Mercurial > repos > marie-tremblay-metatoul > nmr_bucketing

changeset 8:c54c70af216b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author marie-tremblay-metatoul
date Thu, 20 Apr 2017 06:34:51 -0400
parents 1df0b8efe9fc
children 62c62e31fc80
files nmr_bucketing/NmrBucketing_script.R nmr_bucketing/NmrBucketing_wrapper.R nmr_bucketing/NmrBucketing_xml.xml
diffstat 3 files changed, 126 insertions(+), 69 deletions(-) [+]
line wrap: on
line diff
--- a/nmr_bucketing/NmrBucketing_script.R	Mon Mar 06 06:34:01 2017 -0500
+++ b/nmr_bucketing/NmrBucketing_script.R	Thu Apr 20 06:34:51 2017 -0400
@@ -109,14 +109,32 @@
       }
 
       if (exclusion.in)
-        j <- j + 1
+      {
+        # Bucketing
+        {
+          BLB <- BUB - bucketSize
+          bucket <- spectrum[j,]
+          while (j < dim(spectrum)[1] && spectrum[j,1] > BLB)
+          {
+            j <- j + 1
+            if (spectrum[j,1] > BLB)
+              bucket <- rbind(bucket,spectrum[j,])
+          }
+          
+          f.bucket[b,] <- c(round(mean(bucket[,1]),3),0)
+          
+          # Next bucket boundary
+          BUB <- spectrum[j,1]
+          b <- b + 1
+        }
+      }
       
       if (!exclusion.in)
         # Bucketing
       {
         BLB <- BUB - bucketSize
         bucket <- spectrum[j,]
-        while (j < dim(spectrum)[1] && spectrum[j,1] >= BLB)
+        while (j < dim(spectrum)[1] && spectrum[j,1] > BLB)
         {
           j <- j + 1
           if (spectrum[j,1] > BLB)
@@ -219,6 +237,7 @@
   
   identifiants <- gsub("([- , * { } | \\[ ])","_",colnames(bucketedSpectra)[-1])
   colnames(bucketedSpectra) <- c(colnames(bucketedSpectra)[1],identifiants)
+
   bucketedSpectra <- bucketedSpectra[bucketedSpectra[,1]!=0,]
   rownames(bucketedSpectra) <- paste("B",bucketedSpectra[,1],sep="")
   bucketedSpectra <- bucketedSpectra[,-1]
@@ -232,7 +251,7 @@
   rownames(variableMetadata) <- rownames(bucketedSpectra)
   colnames(variableMetadata) <- "VariableOrder"
 
-  ## OUTPUTS
+
   return(list(bucketedSpectra,sampleMetadata,variableMetadata,ppm)) # ,truncatedSpectrum_matrice
 }
 
--- a/nmr_bucketing/NmrBucketing_wrapper.R	Mon Mar 06 06:34:01 2017 -0500
+++ b/nmr_bucketing/NmrBucketing_wrapper.R	Thu Apr 20 06:34:51 2017 -0400
@@ -39,7 +39,7 @@
 ## Libraries laoding
 ##------------------------------
 # For parseCommandArgs function
-library(batch) 
+library(batch)
 # For cumtrapz function
 library(pracma)
 
@@ -72,8 +72,6 @@
 if(!runExampleL)
     argLs <- parseCommandArgs(evaluate=FALSE)
 
-## sink(argLs[["logOut"]])
-
 
 ## Parameters Loading
 ##-------------------
@@ -83,14 +81,6 @@
 	zipfile= argLs[["zipfile"]]
 	directory=unzip(zipfile, list=F)
 	directory=paste(getwd(),strsplit(directory[1],"/")[[1]][2],sep="/")
-} else if (!is.null(argLs[["library"]])){
-	fileType="zip"
-	directory=argLs[["library"]]
-    	if(!file.exists(directory)){
-		error_message=paste("Cannot access the directory :",directory,".Please verify if the directory exists or not.")
-		print(error_message)
-		stop(error_message)
-	}
 } else if (!is.null(argLs[["tsvfile"]])){
 	fileType="tsv"
 	directory <- read.table(argLs[["tsvfile"]],check.names=FALSE,header=TRUE,sep="\t")
@@ -128,12 +118,12 @@
 
 if(length(error.stock) > 1)
   stop(error.stock)
-  
-  
+
+
 ## Computation
 ##------------
-outputs <- NmrBucketing(fileType=fileType, fileName=directory, leftBorder=leftBorder, rightBorder=rightBorder, bucketSize=bucketSize, 
-						exclusionZones=exclusionZones, exclusionZonesBorders=exclusionZonesBorders, graph=graphique, nomFichier=nomGraphe, 
+outputs <- NmrBucketing(fileType=fileType, fileName=directory, leftBorder=leftBorder, rightBorder=rightBorder, bucketSize=bucketSize,
+						exclusionZones=exclusionZones, exclusionZonesBorders=exclusionZonesBorders, graph=graphique, nomFichier=nomGraphe,
 						savLog.txtC=logFile)
 data_bucket <- outputs[[1]]
 data_sample <- outputs[[2]]
@@ -166,17 +156,33 @@
     ## Zoomed spectral window depending on exclusion zone(s)
     if (nbZones != 0)
     {
-      spectra <- data.frame(t(data_bucket[1:(which(ppm == excludedZone[n])[[1]]),]))
+      BInf <- excludedZone[n]
+      if (round(BInf,1) == BInf)
+      {
+        BInf <- BInf+0.01
+      }
+      spectra <- data.frame(t(data_bucket[1:(which(ppm == BInf)[[1]]),]))
       drawSpec(spectra,xlab="", ylab="Intensity", main="")			
       n <- n - 1
       
       while (n >= nbZones & nbZones > 1)
       {
-        spectra <- data.frame(t(data_bucket[(which(ppm == excludedZone[n])[[1]]):(which(ppm == excludedZone[n-1])[[1]]),]))
+        BInf <- excludedZone[n-1]
+        if (round(BInf,1) > BInf)
+        {
+          BInf <- BInf+0.01
+        }
+        spectra <- data.frame(t(data_bucket[(which(ppm == excludedZone[n])[[1]]):(which(ppm == BInf)[[1]]),]))
         drawSpec(spectra,xlab="", ylab="Intensity", main="")
         n <- n - 2
       }
-      spectra <- data.frame(t(data_bucket[(which(ppm == excludedZone[1])[[1]]):nrow(data_bucket),]))
+      
+      BInf <- excludedZone[1]
+      if (round(BInf,1) <= BInf)
+      {
+        BInf <- BInf+0.01
+      }
+      spectra <- data.frame(t(data_bucket[(which(ppm == BInf)[[1]]):nrow(data_bucket),]))
       drawSpec(spectra,xlab="", ylab="Intensity", main="")
     }
   }
@@ -187,47 +193,95 @@
       par(mfrow=c((nbZones+2),1))
       n <- length(excludedZone)
       spectra <- t(data_bucket[,i])
-      drawSpec(spectra,xlab="", ylab="Intensity", main=colnames(data_bucket)[i])
-      
+	  names(spectra) <- rownames(data_bucket)
+      plot(1:length(spectra), spectra, type='l', xlab="", ylab="Intensity", main=colnames(data_bucket)[i], xaxt = "n")
+	  xPos <- 1
+	  nAxisPos <- 4
+	  startP <- length(nAxisPos) 
+	  endP <- nrow(data_bucket)
+	  GraphRange <- c(startP:endP)
+	  tempVal = trunc(length(GraphRange)/nAxisPos)
+	  xPos = c(0:nAxisPos) * tempVal
+	  axis(1, at = xPos, labels = rownames(data_bucket)[xPos + startP])
+     
       ## Zoomed spectral window depending on exclusion zone(s)
       if (nbZones != 0)
       {
-        spectra <- t(data_bucket[1:(which(ppm == excludedZone[n])[[1]]),i])
-        drawSpec(spectra,xlab="", ylab="Intensity", main="")			
+        BInf <- excludedZone[n]
+        if (round(BInf,1) == BInf)
+        {
+          BInf <- BInf+0.01
+        }
+        spectra <- t(data_bucket[1:(which(ppm == BInf)[[1]]),i])
+		names(spectra) <- rownames(data_bucket)[1:(which(ppm == BInf)[[1]])]
+		plot(1:length(spectra), spectra, type='l',xlab="", ylab="Intensity", main="", xaxt = "n")			
+		xPos <- 1
+		nAxisPos <- 4
+		startP <- length(nAxisPos) 
+		endP <- length(spectra)
+		GraphRange <- c(startP:endP)
+		tempVal = trunc(length(GraphRange)/nAxisPos)
+		xPos = c(0:nAxisPos) * tempVal
+		axis(1, at = xPos, labels = rownames(data_bucket)[xPos + startP])
         n <- n - 1
         
         while (n >= nbZones & nbZones > 1)
         {
-          spectra <- t(data_bucket[(which(ppm == excludedZone[n])[[1]]):(which(ppm == excludedZone[n-1])[[1]]),i])
-          drawSpec(spectra,xlab="", ylab="Intensity", main="")
+          BInf <- excludedZone[n-1]
+          if (round(BInf,1) > BInf)
+          {
+            BInf <- BInf+0.01
+          }
+          spectra <- t(data_bucket[(which(ppm == excludedZone[n])[[1]]):(which(ppm == BInf)[[1]]),i])
+		  names(spectra) <- rownames(data_bucket)[(which(ppm == excludedZone[n])[[1]]):(which(ppm == BInf)[[1]])]
+          plot(1:length(spectra), spectra, type='l',xlab="", ylab="Intensity", main="", xaxt = "n")
+		  xPos <- 1
+		  nAxisPos <- 4
+		  startP <- length(nAxisPos) 
+		  endP <- length(spectra)
+		  GraphRange <- c(startP:endP)
+		  tempVal = trunc(length(GraphRange)/nAxisPos)
+		  xPos = c(0:nAxisPos) * tempVal
+		  axis(1, at = xPos, labels = rownames(data_bucket)[xPos + startP])
           n <- n - 2
         }
         
-        spectra <- t(data_bucket[(which(ppm == excludedZone[1])[[1]]):nrow(data_bucket),i])
-        drawSpec(spectra,xlab="", ylab="Intensity", main="")
+        BInf <- excludedZone[1]
+        if (round(BInf,1) <= BInf)
+        {
+          BInf <- BInf+0.01
+        }
+        spectra <- t(data_bucket[(which(ppm == BInf)[[1]]):nrow(data_bucket),i])
+		names(spectra) <- rownames(data_bucket)[(which(ppm == BInf)[[1]]):nrow(data_bucket)]
+        plot(1:length(spectra), spectra, type='l',xlab="", ylab="Intensity", main="", xaxt = "n")
+		xPos <- 1
+		nAxisPos <- 4
+		startP <- length(nAxisPos) 
+		endP <- length(spectra)
+		GraphRange <- c(startP:endP)
+		tempVal = trunc(length(GraphRange)/nAxisPos)
+		xPos = c(0:nAxisPos) * tempVal
+		axis(1, at = xPos, labels = rownames(data_bucket)[xPos + startP])
       }
     }
   }
   dev.off()
 }
-
 ## Saving
 ##-------
   # Data
 data_bucket <- cbind(rownames(data_bucket),data_bucket)
 colnames(data_bucket) <- c("Bucket",colnames(data_bucket)[-1])
 write.table(data_bucket,file=argLs$dataMatrixOut,quote=FALSE,row.names=FALSE,sep="\t")
-if (fileType=="zip")
-{
   # Sample
-  data_sample <- cbind(rownames(data_sample),data_sample)
-  colnames(data_sample) <- c("Sample",colnames(data_sample)[-1])
-  write.table(data_sample,file=argLs$sampleOut,quote=FALSE,row.names=FALSE,sep="\t")
-    # Variable
-  data_variable <- cbind(rownames(data_variable),data_variable)
-  colnames(data_variable) <- c("Bucket",colnames(data_variable)[-1])
-  write.table(data_variable,file=argLs$variableOut,quote=FALSE,row.names=FALSE,sep="\t")
-}
+data_sample <- cbind(rownames(data_sample),data_sample)
+colnames(data_sample) <- c("Sample",colnames(data_sample)[-1])
+write.table(data_sample,file=argLs$sampleOut,quote=FALSE,row.names=FALSE,sep="\t")
+  # Variable
+data_variable <- cbind(rownames(data_variable),data_variable)
+colnames(data_variable) <- c("Bucket",colnames(data_variable)[-1])
+write.table(data_variable,file=argLs$variableOut,quote=FALSE,row.names=FALSE,sep="\t")
+
 
 ## Ending
 ##---------------------
--- a/nmr_bucketing/NmrBucketing_xml.xml	Mon Mar 06 06:34:01 2017 -0500
+++ b/nmr_bucketing/NmrBucketing_xml.xml	Thu Apr 20 06:34:51 2017 -0400
@@ -1,9 +1,8 @@
-<tool id="NmrBucketing" name="NMR_Bucketing" version="2.0.1">
+<tool id="NmrBucketing" name="NMR_Bucketing" version="1.0.3">
 
     <description> Bucketing and integration of NMR Bruker raw data</description>
 
     <requirements>
-        <requirement type="package" version="3.1.2">R</requirement>
 	    <requirement type="package" version="1.1_4">r-batch</requirement>
 	    <requirement type="package" version="1.8.8">r-pracma</requirement>
     </requirements>
@@ -15,9 +14,7 @@
     <command>
         Rscript '$__tool_directory__/NmrBucketing_wrapper.R'
 
-        #if $inputs.input == "lib":
-            library '$__app__.config.user_library_import_dir/$__user_email__/$inputs.library'
-        #elif $inputs.input == "tsv_file":
+        #if $inputs.input == "tsv_file":
             tsvfile '$inputs.tsv_file'
         #elif $inputs.input == "zip_file":
             zipfile '$inputs.zip_file'
@@ -57,7 +54,6 @@
             <param name="input" type="select" label="Choose your inputs method" >
                 <option value="zip_file" selected="true">Zip file from your history containing your Bruker directories</option>
                 <option value="tsv_file">Tsv file containing preprocessed spectra (from your history)</option>
-                <option value="lib" >Library directory name</option>
             </param>
             <when value="zip_file">
                 <param name="zip_file" type="data" format="no_unzip.zip" label="Zip file" />
@@ -65,12 +61,6 @@
             <when value="tsv_file">
                 <param name="tsv_file" type="data" format="tabular" label="Tsv file" />
             </when>
-            <when value="lib">
-                <param name="library" type="text" size="40" label="Library directory name" help="The name of your directory containing all your data" >
-                    <validator type="empty_field"/> 
-                </param>
-            </when>
-
         </conditional>
 
         <param name="bucket_width" label="Bucket width" type="float" value="0.04" help="Default value is 0.04 ppm"/>
@@ -102,18 +92,14 @@
     </inputs>
 
     <outputs>
-        <data format="tabular" name="sampleOut" label="${tool.name}_sampleMetadata" >
-					<filter> input == "zip_file" </filter>
-        </data>
-        <data format="tabular" name="variableOut" label="${tool.name}_variableMetadata" >
-			<filter> input == "zip_file" </filter>
-        </data>
+        <data format="tabular" name="sampleOut" label="${tool.name}_sampleMetadata" />
+        <data format="tabular" name="variableOut" label="${tool.name}_variableMetadata" />
         <data format="tabular" name="dataMatrixOut" label="${tool.name}_bucketedData" />
         <data format="pdf" name="graphOut" label="${tool.name}_spectra" >
             <filter> graphType != "None" </filter>
         </data>
     </outputs>
-    
+
     <tests>
         <test>
             <param name="inputs|input" value="zip_file" />
@@ -132,7 +118,7 @@
             <output name="variableOut" file="MTBLS1_variableMetadata.tabular" />
         </test>
     </tests>
-    
+
     <help>
 
 .. class:: infomark
@@ -157,9 +143,9 @@
 **Upstream tools**
 
 ========================= ============================ =======
-Name                      output file                  format 
+Name                      output file                  format
 ========================= ============================ =======
-NMRAlignment              NMR_Alignment_alignedSpectra tsv    
+NMRAlignment              NMR_Alignment_alignedSpectra tsv
 ========================= ============================ =======
 
 **Downstream tools**
@@ -194,7 +180,6 @@
 You have three methods for your inputs:
 
 | Zip file (recommended): You can put a zip file containing your inputs as raw Bruker files: myinputs.zip (containing all your conditions as sub-directories).
-| library folder: You must specify the name of your "library" (folder) created within your space project (for example: /projet/externe/institut/login/galaxylibrary/yourlibrary). Your library must contain all your conditions as sub-directories.
 | Tsv file: You can put a tsv file containing your inputs as preprocessed spectra: myinputs.tsv (containing all your conditions in columns and chemical shifts in rows).
 
 .. image:: ./static/images/Mth_Architecture_Repertoire_Bruker.png
@@ -230,7 +215,7 @@
 Right exclusion zone
 | Lower boundary of exclusion zone
 
-| *Notes:* 
+| *Notes:*
 | - these parameters can be used several times using the "Add new exclusion zones" button
 |
 
@@ -264,7 +249,7 @@
 spectra.pdf
 | pdf output
 | Graphical chart of bucketed and integrated data
-| 
+|
 
 
 ---------------------------------------------------
@@ -288,11 +273,11 @@
 
 **Version 1.0.3 - 24/10/2016**
 
-- ENHANCEMENT: add possibility of bucketing processed files (upstream tools)	    
-	    
+- ENHANCEMENT: add possibility of bucketing processed files (upstream tools)
+
 **Version 1.0.2 - 12/08/2016**
 
-- ENHANCEMENT: x-axis customization: add chemical shift labels 
+- ENHANCEMENT: x-axis customization: add chemical shift labels
 
 **Version 1.0.1 - 04/04/2016**
 
@@ -306,4 +291,3 @@
         <citation type="doi">10.1093/bioinformatics/btu813</citation>
     </citations>
 </tool>
-