Efrain Gonzalez / Cleaning and Fixing Data with R

Download as
Browse Code ยป

Commit b3a97716377820e2cd3097e6e96e20b7a2622cad

Authored by Efrain Gonzalez
1 parent 22a75a38eb
Exists in master

Update to the Rcode (UNTESTED)

Showing 1 changed file with 9 additions and 8 deletions   Show diff stats
... ... @@ -241,20 +241,20 @@ 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",colnames(.)))
  244 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.)))
245 245 }
246 246 if(IDF == 0){
247 247 #No information on this particular GPL file
248 248 idLOCGPL <- genena %>%
249 249 read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>%
250 250 t(.) %>%
251   - grep("^\\D",.) %>%
252   - length()-1
  251 + grep("^ID\\s*$",.) %>%
  252 + -1
253 253 cbind(as.integer(gplnum),as.integer(idLOCGPL)) %>%
254 254 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE)
255 255 geneIDNam <- genena %>%
256 256 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
257   - dplyr::select(.,ID,grep("Symbol|ORF",colnames(.)))
  257 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.)))
258 258 }
259 259 }
260 260 if(fileex == 0){
... ... @@ -262,20 +262,20 @@ if(clfileex == 0){
262 262 idLOCGPL <- genena %>%
263 263 read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>%
264 264 t(.) %>%
265   - grep("^\\D",.) %>%
266   - length()-1
  265 + grep("^ID\\s*$",.) %>%
  266 + -1
267 267 Firstval <- cbind(as.integer(gplnum),as.integer(idLOCGPL))
268 268 colnames(Firstval) <- c("GPL_FILE_NUM","LOC_ID")
269 269 write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE)
270 270 geneIDNam <- genena %>%
271 271 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
272   - dplyr::select(.,ID,grep("Symbol|ORF",colnames(.)))
  272 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.)))
273 273 }
274 274 }
275 275 if(soft == FALSE){
276 276 geneIDNam <- genena %>%
277 277 read_delim(delim="\t",comment = "#")%>%
278   - dplyr::select(.,ID,grep("Symbol|ORF",colnames(.)))
  278 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.)))
279 279 }
280 280  
281 281 ##Labeling the gene IDs without names
... ... @@ -322,3 +322,4 @@ nfnaex &lt;- strsplit(alz,&quot;[\\]&quot;) %&gt;%
322 322 paste(collapse = "")
323 323 write.table(t(Fullalzdw), file = nfnaex, sep = "\t")
324 324  
  325 +