comparison rgedgeRpaired_nocamera.xml @ 143:1435811cbf01 draft

Uploaded
author iuc
date Thu, 26 Feb 2015 22:41:57 -0500
parents e7894f37320a
children
comparison
equal deleted inserted replaced
142:e7894f37320a 143:1435811cbf01
1 <?xml version="1.0"?>
1 <tool id="rgdifferentialcount" name="Differential_Count" version="0.28"> 2 <tool id="rgdifferentialcount" name="Differential_Count" version="0.28">
2 <description>models using BioConductor packages</description> 3 <description>models using BioConductor packages</description>
3 <requirements> 4 <requirements>
4 <requirement type="package" version="3.1.2">R</requirement> 5 <requirement type="package" version="3.1.2">R</requirement>
5 <requirement type="package" version="1.3.18">graphicsmagick</requirement> 6 <requirement type="package" version="1.3.18">graphicsmagick</requirement>
6 <requirement type="package" version="9.10">ghostscript</requirement> 7 <requirement type="package" version="9.10">ghostscript</requirement>
7 <requirement type="package" version="2.14">biocbasics</requirement> 8 <requirement type="package" version="2.14">biocbasics</requirement>
8 </requirements> 9 </requirements>
9
10 <command interpreter="python"> 10 <command interpreter="python">
11 rgToolFactory.py --script_path "$runme" --interpreter "Rscript" --tool_name "Differential_Counts" 11 rgToolFactory.py --script_path "$runme" --interpreter "Rscript" --tool_name "Differential_Counts"
12 --output_dir "$html_file.files_path" --output_html "$html_file" --make_HTML "yes" 12 --output_dir "$html_file.files_path" --output_html "$html_file" --make_HTML "yes"
13 </command> 13 </command>
14 <inputs> 14 <inputs>
15 <param name="input1" type="data" format="tabular" label="Select an input matrix - rows are contigs, columns are counts for each sample" 15 <param name="input1" type="data" format="tabular" label="Select an input matrix - rows are contigs, columns are counts for each sample" help="Use the HTSeq based count matrix preparation tool to create these matrices from BAM/SAM files and a GTF file of genomic features"/>
16 help="Use the HTSeq based count matrix preparation tool to create these matrices from BAM/SAM files and a GTF file of genomic features"/> 16 <param name="title" type="text" value="Differential Counts" size="80" label="Title for job outputs" help="Supply a meaningful name here to remind you what the outputs contain">
17 <param name="title" type="text" value="Differential Counts" size="80" label="Title for job outputs"
18 help="Supply a meaningful name here to remind you what the outputs contain">
19 <sanitizer invalid_char=""> 17 <sanitizer invalid_char="">
20 <valid initial="string.letters,string.digits"><add value="_" /> </valid> 18 <valid initial="string.letters,string.digits">
19 <add value="_"/>
20 </valid>
21 </sanitizer> 21 </sanitizer>
22 </param> 22 </param>
23 <param name="treatment_name" type="text" value="Treatment" size="50" label="Treatment Name"/> 23 <param name="treatment_name" type="text" value="Treatment" size="50" label="Treatment Name"/>
24 <param name="Treat_cols" label="Select columns containing treatment." type="data_column" data_ref="input1" numerical="True" 24 <param name="Treat_cols" label="Select columns containing treatment." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True">
25 multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True"> 25 <validator type="no_options" message="Please select at least one column."/>
26 <validator type="no_options" message="Please select at least one column."/>
27 </param> 26 </param>
28 <param name="control_name" type="text" value="Control" size="50" label="Control Name"/> 27 <param name="control_name" type="text" value="Control" size="50" label="Control Name"/>
29 <param name="Control_cols" label="Select columns containing control." type="data_column" data_ref="input1" numerical="True" 28 <param name="Control_cols" label="Select columns containing control." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True">
30 multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True">
31 </param> 29 </param>
32 <param name="subjectids" type="text" optional="true" size="120" value = "" 30 <param name="subjectids" type="text" optional="true" size="120" value="" label="IF SUBJECTS NOT ALL INDEPENDENT! Enter comma separated strings to indicate sample labels for (eg) pairing - must be one for every column in input" help="Leave blank if no pairing, but eg if data from sample id A99 is in columns 2,4 and id C21 is in 3,5 then enter 'A99,C21,A99,C21'">
33 label="IF SUBJECTS NOT ALL INDEPENDENT! Enter comma separated strings to indicate sample labels for (eg) pairing - must be one for every column in input"
34 help="Leave blank if no pairing, but eg if data from sample id A99 is in columns 2,4 and id C21 is in 3,5 then enter 'A99,C21,A99,C21'">
35 <sanitizer> 31 <sanitizer>
36 <valid initial="string.letters,string.digits"><add value="," /> </valid> 32 <valid initial="string.letters,string.digits">
33 <add value=","/>
34 </valid>
37 </sanitizer> 35 </sanitizer>
38 </param> 36 </param>
39 <param name="fQ" type="float" value="0.3" size="5" label="Non-differential contig count quantile threshold - zero to analyze all non-zero read count contigs" 37 <param name="fQ" type="float" value="0.3" size="5" label="Non-differential contig count quantile threshold - zero to analyze all non-zero read count contigs" help="May be a good or a bad idea depending on the biology and the question. EG 0.3 = sparsest 30% of contigs with at least one read are removed before analysis"/>
40 help="May be a good or a bad idea depending on the biology and the question. EG 0.3 = sparsest 30% of contigs with at least one read are removed before analysis"/> 38 <param name="useNDF" type="boolean" truevalue="T" falsevalue="F" checked="false" size="1" label="Non differential filter - remove contigs below a threshold (1 per million) for half or more samples" help="May be a good or a bad idea depending on the biology and the question. This was the old default. Quantile based is available as an alternative"/>
41 <param name="useNDF" type="boolean" truevalue="T" falsevalue="F" checked="false" size="1"
42 label="Non differential filter - remove contigs below a threshold (1 per million) for half or more samples"
43 help="May be a good or a bad idea depending on the biology and the question. This was the old default. Quantile based is available as an alternative"/>
44
45 <conditional name="edgeR"> 39 <conditional name="edgeR">
46 <param name="doedgeR" type="select" 40 <param name="doedgeR" type="select" label="Run this model using edgeR" help="edgeR uses a negative binomial model and seems to be powerful, even with few replicates">
47 label="Run this model using edgeR" 41 <option value="F">Do not run edgeR</option>
48 help="edgeR uses a negative binomial model and seems to be powerful, even with few replicates"> 42 <option value="T" selected="true">Run edgeR</option>
49 <option value="F">Do not run edgeR</option> 43 </param>
50 <option value="T" selected="true">Run edgeR</option> 44 <when value="T">
51 </param> 45 <param name="edgeR_priordf" type="integer" value="10" size="3" label="prior.df for tagwise dispersion - larger value = more squeezing of tag dispersions to common dispersion. Replaces prior.n and prior.df = prior.n * residual.df" help="10 = edgeR default. Use a larger value to 'smooth' small samples. See edgeR docs and note below"/>
52 <when value="T"> 46 <param name="edgeR_robust_method" type="select" value="20" size="3" label="Use robust dispersion method" help="Use ordinary, anscombe or deviance robust deviance estimates">
53 <param name="edgeR_priordf" type="integer" value="10" size="3" 47 <option value="ordinary" selected="true">Use ordinary deviance estimates</option>
54 label="prior.df for tagwise dispersion - larger value = more squeezing of tag dispersions to common dispersion. Replaces prior.n and prior.df = prior.n * residual.df" 48 <option value="deviance">Use robust deviance estimates</option>
55 help="10 = edgeR default. Use a larger value to 'smooth' small samples. See edgeR docs and note below"/> 49 <option value="anscombe">use Anscombe robust deviance estimates</option>
56 <param name="edgeR_robust_method" type="select" value="20" size="3" 50 </param>
57 label="Use robust dispersion method" 51 </when>
58 help="Use ordinary, anscombe or deviance robust deviance estimates"> 52 <when value="F"/>
59 <option value="ordinary" selected="true">Use ordinary deviance estimates</option>
60 <option value="deviance">Use robust deviance estimates</option>
61 <option value="anscombe">use Anscombe robust deviance estimates</option>
62 </param>
63 </when>
64 <when value="F"></when>
65 </conditional> 53 </conditional>
66 <conditional name="DESeq2"> 54 <conditional name="DESeq2">
67 <param name="doDESeq2" type="select" 55 <param name="doDESeq2" type="select" label="Run the same model with DESeq2 and compare findings" help="DESeq2 is an update to the DESeq package. It uses different assumptions and methods to edgeR">
68 label="Run the same model with DESeq2 and compare findings" 56 <option value="F" selected="true">Do not run DESeq2</option>
69 help="DESeq2 is an update to the DESeq package. It uses different assumptions and methods to edgeR"> 57 <option value="T">Run DESeq2</option>
70 <option value="F" selected="true">Do not run DESeq2</option> 58 </param>
71 <option value="T">Run DESeq2</option> 59 <when value="T">
72 </param> 60 <param name="DESeq_fitType" type="select">
73 <when value="T"> 61 <option value="parametric" selected="true">Parametric (default) fit for dispersions</option>
74 <param name="DESeq_fitType" type="select"> 62 <option value="local">Local fit - this will automagically be used if parametric fit fails</option>
75 <option value="parametric" selected="true">Parametric (default) fit for dispersions</option> 63 <option value="mean">Mean dispersion fit- use this if you really understand what you're doing - read the fine manual linked below in the documentation</option>
76 <option value="local">Local fit - this will automagically be used if parametric fit fails</option> 64 </param>
77 <option value="mean">Mean dispersion fit- use this if you really understand what you're doing - read the fine manual linked below in the documentation</option> 65 </when>
78 </param> 66 <when value="F"> </when>
79 </when>
80 <when value="F"> </when>
81 </conditional> 67 </conditional>
82 <param name="doVoom" type="select" 68 <param name="doVoom" type="select" label="Run the same model with Voom/limma and compare findings" help="Voom uses counts per million and a precise transformation of variance so count data can be analysed using limma">
83 label="Run the same model with Voom/limma and compare findings"
84 help="Voom uses counts per million and a precise transformation of variance so count data can be analysed using limma">
85 <option value="F" selected="true">Do not run VOOM</option> 69 <option value="F" selected="true">Do not run VOOM</option>
86 <option value="T">Run VOOM</option> 70 <option value="T">Run VOOM</option>
87 </param> 71 </param>
88 <param name="fdrthresh" type="float" value="0.05" size="5" label="P value threshold for FDR filtering for amily wise error rate control" 72 <param name="fdrthresh" type="float" value="0.05" size="5" label="P value threshold for FDR filtering for amily wise error rate control" help="Conventional default value of 0.05 recommended"/>
89 help="Conventional default value of 0.05 recommended"/> 73 <param name="fdrtype" type="select" label="FDR (Type II error) control method" help="Use fdr or bh typically to control for the number of tests in a reliable way">
90 <param name="fdrtype" type="select" label="FDR (Type II error) control method" 74 <option value="fdr" selected="true">fdr</option>
91 help="Use fdr or bh typically to control for the number of tests in a reliable way"> 75 <option value="BH">Benjamini Hochberg</option>
92 <option value="fdr" selected="true">fdr</option> 76 <option value="BY">Benjamini Yukateli</option>
93 <option value="BH">Benjamini Hochberg</option> 77 <option value="bonferroni">Bonferroni</option>
94 <option value="BY">Benjamini Yukateli</option> 78 <option value="hochberg">Hochberg</option>
95 <option value="bonferroni">Bonferroni</option> 79 <option value="holm">Holm</option>
96 <option value="hochberg">Hochberg</option> 80 <option value="hommel">Hommel</option>
97 <option value="holm">Holm</option> 81 <option value="none">no control for multiple tests</option>
98 <option value="hommel">Hommel</option>
99 <option value="none">no control for multiple tests</option>
100 </param> 82 </param>
101 </inputs> 83 </inputs>
102 <outputs> 84 <outputs>
103 <data format="tabular" name="out_edgeR" label="${title}_topTable_edgeR.xls"> 85 <data format="tabular" name="out_edgeR" label="${title}_topTable_edgeR.xls">
104 <filter>edgeR['doedgeR'] == "T"</filter> 86 <filter>edgeR['doedgeR'] == "T"</filter>
105 </data> 87 </data>
106 <data format="tabular" name="out_DESeq2" label="${title}_topTable_DESeq2.xls"> 88 <data format="tabular" name="out_DESeq2" label="${title}_topTable_DESeq2.xls">
107 <filter>DESeq2['doDESeq2'] == "T"</filter> 89 <filter>DESeq2['doDESeq2'] == "T"</filter>
108 </data> 90 </data>
109 <data format="tabular" name="out_VOOM" label="${title}_topTable_VOOM.xls"> 91 <data format="tabular" name="out_VOOM" label="${title}_topTable_VOOM.xls">
110 <filter>doVoom == "T"</filter> 92 <filter>doVoom == "T"</filter>
111 </data> 93 </data>
112 <data format="html" name="html_file" label="${title}.html"/> 94 <data format="html" name="html_file" label="${title}.html"/>
113 </outputs> 95 </outputs>
114 <stdio> 96 <stdio>
115 <exit_code range="4" level="fatal" description="Number of subject ids must match total number of samples in the input matrix" /> 97 <exit_code range="4" level="fatal" description="Number of subject ids must match total number of samples in the input matrix"/>
116 </stdio> 98 </stdio>
117 <tests> 99 <tests>
118 <test> 100 <test>
119 <param name='input1' value='test_bams2mx.xls' ftype='tabular' /> 101 <param name="input1" value="test_bams2mx.xls" ftype="tabular"/>
120 <param name='treatment_name' value='liver' /> 102 <param name="treatment_name" value="liver"/>
121 <param name='title' value='edgeRtest' /> 103 <param name="title" value="edgeRtest"/>
122 <param name='useNDF' value='' /> 104 <param name="useNDF" value=""/>
123 <param name='doedgeR' value='T' /> 105 <param name="doedgeR" value="T"/>
124 <param name='doVoom' value='T' /> 106 <param name="doVoom" value="T"/>
125 <param name='doDESeq2' value='T' /> 107 <param name="doDESeq2" value="T"/>
126 <param name='fdrtype' value='fdr' /> 108 <param name="fdrtype" value="fdr"/>
127 <param name='edgeR_priordf' value="8" /> 109 <param name="edgeR_priordf" value="8"/>
128 <param name='edgeR_robust' value="ordinary" /> 110 <param name="edgeR_robust" value="ordinary"/>
129 <param name='fdrthresh' value="0.05" /> 111 <param name="fdrthresh" value="0.05"/>
130 <param name='control_name' value='heart' /> 112 <param name="control_name" value="heart"/>
131 <param name='subjectids' value='' /> 113 <param name="subjectids" value=""/>
132 <param name='Control_cols' value='3,4,5,9' /> 114 <param name="Control_cols" value="3,4,5,9"/>
133 <param name='Treat_cols' value='2,6,7,8' /> 115 <param name="Treat_cols" value="2,6,7,8"/>
134 <output name='out_edgeR' file='edgeRtest1out.xls' compare='diff' lines_diff='20' /> 116 <output name="out_edgeR" file="edgeRtest1out.xls" compare="diff" lines_diff="20"/>
135 <output name='html_file' file='edgeRtest1out.html' compare='diff' lines_diff='20' /> 117 <output name="html_file" file="edgeRtest1out.html" compare="diff" lines_diff="20"/>
136 </test> 118 </test>
137 </tests> 119 </tests>
138 120 <configfiles>
139 <configfiles> 121 <configfile name="runme"><![CDATA[
140 <configfile name="runme">
141 <![CDATA[
142 # 122 #
143 # edgeR.Rscript 123 # edgeR.Rscript
144 # updated feb 2014 adding outlier-robust deviance estimate options by ross for R 3.0.2/bioc 2.13 124 # updated feb 2014 adding outlier-robust deviance estimate options by ross for R 3.0.2/bioc 2.13
145 # updated npv 2011 for R 2.14.0 and edgeR 2.4.0 by ross 125 # updated npv 2011 for R 2.14.0 and edgeR 2.4.0 by ross
146 # Performs DGE on a count table containing n replicates of two conditions 126 # Performs DGE on a count table containing n replicates of two conditions
883 sessionInfo() 863 sessionInfo()
884 864
885 sink() 865 sink()
886 ]]> 866 ]]>
887 </configfile> 867 </configfile>
888 </configfiles> 868 </configfiles>
889 <help> 869 <help>
890 870
891 **What it does** 871 **What it does**
892 872
893 Allows short read sequence counts from controlled experiments to be analysed for differentially expressed genes. 873 Allows short read sequence counts from controlled experiments to be analysed for differentially expressed genes.
894 Optionally adds a term for subject if not all samples are independent or if some other factor needs to be blocked in the design. 874 Optionally adds a term for subject if not all samples are independent or if some other factor needs to be blocked in the design.
1061 .. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html 1041 .. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html
1062 .. _DESeq2: http://www.bioconductor.org/packages/release/bioc/html/DESeq2.html 1042 .. _DESeq2: http://www.bioconductor.org/packages/release/bioc/html/DESeq2.html
1063 .. _limma_VOOM: http://www.bioconductor.org/packages/release/bioc/html/limma.html 1043 .. _limma_VOOM: http://www.bioconductor.org/packages/release/bioc/html/limma.html
1064 .. _Galaxy: http://getgalaxy.org 1044 .. _Galaxy: http://getgalaxy.org
1065 </help> 1045 </help>
1066 <citations> 1046 <citations>
1067 <citation type="doi">doi: 10.1093/bioinformatics/btp616</citation> 1047 <citation type="doi">doi: 10.1093/bioinformatics/btp616</citation>
1068 </citations> 1048 </citations>
1069
1070 </tool> 1049 </tool>
1071
1072