Mercurial > repos > davidvanzessen > shm_csr

changeset 13:933fb21568ce draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Fri, 11 Nov 2016 03:49:30 -0500
parents 6b66c1c57f22
children 59765d2c8890
files merge_and_filter.r shm_csr.xml
diffstat 2 files changed, 7 insertions(+), 5 deletions(-) [+]
line wrap: on
line diff
--- a/merge_and_filter.r	Thu Nov 10 08:36:18 2016 -0500
+++ b/merge_and_filter.r	Fri Nov 11 03:49:30 2016 -0500
@@ -187,11 +187,13 @@
 	stop("No data remaining after filter")
 }
 
+result$best_match_class = gsub(",.*", "", result$best_match) #gsub so the unmatched don't have a class after it
+
 result$past = do.call(paste, c(result[unlist(strsplit(unique.type, ","))], sep = ":"))
 
 result = result[!(duplicated(result$past)), ]
 
-result = result[,!(names(result) %in% c("past"))]
+result = result[,!(names(result) %in% c("past", "best_match_class"))]
 
 print(paste("Number of sequences in result after", unique.type, "filtering:", nrow(result)))
 
--- a/shm_csr.xml	Thu Nov 10 08:36:18 2016 -0500
+++ b/shm_csr.xml	Fri Nov 11 03:49:30 2016 -0500
@@ -22,14 +22,14 @@
 			<option value="no">No</option>
 		</param>
 		<param name="unique" type="select" label="Remove duplicates based on" help="" >
-			<option value="VGene,AA.JUNCTION,best_match">Top.V.Gene, CDR3 (AA), C region</option>
+			<option value="VGene,AA.JUNCTION,best_match_class">Top.V.Gene, CDR3 (AA), C region</option>
 			<option value="VGene,AA.JUNCTION">Top.V.Gene, CDR3 (AA)</option>
-			<option value="AA.JUNCTION,best_match">CDR3 (AA), C region</option>
+			<option value="AA.JUNCTION,best_match_class">CDR3 (AA), C region</option>
 			<option value="AA.JUNCTION">CDR3 (AA)</option>
 			
-			<option value="VGene,CDR3.IMGT.seq,best_match">Top.V.Gene, CDR3.nt.Seq, C region</option>
+			<option value="VGene,CDR3.IMGT.seq,best_match_class">Top.V.Gene, CDR3.nt.Seq, C region</option>
 			<option value="VGene,CDR3.IMGT.seq">Top.V.Gene, CDR3 (nt)</option>
-			<option value="CDR3.IMGT.seq,best_match">CDR3 (nt), C region</option>
+			<option value="CDR3.IMGT.seq,best_match_class">CDR3 (nt), C region</option>
 			<option value="CDR3.IMGT.seq">CDR3 (nt)</option>
 			<option value="Sequence.ID" selected="true">Don't remove duplicates</option>
 		</param>