comparison deseq2.xml @ 29:07620fe97c88 draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/deseq2 commit d033f887f37ec95f83a8786e8463e0c744773cc4
author bgruening
date Sat, 10 Dec 2016 18:33:07 -0500
parents 6947d8ed51cc
children
comparison
equal deleted inserted replaced
28:6947d8ed51cc 29:07620fe97c88
1 <tool id="iuc_deseq2" name="DESeq2" version="2.1.6.0">
2 <description>Determines differentially expressed features from count tables</description>
3 <requirements>
4 <requirement type="binary">Rscript</requirement>
5 <requirement type="R-module">DESeq2</requirement>
6 <!-- odering is crucial, otherwise R will override the ENV variables from deseq2 -->
7 <requirement type="package" version="3.1.0">R</requirement>
8 <requirement type="package" version="1.6.1">deseq2</requirement>
9 </requirements>
10 <code file="helper.py" />
11 <command interpreter="Rscript">
12 #import json
13 deseq2.R
14 -o "$deseq_out"
15 --outfilefiltered "$deseq_out_filtered"
16
17 #if $pdf:
18 -p "$plots"
19 #end if
20
21 #set $temp_factor_names = list()
22 #for $factor in $rep_factorName:
23
24 #set $temp_factor = list()
25 #for $level in $factor.rep_factorLevel:
26 #set $count_files = list()
27 #for $file in $level.countsFile:
28 $count_files.append(str($file))
29 #end for
30 $temp_factor.append( {str($level.factorLevel): $count_files} )
31 #end for
32 $temp_factor_names.append([str($factor.factorName), $temp_factor])
33
34 #end for
35
36 -m '#echo json.dumps(temp_factor_names)#'
37 #if str($filtermode.mode) == "absolute":
38 -c $filtermode.count_abs
39 #elif str($filtermode.mode) == "quantile":
40 -c $filtermode.count_quant
41 #end if
42 --filtermode $filtermode.mode
43 </command>
44 <stdio>
45 <regex match="Execution halted"
46 source="both"
47 level="fatal"
48 description="Execution halted." />
49 <regex match="Error in"
50 source="both"
51 level="fatal"
52 description="An undefined error occured, please check your intput carefully and contact your administrator." />
53 </stdio>
54 <inputs>
55 <repeat name="rep_factorName" title="Factor" min="1">
56 <param name="factorName" type="text" value="FactorName" label="Specify a factor name"
57 help="Only letters, numbers and underscores will be retained in this field">
58 <sanitizer>
59 <valid initial="string.letters,string.digits"><add value="_" /></valid>
60 </sanitizer>
61 </param>
62 <repeat name="rep_factorLevel" title="Factor level" min="2" max="2" default="2">
63 <param name="factorLevel" type="text" value="FactorLevel" label="Specify a factor level"
64 help="Only letters, numbers and underscores will be retained in this field">
65 <sanitizer>
66 <valid initial="string.letters,string.digits"><add value="_" /></valid>
67 </sanitizer>
68 </param>
69 <param name="countsFile" type="data" multiple="true" label="Counts file"/>
70 </repeat>
71 </repeat>
72 <conditional name="filtermode">
73 <param name="mode" type="select" label="Filter out features with following criteria">
74 <option value="absolute">Filter based on absolute normalized mean counts</option>
75 <option value="quantile">Filter based on quantiles</option>
76 </param>
77 <when value="absolute">
78 <param name="count_abs" size="10" type="float" value="10.0" label="Filter out features with mean normalized counts lower than this value"/>
79 </when>
80 <when value="quantile">
81 <param name="count_quant" size="10" type="float" value="10.0" min="0" max="100" label="Filter out features with mean normalized counts lower than this % of values" />
82 </when>
83 </conditional>
84 <param name="pdf" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Visualising the analysis results"
85 help="output an additional PDF files" />
86 </inputs>
87
88 <outputs>
89 <data format="tabular" name="deseq_out" label="DESeq2 result file on ${on_string}"/>
90 <data format="tabular" name="deseq_out_filtered" label="Independent filtering result file on ${on_string}"/>
91 <data format="pdf" name="plots" label="DESeq2 plots on ${on_string}">
92 <filter>pdf == True</filter>
93 </data>
94 </outputs>
95
96 <tests>
97 <test>
98 <repeat name="rep_factorName">
99 <param name="factorName" value="Treatment"/>
100 <repeat name="rep_factorLevel">
101 <param name="factorLevel" value="Treated"/>
102 <param name="countsFile" value="GSM461179_treat_single.counts,GSM461180_treat_paired.counts,GSM461181_treat_paired.counts"/>
103 </repeat>
104 <repeat name="rep_factorLevel">
105 <param name="factorLevel" value="Untreated"/>
106 <param name="countsFile" value="GSM461176_untreat_single.counts,GSM461177_untreat_paired.counts,GSM461178_untreat_paired.counts,GSM461182_untreat_single.counts"/>
107 </repeat>
108 </repeat>
109 <param name="pdf" value="no"/>
110 <output name="deseq_out" file="deseq2_out.tab"/>
111 <output name="deseq_out_filtered" file="deseq2_out_filtered.tab"/>
112 </test>
113 </tests>
114
115 <help>
116
117 .. class:: infomark
118
119 **What it does**
120
121 Estimate variance-mean dependence in count data from high-throughput sequencing assays and test for differential expression based on a model using the negative binomial distribution
122
123
124 **Inputs**
125
126 DESeq2_ takes count tables that generated from the htseq-count as input. Count tables must be generated for each sample individually. DESeq2 is capable of handling multiple factors that effect your experiment. The first factor you input is considered as the primary factor that affects gene expressions. You also input several secondary factors that might influence your experiment. But the final output will be changes in genes due to primary factor in presence of secondary factors. Each factor has two levels/states. You need to select appropriate count table from your history for each factor level.
127
128 The following table gives some examples of factors and their levels:
129
130 ========= ============== ===============
131 Factor Factor level 1 Factor level 2
132 --------- -------------- ---------------
133 Treatment Treated Untreated
134 --------- -------------- ---------------
135 Condition Knockdown Wildtype
136 --------- -------------- ---------------
137 TimePoint Day4 Day1
138 --------- -------------- ---------------
139 SeqType SingleEnd PairedEnd
140 --------- -------------- ---------------
141 Gender Female Male
142 ========= ============== ===============
143
144 *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.
145
146 **Output**
147
148 DESeq2_ generates a tabular file containing the different columns and optional visualized results as PDF.
149
150 ====== ==========================================================
151 Column Description
152 ------ ----------------------------------------------------------
153 1 Gene Identifiers
154 2 mean normalised counts, averaged over all samples from both conditions
155 3 the logarithm (to basis 2) of the fold change (See the note in inputs section)
156 4 standard error estimate for the log2 fold change estimate
157 5 p value for the statistical significance of this change
158 6 p value adjusted for multiple testing with the Benjamini-Hochberg procedure
159 which controls false discovery rate (FDR)
160 ====== ==========================================================
161
162
163 .. _DESeq2: http://master.bioconductor.org/packages/release/bioc/html/DESeq2.html
164
165 </help>
166 <citations>
167 <citation type="doi">10.1101/002832</citation>
168 </citations>
169 </tool>