Merge pull request #4 from paulzierep/mmuphin_wrapper

Mmuphin wrapper

tools/mmuphin/macros.xml

@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
 <macros>
-    <token name="@TOOL_VERSION@">1.18.1</token>
+    <token name="@TOOL_VERSION@">1.16.0</token>
     <token name="@VERSION_SUFFIX@">0</token>
     <token name="@PROFILE@">23.2</token>
 
@@ -13,12 +13,7 @@
     </xml>
     <xml name="requirements">
         <requirements>
-            <requirement type="package" version="@TOOL_VERSION@">bioconductor-mmuphin</requirement>
-            <requirement type="package" version="2.0.3">r-magrittr</requirement>
-            <requirement type="package" version="1.1.4">r-dplyr</requirement>
-            <requirement type="package" version="0.33">r-dt</requirement>
-        <requirement type="package" version="3.5.1">r-ggplot2</requirement>
-        <requirement type="package" version="2.1.5">r-readr</requirement>
+        <requirement type="package" version="@TOOL_VERSION@">bioconductor-mmuphin</requirement>
         </requirements>
     </xml>
     <xml name="citations">

tools/mmuphin/mmuphin.xml

@@ -6,47 +6,69 @@
     <expand macro="xrefs"/>
     <expand macro="requirements"/>
     <command detect_errors="exit_code"><![CDATA[
-        Rscript '$rscript'
+
+        ## get the batch name
+        export batch=`awk -v idx='$batch_input' -F"\t" 'NR == 1 { print \$idx }' '$input_metadata'` &&
+
+
+        ## get covariates names
+        #if $covariates_input
+        #set idx = []
+        #for $i in $covariates_input:
+            #silent idx.append(f'${i}')
+        #end for
+        #set idx_for_awk = ','.join(idx)
+
+        export covariates=`awk -v OFS=',' -F"\t" 'NR == 1 { print $idx_for_awk}' '$input_metadata'` &&
+        
+        #end if
+
+        echo 'Assigned batch columns:' \$batch &&
+        echo 'Assigned covariates:' \$covariates &&
+
+        Rscript '$rscript' &&
+        cp 'adjust_batch_diagnostic.pdf' '$diagnostic_plot_output' 
     ]]></command>
 
     <configfiles>
     <configfile name="rscript"><![CDATA[
         
         library(MMUPHin)
-        library(magrittr)
-        library(dplyr)
-        library(ggplot2)
-        library(readr)  
-     
-        source(adjust_batch.R)
-        
-        #input files
-        print(" Read input files")
-        abd_data <- read_tsv("$input_data")
-        meta_data <- read_tsv("$input_metadata")
+
+        ## input files
+        print("Read input files")
+        data <- read.csv("$input_data", sep = "\t", row.names=1, check.names = FALSE)
+        meta_data <- read.csv("$input_metadata", sep = "\t", row.names=1, check.names = FALSE)
         
         # Define control list
-        controls <- list("$zero_inflation", 
-                         "$pseudo_count", 
-                         "$conv", 
-                         "$maxit", 
-                         "$verbose", 
-                         "$diagnostic_plot")
+        controls <- list("$additional_options.zero_inflation", 
+                         "$additional_options.pseudo_count", 
+                         "$additional_options.conv", 
+                         "$additional_options.maxit", 
+                         "$additional_options.verbose", 
+                         "$additional_options.diagnostic_plot")
         
         #Perform batch adjustment
-        source(adjust_batch.R)
-        result <- adjust_batch(feature_abd = abd_data, 
-                               batch = "$batch_input", 
-                               covariates = "$covariates_input", 
+
+        ## get var names from env
+        batch <- Sys.getenv("batch")
+        covariates <- Sys.getenv("covariates")
+
+        covariates_vector <- unlist(strsplit(covariates, split = ","))
+
+
+        result <- adjust_batch(feature_abd = data, 
+                               batch = batch, 
+                               covariates = covariates_vector, 
                                data = meta_data,
                                control=controls
                                )
         
         # Save results into output files
-        print(result)
-        write.table(result$feature_abd_adj,file="$output",quote = FALSE)
-        write.table(result$control,file="$control_output",quote = FALSE)
-        #save adjust_batch_diagnostic.pdf into diagnostic_plot_output file too 
+
+        write.table(result\$feature_abd_adj,file="$output",quote = FALSE, sep="\t")
+        ## write.table(result\$control,file="$control_output",quote = FALSE)
+ 
     ]]></configfile>
 </configfiles>
 
@@ -56,7 +78,7 @@
         <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="batch_input" type="data_column" data_ref="input_metadata" use_header_names="true"  label="batch" />
-        <param argument="covariates_input" type="data_column" data_ref="input_metadata" use_header_names="true"  optional="true" label="covariates" />
+        <param argument="covariates_input" type="data_column" data_ref="input_metadata" use_header_names="true" multiple="true" optional="true" label="covariates" />
         <section name="additional_options" title="Additional Options" expanded="true">
             <param argument="zero_inflation" type="boolean" truevalue="zero_inflation TRUE" falsevalue="zero_inflation FALSE" checked="true" label=" Run zero-inflated model"/>            
             <param argument="pseudo_count" type="float" optional="true" label="Pseudo_count" help="Pseudo count to add feature_abd before the methods' log transformation.Default to NULL, in which case will be set to half of minimal non-zero values in feature_abd"/>
@@ -71,7 +93,6 @@
     <outputs>
           <data name="output" format="tabular"  label="Adjusted abundance table"/>
           <data name="diagnostic_plot_output" format="pdf" label="diagnostic figure file"/>
-          <data name="control_output" format="tabular" label="control list used in batch adjustment"/>
    </outputs>
     <tests>
         <test expect_num_outputs="3">