fixed effects, random effects , corrections methods modified and vers…

…ion bumped

tools/maaslin2/maaslin2.xml

@@ -7,6 +7,29 @@
     <expand macro="xrefs"/>
     <expand macro="requirements"/>
     <command detect_errors="exit_code"><![CDATA[
+    
+## get column names of fixed and random effect from the input file, since galaxy 
+## can only return indices with type="data_column" 
+## using awk so that the file is only parsed on command line execution
+
+#set idx = []
+#for $i in $fixed_effects:
+    #silent idx.append(f'${i}')
+#end for
+#set idx_for_awk = ','.join(idx)
+
+fixed_effects=`awk -v OFS=',' -F"\t" 'NR == 1 { print $idx_for_awk}' '$input_metadata'` &&
+echo 'Assigned fixed effects as:' \$fixed_effects &&
+
+#set idx = []
+#for $i in $random_effects:
+    #silent idx.append(f'${i}')
+#end for
+#set idx_for_awk = ','.join(idx)
+
+random_effects=`awk -v OFS=',' -F"\t" 'NR == 1 { print $idx_for_awk}' '$input_metadata'` &&
+echo 'Assigned random effects as:' \$random_effects &&
+
 ln -s '$input_data' 'input_data.tsv'
 &&
 ln -s '$input_metadata' 'input_metadata.tsv'
@@ -31,10 +54,10 @@ Maaslin2.R
     --analysis_method '$additional_options.analysis_method'
 #end if
 #if $random_effects
-    --random_effects '$random_effects'
+    --random_effects \$random_effects
 #end if
 #if $fixed_effects
-    --fixed_effects '$fixed_effects'
+    --fixed_effects \$fixed_effects
 #end if
 #if $additional_options.correction
     --correction '$additional_options.correction'
@@ -51,19 +74,17 @@ Maaslin2.R
     'outputFolder'
 &&
 cd outputFolder && mkdir -p figures/ && cp *.pdf figures
+
     ]]></command>
     <inputs>
         <param name="input_data" type="data" format="tabular" label="Data (or features) file"/>
         <param name="input_metadata" type="data" format="tabular" label="Metadata file"/>
-        <param argument="--fixed_effects" type="text" multiple="true" optional="true" label="Interactions: Fixed effects" help="The fixed effects for the model, comma-delimited for multiple effects">
-            <option value="diagnosis" selected="true">diagnosis</option>
-            <option value="dysbiosisnonIBD" selected="true">dysbiosisnonIBD</option>
-            <option value="dysbiosisUC" selected="true">dysbiosisUC</option>
-            <option value="dysbiosisCD" selected="true">dysbiosisCD</option>
-            <option value="antibiotics" selected="true">antibiotics</option>
-            <option value="age" selected="true">age</option>
-        </param>        
-        <param argument="--random_effects" type="text" multiple="true" optional="true" label="Random effects" help="The random effects for the model,  comma-delimited for multiple effects"/>        
+        <param argument="--fixed_effects" type="data_column" data_ref="input_metadata" use_header_names="true"  multiple="true" optional="true" label="Interactions: Fixed effects" help="The fixed effects for the model, comma-delimited for multiple effects" />
+
+        <param argument="--random_effects" type="data_column" data_ref="input_metadata" use_header_names="true" multiple="true" optional="true" label="Random effects" help="The random effects for the model,  comma-delimited for multiple effects" />
+
+
+
         <section name="additional_options" title="Additional Options" expanded="true">
             <param argument="--min_abundance" type="float" value="0.0" optional="true" label="Minimum abundance" help="The minimum abundance for each feature"/>
             <param argument="--min_prevalence" type="float" value="0.1" optional="true" label="Minimum prevalence" help="The minimum percent of samples for which a feature is detected at minimum abundance"/>
@@ -87,13 +108,13 @@ cd outputFolder && mkdir -p figures/ && cp *.pdf figures
                 <option value="NEGBIN">NEGBIN</option>
                 <option value="ZINB">ZINB</option>
             </param>
-            <param argument="--correction" type="select" value="BH" multiple="true" optional="true" label="Correction" help="The correction method for computing  the q-value">
-            <option value="holm">holm</option>
-            <option value="hochberg">hochberg</option>
-            <option value="hommel">hommel</option>
-            <option value="bonferroni">bonferroni</option>
-            <option value="BH">BH</option>
-            <option value="BY">BY</option>
+            <param argument="--correction" type="select" value="BH" multiple="true" optional="true" label="Correction" help="The correction method for computing  the q-value ">
+                <option value="holm">Holm</option>
+                <option value="hochberg">Hochberg</option>
+                <option value="hommel">Hommel</option>
+                <option value="bonferroni">Bonferroni</option>
+                <option value="BH">Benjamini-Hochberg(BH)</option>
+                <option value="BY">Benjamini-Yekutieli(BY)</option>
             </param>
             <param argument="--standardize" type="boolean" truevalue="--standardize TRUE" falsevalue="--standardize FALSE" checked="true" label="Apply z-score so continuous metadata are on  the same scale"/>
         </section>          
@@ -122,8 +143,8 @@ cd outputFolder && mkdir -p figures/ && cp *.pdf figures
         <test expect_num_outputs="5">
             <param name="input_data" value="HMP2_taxonomy.tsv"/>
             <param name="input_metadata" value="HMP2_metadata.tsv"/>
-            <param name="random_effects" value="site,subject"/>
-            <param name="fixed_effects" value="diagnosis,dysbiosisnonIBD,dysbiosisUC,dysbiosisCD,antibiotics,age"/>
+            <param name="random_effects" value= "c2: site,c5: subject"/> 
+            <param name="fixed_effects" value="c4: diagnosis,c9: dysbiosisnonIBD,c10: dysbiosisUC,c11: dysbiosisCD,c6: antibiotics,c3: age"/> 
             <section name="additional_options">
                 <param name="min_abundance" value="0.0"/>
                 <param name="min_prevalence" value="0.1"/>
@@ -205,7 +226,7 @@ cd outputFolder && mkdir -p figures/ && cp *.pdf figures
         <test expect_num_outputs="5">
             <param name="input_data" value="HMP2_taxonomy.tsv"/>
             <param name="input_metadata" value="HMP2_metadata.tsv"/>
-            <param name="fixed_effects" value="diagnosis,dysbiosisnonIBD"/>
+            <param name="fixed_effects" value="c4: diagnosis,c9: dysbiosisnonIBD"/>
             <section name="additional_options">
                 <param name="min_abundance" value="0.0"/>
                 <param name="min_prevalence" value="0.1"/>
@@ -252,7 +273,7 @@ cd outputFolder && mkdir -p figures/ && cp *.pdf figures
         <test expect_num_outputs="5">
             <param name="input_data" value="HMP2_taxonomy.tsv"/>
             <param name="input_metadata" value="HMP2_metadata.tsv"/>
-            <param name="fixed_effects" value="diagnosis,dysbiosisnonIBD"/>
+            <param name="fixed_effects" value="c4: diagnosis,c9: dysbiosisnonIBD"/>
             <section name="additional_options">
                 <param name="min_abundance" value="0.0001"/>
                 <param name="min_prevalence" value="0.1"/>
@@ -354,6 +375,9 @@ Output
         - It only includes associations with q-values <= to the threshold.
     - Data frame with residuals for each feature (R data file)
         - This file contains a data frame with residuals for each feature.
+        
+Correction methods to compute the q-value : https://www.rdocumentation.org/packages/stats/versions/3.6.2/topics/p.adjust
+
 2- Visualization output files
     - Heatmap of the significant associations (PDF file)
         - This file contains a heatmap of the significant associations.

tools/maaslin2/macros.xml

@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
 <macros>
-    <token name="@TOOL_VERSION@">0.99.12</token>
+    <token name="@TOOL_VERSION@">1.7.3</token>
     <token name="@VERSION_SUFFIX@">0</token>
     <token name="@PROFILE@">20.01</token>
     <xml name="edam_ontology">
@@ -21,4 +21,4 @@
             <yield/>
         </requirements>
     </xml>
- </macros>
+ </macros>