diff deseq2.xml @ 15:9a616afdbda5 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/deseq2 commit 83eb5b2665d87c02b270596f8175499e69061032
author iuc
date Sat, 19 May 2018 03:55:48 -0400
parents d0c39b5e78cf
children a416957ee305
line wrap: on
line diff
--- a/deseq2.xml	Thu Apr 12 17:29:45 2018 -0400
+++ b/deseq2.xml	Sat May 19 03:55:48 2018 -0400
@@ -1,4 +1,4 @@
-<tool id="deseq2" name="DESeq2" version="2.11.40.1">
+<tool id="deseq2" name="DESeq2" version="2.11.40.2">
     <description>Determines differentially expressed features from count tables</description>
     <requirements>
         <requirement type="package" version="1.18.1">bioconductor-deseq2</requirement>
@@ -58,6 +58,9 @@
         $temp_factor.reverse()
         $temp_factor_names.append([str($factor.factorName), $temp_factor])
     #end for
+
+    $header
+
     -f '#echo json.dumps(temp_factor_names)#'
     -l '#echo json.dumps(filename_to_element_identifiers)#'
     -t $fit_type
@@ -103,6 +106,8 @@
             </repeat>
         </repeat>
 
+        <param name="header" type="boolean" truevalue="-H" falsevalue="" checked="true" label="Files have header?" help="If this option is set to Yes, the tool will assume that the count files have column headers in the first row. Default: Yes" />
+
         <conditional name="tximport">
             <param name="tximport_selector" type="select" label="Choice of Input data">
                 <option value="count" selected="True">Count data (e.g. from HTSeq-count, featureCounts or StringTie)</option>
@@ -174,7 +179,7 @@
         </data>
     </outputs>
     <tests>
-        <!--Ensure tables output works-->
+        <!--Ensure counts files with header works -->
         <test expect_num_outputs="2">
             <repeat name="rep_factorName">
                 <param name="factorName" value="Treatment"/>
@@ -189,8 +194,45 @@
             </repeat>
             <param name="pdf" value="False"/>
             <param name="normCounts" value="True"/>
-            <output name="counts_out" file="normalized_readcounts.tab"/>
-            <output name="deseq_out" file="deseq2_out.tab"/>
+            <output name="counts_out">
+                <assert_contents>
+                    <has_text_matching expression="untreat1\tuntreat2\tuntreat3\tuntreat4\ttreat1\ttreat2\ttreat3" />
+                    <has_text_matching expression="FBgn0000003\t0\t0\t0\t0\t0\t0\t0" />
+                </assert_contents>
+            </output>
+            <output name="deseq_out" >
+                <assert_contents>
+                    <has_text_matching expression="FBgn0003360\t1933.9504.*\t-2.8399.*\t0.1309.*-21.6851.*2.831.*8.024" />
+                </assert_contents>
+            </output>
+        </test>
+        <!--Ensure counts files without header works -->
+        <test expect_num_outputs="2">
+            <repeat name="rep_factorName">
+                <param name="factorName" value="Treatment"/>
+                <repeat name="rep_factorLevel">
+                    <param name="factorLevel" value="Treated"/>
+                    <param name="countsFile" value="GSM461179_treat_single.counts.noheader,GSM461180_treat_paired.counts.noheader,GSM461181_treat_paired.counts.noheader"/>
+                </repeat>
+                <repeat name="rep_factorLevel">
+                    <param name="factorLevel" value="Untreated"/>
+                    <param name="countsFile" value="GSM461176_untreat_single.counts.noheader,GSM461177_untreat_paired.counts.noheader,GSM461178_untreat_paired.counts.noheader,GSM461182_untreat_single.counts.noheader"/>
+                </repeat>
+            </repeat>
+            <param name="header" value="False"/>
+            <param name="pdf" value="False"/>
+            <param name="normCounts" value="True"/>
+            <output name="counts_out">
+                <assert_contents>
+                    <has_text_matching expression="GSM461176_untreat_single.counts.noheader\tGSM461177_untreat_paired.counts.noheader\tGSM461178_untreat_paired.counts.noheader\tGSM461182_untreat_single.counts.noheader\tGSM461179_treat_single.counts.noheader\tGSM461180_treat_paired.counts.noheader\tGSM461181_treat_paired.counts.noheader" />
+                    <has_text_matching expression="FBgn0000003\t0\t0\t0\t0\t0\t0\t0" />
+                </assert_contents>
+            </output>
+            <output name="deseq_out" >
+                <assert_contents>
+                    <has_text_matching expression="FBgn0003360\t1933.9504.*\t-2.8399.*\t0.1309.*-21.6851.*2.831.*8.024" />
+                </assert_contents>
+            </output>
         </test>
         <!--Ensure Sailfish/Salmon input with tx2gene table works-->
         <test expect_num_outputs="1">
@@ -210,8 +252,12 @@
             <param name="txtype" value="sailfish"/>
             <param name="mapping_format_selector" value="tabular"/>
             <param name="tabular_file" value="tx2gene.tab"/>
-            <output name="deseq_out" file="sailfish/out_deseq2_sailfish.tab"/>
-        </test>               
+            <output name="deseq_out" >
+                <assert_contents>
+                    <has_text_matching expression="MIR6859-2\t1.1858.*\t-1.5832.*\t1.2956.*\t-1.2219.*\t0.2217.*\t0.8868.*" />
+                </assert_contents>
+            </output>
+        </test>
     </tests>
     <help><![CDATA[
 .. class:: infomark
@@ -226,7 +272,7 @@
 
 **Count Files**
 
-DESeq2_ takes count tables generated from **featureCounts**, **HTSeq-count** or **StringTie** as input. Count tables must be generated for each sample individually, should have no header rows, and rows should be in the same order. DESeq2 is capable of handling multiple factors that affect your experiment. The first factor you input is considered as the primary factor that affects gene expressions. Optionally, you can input one or more 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.
+DESeq2_ takes count tables generated from **featureCounts**, **HTSeq-count** or **StringTie** as input. Count tables must be generated for each sample individually. One header row is assumed, but files with no header (e.g from HTSeq) can be input with the *Files have header?* option set to No. DESeq2 is capable of handling multiple factors that affect your experiment. The first factor you input is considered as the primary factor that affects gene expressions. Optionally, you can input one or more 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.
 
 The following table gives some examples of factors and their levels:
 
@@ -246,7 +292,7 @@
 
 *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.
 
-DESeq2_ can also take transcript-level counts from quantification tools such as, **kallisto**, **Salmon** and **Sailfish**, and this Galaxy wrapper incorporates the Bioconductor tximport_ package to process the transcript counts for DESeq2. 
+DESeq2_ can also take transcript-level counts from quantification tools such as, **kallisto**, **Salmon** and **Sailfish**, and this Galaxy wrapper incorporates the Bioconductor tximport_ package to process the transcript counts for DESeq2.
 
 **Salmon or Sailfish Files**
 
@@ -275,17 +321,17 @@
 Example:
 
 ============ ========== =============== =========== ===========
-target_id    length     eff_length      est_counts  tpm 
+target_id    length     eff_length      est_counts  tpm
 ------------ ---------- --------------- ----------- -----------
-NR_001526    164        20.4518         0           0          
-NR_001526_1  164        20.4518         0           0          
-NR_001526_2  164        20.4518         0           0          
-NM_130786    1764       1956.04         109.165     2.47415    
-NR_015380    2129       2139.53         85.5821     1.77331    
+NR_001526    164        20.4518         0           0
+NR_001526_1  164        20.4518         0           0
+NR_001526_2  164        20.4518         0           0
+NM_130786    1764       1956.04         109.165     2.47415
+NR_015380    2129       2139.53         85.5821     1.77331
 NM_001198818 9360       7796.58         4.19648e-05 2.38616e-07
-NM_001198819 9527       7964.62         0           0          
-NM_001198820 9410       7855.78         0           0          
-NM_014576    9267       7714.88         8.37255     0.0481114  
+NM_001198819 9527       7964.62         0           0
+NM_001198820 9410       7855.78         0           0
+NM_014576    9267       7714.88         8.37255     0.0481114
 ============ ========== =============== =========== ===========
 
 -----