Efrain Gonzalez / Cleaning and Fixing Data with R

Download as
Browse Code ยป

Commit 2677909e39ee690329745832c97a3fb94154909c

Authored by Efrain Gonzalez
1 parent cb1063ceb9
Exists in master

Added "Gene symbol" to glossary for geneIDNam

Showing 1 changed file with 8 additions and 8 deletions   Show diff stats
... ... @@ -264,7 +264,7 @@ THEFT <- function(){
264 264 .[IDLOCAL]
265 265 geneIDNam <- genena %>%
266 266 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>%
267   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
  267 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
268 268 } else if(IDF == 0){
269 269 #No information on this particular GPL file
270 270 idLOCGPL <- genena %>%
... ... @@ -276,7 +276,7 @@ THEFT &lt;- function(){
276 276 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE)
277 277 geneIDNam <- genena %>%
278 278 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
279   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
  279 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
280 280 }
281 281 } else if(fileex == 0){
282 282 #We must create a file that we can access for later use
... ... @@ -290,12 +290,12 @@ THEFT &lt;- function(){
290 290 write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE)
291 291 geneIDNam <- genena %>%
292 292 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
293   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
  293 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
294 294 }
295 295 } else if(soft == FALSE){
296 296 geneIDNam <- genena %>%
297 297 read_delim(delim="\t",comment = "#")%>%
298   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
  298 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
299 299 }
300 300  
301 301 ##Labeling the gene IDs without names
... ... @@ -552,7 +552,7 @@ THEFT &lt;- function(){
552 552 .[IDLOCAL]
553 553 geneIDNam <- genena %>%
554 554 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>%
555   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
  555 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
556 556 } else if(IDF == 0){
557 557 #No information on this particular GPL file
558 558 idLOCGPL <- genena %>%
... ... @@ -564,7 +564,7 @@ THEFT &lt;- function(){
564 564 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE)
565 565 geneIDNam <- genena %>%
566 566 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
567   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
  567 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
568 568 }
569 569 } else if(fileex == 0){
570 570 #We must create a file that we can access for later use
... ... @@ -578,12 +578,12 @@ THEFT &lt;- function(){
578 578 write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE)
579 579 geneIDNam <- genena %>%
580 580 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
581   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
  581 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
582 582 }
583 583 } else if(soft == FALSE){
584 584 geneIDNam <- genena %>%
585 585 read_delim(delim="\t",comment = "#")%>%
586   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
  586 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
587 587 }
588 588  
589 589 ##Labeling the gene IDs without names