Commit 501231d3ebcc148491cc9f407215c4a8d1369b35
1 parent
48208ef1ad
Exists in
master
Added |^UCSC_RefGene_Name$ to list of potential names in GPL
Showing
1 changed file
with
4 additions
and
4 deletions
Show diff stats
RCleanDscret.R
... | ... | @@ -258,7 +258,7 @@ geneIDNam <- paste0("Clean_GPL",gplnum,".txt") %>% |
258 | 258 | .[IDLOCAL] |
259 | 259 | geneIDNam <- genena %>% |
260 | 260 | read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>% |
261 | - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.))) | |
261 | + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.))) | |
262 | 262 | } else if(IDF == 0){ |
263 | 263 | #No information on this particular GPL file |
264 | 264 | idLOCGPL <- genena %>% |
... | ... | @@ -270,7 +270,7 @@ geneIDNam <- paste0("Clean_GPL",gplnum,".txt") %>% |
270 | 270 | cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE) |
271 | 271 | geneIDNam <- genena %>% |
272 | 272 | read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% |
273 | - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.))) | |
273 | + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.))) | |
274 | 274 | } |
275 | 275 | } else if(fileex == 0){ |
276 | 276 | #We must create a file that we can access for later use |
... | ... | @@ -284,12 +284,12 @@ geneIDNam <- paste0("Clean_GPL",gplnum,".txt") %>% |
284 | 284 | write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE) |
285 | 285 | geneIDNam <- genena %>% |
286 | 286 | read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% |
287 | - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.))) | |
287 | + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.))) | |
288 | 288 | } |
289 | 289 | } else if(soft == FALSE){ |
290 | 290 | geneIDNam <- genena %>% |
291 | 291 | read_delim(delim="\t",comment = "#")%>% |
292 | - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.))) | |
292 | + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.))) | |
293 | 293 | } |
294 | 294 | |
295 | 295 | ##Labeling the gene IDs without names |