Efrain Gonzalez / Cleaning and Fixing Data with R

Download as
Browse Code ยป

Commit 05d7395375781d72a30f10f69ea2125cdd574831

Authored by Efrain Gonzalez
1 parent 39173eac2a
Exists in master

added gene_assignment to GPL glossary (UNTESTED)

Showing 1 changed file with 4 additions and 4 deletions   Show diff stats
... ... @@ -241,7 +241,7 @@ if(clfileex == 0){
241 241 .[IDLOCAL]
242 242 geneIDNam <- genena %>%
243 243 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>%
244   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.)))
  244 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
245 245 }
246 246 if(IDF == 0){
247 247 #No information on this particular GPL file
... ... @@ -255,7 +255,7 @@ if(clfileex == 0){
255 255 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE)
256 256 geneIDNam <- genena %>%
257 257 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
258   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.)))
  258 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
259 259 }
260 260 }
261 261 if(fileex == 0){
... ... @@ -271,13 +271,13 @@ if(clfileex == 0){
271 271 write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE)
272 272 geneIDNam <- genena %>%
273 273 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
274   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.)))
  274 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
275 275 }
276 276 }
277 277 if(soft == FALSE){
278 278 geneIDNam <- genena %>%
279 279 read_delim(delim="\t",comment = "#")%>%
280   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.))
  280 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))
281 281 }
282 282  
283 283 ##Labeling the gene IDs without names