diff 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

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/edgeR_Concatenate_Expression_Matrices.xml	Tue Sep 01 04:59:05 2015 -0400
@@ -0,0 +1,190 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<tool id="concatenate_expression_matrices" name="edgeR: Concatenate Expression Matrices" version="1.0.0">
+    <description>Create a full expression matrix by selecting the desired columns from specific count tables</description>
+    
+    <macros>
+        <import>edgeR_macros.xml</import>
+    </macros>
+    
+    <command>
+        #set $j = 0
+        #set $paste = []
+        
+        #if $add_geneids.choice == "true":
+            #set $filename = str($j)+".txt"
+            #set paste = paste + [$filename]
+            
+            cut -f $add_geneids.column_geneids.value "$add_geneids.sample_geneids" > $filename ;
+            #set $j += 1
+        #end if
+        
+        #for $sample in $samples:
+            ##echo "$sample.column_index"
+            ##echo "$sample.column_index.value"
+            
+            #set $column_str = ",".join([str(x).strip() for x in $sample.column_index.value])
+            #set $filename = str($j)+".txt"
+            #set paste = paste + [$filename]
+            
+            cut -f "$column_str" "$sample.sample" > $filename ;
+            #set $j += 1
+        #end for
+        
+        #if $add_lengths.choice == "true":
+            #set $filename = str($j)+".txt"
+            #set paste = paste + [$filename]
+            
+            cut -f $add_lengths.column_lengths.value "$add_lengths.sample_lengths" > $filename ;
+            #set $j += 1
+        #end if
+        
+        #set $paste_str = " ".join([str(x).strip() for x in $paste])
+        
+        paste $paste_str > $expression_matrix
+    </command>
+    
+    <inputs>
+        <conditional name="add_geneids">
+            <param name="choice" type="select" label="Add a gene-IDs column at the end of the file" help="Highly recommended to select!" >
+                <option value="false">No</option>
+                <option value="true" selected="true">Yes</option>
+            </param>
+            <when value="false" />
+            <when value="true">
+                <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." />
+                <param name="column_geneids" numerical="false" use_header_names="true" label="Select GeneID column" type="data_column" data_ref="sample_geneids" multiple="false">
+                    <validator type="no_options" message="Please select at least one column." />
+                </param>
+            </when>
+        </conditional>
+        
+        <repeat name="samples" title="Expression Table" help="E.g. a earlier concatenated table, or a HT-seq, featureCounts or DESeq-count result.">
+            <param name="sample" type="data" format="tabular" label="Read-count dataset that belongs to a pair" help="from featureCounts/DEXSeq-count/HTSeq-count, etc." />
+            <!-- select columns  -->
+            <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">
+                <validator type="no_options" message="Please select at least one column." />
+            </param>
+        </repeat>
+        
+        <conditional name="add_lengths">
+            <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." >
+                <option value="false">No</option>
+                <option value="true">Yes</option>
+            </param>
+            <when value="false" />
+            <when value="true">
+                <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." />
+                <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">
+                    <validator type="no_options" message="Please select at least one column." />
+                </param>
+            </when>
+        </conditional>
+        
+        <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." />
+        
+    </inputs>
+    
+    <outputs>
+        <data format="tabular" name="expression_matrix" label="Expression matrix" />
+    </outputs>
+    
+    <tests>
+        <test>
+            <conditional name="add_geneids">
+                <param name="choice" value="true" />
+                <param name="sample_geneids" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" />
+                <param name="column_geneids" value="1" />
+            </conditional>
+            
+            <param name="samples_0|sample" value="GSE51403/GSE51403_expression_matrix_Control_1.txt" />
+            <param name="samples_0|column_index" value="2" />
+            
+            <conditional name="add_lengths">
+                <param name="choice" value="false" />
+            </conditional>
+            
+            <param name="remove_comment_lines" value="false" />
+            
+            <output name="expression_matrix" file="GSE51403/GSE51403_expression_matrix_Control_1.txt" />
+        </test>
+        <test>
+            <conditional name="add_geneids">
+                <param name="choice" value="true" />
+                <param name="sample_geneids" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" />
+                <param name="column_geneids" value="1" />
+            </conditional>
+            
+            <!-- <repeat name="samples"> -->
+                <param name="samples_0|sample" value="GSE51403/GSE51403_expression_matrix_Control_1.txt" />
+                <param name="samples_0|column_index" value="2" />
+            <!-- </repeat> -->
+            
+            <!-- <repeat name="samples"> -->
+                <param name="samples_1|sample" value="GSE51403/GSE51403_expression_matrix_Control_2.txt" />
+                <param name="samples_1|column_index" value="2" />
+            <!-- </repeat> -->
+            
+            <!-- <repeat name="samples"> -->
+                <param name="samples_2|sample" value="GSE51403/GSE51403_expression_matrix_Control_3.txt" />
+                <param name="samples_2|column_index" value="2" />
+            <!-- </repeat> -->
+            
+            <!-- <repeat name="samples"> -->
+                <param name="samples_3|sample" value="GSE51403/GSE51403_expression_matrix_Control_4.txt" />
+                <param name="samples_3|column_index" value="2" />
+            <!-- </repeat> -->
+            
+            <!-- <repeat name="samples"> -->
+                <param name="samples_4|sample" value="GSE51403/GSE51403_expression_matrix_Control_5.txt" />
+                <param name="samples_4|column_index" value="2" />
+            <!-- </repeat> -->
+            
+            <!-- <repeat name="samples"> -->
+                <param name="samples_5|sample" value="GSE51403/GSE51403_expression_matrix_Control_6.txt" />
+                <param name="samples_5|column_index" value="2" />
+            <!-- </repeat> -->
+            
+            <!-- <repeat name="samples"> -->
+                <param name="samples_6|sample" value="GSE51403/GSE51403_expression_matrix_Control_7.txt" />
+                <param name="samples_6|column_index" value="2" />
+            <!-- </repeat> -->
+            
+            <!-- <repeat name="samples"> -->
+                <param name="samples_7|sample" value="GSE51403/GSE51403_expression_matrix_E2.txt" />
+                <param name="samples_7|column_index" value="2,3,4,5,6,7,8" />
+            <!-- </repeat> -->
+            
+            <conditional name="add_lengths">
+                <param name="choice" value="true" />
+                <param name="sample_lengths" value="GSE51403/GSE51403_expression_matrix_GeneLengths.txt" />
+                <param name="column_lengths" value="2" />
+            </conditional>
+            
+            <param name="remove_comment_lines" value="false" />
+            
+            <output name="expression_matrix" file="GSE51403/GSE51403_expression_matrix_full.txt" />
+        </test>
+    </tests>
+    
+    <help>
+edgeR: Concatenate Expression Matrices
+#######################################
+
+Overview
+--------
+
+Create subsets from or combined expression matrices.
+
+**Notes**
+
+Make sure the tables have an identical number of columns compared to the number of headers.
+If you export tables using R, make sure you set: col.names=NA. Otherwise column may be swapped during concatenation.
+
+Input
+-----
+
+@CONTACT@
+    </help>
+    
+    <expand macro="citations" />
+</tool>