comparison edger-repenrich.xml @ 0:f6f0f1e5e940 draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/repenrich commit 61e203df0be5ed877ff92b917c7cde6eeeab8310
author artbio
date Wed, 02 Aug 2017 05:17:29 -0400
parents
children 51b4590a972d
comparison
equal deleted inserted replaced
-1:000000000000 0:f6f0f1e5e940
1 <tool id="edger-repenrich" name="edgeR-repenrich" version="1.4.0">
2 <description>Determines differentially expressed features from RepEnrich counts</description>
3 <requirements>
4 <requirement type="package" version="3.16.5">bioconductor-edger</requirement>
5 <requirement type="package" version="3.30.13">bioconductor-limma</requirement>
6 <requirement type="package" version="1.20.0">r-getopt</requirement>
7 <requirement type="package" version="0.2.15">r-rjson</requirement>
8 </requirements>
9 <stdio>
10 <regex match="Execution halted"
11 source="both"
12 level="fatal"
13 description="Execution halted." />
14 <regex match="Error in"
15 source="both"
16 level="fatal"
17 description="An undefined error occurred, please check your input carefully and contact your administrator." />
18 <regex match="Fatal error"
19 source="both"
20 level="fatal"
21 description="An undefined error occurred, please check your input carefully and contact your administrator." />
22 </stdio>
23 <version_command>
24 <![CDATA[
25 echo $(R --version | grep version | grep -v GNU)", edgeR version" $(R --vanilla --slave -e "library(edgeR) &&
26 cat(sessionInfo()\$otherPkgs\$edgeR\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
27 ]]>
28 </version_command>
29 <command>
30 <![CDATA[
31 #import json
32 Rscript '${__tool_directory__}/edgeR_repenrich.R'
33 --factorName '$factorName'
34
35 --levelNameA '$factorLevel_A'
36 #set $factorlevelsA = list()
37 #for $file in $countsFiles_A:
38 $factorlevelsA.append(str($file))
39 #end for
40 $factorlevelsA.reverse()
41 --levelAfiles '#echo json.dumps(factorlevelsA)#'
42
43 --levelNameB '$factorLevel_B'
44 #set $factorlevelsB = list()
45 #for $file in $countsFiles_B:
46 $factorlevelsB.append(str($file))
47 #end for
48 $factorlevelsB.reverse()
49 --levelBfiles '#echo json.dumps(factorlevelsB)#'
50
51 #set $alignedA = list()
52 #for file in $alignmentFiles_A:
53 $alignedA.append(str($file))
54 #end for
55 $alignedA.reverse()
56 --alignmentA '#echo json.dumps(alignedA)#'
57
58 #set $alignedB = list()
59 #for file in $alignmentFiles_B:
60 $alignedB.append(str($file))
61 #end for
62 $alignedB.reverse()
63 --alignmentB '#echo json.dumps(alignedB)#'
64
65 -o 'edger_out'
66
67 -p '$plots'
68 #if $normCounts:
69 -n '$counts_out'
70 #end if
71 -o '$edger_out'
72 ]]>
73 </command>
74 <inputs>
75 <param name="factorName" type="text" value="FactorName" label="Specify a factor name, e.g. genotype or age or drug_x"
76 help="Only letters, numbers and underscores will be retained in this field">
77 <sanitizer>
78 <valid initial="string.letters,string.digits"><add value="_" /></valid>
79 </sanitizer>
80 </param>
81 <param name="factorLevel_A" type="text" value="FactorLevel1" label="Specify a factor level, typical values could be 'wildtype' or 'control'"
82 help="Only letters, numbers and underscores will be retained in this field">
83 <sanitizer>
84 <valid initial="string.letters,string.digits"><add value="_" /></valid>
85 </sanitizer>
86 </param>
87 <param name="countsFiles_A" type="data" format="tabular" multiple="true" label="Counts file(s)" help="Count files must have been generated by repenrich" />
88 <param name="alignmentFiles_A" type="data" format="tabular" multiple="true" label="Number of aligned reads file(s)" help="files of total aligned reads generated by repenrich"/>
89 <param name="factorLevel_B" type="text" value="FactorLevel2" label="Specify a factor level, typical values could be 'mutant' or 'Drug_X'"
90 help="Only letters, numbers and underscores will be retained in this field">
91 <sanitizer>
92 <valid initial="string.letters,string.digits"><add value="_" /></valid>
93 </sanitizer>
94 </param>
95 <param name="countsFiles_B" type="data" format="tabular" multiple="true" label="Counts file(s)" help="Count files must have been generated by repenrich tool" />
96 <param name="alignmentFiles_B" type="data" format="tabular" multiple="true" label="Number of aligned reads file(s)" help="files of total aligned reads generated by repenrich"/>
97 <param name="normCounts" type="boolean" truevalue="1" falsevalue="0" checked="false"
98 label="Output normalized counts table" />
99 </inputs>
100 <outputs>
101 <data format="tabular" name="edger_out" label="edgeR: ${factorLevel_A} compared to ${factorLevel_B}">
102 <actions>
103 <action name="column_names" type="metadata" default="Tag,log2(FC),FDR,Class,Type" />
104 </actions>
105 </data>
106 <data format="pdf" name="plots" label="edgeR plots" />
107 <data format="tabular" name="counts_out" label="Normalized counts file">
108 <filter>normCounts == True</filter>
109 </data>
110 </outputs>
111 <tests>
112 <test>
113 <param name="factorName" value="Genotype"/>
114 <param name="factorLevel_A" value="Mutant"/>
115 <param name="countsFiles_A" value="355_fraction_counts.tab,356_fraction_counts.tab"/>
116 <param name="alignmentFiles_A" value="aligned_355.tab,aligned_356.tab"/>
117 <param name="factorLevel_B" value="Wildtype"/>
118 <param name="countsFiles_B" value="353_fraction_counts.tab,354_fraction_counts.tab"/>
119 <param name="alignmentFiles_B" value="aligned_353.tab,aligned_354.tab"/>
120 <param name="normCounts" value="True"/>
121 <output name="counts_out" file="Normalized_counts_file.tab"/>
122 <output name="plots" file="edgeR_plots.pdf"/>
123 <output name="edger_out" file="edgeR_result_file.tab"/>
124
125 </test>
126 </tests>
127 <help>
128 <![CDATA[
129 .. class:: infomark
130
131 **What it does**
132
133 Estimate Distance between samples (MDS) and Biological Coefficient Variation (BCV) in count data from high-throughput sequencing assays and test for differential expression using edgeR_.
134
135 **Inputs**
136
137 edger-repenrich takes count tables generated by repenrich as input. Count tables must be generated for each sample individually. Here, edgeR_ is handling a single factor (genotype, age, treatment, etc) that effect your experiment. This factor has two levels/states (for instance, "wild-type" and "mutant".
138 You need to select appropriate count table from your history for each factor level.
139
140 The following table gives some examples of factors and their levels:
141
142 ========= ============== ===============
143 Factor Factorlevel1 Factorlevel2
144 --------- -------------- ---------------
145 Treatment Treated Untreated
146 --------- -------------- ---------------
147 Genotype Knockdown Wildtype
148 --------- -------------- ---------------
149 TimePoint Day4 Day1
150 --------- -------------- ---------------
151 Gender Female Male
152 ========= ============== ===============
153
154 *Note*: Output log2 fold changes are based on primary factor level 1 vs. factor level2. Here the order of factor levels is important. For example, for the factor 'Treatment' given in above table, DESeq2 computes fold changes of 'Treated' samples against 'Untreated', i.e. the values correspond to up or down regulations of genes in Treated samples.
155
156 **Output**
157
158 edgeR_ generates a tabular file containing the different columns and results visualized in a PDF:
159
160 ====== =============================================================================
161 Column Description
162 ------ -----------------------------------------------------------------------------
163 1 Tag (transposon element ID)
164 2 the logarithm (to basis 2) of the fold change (See the note in inputs section)
165 3 p value adjusted for multiple testing with the Benjamini-Hochberg procedure
166 which controls false discovery rate (FDR)
167 4 Class the transposon belongs to
168 5 Type the transposon belongs to
169 ====== =============================================================================
170
171 .. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html
172 ]]>
173
174 **Note**: This edgeR_ wrapper was adapted from code available at https://github.com/nskvir/RepEnrich
175
176 </help>
177 <citations>
178 <citation type="doi">10.1093/bioinformatics/btp616</citation>
179 </citations>
180 </tool>