_tail_qualities" type="integer" value="2" optional="true" label="Minimum tail quality" help="--minimum_tail_qualities / -mintail Reads have notoriously low quality bases on the tails (left and right). Consecutive bases with quality lower than this threshold will be hard clipped off before entering the reduce reads algorithm.">
340633249b3d Uploaded
bgruening
parents:
diff changeset
128 <validator type="in_range" message="value between 0 and 127" min="0" max="127"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
129 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
130 <param name="minimum_base_quality_to_consider" type="integer" value="20" optional="true" label="Minimum mapping quality for consensus read" help="--minimum_mapping_quality / -minmap The minimum mapping quality to be considered for the consensus synthetic read. Reads that have mapping quality below this threshold will not be counted towards consensus, but are still counted towards variable regions.">
340633249b3d Uploaded
bgruening
parents:
diff changeset
131 <validator type="in_range" message="value between 0 and 127" min="0" max="127"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
132 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
133 <param name="minimum_alt_proportion_to_trigger_variant" type="float" value="0.05" optional="true" label="Minimum proportion of mismatches in a site to trigger a variant region" help="--minimum_alt_proportion_to_trigger_variant / -minvar Minimum proportion of mismatches in a site to trigger a variant region. Anything below this will be considered consensus.">
340633249b3d Uploaded
bgruening
parents:
diff changeset
134 <validator type="in_range" message="value between 0.00 and 1.00" min="0.0" max="1.0"/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
135 </param>
340633249b3d Uploaded
bgruening
parents:
diff changeset
136 <param name="dont_hardclip_adaptor_sequences" type="boolean" checked="False" truevalue="-noclip_ad" falsevalue="" label="Do not hard clip adaptor sequences" help="--dont_hardclip_adaptor_sequences / -noclip_ad Do not hard clip adaptor sequences. Note: You don't have to turn this on for reads that are not mate paired. The program will behave correctly in those cases."/>
340633249b3d Uploaded
bgruening
parents:
diff changeset
137 </when>
340633249b3d Uploaded
bgruening
parents:
diff changeset
138 </conditional>
340633249b3d Uploaded
bgruening
parents:
diff changeset
139 </inputs>
340633249b3d Uploaded
bgruening
parents:
diff changeset
140 <outputs>
340633249b3d Uploaded
bgruening
parents:
diff changeset
141 <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (BAM)" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
142 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
143 </outputs>
340633249b3d Uploaded
bgruening
parents:
diff changeset
144 <tests>
340633249b3d Uploaded
bgruening
parents:
diff changeset
145 <test>
340633249b3d Uploaded
bgruening
parents:
diff changeset
146 <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
147 <param name="reference_source_selector" value="history" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
148 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
149 <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
150 <param name="gatk_param_type_selector" value="basic" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
151 <param name="analysis_param_type_selector" value="basic" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
152 <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
153 <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" />
340633249b3d Uploaded
bgruening
parents:
diff changeset
154 </test>
340633249b3d Uploaded
bgruening
parents:
diff changeset
155 </tests>
340633249b3d Uploaded
bgruening
parents:
diff changeset
156 <help>
340633249b3d Uploaded
bgruening
parents:
diff changeset
157 **What it does**
340633249b3d Uploaded
bgruening
parents:
diff changeset
158
340633249b3d Uploaded
bgruening
parents:
diff changeset
159 ReduceReads
340633249b3d Uploaded
bgruening
parents:
diff changeset
160 Reduces the BAM file using read based compression that keeps only essential information for variant calling
340633249b3d Uploaded
bgruening
parents:
diff changeset
161
340633249b3d Uploaded
bgruening
parents:
diff changeset
162 This walker will generated reduced versions of the BAM files that still follow the BAM spec and contain all the information necessary for the GSA variant calling pipeline. Some options allow you to tune in how much compression you want to achieve. The default values have been shown to reduce a typical whole exome BAM file 100x. The higher the coverage, the bigger the savings in file size and performance of the downstream tools.
340633249b3d Uploaded
bgruening
parents:
diff changeset
163
340633249b3d Uploaded
bgruening
parents:
diff changeset
164 For more information on using read based compression in the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_compression_reducereads_ReduceReads.html&gt;`_.
340633249b3d Uploaded
bgruening
parents:
diff changeset
165
340633249b3d Uploaded
bgruening
parents:
diff changeset
166 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
167
340633249b3d Uploaded
bgruening
parents:
diff changeset
168 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
169
340633249b3d Uploaded
bgruening
parents:
diff changeset
170 ------
340633249b3d Uploaded
bgruening
parents:
diff changeset
171
340633249b3d Uploaded
bgruening
parents:
diff changeset
172 **Inputs**
340633249b3d Uploaded
bgruening
parents:
diff changeset
173
340633249b3d Uploaded
bgruening
parents:
diff changeset
174 GenomeAnalysisTK: PrintReads accepts an aligned BAM and a recalibration CSV input files.
340633249b3d Uploaded
bgruening
parents:
diff changeset
175
340633249b3d Uploaded
bgruening
parents:
diff changeset
176
340633249b3d Uploaded
bgruening
parents:
diff changeset
177 **Outputs**
340633249b3d Uploaded
bgruening
parents:
diff changeset
178
340633249b3d Uploaded
bgruening
parents:
diff changeset
179 The output is in BAM format.
340633249b3d Uploaded
bgruening
parents:
diff changeset
180
340633249b3d Uploaded
bgruening
parents:
diff changeset
181
340633249b3d Uploaded
bgruening
parents:
diff changeset
182 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
183
340633249b3d Uploaded
bgruening
parents:
diff changeset
184 -------
340633249b3d Uploaded
bgruening
parents:
diff changeset
185
340633249b3d Uploaded
bgruening
parents:
diff changeset
186 **Settings**::
340633249b3d Uploaded
bgruening
parents:
diff changeset
187
340633249b3d Uploaded
bgruening
parents:
diff changeset
188
340633249b3d Uploaded
bgruening
parents:
diff changeset
189 --allow_polyploid_reduction / -polyploid ( boolean with default value false )
340633249b3d Uploaded
bgruening
parents:
diff changeset
190 Allow the experimental polyploid-based reduction capabilities of this tool
340633249b3d Uploaded
bgruening
parents:
diff changeset
191
340633249b3d Uploaded
bgruening
parents:
diff changeset
192 --context_size / -cs ( int with default value 10 )
340633249b3d Uploaded
bgruening
parents:
diff changeset
193 The number of bases to keep around mismatches (potential variation)
340633249b3d Uploaded
bgruening
parents:
diff changeset
194
340633249b3d Uploaded
bgruening
parents:
diff changeset
195 --dont_compress_read_names / -nocmp_names ( boolean with default value false )
340633249b3d Uploaded
bgruening
parents:
diff changeset
196 Do not compress read names. By default, ReduceReads will compress read names to numbers and guarantee uniqueness and reads with similar name will still have similar compressed names. Note: If you scatter/gather there is no guarantee that read name uniqueness will be maintained -- in this case we recommend not compressing.
340633249b3d Uploaded
bgruening
parents:
diff changeset
197
340633249b3d Uploaded
bgruening
parents:
diff changeset
198 --dont_hardclip_low_qual_tails / -noclip_tail ( boolean with default value false )
340633249b3d Uploaded
bgruening
parents:
diff changeset
199 Do not hard clip the low quality tails of the reads. This option overrides the argument of minimum tail quality.
340633249b3d Uploaded
bgruening
parents:
diff changeset
200
340633249b3d Uploaded
bgruening
parents:
diff changeset
201 --dont_simplify_reads / -nosimplify ( boolean with default value false )
340633249b3d Uploaded
bgruening
parents:
diff changeset
202 Do not simplify read (strip away all extra information of the read -- anything other than bases, quals and read group).
340633249b3d Uploaded
bgruening
parents:
diff changeset
203
340633249b3d Uploaded
bgruening
parents:
diff changeset
204 --dont_use_softclipped_bases / -no_soft ( boolean with default value false )
340633249b3d Uploaded
bgruening
parents:
diff changeset
205 Do not use high quality soft-clipped bases. By default, ReduceReads will hard clip away any low quality soft clipped base left by the aligner and use the high quality soft clipped bases in it's traversal algorithm to identify variant regions. The minimum quality for soft clipped bases is the same as the minimum base quality to consider (minqual)
340633249b3d Uploaded
bgruening
parents:
diff changeset
206
340633249b3d Uploaded
bgruening
parents:
diff changeset
207 --downsample_coverage / -ds ( int with default value 250 )
340633249b3d Uploaded
bgruening
parents:
diff changeset
208 Downsamples the coverage of a variable region approximately (guarantees the minimum to be equal to this). A value of 0 turns downsampling off.
340633249b3d Uploaded
bgruening
parents:
diff changeset
209
340633249b3d Uploaded
bgruening
parents:
diff changeset
210 --hard_clip_to_interval / -clip_int ( boolean with default value false )
340633249b3d Uploaded
bgruening
parents:
diff changeset
211 Optionally hard clip all incoming reads to the desired intervals. The hard clips will happen exactly at the interval border.
340633249b3d Uploaded
bgruening
parents:
diff changeset
212
340633249b3d Uploaded
bgruening
parents:
diff changeset
213 -mindel / --minimum_del_proportion_to_trigger_variant ( double with default value 0.05 )
340633249b3d Uploaded
bgruening
parents:
diff changeset
214 Minimum proportion of indels in a site to trigger a variant region. Anything below this will be considered consensus.
340633249b3d Uploaded
bgruening
parents:
diff changeset
215
340633249b3d Uploaded
bgruening
parents:
diff changeset
216 --minimum_mapping_quality / -minmap ( int with default value 20 )
340633249b3d Uploaded
bgruening
parents:
diff changeset
217 The minimum mapping quality to be considered for the consensus synthetic read. Reads that have mapping quality below this threshold will not be counted towards consensus, but are still counted towards variable regions.
340633249b3d Uploaded
bgruening
parents:
diff changeset
218
340633249b3d Uploaded
bgruening
parents:
diff changeset
219 --minimum_tail_qualities / -mintail ( byte with default value 2 )
340633249b3d Uploaded
bgruening
parents:
diff changeset
220 Reads have notoriously low quality bases on the tails (left and right). Consecutive bases with quality lower than this threshold will be hard clipped off before entering the reduce reads algorithm.
340633249b3d Uploaded
bgruening
parents:
diff changeset
221
340633249b3d Uploaded
bgruening
parents:
diff changeset
222 -minqual / --minimum_base_quality_to_consider ( byte with default value 20 )
340633249b3d Uploaded
bgruening
parents:
diff changeset
223 The minimum base quality to be considered for the consensus synthetic read. Reads that have base quality below this threshold will not be counted towards consensus, but are still counted towards variable regions.
340633249b3d Uploaded
bgruening
parents:
diff changeset
224
340633249b3d Uploaded
bgruening
parents:
diff changeset
225 -minvar / --minimum_alt_proportion_to_trigger_variant ( double with default value 0.05 )
340633249b3d Uploaded
bgruening
parents:
diff changeset
226 Minimum proportion of mismatches in a site to trigger a variant region. Anything below this will be considered consensus.
340633249b3d Uploaded
bgruening
parents:
diff changeset
227
340633249b3d Uploaded
bgruening
parents:
diff changeset
228 -noclip_ad / --dont_hardclip_adaptor_sequences ( boolean with default value false )
340633249b3d Uploaded
bgruening
parents:
diff changeset
229 Do not hard clip adaptor sequences. Note: You don't have to turn this on for reads that are not mate paired. The program will behave correctly in those cases.
340633249b3d Uploaded
bgruening
parents:
diff changeset
230
340633249b3d Uploaded
bgruening
parents:
diff changeset
231 ------
340633249b3d Uploaded
bgruening
parents:
diff changeset
232
340633249b3d Uploaded
bgruening
parents:
diff changeset
233 @CITATION_SECTION@
340633249b3d Uploaded
bgruening
parents:
diff changeset
234 </help>
340633249b3d Uploaded
bgruening
parents:
diff changeset
235 </tool>