annotate reduce_reads.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_reduce_reads" name="Reduce Reads" version="@VERSION@.0">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
2 <description>in BAM files</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 "${output_log}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
11 -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
12 #if str( $reference_source.input_bam.metadata.bam_index ) != "None":
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
13 -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
14 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
15 -p '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
16 @JAR_PATH@
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
17 -T "ReduceReads"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
18 -o "${output_bam}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
19
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
20 \$GATK2_SITE_OPTIONS
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
21
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
22 ## according to http://www.broadinstitute.org/gatk/guide/article?id=1975
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
23 --num_cpu_threads_per_data_thread 1
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
24
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
25 #if $reference_source.reference_source_selector != "history":
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
26 -R "${reference_source.ref_file.fields.path}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
27 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
28 #if str($input_recal) != 'None':
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
29 --BQSR "${input_recal}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
30 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
31 --disable_bam_indexing
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
32 '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
33 #include source=$standard_gatk_options#
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
34
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
35 ##start analysis specific options
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
36 #if $analysis_param_type.analysis_param_type_selector == "advanced":
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
37 -p '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
38 #if $analysis_param_type.context_size.__str__.strip() != '':
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
39 --context_size $analysis_param_type.context_size
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
40 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
41 #if $analysis_param_type.downsample_coverage.__str__.strip() != '':
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
42 --downsample_coverage $analysis_param_type.downsample_coverage
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
43 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
44 #if $analysis_param_type.minimum_del_proportion_to_trigger_variant.__str__.strip() != '':
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
45 --minimum_del_proportion_to_trigger_variant $analysis_param_type.minimum_del_proportion_to_trigger_variant
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
46 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
47 #if $analysis_param_type.minimum_mapping_quality.__str__.strip() != '':
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
48 --minimum_mapping_quality $analysis_param_type.minimum_mapping_quality
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
49 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
50 #if $analysis_param_type.minimum_tail_qualities.__str__.strip() != '':
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
51 --minimum_tail_qualities $analysis_param_type.minimum_tail_qualities
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
52 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
53 #if $analysis_param_type.minimum_base_quality_to_consider.__str__.strip() != '':
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
54 --minimum_base_quality_to_consider $analysis_param_type.minimum_base_quality_to_consider
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
55 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
56 #if $analysis_param_type.minimum_alt_proportion_to_trigger_variant.__str__.strip() != '':
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
57 --minimum_alt_proportion_to_trigger_variant $analysis_param_type.minimum_alt_proportion_to_trigger_variant
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
58 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
59 $analysis_param_type.allow_polyploid_reduction
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
60 $analysis_param_type.dont_compress_read_names
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
61 $analysis_param_type.dont_hardclip_low_qual_tails
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
62 $analysis_param_type.dont_simplify_reads
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
63 $analysis_param_type.dont_use_softclipped_bases
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
64 $analysis_param_type.hard_clip_to_interval
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
65 $analysis_param_type.dont_hardclip_adaptor_sequences
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
66 '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
67 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
68 </command>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
69 <inputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
70 <param name="input_recal" type="data" format="csv" optional="true" label="Covariates table recalibration file" help="The input covariates table file which enables on-the-fly base quality score recalibration. Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool. Please be aware that one should only run recalibration with the covariates file created on the same input bam(s) (-BQSR,--BQSR &amp;lt;recal_file&amp;gt;)" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
71 <conditional name="reference_source">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
72 <expand macro="reference_source_selector_param" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
73 <when value="cached">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
74 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
75 <validator type="unspecified_build" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
76 <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 -->
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
77 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
78 <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
79 <options from_data_table="gatk2_picard_indexes">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
80 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
81 </options>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
82 <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
83 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
84 </when>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
85 <when value="history">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
86 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
87 <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
88 <options>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
89 <filter type="data_meta" key="dbkey" ref="input_bam" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
90 </options>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
91 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
92 </when>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
93 </conditional>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
94
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
95 <expand macro="gatk_param_type_conditional" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
96
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
97 <conditional name="analysis_param_type">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
98 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
99 <option value="basic" selected="True">Basic</option>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
100 <option value="advanced">Advanced</option>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
101 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
102 <when value="basic">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
103 <!-- Do nothing here -->
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
104 </when>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
105 <when value="advanced">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
106 <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"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
107 <param name="context_size" type="integer" value="10" optional="true" label="context_size" help="The number of bases to keep around mismatches (potential variation)">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
108 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
109 <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."/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
110 <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"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
111
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
112 <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)."/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
113 <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)"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
114 <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.">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
115 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
116 <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."/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
117 <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. ">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
118 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
119 <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.">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
120 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
121 <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.">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
122 <validator type="in_range" message="value between 0 and 127" min="0" max="127"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
123 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
124 <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.">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
125 <validator type="in_range" message="value between 0 and 127" min="0" max="127"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
126 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
127 <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.">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
128 <validator type="in_range" message="value between 0.00 and 1.00" min="0.0" max="1.0"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
129 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
130 <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."/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
131 </when>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
132 </conditional>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
133 </inputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
134 <outputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
135 <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (BAM)" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
136 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
137 </outputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
138 <tests>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
139 <test>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
140 <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
141 <param name="reference_source_selector" value="history" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
142 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
143 <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
144 <param name="gatk_param_type_selector" value="basic" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
145 <param name="analysis_param_type_selector" value="basic" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
146 <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
147 <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
148 </test>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
149 </tests>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
150 <help>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
151 **What it does**
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
152
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
153 ReduceReads
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
154 Reduces the BAM file using read based compression that keeps only essential information for variant calling
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
155
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
156 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.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
157
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
158 .. 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;`_.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
159
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
160 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
161
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
162 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
163
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
164 ------
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
165
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
166 **Inputs**
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
167
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
168 GenomeAnalysisTK: PrintReads accepts an aligned BAM and a recalibration CSV input files.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
169
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
170
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
171 **Outputs**
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
172
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
173 The output is in BAM format.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
174
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
175
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
176 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
177
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
178 -------
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
179
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
180 **Settings**::
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
181
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
182
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
183 --allow_polyploid_reduction / -polyploid ( boolean with default value false )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
184 Allow the experimental polyploid-based reduction capabilities of this tool
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
185
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
186 --context_size / -cs ( int with default value 10 )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
187 The number of bases to keep around mismatches (potential variation)
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
188
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
189 --dont_compress_read_names / -nocmp_names ( boolean with default value false )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
190 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.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
191
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
192 --dont_hardclip_low_qual_tails / -noclip_tail ( boolean with default value false )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
193 Do not hard clip the low quality tails of the reads. This option overrides the argument of minimum tail quality.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
194
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
195 --dont_simplify_reads / -nosimplify ( boolean with default value false )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
196 Do not simplify read (strip away all extra information of the read -- anything other than bases, quals and read group).
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
197
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
198 --dont_use_softclipped_bases / -no_soft ( boolean with default value false )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
199 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)
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
200
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
201 --downsample_coverage / -ds ( int with default value 250 )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
202 Downsamples the coverage of a variable region approximately (guarantees the minimum to be equal to this). A value of 0 turns downsampling off.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
203
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
204 --hard_clip_to_interval / -clip_int ( boolean with default value false )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
205 Optionally hard clip all incoming reads to the desired intervals. The hard clips will happen exactly at the interval border.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
206
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
207 -mindel / --minimum_del_proportion_to_trigger_variant ( double with default value 0.05 )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
208 Minimum proportion of indels in a site to trigger a variant region. Anything below this will be considered consensus.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
209
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
210 --minimum_mapping_quality / -minmap ( int with default value 20 )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
211 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.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
212
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
213 --minimum_tail_qualities / -mintail ( byte with default value 2 )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
214 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.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
215
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
216 -minqual / --minimum_base_quality_to_consider ( byte with default value 20 )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
217 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.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
218
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
219 -minvar / --minimum_alt_proportion_to_trigger_variant ( double with default value 0.05 )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
220 Minimum proportion of mismatches in a site to trigger a variant region. Anything below this will be considered consensus.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
221
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
222 -noclip_ad / --dont_hardclip_adaptor_sequences ( boolean with default value false )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
223 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.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
224
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
225 @CITATION_SECTION@
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
226 </help>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
227 <expand macro="citations" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
228 </tool>