Efrain Gonzalez / Cleaning and Fixing Data with R

Download as
Browse Code ยป

Commit 77a0d64ff05e500f7e8ce62ee77861c5ec72b0b3

Authored by Efrain Gonzalez
1 parent 7f2b84c8cf
Exists in master

Updated: Added |^GENE_SYMBOL$ to glossary

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*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  267 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^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*$|^Gene symbol$",colnames(.)))
  279 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",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*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  293 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^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*$|^Gene symbol$",colnames(.)))
  298 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
299 299 }
300 300  
301 301 ##Labeling the gene IDs without names
... ... @@ -565,7 +565,7 @@ THEFT &lt;- function(){
565 565 .[IDLOCAL]
566 566 geneIDNam <- genena %>%
567 567 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>%
568   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  568 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
569 569 } else if(IDF == 0){
570 570 #No information on this particular GPL file
571 571 idLOCGPL <- genena %>%
... ... @@ -577,7 +577,7 @@ THEFT &lt;- function(){
577 577 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE)
578 578 geneIDNam <- genena %>%
579 579 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
580   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  580 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
581 581 }
582 582 } else if(fileex == 0){
583 583 #We must create a file that we can access for later use
... ... @@ -591,12 +591,12 @@ THEFT &lt;- function(){
591 591 write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE)
592 592 geneIDNam <- genena %>%
593 593 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
594   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  594 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
595 595 }
596 596 } else if(soft == FALSE){
597 597 geneIDNam <- genena %>%
598 598 read_delim(delim="\t",comment = "#")%>%
599   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  599 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
600 600 }
601 601  
602 602 ##Labeling the gene IDs without names