Mercurial > repos > yhoogstrate > edger_with_design_matrix
comparison edgeR_Concatenate_Expression_Matrices.xml @ 1:a4a4c88783ea draft
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 04:59:05 -0400 |
| parents | |
| children | ec951a5017f8 |
comparison
equal
deleted
inserted
replaced
| 0:acb56603b268 | 1:a4a4c88783ea |
|---|---|
| 1 <?xml version="1.0" encoding="UTF-8"?> | |
| 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> | |
| 4 | |
| 5 <macros> | |
| 6 <import>edgeR_macros.xml</import> | |
| 7 </macros> | |
| 8 | |
| 9 <command> | |
| 10 #set $j = 0 | |
| 11 #set $paste = [] | |
| 12 | |
| 13 #if $add_geneids.choice == "true": | |
| 14 #set $filename = str($j)+".txt" | |
| 15 #set paste = paste + [$filename] | |
| 16 | |
| 17 cut -f $add_geneids.column_geneids.value "$add_geneids.sample_geneids" > $filename ; | |
| 18 #set $j += 1 | |
| 19 #end if | |
| 20 | |
| 21 #for $sample in $samples: | |
| 22 ##echo "$sample.column_index" | |
| 23 ##echo "$sample.column_index.value" | |
| 24 | |
| 25 #set $column_str = ",".join([str(x).strip() for x in $sample.column_index.value]) | |
| 26 #set $filename = str($j)+".txt" | |
| 27 #set paste = paste + [$filename] | |
| 28 | |
| 29 cut -f "$column_str" "$sample.sample" > $filename ; | |
| 30 #set $j += 1 | |
| 31 #end for | |
| 32 | |
| 33 #if $add_lengths.choice == "true": | |
| 34 #set $filename = str($j)+".txt" | |
| 35 #set paste = paste + [$filename] | |
| 36 | |
| 37 cut -f $add_lengths.column_lengths.value "$add_lengths.sample_lengths" > $filename ; | |
| 38 #set $j += 1 | |
| 39 #end if | |
| 40 | |
| 41 #set $paste_str = " ".join([str(x).strip() for x in $paste]) | |
| 42 | |
| 43 paste $paste_str > $expression_matrix | |
| 44 </command> | |
| 45 | |
| 46 <inputs> | |
| 47 <conditional name="add_geneids"> | |
| 48 <param name="choice" type="select" label="Add a gene-IDs column at the end of the file" help="Highly recommended to select!" > | |
| 49 <option value="false">No</option> | |
| 50 <option value="true" selected="true">Yes</option> | |
| 51 </param> | |
| 52 <when value="false" /> | |
| 53 <when value="true"> | |
| 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 <param name="column_geneids" numerical="false" use_header_names="true" label="Select GeneID column" type="data_column" data_ref="sample_geneids" multiple="false"> | |
| 56 <validator type="no_options" message="Please select at least one column." /> | |
| 57 </param> | |
| 58 </when> | |
| 59 </conditional> | |
| 60 | |
| 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 name="sample" type="data" format="tabular" label="Read-count dataset that belongs to a pair" help="from featureCounts/DEXSeq-count/HTSeq-count, etc." /> | |
| 63 <!-- select columns --> | |
| 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 <validator type="no_options" message="Please select at least one column." /> | |
| 66 </param> | |
| 67 </repeat> | |
| 68 | |
| 69 <conditional name="add_lengths"> | |
| 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 <option value="false">No</option> | |
| 72 <option value="true">Yes</option> | |
| 73 </param> | |
| 74 <when value="false" /> | |
| 75 <when value="true"> | |
| 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 <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 <validator type="no_options" message="Please select at least one column." /> | |
| 79 </param> | |
| 80 </when> | |
| 81 </conditional> | |
| 82 | |
| 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 | |
| 85 </inputs> | |
| 86 | |
| 87 <outputs> | |
| 88 <data format="tabular" name="expression_matrix" label="Expression matrix" /> | |
| 89 </outputs> | |
| 90 | |
| 91 <tests> | |
| 92 <test> | |
| 93 <conditional name="add_geneids"> | |
| 94 <param name="choice" value="true" /> | |
| 95 <param name="sample_geneids" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" /> | |
| 96 <param name="column_geneids" value="1" /> | |
| 97 </conditional> | |
| 98 | |
| 99 <param name="samples_0|sample" value="GSE51403/GSE51403_expression_matrix_Control_1.txt" /> | |
| 100 <param name="samples_0|column_index" value="2" /> | |
| 101 | |
| 102 <conditional name="add_lengths"> | |
| 103 <param name="choice" value="false" /> | |
| 104 </conditional> | |
| 105 | |
| 106 <param name="remove_comment_lines" value="false" /> | |
| 107 | |
| 108 <output name="expression_matrix" file="GSE51403/GSE51403_expression_matrix_Control_1.txt" /> | |
| 109 </test> | |
| 110 <test> | |
| 111 <conditional name="add_geneids"> | |
| 112 <param name="choice" value="true" /> | |
| 113 <param name="sample_geneids" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" /> | |
| 114 <param name="column_geneids" value="1" /> | |
| 115 </conditional> | |
| 116 | |
| 117 <!-- <repeat name="samples"> --> | |
| 118 <param name="samples_0|sample" value="GSE51403/GSE51403_expression_matrix_Control_1.txt" /> | |
| 119 <param name="samples_0|column_index" value="2" /> | |
| 120 <!-- </repeat> --> | |
| 121 | |
| 122 <!-- <repeat name="samples"> --> | |
| 123 <param name="samples_1|sample" value="GSE51403/GSE51403_expression_matrix_Control_2.txt" /> | |
| 124 <param name="samples_1|column_index" value="2" /> | |
| 125 <!-- </repeat> --> | |
| 126 | |
| 127 <!-- <repeat name="samples"> --> | |
| 128 <param name="samples_2|sample" value="GSE51403/GSE51403_expression_matrix_Control_3.txt" /> | |
| 129 <param name="samples_2|column_index" value="2" /> | |
| 130 <!-- </repeat> --> | |
| 131 | |
| 132 <!-- <repeat name="samples"> --> | |
| 133 <param name="samples_3|sample" value="GSE51403/GSE51403_expression_matrix_Control_4.txt" /> | |
| 134 <param name="samples_3|column_index" value="2" /> | |
| 135 <!-- </repeat> --> | |
| 136 | |
| 137 <!-- <repeat name="samples"> --> | |
| 138 <param name="samples_4|sample" value="GSE51403/GSE51403_expression_matrix_Control_5.txt" /> | |
| 139 <param name="samples_4|column_index" value="2" /> | |
| 140 <!-- </repeat> --> | |
| 141 | |
| 142 <!-- <repeat name="samples"> --> | |
| 143 <param name="samples_5|sample" value="GSE51403/GSE51403_expression_matrix_Control_6.txt" /> | |
| 144 <param name="samples_5|column_index" value="2" /> | |
| 145 <!-- </repeat> --> | |
| 146 | |
| 147 <!-- <repeat name="samples"> --> | |
| 148 <param name="samples_6|sample" value="GSE51403/GSE51403_expression_matrix_Control_7.txt" /> | |
| 149 <param name="samples_6|column_index" value="2" /> | |
| 150 <!-- </repeat> --> | |
| 151 | |
| 152 <!-- <repeat name="samples"> --> | |
| 153 <param name="samples_7|sample" value="GSE51403/GSE51403_expression_matrix_E2.txt" /> | |
| 154 <param name="samples_7|column_index" value="2,3,4,5,6,7,8" /> | |
| 155 <!-- </repeat> --> | |
| 156 | |
| 157 <conditional name="add_lengths"> | |
| 158 <param name="choice" value="true" /> | |
| 159 <param name="sample_lengths" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" /> | |
| 160 <param name="column_lengths" value="2" /> | |
| 161 </conditional> | |
| 162 | |
| 163 <param name="remove_comment_lines" value="false" /> | |
| 164 | |
| 165 <output name="expression_matrix" file="GSE51403/GSE51403_expression_matrix_full.txt" /> | |
| 166 </test> | |
| 167 </tests> | |
| 168 | |
| 169 <help> | |
| 170 edgeR: Concatenate Expression Matrices | |
| 171 ####################################### | |
| 172 | |
| 173 Overview | |
| 174 -------- | |
| 175 | |
| 176 Create subsets from or combined expression matrices. | |
| 177 | |
| 178 **Notes** | |
| 179 | |
| 180 Make sure the tables have an identical number of columns compared to the number of headers. | |
| 181 If you export tables using R, make sure you set: col.names=NA. Otherwise column may be swapped during concatenation. | |
| 182 | |
| 183 Input | |
| 184 ----- | |
| 185 | |
| 186 @CONTACT@ | |
| 187 </help> | |
| 188 | |
| 189 <expand macro="citations" /> | |
| 190 </tool> |
