|
27
|
1 <?xml version="1.0" encoding="UTF-8"?>
|
|
|
2 <tool id="concatenate_expression_matrices" name="edgeR: Concatenate Expression Matrices">
|
|
|
3 <description>Create a full expression matrix by selecting the desired columns from specific count tables</description>
|
|
|
4
|
|
|
5 <command>
|
|
|
6 #set $j = 0
|
|
|
7 #set $paste = []
|
|
|
8
|
|
|
9 #if $add_geneids.choice == "true":
|
|
|
10 #set $filename = str($j)+".txt"
|
|
|
11 #set paste = paste + [$filename]
|
|
|
12
|
|
|
13 cut -f $add_geneids.column_geneids.value "$add_geneids.sample_geneids" > $filename ;
|
|
|
14 #set $j += 1
|
|
|
15 #end if
|
|
|
16
|
|
|
17 #for $sample in $samples:
|
|
|
18 ##echo "$sample.column_index"
|
|
|
19 ##echo "$sample.column_index.value"
|
|
|
20
|
|
|
21 #set $column_str = ",".join([str(x).strip() for x in $sample.column_index.value])
|
|
|
22 #set $filename = str($j)+".txt"
|
|
|
23 #set paste = paste + [$filename]
|
|
|
24
|
|
|
25 cut -f "$column_str" "$sample.sample" > $filename ;
|
|
|
26 #set $j += 1
|
|
|
27 #end for
|
|
|
28
|
|
|
29 #if $add_lengths.choice == "true":
|
|
|
30 #set $filename = str($j)+".txt"
|
|
|
31 #set paste = paste + [$filename]
|
|
|
32
|
|
|
33 cut -f $add_lengths.column_lengths.value "$add_lengths.sample_lengths" > $filename ;
|
|
|
34 #set $j += 1
|
|
|
35 #end if
|
|
|
36
|
|
|
37 #set $paste_str = " ".join([str(x).strip() for x in $paste])
|
|
|
38
|
|
|
39 paste $paste_str > $expression_matrix
|
|
|
40 </command>
|
|
|
41
|
|
|
42 <inputs>
|
|
|
43 <conditional name="add_geneids">
|
|
|
44 <param name="choice" type="select" label="Add a gene-IDs column at the end of the file" help="Highly recommended to select!" >
|
|
|
45 <option value="false">No</option>
|
|
|
46 <option value="true" selected="true">Yes</option>
|
|
|
47 </param>
|
|
|
48 <when value="false" />
|
|
|
49 <when value="true">
|
|
|
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." />
|
|
|
51 <param name="column_geneids" numerical="false" use_header_names="true" label="Select GeneID column" type="data_column" data_ref="sample_geneids" multiple="false">
|
|
|
52 <validator type="no_options" message="Please select at least one column." />
|
|
|
53 </param>
|
|
|
54 </when>
|
|
|
55 </conditional>
|
|
|
56
|
|
|
57 <repeat name="samples" title="Expression Table" help="E.g. a earlier concatenated table, or a HT-seq, featureCounts or DESeq-count result.">
|
|
|
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." />
|
|
|
59 <!-- select columns -->
|
|
|
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">
|
|
|
61 <validator type="no_options" message="Please select at least one column." />
|
|
|
62 </param>
|
|
|
63 </repeat>
|
|
|
64
|
|
|
65 <conditional name="add_lengths">
|
|
|
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." >
|
|
|
67 <option value="false">No</option>
|
|
|
68 <option value="true">Yes</option>
|
|
|
69 </param>
|
|
|
70 <when value="false" />
|
|
|
71 <when value="true">
|
|
|
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." />
|
|
|
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">
|
|
|
74 <validator type="no_options" message="Please select at least one column." />
|
|
|
75 </param>
|
|
|
76 </when>
|
|
|
77 </conditional>
|
|
|
78
|
|
|
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." />
|
|
|
80
|
|
|
81 </inputs>
|
|
|
82
|
|
|
83 <outputs>
|
|
|
84 <data format="tabular" name="expression_matrix" label="Expression matrix" />
|
|
|
85 </outputs>
|
|
|
86
|
|
|
87 <tests>
|
|
|
88 <test>
|
|
|
89 <param name="add_geneids.choice" value="true" />
|
|
|
90 <param name="choice" value="true" />
|
|
|
91 <param name="add_geneids" value="true" />
|
|
|
92
|
|
|
93
|
|
|
94 <!--
|
|
|
95 Add a gene-IDs column at the end of the file true
|
|
|
96 Select Read-count dataset that contains a column for GeneIDs 21: MCF7_featureCounts_E2.txt
|
|
|
97 Select GeneID column 1
|
|
|
98 Read-count dataset that belongs to a pair 14: MCF7_featureCounts_Control_1.txt
|
|
|
99 Select columns that are associated with this factor level 2
|
|
|
100 Read-count dataset that belongs to a pair 15: MCF7_featureCounts_Control_2.txt
|
|
|
101 Select columns that are associated with this factor level 2
|
|
|
102 Read-count dataset that belongs to a pair 16: MCF7_featureCounts_Control_3.txt
|
|
|
103 Select columns that are associated with this factor level 2
|
|
|
104 Read-count dataset that belongs to a pair 17: MCF7_featureCounts_Control_4.txt
|
|
|
105 Select columns that are associated with this factor level 2
|
|
|
106 Read-count dataset that belongs to a pair 18: MCF7_featureCounts_Control_5.txt
|
|
|
107 Select columns that are associated with this factor level 2
|
|
|
108 Read-count dataset that belongs to a pair 22: MCF7_featureCounts_Control_6.txt
|
|
|
109 Select columns that are associated with this factor level 2
|
|
|
110 Read-count dataset that belongs to a pair 20: MCF7_featureCounts_Control_7.txt
|
|
|
111 Select columns that are associated with this factor level 2
|
|
|
112 Read-count dataset that belongs to a pair 21: MCF7_featureCounts_E2.txt
|
|
|
113 Select columns that are associated with this factor level 2 3 4 5 6 7 8
|
|
|
114 Add a gene-lengths column at the end of the file true
|
|
|
115 Read-count dataset that belongs to a pair 26: MCF7_featureCounts_GeneLengths.txt
|
|
|
116 Select columns that are associated with this factor level 2
|
|
|
117 Automatically remove 'comment' lines starting with a '#' False
|
|
|
118 -->
|
|
|
119
|
|
|
120 <output name="expression_matrix" file="MCF7_featureCounts_concatenated.txt" />
|
|
|
121 </test>
|
|
|
122 </tests>
|
|
|
123
|
|
|
124 <help>
|
|
|
125 edgeR: Concatenate Expression Matrices
|
|
|
126
|
|
|
127 **Notes**
|
|
|
128
|
|
|
129 Make sure the tables have an identical number of columns compared to the number of headers.
|
|
|
130 If you export tables using R, make sure you set: col.names=NA. Otherwise column may be swapped during concatenation.
|
|
|
131
|
|
|
132 **References**
|
|
|
133
|
|
|
134 The test data is coming from: doi: 10.1093/bioinformatics/btt688.
|
|
|
135 http://www.ncbi.nlm.nih.gov/pubmed/24319002
|
|
|
136
|
|
|
137 </help>
|
|
|
138 </tool>
|
