Mercurial > repos > yhoogstrate > edger_with_design_matrix

comparison edgeR_Concatenate_Expression_Matrices.xml @ 108:a02794bb9073 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://bitbucket.org/EMCbioinf/galaxy-tool-shed-tools/raw/master/edger_with_design_matrix commit 2700e500a4fb135a20ede7d52221a9d31f1aaa5e-dirty
author yhoogstrate
date Tue, 01 Sep 2015 04:45:24 -0400
parents 450c1c9a2938
children f06dceb5b966
comparison
equal deleted inserted replaced
107:049d8bc2214e 108:a02794bb9073
1 <?xml version="1.0" encoding="UTF-8"?> 1 <?xml version="1.0" encoding="UTF-8"?>
2 <tool id="concatenate_expression_matrices" name="edgeR: Concatenate Expression Matrices" version="1.0.0"> 2 <tool id="concatenate_expression_matrices" name="edgeR: Concatenate Expression Matrices" version="1.0.0">
3 <description>Create a full expression matrix by selecting the desired columns from specific count tables</description> 3 <description>Create a full expression matrix by selecting the desired columns from specific count tables</description>
4 4
5 <command> 5 <macros>
6 #set $j = 0 6 <import>edgeR_macros.xml</import>
7 #set $paste = [] 7 </macros>
8 8
9 #if $add_geneids.choice == "true": 9 <command>
10 #set $filename = str($j)+".txt" 10 #set $j = 0
11 #set paste = paste + [$filename] 11 #set $paste = []
12 12
13 cut -f $add_geneids.column_geneids.value "$add_geneids.sample_geneids" > $filename ; 13 #if $add_geneids.choice == "true":
14 #set $j += 1 14 #set $filename = str($j)+".txt"
15 #end if 15 #set paste = paste + [$filename]
16 16
17 #for $sample in $samples: 17 cut -f $add_geneids.column_geneids.value "$add_geneids.sample_geneids" > $filename ;
18 ##echo "$sample.column_index" 18 #set $j += 1
19 ##echo "$sample.column_index.value" 19 #end if
20 20
21 #set $column_str = ",".join([str(x).strip() for x in $sample.column_index.value]) 21 #for $sample in $samples:
22 #set $filename = str($j)+".txt" 22 ##echo "$sample.column_index"
23 #set paste = paste + [$filename] 23 ##echo "$sample.column_index.value"
24 24
25 cut -f "$column_str" "$sample.sample" > $filename ; 25 #set $column_str = ",".join([str(x).strip() for x in $sample.column_index.value])
26 #set $j += 1 26 #set $filename = str($j)+".txt"
27 #end for 27 #set paste = paste + [$filename]
28 28
29 #if $add_lengths.choice == "true": 29 cut -f "$column_str" "$sample.sample" > $filename ;
30 #set $filename = str($j)+".txt" 30 #set $j += 1
31 #set paste = paste + [$filename] 31 #end for
32 32
33 cut -f $add_lengths.column_lengths.value "$add_lengths.sample_lengths" > $filename ; 33 #if $add_lengths.choice == "true":
34 #set $j += 1 34 #set $filename = str($j)+".txt"
35 #end if 35 #set paste = paste + [$filename]
36 36
37 #set $paste_str = " ".join([str(x).strip() for x in $paste]) 37 cut -f $add_lengths.column_lengths.value "$add_lengths.sample_lengths" > $filename ;
38 38 #set $j += 1
39 paste $paste_str > $expression_matrix 39 #end if
40 </command> 40
41 41 #set $paste_str = " ".join([str(x).strip() for x in $paste])
42 <inputs> 42
43 <conditional name="add_geneids"> 43 paste $paste_str > $expression_matrix
44 <param name="choice" type="select" label="Add a gene-IDs column at the end of the file" help="Highly recommended to select!" > 44 </command>
45 <option value="false">No</option> 45
46 <option value="true" selected="true">Yes</option> 46 <inputs>
47 </param> 47 <conditional name="add_geneids">
48 <when value="false" /> 48 <param name="choice" type="select" label="Add a gene-IDs column at the end of the file" help="Highly recommended to select!" >
49 <when value="true"> 49 <option value="false">No</option>
50 <param name="sample_geneids" type="data" format="tabular" label="Select Read-count dataset that contains a column for GeneIDs" help="from featureCounts/DEXSeq-count/HTSeq-count, etc." /> 50 <option value="true" selected="true">Yes</option>
51 <param name="column_geneids" numerical="false" use_header_names="true" label="Select GeneID column" type="data_column" data_ref="sample_geneids" multiple="false"> 51 </param>
52 <validator type="no_options" message="Please select at least one column." /> 52 <when value="false" />
53 </param> 53 <when value="true">
54 </when> 54 <param name="sample_geneids" type="data" format="tabular" label="Select Read-count dataset that contains a column for GeneIDs" help="from featureCounts/DEXSeq-count/HTSeq-count, etc." />
55 </conditional> 55 <param name="column_geneids" numerical="false" use_header_names="true" label="Select GeneID column" type="data_column" data_ref="sample_geneids" multiple="false">
56 56 <validator type="no_options" message="Please select at least one column." />
57 <repeat name="samples" title="Expression Table" help="E.g. a earlier concatenated table, or a HT-seq, featureCounts or DESeq-count result."> 57 </param>
58 <param name="sample" type="data" format="tabular" label="Read-count dataset that belongs to a pair" help="from featureCounts/DEXSeq-count/HTSeq-count, etc." /> 58 </when>
59 <!-- select columns --> 59 </conditional>
60 <param name="column_index" numerical="false" use_header_names="true" label="Select columns that are associated with this factor level" type="data_column" data_ref="sample" multiple="true" size="120" display="checkboxes"> 60
61 <validator type="no_options" message="Please select at least one column." /> 61 <repeat name="samples" title="Expression Table" help="E.g. a earlier concatenated table, or a HT-seq, featureCounts or DESeq-count result.">
62 </param> 62 <param name="sample" type="data" format="tabular" label="Read-count dataset that belongs to a pair" help="from featureCounts/DEXSeq-count/HTSeq-count, etc." />
63 </repeat> 63 <!-- select columns -->
64 64 <param name="column_index" numerical="false" use_header_names="true" label="Select columns that are associated with this factor level" type="data_column" data_ref="sample" multiple="true" size="120" display="checkboxes">
65 <conditional name="add_lengths"> 65 <validator type="no_options" message="Please select at least one column." />
66 <param name="choice" type="select" label="Add a gene-lengths column at the end of the file" help="Optional, only usefull if RPKM/FPKM calculation is desired." > 66 </param>
67 <option value="false">No</option> 67 </repeat>
68 <option value="true">Yes</option> 68
69 </param> 69 <conditional name="add_lengths">
70 <when value="false" /> 70 <param name="choice" type="select" label="Add a gene-lengths column at the end of the file" help="Optional, only usefull if RPKM/FPKM calculation is desired." >
71 <when value="true"> 71 <option value="false">No</option>
72 <param name="sample_lengths" type="data" format="tabular" label="Read-count dataset that belongs to a pair" help="from featureCounts/DEXSeq-count/HTSeq-count, etc." /> 72 <option value="true">Yes</option>
73 <param name="column_lengths" numerical="false" use_header_names="true" label="Select columns that are associated with this factor level" type="data_column" data_ref="sample_lengths" multiple="false" size="120"> 73 </param>
74 <validator type="no_options" message="Please select at least one column." /> 74 <when value="false" />
75 </param> 75 <when value="true">
76 </when> 76 <param name="sample_lengths" type="data" format="tabular" label="Read-count dataset that belongs to a pair" help="from featureCounts/DEXSeq-count/HTSeq-count, etc." />
77 </conditional> 77 <param name="column_lengths" numerical="false" use_header_names="true" label="Select columns that are associated with this factor level" type="data_column" data_ref="sample_lengths" multiple="false" size="120">
78 78 <validator type="no_options" message="Please select at least one column." />
79 <param name="remove_comment_lines" type="boolean" label="Automatically remove 'comment' lines starting with a '#'" truevale="true" falsevalue="false" selected="true" help="Some tools (incl. featureCounts) include comment lines that are not neccesairy for downstream analyis. By enabling this function, these lines will be removed." /> 79 </param>
80 80 </when>
81 </inputs> 81 </conditional>
82 82
83 <outputs> 83 <param name="remove_comment_lines" type="boolean" label="Automatically remove 'comment' lines starting with a '#'" truevale="true" falsevalue="false" selected="true" help="Some tools (incl. featureCounts) include comment lines that are not neccesairy for downstream analyis. By enabling this function, these lines will be removed." />
84 <data format="tabular" name="expression_matrix" label="Expression matrix" /> 84
85 </outputs> 85 </inputs>
86 86
87 <tests> 87 <outputs>
88 <test> 88 <data format="tabular" name="expression_matrix" label="Expression matrix" />
89 <conditional name="add_geneids"> 89 </outputs>
90 <param name="choice" value="true" /> 90
91 <param name="sample_geneids" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" /> 91 <tests>
92 <param name="column_geneids" value="1" /> 92 <test>
93 </conditional> 93 <conditional name="add_geneids">
94 94 <param name="choice" value="true" />
95 <param name="samples_0|sample" value="GSE51403/GSE51403_expression_matrix_Control_1.txt" /> 95 <param name="sample_geneids" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" />
96 <param name="samples_0|column_index" value="2" /> 96 <param name="column_geneids" value="1" />
97 97 </conditional>
98 <conditional name="add_lengths"> 98
99 <param name="choice" value="false" /> 99 <param name="samples_0|sample" value="GSE51403/GSE51403_expression_matrix_Control_1.txt" />
100 </conditional> 100 <param name="samples_0|column_index" value="2" />
101 101
102 <param name="remove_comment_lines" value="false" /> 102 <conditional name="add_lengths">
103 103 <param name="choice" value="false" />
104 <output name="expression_matrix" file="GSE51403/GSE51403_expression_matrix_Control_1.txt" /> 104 </conditional>
105 </test> 105
106 <test> 106 <param name="remove_comment_lines" value="false" />
107 <conditional name="add_geneids"> 107
108 <param name="choice" value="true" /> 108 <output name="expression_matrix" file="GSE51403/GSE51403_expression_matrix_Control_1.txt" />
109 <param name="sample_geneids" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" /> 109 </test>
110 <param name="column_geneids" value="1" /> 110 <test>
111 </conditional> 111 <conditional name="add_geneids">
112 112 <param name="choice" value="true" />
113 <!-- <repeat name="samples"> --> 113 <param name="sample_geneids" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" />
114 <param name="samples_0|sample" value="GSE51403/GSE51403_expression_matrix_Control_1.txt" /> 114 <param name="column_geneids" value="1" />
115 <param name="samples_0|column_index" value="2" /> 115 </conditional>
116 <!-- </repeat> --> 116
117 117 <!-- <repeat name="samples"> -->
118 <!-- <repeat name="samples"> --> 118 <param name="samples_0|sample" value="GSE51403/GSE51403_expression_matrix_Control_1.txt" />
119 <param name="samples_1|sample" value="GSE51403/GSE51403_expression_matrix_Control_2.txt" /> 119 <param name="samples_0|column_index" value="2" />
120 <param name="samples_1|column_index" value="2" /> 120 <!-- </repeat> -->
121 <!-- </repeat> --> 121
122 122 <!-- <repeat name="samples"> -->
123 <!-- <repeat name="samples"> --> 123 <param name="samples_1|sample" value="GSE51403/GSE51403_expression_matrix_Control_2.txt" />
124 <param name="samples_2|sample" value="GSE51403/GSE51403_expression_matrix_Control_3.txt" /> 124 <param name="samples_1|column_index" value="2" />
125 <param name="samples_2|column_index" value="2" /> 125 <!-- </repeat> -->
126 <!-- </repeat> --> 126
127 127 <!-- <repeat name="samples"> -->
128 <!-- <repeat name="samples"> --> 128 <param name="samples_2|sample" value="GSE51403/GSE51403_expression_matrix_Control_3.txt" />
129 <param name="samples_3|sample" value="GSE51403/GSE51403_expression_matrix_Control_4.txt" /> 129 <param name="samples_2|column_index" value="2" />
130 <param name="samples_3|column_index" value="2" /> 130 <!-- </repeat> -->
131 <!-- </repeat> --> 131
132 132 <!-- <repeat name="samples"> -->
133 <!-- <repeat name="samples"> --> 133 <param name="samples_3|sample" value="GSE51403/GSE51403_expression_matrix_Control_4.txt" />
134 <param name="samples_4|sample" value="GSE51403/GSE51403_expression_matrix_Control_5.txt" /> 134 <param name="samples_3|column_index" value="2" />
135 <param name="samples_4|column_index" value="2" /> 135 <!-- </repeat> -->
136 <!-- </repeat> --> 136
137 137 <!-- <repeat name="samples"> -->
138 <!-- <repeat name="samples"> --> 138 <param name="samples_4|sample" value="GSE51403/GSE51403_expression_matrix_Control_5.txt" />
139 <param name="samples_5|sample" value="GSE51403/GSE51403_expression_matrix_Control_6.txt" /> 139 <param name="samples_4|column_index" value="2" />
140 <param name="samples_5|column_index" value="2" /> 140 <!-- </repeat> -->
141 <!-- </repeat> --> 141
142 142 <!-- <repeat name="samples"> -->
143 <!-- <repeat name="samples"> --> 143 <param name="samples_5|sample" value="GSE51403/GSE51403_expression_matrix_Control_6.txt" />
144 <param name="samples_6|sample" value="GSE51403/GSE51403_expression_matrix_Control_7.txt" /> 144 <param name="samples_5|column_index" value="2" />
145 <param name="samples_6|column_index" value="2" /> 145 <!-- </repeat> -->
146 <!-- </repeat> --> 146
147 147 <!-- <repeat name="samples"> -->
148 <!-- <repeat name="samples"> --> 148 <param name="samples_6|sample" value="GSE51403/GSE51403_expression_matrix_Control_7.txt" />
149 <param name="samples_7|sample" value="GSE51403/GSE51403_expression_matrix_E2.txt" /> 149 <param name="samples_6|column_index" value="2" />
150 <param name="samples_7|column_index" value="2,3,4,5,6,7,8" /> 150 <!-- </repeat> -->
151 <!-- </repeat> --> 151
152 152 <!-- <repeat name="samples"> -->
153 <conditional name="add_lengths"> 153 <param name="samples_7|sample" value="GSE51403/GSE51403_expression_matrix_E2.txt" />
154 <param name="choice" value="true" /> 154 <param name="samples_7|column_index" value="2,3,4,5,6,7,8" />
155 <param name="sample_lengths" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" /> 155 <!-- </repeat> -->
156 <param name="column_lengths" value="2" /> 156
157 </conditional> 157 <conditional name="add_lengths">
158 158 <param name="choice" value="true" />
159 <param name="remove_comment_lines" value="false" /> 159 <param name="sample_lengths" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" />
160 160 <param name="column_lengths" value="2" />
161 <output name="expression_matrix" file="GSE51403/GSE51403_expression_matrix_full.txt" /> 161 </conditional>
162 </test> 162
163 </tests> 163 <param name="remove_comment_lines" value="false" />
164 164
165 <help> 165 <output name="expression_matrix" file="GSE51403/GSE51403_expression_matrix_full.txt" />
166 </test>
167 </tests>
168
169 <help>
166 edgeR: Concatenate Expression Matrices 170 edgeR: Concatenate Expression Matrices
167 ####################################### 171 #######################################
168 172
169 Overview 173 Overview
170 -------- 174 --------
177 If you export tables using R, make sure you set: col.names=NA. Otherwise column may be swapped during concatenation. 181 If you export tables using R, make sure you set: col.names=NA. Otherwise column may be swapped during concatenation.
178 182
179 Input 183 Input
180 ----- 184 -----
181 185
182 186 @CONTACT@
183 Contact 187 </help>
184 ------- 188
185 189 <expand macro="citations" />
186 The tool wrapper has been written by Youri Hoogstrate from the Erasmus
187 Medical Center (Rotterdam, Netherlands) on behalf of the Translational
188 Research IT (TraIT) project:
189
190 http://www.ctmm.nl/en/programmas/infrastructuren/traitprojecttranslationeleresearch
191
192 More tools by the Translational Research IT (TraIT) project can be found
193 in the following toolsheds:
194
195 http://toolshed.dtls.nl/
196
197 http://toolshed.g2.bx.psu.edu
198
199 http://testtoolshed.g2.bx.psu.edu/
200 </help>
201
202 <citations>
203 <citation type="doi">10.1093/bioinformatics/btp616</citation>
204 <citation type="doi">10.1093/bioinformatics/btt688</citation>
205 </citations>
206 </tool> 190 </tool>