Mercurial > repos > galaxyp > cardinal_classification

changeset 3:585ef27873c9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit 2c4a1a862900b4efbc30824cbcb798f835b168b2
author galaxyp
date Thu, 28 Feb 2019 09:24:53 -0500
parents cbc7e53518ce
children 47fc5b518ffc
files classification.xml test-data/preprocessing_results1.ibd test-data/preprocessing_results1.imzml test-data/preprocessing_results1.imzml.txt test-data/preprocessing_results1.pdf test-data/preprocessing_results2.ibd test-data/preprocessing_results2.imzml test-data/preprocessing_results2.imzml.txt test-data/preprocessing_results2.pdf test-data/preprocessing_results3.ibd test-data/preprocessing_results3.imzml test-data/preprocessing_results3.imzml.txt test-data/preprocessing_results3.pdf test-data/preprocessing_results4.ibd test-data/preprocessing_results4.imzml test-data/preprocessing_results4.imzml.txt test-data/preprocessing_results4.pdf test-data/preprocessing_results5.RData test-data/preprocessing_results5.pdf
diffstat 19 files changed, 44 insertions(+), 29 deletions(-) [+]
line wrap: on
line diff
--- a/classification.xml	Fri Feb 15 10:18:51 2019 -0500
+++ b/classification.xml	Thu Feb 28 09:24:53 2019 -0500
@@ -33,6 +33,10 @@
 ## to make sure that processed files work as well: 
 iData(msidata) = iData(msidata)[]
 
+## remove duplicated coordinates
+print(paste0(sum(duplicated(coord(msidata))), " duplicated coordinates were removed"))
+msidata <- msidata[,!duplicated(coord(msidata))]
+
 @DATA_PROPERTIES_INRAM@
 
 
@@ -231,10 +235,13 @@
 
                 ### m/z and pixel information output
                 pls_classes = data.frame(msidata.pls\$classes[[1]])
-                pixel_names = gsub(", y = ", "_", names(pixels(msidata)))
-                pixel_names = gsub(" = ", "y_", pixel_names)
-                x_coordinates = matrix(unlist(strsplit(pixel_names, "_")), ncol=3, byrow=TRUE)[,2]
-                y_coordinates = matrix(unlist(strsplit(pixel_names, "_")), ncol=3, byrow=TRUE)[,3]
+                ## pixel names and coordinates
+                ## to remove potential sample names and z dimension, split at comma and take only x and y 
+                x_coords = unlist(lapply(strsplit(names(pixels(msidata)), ","), `[[`, 1))
+                y_coords = unlist(lapply(strsplit(names(pixels(msidata)), ","), `[[`, 2))
+                x_coordinates = gsub("x = ","",x_coords)
+                y_coordinates = gsub(" y = ","",y_coords)
+                pixel_names = paste0("xy_", x_coordinates, "_", y_coordinates)
 
                 ## remove msidata to clean up RAM space
                 rm(msidata)
@@ -373,12 +380,15 @@
                 maximumy = max(coord(msidata)[,2])
                 print(image(msidata, mz = topLabels(msidata.opls)[1,1], normalize.image = "linear", contrast.enhance = "histogram",smooth.image="gaussian", ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy), main="best m/z heatmap"))
 
-                ## m/z and pixel information output
                 opls_classes = data.frame(msidata.opls\$classes[[1]])
-                pixel_names = gsub(", y = ", "_", names(pixels(msidata)))
-                pixel_names = gsub(" = ", "y_", pixel_names)
-                x_coordinates = matrix(unlist(strsplit(pixel_names, "_")), ncol=3, byrow=TRUE)[,2]
-                y_coordinates = matrix(unlist(strsplit(pixel_names, "_")), ncol=3, byrow=TRUE)[,3]
+                ## pixel names and coordinates
+                ## to remove potential sample names and z dimension, split at comma and take only x and y
+                x_coords = unlist(lapply(strsplit(names(pixels(msidata)), ","), `[[`, 1))
+                y_coords = unlist(lapply(strsplit(names(pixels(msidata)), ","), `[[`, 2))
+                x_coordinates = gsub("x = ","",x_coords)
+                y_coordinates = gsub(" y = ","",y_coords)
+                pixel_names = paste0("xy_", x_coordinates, "_", y_coordinates)
+
                 opls_classes2 = data.frame(pixel_names, x_coordinates, y_coordinates, opls_classes)
                 colnames(opls_classes2) = c("pixel names", "x", "y","predicted condition")
 
@@ -520,10 +530,15 @@
 
                 ## m/z and pixel information output
                 ssc_classes = data.frame(msidata.ssc\$classes[[1]])
-                pixel_names = gsub(", y = ", "_", names(pixels(msidata)))
-                pixel_names = gsub(" = ", "y_", pixel_names)
-                x_coordinates = matrix(unlist(strsplit(pixel_names, "_")), ncol=3, byrow=TRUE)[,2]
-                y_coordinates = matrix(unlist(strsplit(pixel_names, "_")), ncol=3, byrow=TRUE)[,3]
+
+                ## pixel names and coordinates
+                ## to remove potential sample names and z dimension, split at comma and take only x and y 
+                x_coords = unlist(lapply(strsplit(names(pixels(msidata)), ","), `[[`, 1))
+                y_coords = unlist(lapply(strsplit(names(pixels(msidata)), ","), `[[`, 2))
+                x_coordinates = gsub("x = ","",x_coords)
+                y_coordinates = gsub(" y = ","",y_coords)
+                pixel_names = paste0("xy_", x_coordinates, "_", y_coordinates)
+
 
                 ## remove msidata to clean up RAM space
                 rm(msidata)
Binary file test-data/preprocessing_results1.ibd has changed
--- a/test-data/preprocessing_results1.imzml	Fri Feb 15 10:18:51 2019 -0500
+++ b/test-data/preprocessing_results1.imzml	Thu Feb 28 09:24:53 2019 -0500
@@ -9,8 +9,8 @@
 		<fileContent>
 			<cvParam cvRef="MS" accession="MS:1000579" name="MS1 spectrum" value="" />
 			<cvParam cvRef="MS" accession="MS:1000127" name="centroid spectrum" value="" />
-			<cvParam cvRef="IMS" accession="IMS:1000080" name="universally unique identifier" value="{002DF5BA-0549-44DF-A8BB-27DA3E197EB7}" />
-			<cvParam cvRef="IMS" accession="IMS:1000091" name="ibd SHA-1" value="0379019A6F9D0B55F9217420030633F7163AF9D3" />
+			<cvParam cvRef="IMS" accession="IMS:1000080" name="universally unique identifier" value="{728FBFFE-E6FC-4283-8068-393A66F6BD5C}" />
+			<cvParam cvRef="IMS" accession="IMS:1000091" name="ibd SHA-1" value="375094460F3B80674CB2F541DCD9928B3D61B2FF" />
 			<cvParam cvRef="IMS" accession="IMS:1000030" name="continuous" value="" />
 		</fileContent>
 	</fileDescription>
--- a/test-data/preprocessing_results1.imzml.txt	Fri Feb 15 10:18:51 2019 -0500
+++ b/test-data/preprocessing_results1.imzml.txt	Thu Feb 28 09:24:53 2019 -0500
@@ -1,4 +1,4 @@
 imzML file:
 total 24
--rw-r--r-- 1 meli meli    96 Feb 12 21:24 ibd
--rw-r--r-- 1 meli meli 16714 Feb 12 21:24 imzml
+-rw-r--r-- 1 meli meli    96 Feb 24 14:11 ibd
+-rw-r--r-- 1 meli meli 16714 Feb 24 14:11 imzml
Binary file test-data/preprocessing_results1.pdf has changed
Binary file test-data/preprocessing_results2.ibd has changed
--- a/test-data/preprocessing_results2.imzml	Fri Feb 15 10:18:51 2019 -0500
+++ b/test-data/preprocessing_results2.imzml	Thu Feb 28 09:24:53 2019 -0500
@@ -9,8 +9,8 @@
 		<fileContent>
 			<cvParam cvRef="MS" accession="MS:1000579" name="MS1 spectrum" value="" />
 			<cvParam cvRef="MS" accession="MS:1000127" name="centroid spectrum" value="" />
-			<cvParam cvRef="IMS" accession="IMS:1000080" name="universally unique identifier" value="{84BEACDD-B841-4730-81A0-A19A28C7B48A}" />
-			<cvParam cvRef="IMS" accession="IMS:1000091" name="ibd SHA-1" value="1BC49DCCC566E7A6938CE3DE62090650C2A04798" />
+			<cvParam cvRef="IMS" accession="IMS:1000080" name="universally unique identifier" value="{40F230A1-1893-4A8C-BAE2-A8BBEF24DB20}" />
+			<cvParam cvRef="IMS" accession="IMS:1000091" name="ibd SHA-1" value="417ADF38FBC4D0304A9B75B4C85799137846DD2F" />
 			<cvParam cvRef="IMS" accession="IMS:1000030" name="continuous" value="" />
 		</fileContent>
 	</fileDescription>
--- a/test-data/preprocessing_results2.imzml.txt	Fri Feb 15 10:18:51 2019 -0500
+++ b/test-data/preprocessing_results2.imzml.txt	Thu Feb 28 09:24:53 2019 -0500
@@ -1,4 +1,4 @@
 imzML file:
 total 80
--rw-r--r-- 1 meli meli 54720 Feb 12 21:25 ibd
--rw-r--r-- 1 meli meli 21132 Feb 12 21:25 imzml
+-rw-r--r-- 1 meli meli 54720 Feb 24 14:12 ibd
+-rw-r--r-- 1 meli meli 21132 Feb 24 14:12 imzml
Binary file test-data/preprocessing_results2.pdf has changed
Binary file test-data/preprocessing_results3.ibd has changed
--- a/test-data/preprocessing_results3.imzml	Fri Feb 15 10:18:51 2019 -0500
+++ b/test-data/preprocessing_results3.imzml	Thu Feb 28 09:24:53 2019 -0500
@@ -9,8 +9,8 @@
 		<fileContent>
 			<cvParam cvRef="MS" accession="MS:1000579" name="MS1 spectrum" value="" />
 			<cvParam cvRef="MS" accession="MS:1000127" name="centroid spectrum" value="" />
-			<cvParam cvRef="IMS" accession="IMS:1000080" name="universally unique identifier" value="{4C387879-DE12-49A4-878F-6980D6F7C6F0}" />
-			<cvParam cvRef="IMS" accession="IMS:1000091" name="ibd SHA-1" value="94ED775BCF16644D23DACFCA1E62D28D5C755178" />
+			<cvParam cvRef="IMS" accession="IMS:1000080" name="universally unique identifier" value="{D767424F-5E74-45AB-AF1B-0D25244B435B}" />
+			<cvParam cvRef="IMS" accession="IMS:1000091" name="ibd SHA-1" value="445E32981D0B3D08ED2BA74E11500A3A08CDB9B7" />
 			<cvParam cvRef="IMS" accession="IMS:1000030" name="continuous" value="" />
 		</fileContent>
 	</fileDescription>
--- a/test-data/preprocessing_results3.imzml.txt	Fri Feb 15 10:18:51 2019 -0500
+++ b/test-data/preprocessing_results3.imzml.txt	Thu Feb 28 09:24:53 2019 -0500
@@ -1,4 +1,4 @@
 imzML file:
 total 36
--rw-r--r-- 1 meli meli 14216 Feb 12 21:26 ibd
--rw-r--r-- 1 meli meli 16824 Feb 12 21:26 imzml
+-rw-r--r-- 1 meli meli 14216 Feb 24 14:12 ibd
+-rw-r--r-- 1 meli meli 16824 Feb 24 14:12 imzml
Binary file test-data/preprocessing_results3.pdf has changed
Binary file test-data/preprocessing_results4.ibd has changed
--- a/test-data/preprocessing_results4.imzml	Fri Feb 15 10:18:51 2019 -0500
+++ b/test-data/preprocessing_results4.imzml	Thu Feb 28 09:24:53 2019 -0500
@@ -9,8 +9,8 @@
 		<fileContent>
 			<cvParam cvRef="MS" accession="MS:1000579" name="MS1 spectrum" value="" />
 			<cvParam cvRef="MS" accession="MS:1000128" name="profile spectrum" value="" />
-			<cvParam cvRef="IMS" accession="IMS:1000080" name="universally unique identifier" value="{26018306-9D72-49F5-89CB-68E4DDE0527C}" />
-			<cvParam cvRef="IMS" accession="IMS:1000091" name="ibd SHA-1" value="BA6411EC5A5A59ABE5BD7005F4ED8FCEBA775A8E" />
+			<cvParam cvRef="IMS" accession="IMS:1000080" name="universally unique identifier" value="{FE932E04-42E4-4D89-B721-2A6CE83250B6}" />
+			<cvParam cvRef="IMS" accession="IMS:1000091" name="ibd SHA-1" value="36C7C916C176DD85CBBF4B7FA969C92B9403768D" />
 			<cvParam cvRef="IMS" accession="IMS:1000030" name="continuous" value="" />
 		</fileContent>
 	</fileDescription>
--- a/test-data/preprocessing_results4.imzml.txt	Fri Feb 15 10:18:51 2019 -0500
+++ b/test-data/preprocessing_results4.imzml.txt	Thu Feb 28 09:24:53 2019 -0500
@@ -1,4 +1,4 @@
 imzML file:
 total 28
--rw-r--r-- 1 meli meli  6376 Feb 12 21:29 ibd
--rw-r--r-- 1 meli meli 16801 Feb 12 21:29 imzml
+-rw-r--r-- 1 meli meli  6376 Feb 24 14:13 ibd
+-rw-r--r-- 1 meli meli 16801 Feb 24 14:13 imzml
Binary file test-data/preprocessing_results4.pdf has changed
Binary file test-data/preprocessing_results5.RData has changed
Binary file test-data/preprocessing_results5.pdf has changed