Mercurial > repos > ethevenot > multivariate

changeset 4:5526f8258e8a draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/workflow4metabolomics/multivariate.git commit 0f382a5296aae9bfc77df06b0a5ad493eb3c01f3
author ethevenot
date Wed, 28 Feb 2018 09:59:25 -0500
parents e91de3b04320
children
files Makefile build.xml multivariate_config.xml multivariate_wrapper.R runit/NA runit/output/figure.pdf runit/output/information.txt test-data/output-sampleMetadata.tsv test/.gitignore test/test-multi
diffstat 10 files changed, 168 insertions(+), 94 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/Makefile	Wed Feb 28 09:59:25 2018 -0500
@@ -0,0 +1,23 @@
+all:
+
+test:
+	test/test-multi
+
+planemo-venv/bin/planemo: planemo-venv
+	. planemo-venv/bin/activate && pip install --upgrade pip setuptools
+	. planemo-venv/bin/activate && pip install planemo
+
+planemo-venv:
+	virtualenv planemo-venv
+
+planemolint: planemo-venv/bin/planemo
+	. planemo-venv/bin/activate && planemo lint
+
+planemotest: planemo-venv/bin/planemo
+	. planemo-venv/bin/activate && planemo test --conda_dependency_resolution --galaxy_branch release_17.05
+
+clean:
+	$(RM) -r $(HOME)/.planemo
+	$(RM) -r planemo-venv
+
+.PHONY:	all clean test planemolint planemotest
--- a/build.xml	Sat Oct 22 03:02:47 2016 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,78 +0,0 @@
-<project name="multivariate" default="all">
-
-	<property name="tool.xml" value="multivariate_config.xml"/>
-	<property name="conda.dir" value="${user.home}/w4m-conda"/>
-
-	<!--~~~
-	~ ALL ~
-	~~~~~-->
-
-	<target name="all"/>
-
-	<!--~~~~
-	~ TEST ~
-	~~~~~-->
-
-	<target name="test" depends="planemo.lint,planemo.test"/>
-
-	<!--~~~~~~~~~~~~
-	~ PLANEMO LINT ~
-	~~~~~~~~~~~~~-->
-
-	<target name="planemo.lint">
-		<exec executable="planemo" failonerror="true">
-			<arg value="lint"/>
-			<arg value="${tool.xml}"/>
-		</exec>
-	</target>
-
-	<!--~~~~~~~~~~~~
-	~ PLANEMO TEST ~
-	~~~~~~~~~~~~~-->
-
-	<target name="planemo.test" depends="planemo.conda.install">
-		<exec executable="planemo" failonerror="true">
-			<arg value="test"/>
-			<arg value="--conda_prefix"/>
-			<arg value="${conda.dir}"/>
-			<arg value="--galaxy_branch"/>
-			<arg value="release_16.07"/>
-			<arg value="--conda_dependency_resolution"/>
-			<arg value="${tool.xml}"/>
-		</exec>
-	</target>
-
-	<!--~~~~~~~~~~~~~~~~~~~~~
-	~ PLANEMO CONDA INSTALL ~
-	~~~~~~~~~~~~~~~~~~~~~~-->
-
-	<target name="planemo.conda.install" depends="planemo.conda.init">
-		<exec executable="planemo" failonerror="true">
-			<arg value="conda_install"/>
-			<arg value="--conda_prefix"/>
-			<arg value="${conda.dir}"/>
-			<arg value="${tool.xml}"/>
-		</exec>
-	</target>
-
-	<!--~~~~~~~~~~~~~~~~~~
-	~ PLANEMO CONDA INIT ~
-	~~~~~~~~~~~~~~~~~~~-->
-
-	<target name="planemo.conda.init">
-		<exec executable="planemo" failonerror="true">
-			<arg value="conda_init"/>
-			<arg value="--conda_prefix"/>
-			<arg value="${conda.dir}"/>
-		</exec>
-	</target>
-
-	<!--~~~~~
-	~ CLEAN ~
-	~~~~~~-->
-
-	<target name="clean">
-		<delete dir="${conda.dir}"/>
-	</target>
-
-</project>
--- a/multivariate_config.xml	Sat Oct 22 03:02:47 2016 -0400
+++ b/multivariate_config.xml	Wed Feb 28 09:59:25 2018 -0500
@@ -1,10 +1,9 @@
-<tool id="Multivariate" name="Multivariate" version="2.3.8">
+<tool id="Multivariate" name="Multivariate" version="2.3.10">
   <description>PCA, PLS and OPLS</description>
   
   <requirements>
-    <requirement type="package" version="3.3.1">R</requirement>
-    <requirement type="package">r-batch</requirement>
-    <requirement type="package">bioconductor-ropls</requirement>
+    <requirement type="package" version="1.1_4">r-batch</requirement>
+    <requirement type="package" version="1.10.0">bioconductor-ropls</requirement>
   </requirements>
   
   <stdio>
@@ -45,6 +44,10 @@
   variableMetadata_out "$variableMetadata_out"
   figure "$figure"
   information "$information"
+
+  #if $save_rdata:
+    ropls_out "$ropls_out"
+  #end if
   ]]></command>
   
   <inputs>
@@ -181,14 +184,19 @@
 	
       </when>
     </conditional>
-    
+    <param name="save_rdata" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Save RData in your history"
+           help="Save the R ropls::opls object in your history for ad hoc analysis and graphing (outside Galaxy, this requires package 'bioconductor-ropls')"/>
   </inputs>
   
   <outputs>
     <data name="sampleMetadata_out" label="${tool.name}_${sampleMetadata_in.name}" format="tabular" ></data>
     <data name="variableMetadata_out" label="${tool.name}_${variableMetadata_in.name}" format="tabular" ></data>
-    <data name="figure" label="${tool.name}__figure.pdf" format="pdf"/>
-    <data name="information" label="${tool.name}__information.txt" format="txt"/>
+    <data name="figure" label="${tool.name}_figure.pdf" format="pdf"/>
+    <data name="information" label="${tool.name}_information.txt" format="txt"/>
+    <!-- how would an ropls.rdata datatype be added if that were the desired choice here instead?  Specifically, could it be created as part of tool installation? -->
+    <data name="ropls_out" label="${tool.name}_${dataMatrix_in.name}.RData" format="rdata">
+      <filter>save_rdata</filter>
+    </data>
   </outputs>
   
   <tests>
--- a/multivariate_wrapper.R	Sat Oct 22 03:02:47 2016 -0400
+++ b/multivariate_wrapper.R	Wed Feb 28 09:59:25 2018 -0500
@@ -2,6 +2,41 @@
 
 library(batch) ## parseCommandArgs
 
+# Constants
+argv <- commandArgs(trailingOnly = FALSE)
+script.path <- sub("--file=","",argv[grep("--file=",argv)])
+prog.name <- basename(script.path)
+
+# Print help
+if (length(grep('-h', argv)) >0) {
+	cat("Usage:", prog.name,
+	    "dataMatrix_in myDataMatrix.tsv",
+	    "sampleMetadata_in mySampleData.tsv",
+	    "variableMetadata_in myVariableMetadata.tsv",
+		"respC ...",
+		"predI ...",
+		"orthoI ...",
+		"testL ...",
+		"typeC ...",
+		"parAsColC ...",
+		"parCexN ...",
+		"parPc1I ...",
+		"parPc2I ...",
+		"parMahalC ...",
+		"parLabVc ...",
+		"algoC ...",
+		"crossvalI ...",
+		"log10L ...",
+		"permI ...",
+		"scaleC ...",
+	    "sampleMetadata_out mySampleMetadata_out.tsv",
+	    "variableMetadata_out myVariableMetadata_out.tsv",
+	    "figure figure.pdf",
+	    "information information.txt",
+		"\n")
+	quit(status = 0)
+}
+
 ########
 # MAIN #
 ########
@@ -45,7 +80,7 @@
 
     if(!tesL) {
 
-        sink(NULL)
+        sink()
         stpTxtC <- ifelse(is.na(txtC),
                           paste0(tesC, " is FALSE"),
                           txtC)
@@ -74,20 +109,23 @@
                               check.names = FALSE,
                               header = TRUE,
                               row.names = 1,
-                              sep = "\t")))
+                              sep = "\t",
+                              comment.char = "")))
 
 samDF <- read.table(argVc["sampleMetadata_in"],
                     check.names = FALSE,
                     header = TRUE,
                     row.names = 1,
-                    sep = "\t")
+                    sep = "\t",
+                    comment.char = "")
 flgF("identical(rownames(xMN), rownames(samDF))", txtC = "Sample names (or number) in the data matrix (first row) and sample metadata (first column) are not identical; use the 'Check Format' module in the 'Quality Control' section")
 
 varDF <- read.table(argVc["variableMetadata_in"],
                     check.names = FALSE,
                     header = TRUE,
                     row.names = 1,
-                    sep = "\t")
+                    sep = "\t",
+                    comment.char = "")
 flgF("identical(colnames(xMN), rownames(varDF))", txtC = "Variable names (or number) in the data matrix (first column) and sample metadata (first column) are not identical; use the 'Check Format' module in the 'Quality Control' section")
 
 flgF("argVc['respC'] == 'none' || (argVc['respC'] %in% colnames(samDF))",
@@ -427,8 +465,8 @@
             sep = "\t")
 
 # Output ropLs
-if ( ! is.null(argVc['ropls_out']))
-	save(ropLs, file = argVc['ropls_out'])
+if (!is.null(argVc['ropls_out']) && !is.na(argVc['ropls_out']))
+    save(ropLs, file = argVc['ropls_out'])
 
 ## Closing
 ##--------
@@ -436,6 +474,21 @@
 cat("\nEnd of '", modNamC, "' Galaxy module call: ",
     as.character(Sys.time()), "\n", sep = "")
 
+cat("\n\n\n============================================================================")
+cat("\nAdditional information about the call:\n")
+cat("\n1) Parameters:\n")
+print(cbind(value = argVc))
+
+cat("\n2) Session Info:\n")
+sessioninfo <- sessionInfo()
+cat(sessioninfo$R.version$version.string,"\n")
+cat("Main packages:\n")
+for (pkg in names(sessioninfo$otherPkgs)) { cat(paste(pkg,packageVersion(pkg)),"\t") }; cat("\n")
+cat("Other loaded packages:\n")
+for (pkg in names(sessioninfo$loadedOnly)) { cat(paste(pkg,packageVersion(pkg)),"\t") }; cat("\n")
+
+cat("============================================================================\n")
+
 sink()
 
 options(stringsAsFactors = strAsFacL)
Binary file runit/NA has changed
Binary file runit/output/figure.pdf has changed
--- a/runit/output/information.txt	Sat Oct 22 03:02:47 2016 -0400
+++ b/runit/output/information.txt	Wed Feb 28 09:59:25 2018 -0500
@@ -1,5 +1,5 @@
 
-Start of the 'Multivariate' Galaxy module call: Fri 05 Aug 2016 07:03:07 PM
+Start of the 'Multivariate' Galaxy module call: Mon 08 Jan 2018 05:24:55 PM
 
 PLS-DA
 
@@ -11,4 +11,34 @@
 p1 0.0505   0.0505 0.664    0.664  0.4220   0.422      R1     1
 p2 0.0678   0.1180 0.105    0.769 -0.0431   0.397      NS     1
 
-End of 'Multivariate' Galaxy module call: 2016-08-05 19:03:07
+End of 'Multivariate' Galaxy module call: 2018-01-08 17:24:56
+
+
+
+============================================================================
+Additional information about the call:
+
+1) Parameters:
+                     value                                
+dataMatrix_in        "./sacurineTest/dataMatrix.tsv"      
+sampleMetadata_in    "./sacurineTest/sampleMetadata.tsv"  
+variableMetadata_in  "./sacurineTest/variableMetadata.tsv"
+sampleMetadata_out   "./output/sampleMetadata.tsv"        
+variableMetadata_out "./output/variableMetadata.tsv"      
+figure               "./output/figure.pdf"                
+information          "./output/information.txt"           
+respC                "gender"                             
+predI                "2"                                  
+orthoI               "0"                                  
+testL                "TRUE"                               
+parAsColC            "none"                               
+parMahalC            "gender"                             
+parLabVc             "none"                               
+
+2) Session Info:
+R version 3.3.1 (2016-06-21) 
+Main packages:
+ropls 1.6.2 	batch 1.1.4 	
+Other loaded packages:
+parallel 3.3.1 	Biobase 2.34.0 	methods 3.3.1 	BiocGenerics 0.20.0 	
+============================================================================
--- a/test-data/output-sampleMetadata.tsv	Sat Oct 22 03:02:47 2016 -0400
+++ b/test-data/output-sampleMetadata.tsv	Wed Feb 28 09:59:25 2018 -0500
@@ -1,5 +1,5 @@
 sampleMetadata	injectionOrder	mode	age	bmi	gender	age_OPLS_XSCOR-h1	age_OPLS_XSCOR-o1	age_OPLS_predictions
-HU_017	2	pos	41	23.03	M	-0.429194614454735	2.37235221029276	38.3893561920685
+HU_017	2	pos	41	23.03	M	-0.429194614454734	2.37235221029276	38.3893561920685
 HU_028	7	pos	41	23.92	F	-0.043550585350191	-0.997753656394117	40.9597290876492
 HU_034	9	pos	52	23.37	M	0.470935190870015	1.68258805852438	44.3888507505175
 HU_051	20	pos	24	23.23	F	-0.30848953411015	3.52230161266618	39.1938729055699
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test/.gitignore	Wed Feb 28 09:59:25 2018 -0500
@@ -0,0 +1,1 @@
+*.tsv
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test/test-multi	Wed Feb 28 09:59:25 2018 -0500
@@ -0,0 +1,37 @@
+#!/bin/bash
+
+# Constants {{{1
+################################################################
+
+PROG_PATH=$(dirname $0)
+
+# MAIN {{{1
+################################################################
+
+$PROG_PATH/../multivariate_wrapper.R dataMatrix_in $PROG_PATH/../test-data/input-dataMatrix.tsv sampleMetadata_in $PROG_PATH/../test-data/input-sampleMetadata.tsv variableMetadata_in $PROG_PATH/../test-data/input-variableMetadata.tsv respC age predI 1 orthoI 1 testL FALSE sampleMetadata_out $PROG_PATH/outputSampleMetadata.tsv variableMetadata_out $PROG_PATH/outputVariableMetadata.tsv
+
+# Computed numbers are not always the same. We cannot use diff directly on files.
+
+# 0) Check they have the same number of lines
+nlines=$(wc -l <"$PROG_PATH/outputSampleMetadata.tsv")
+ref_nlines=$(wc -l <"$PROG_PATH/../test-data/output-sampleMetadata.tsv")
+if [ $nlines != $ref_nlines ] ; then
+	echo "Incorrect output sample metadata." >&2
+	exit 1
+fi
+
+# 1) We check the header line
+head -n 1 "$PROG_PATH/outputSampleMetadata.tsv" > "$PROG_PATH/header.tsv"
+head -n 1 "$PROG_PATH/../test-data/output-sampleMetadata.tsv" > "$PROG_PATH/ref_header.tsv"
+if ! diff "$PROG_PATH/header.tsv" "$PROG_PATH/ref_header.tsv" ; then
+	echo "Incorrect output sample metadata." >&2
+	exit 1
+fi
+
+# 2) We remove computed values and compare what's left
+awk 'BEGIN{FS=OFS="\t"} {$7=$8=$9="";sub("\t\t","\t")}1' "$PROG_PATH/outputSampleMetadata.tsv" > "$PROG_PATH/nocomput.tsv"
+awk 'BEGIN{FS=OFS="\t"} {$7=$8=$9="";sub("\t\t","\t")}1' "$PROG_PATH/../test-data/output-sampleMetadata.tsv" > "$PROG_PATH/ref_nocomput.tsv"
+if ! diff "$PROG_PATH/nocomput.tsv" "$PROG_PATH/ref_nocomput.tsv" ; then
+	echo "Incorrect output sample metadata." >&2
+	exit 1
+fi