|
0
|
1 <tool id="gatk_analyze_covariates" name="Analyze Covariates" version="0.0.1">
|
|
|
2 <description>- perform local realignment</description>
|
|
|
3 <command interpreter="python">gatk_wrapper.py
|
|
|
4 --stdout "${output_log}"
|
|
|
5 --html_report_from_directory "${output_html}" "${output_html.files_path}"
|
|
|
6 -p 'java
|
|
|
7 -jar "${GALAXY_DATA_INDEX_DIR}/shared/jars/gatk/AnalyzeCovariates.jar"
|
|
|
8 -recalFile "${input_recal}"
|
|
|
9 -outputDir "${output_html.files_path}"
|
|
|
10 ##-log "${output_log}"
|
|
|
11 ##-Rscript,--path_to_Rscript path_to_Rscript; on path is good enough
|
|
|
12 -resources "${GALAXY_DATA_INDEX_DIR}/gatk/R"
|
|
|
13 #if $analysis_param_type.analysis_param_type_selector == "advanced":
|
|
|
14 --ignoreQ "${analysis_param_type.ignore_q}"
|
|
|
15 --numRG "${analysis_param_type.num_read_groups}"
|
|
|
16 --max_quality_score "${analysis_param_type.max_quality_score}"
|
|
|
17 --max_histogram_value "${analysis_param_type.max_histogram_value}"
|
|
|
18 ${analysis_param_type.do_indel_quality}
|
|
|
19 #end if
|
|
|
20 '
|
|
|
21 </command>
|
|
|
22 <inputs>
|
|
|
23 <param name="input_recal" type="data" format="csv" label="Covariates table recalibration file" />
|
|
|
24 <conditional name="analysis_param_type">
|
|
|
25 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced options">
|
|
|
26 <option value="basic" selected="True">Basic</option>
|
|
|
27 <option value="advanced">Advanced</option>
|
|
|
28 </param>
|
|
|
29 <when value="basic">
|
|
|
30 <!-- Do nothing here -->
|
|
|
31 </when>
|
|
|
32 <when value="advanced">
|
|
|
33 <param name="ignore_q" type="integer" value="5" label="Ignore bases with reported quality less than this number."/>
|
|
|
34 <param name="num_read_groups" type="integer" value="-1" label="Only process N read groups."/>
|
|
|
35 <param name="max_quality_score" type="integer" value="50" label="Max quality score"/>
|
|
|
36 <param name="max_histogram_value" type="integer" value="0" label="Max quality score"/>
|
|
|
37 <param name="do_indel_quality" type="boolean" truevalue="--do_indel_quality" falsevalue="" label="Max quality score"/>
|
|
|
38 </when>
|
|
|
39 </conditional>
|
|
|
40 </inputs>
|
|
|
41 <outputs>
|
|
|
42 <data format="html" name="output_html" label="${tool.name} on ${on_string} (HTML)" />
|
|
|
43 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
|
|
|
44 </outputs>
|
|
|
45 <tests>
|
|
|
46 <test>
|
|
|
47 <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" />
|
|
|
48 <param name="analysis_param_type_selector" value="basic" />
|
|
|
49 <output name="output_html" file="gatk/gatk_analyze_covariates/gatk_analyze_covariates_out_1.html" />
|
|
|
50 <output name="output_log" file="gatk/gatk_analyze_covariates/gatk_analyze_covariates_out_1.log.contains" compare="contains" />
|
|
|
51 </test>
|
|
|
52 </tests>
|
|
|
53 <help>
|
|
|
54 **What it does**
|
|
|
55
|
|
|
56 Create collapsed versions of the recal csv file and call R scripts to plot residual error versus the various covariates.
|
|
|
57
|
|
|
58
|
|
|
59 ------
|
|
|
60
|
|
|
61 Please cite the website "http://addlink.here" as well as:
|
|
|
62
|
|
|
63 Add citation here 2011.
|
|
|
64
|
|
|
65 ------
|
|
|
66
|
|
|
67 **Input formats**
|
|
|
68
|
|
|
69 GenomeAnalysisTK: AnalyzeCovariates accepts an recal CSV file.
|
|
|
70
|
|
|
71 ------
|
|
|
72
|
|
|
73 **Outputs**
|
|
|
74
|
|
|
75 The output is in and HTML file with links to PDF graphs and a data files, see http://addlink.here for more details.
|
|
|
76
|
|
|
77 -------
|
|
|
78
|
|
|
79 **Settings**::
|
|
|
80
|
|
|
81 recal_file The input recal csv file to analyze
|
|
|
82 output_dir The directory in which to output all the plots and intermediate data files
|
|
|
83 path_to_Rscript The path to your implementation of Rscript. For Broad users this is maybe /broad/tools/apps/R-2.6.0/bin/Rscript
|
|
|
84 path_to_resources Path to resources folder holding the Sting R scripts.
|
|
|
85 ignoreQ Ignore bases with reported quality less than this number.
|
|
|
86 numRG Only process N read groups. Default value: -1 (process all read groups)
|
|
|
87 max_quality_score The integer value at which to cap the quality scores, default is 50
|
|
|
88 max_histogram_value If supplied, this value will be the max value of the histogram plots
|
|
|
89 do_indel_quality If supplied, this value will be the max value of the histogram plots
|
|
|
90
|
|
|
91 </help>
|
|
|
92 </tool>
|
