Efrain Gonzalez / Cleaning and Fixing Data with R

Download as
Browse Code ยป

Commit 48208ef1ad8e4050e3d595fb12b0e20a87d174e4

Authored by Efrain Gonzalez
1 parent 7360830df3
Exists in master

Update added |^UCSC_RefGene_Name$ to list of potential names in GPL

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$|^GENE_SYMBOL$",colnames(.)))
  267 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.)))
268 268 } else if(IDF == 0){
269 269 #No information on this particular GPL file
270 270 idLOCGPL <- genena %>%
... ... @@ -276,7 +276,7 @@ THEFT &lt;- function(){
276 276 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE)
277 277 geneIDNam <- genena %>%
278 278 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
279   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
  279 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",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$|^GENE_SYMBOL$",colnames(.)))
  293 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.)))
294 294 }
295 295 } else if(soft == FALSE){
296 296 geneIDNam <- genena %>%
297 297 read_delim(delim="\t",comment = "#")%>%
298   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
  298 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.)))
299 299 }
300 300  
301 301 ##Labeling the gene IDs without names
... ... @@ -587,7 +587,7 @@ THEFT &lt;- function(){
587 587 .[IDLOCAL]
588 588 geneIDNam <- genena %>%
589 589 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>%
590   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
  590 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.)))
591 591 } else if(IDF == 0){
592 592 #No information on this particular GPL file
593 593 idLOCGPL <- genena %>%
... ... @@ -599,7 +599,7 @@ THEFT &lt;- function(){
599 599 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE)
600 600 geneIDNam <- genena %>%
601 601 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
602   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
  602 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.)))
603 603 }
604 604 } else if(fileex == 0){
605 605 #We must create a file that we can access for later use
... ... @@ -613,12 +613,12 @@ THEFT &lt;- function(){
613 613 write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE)
614 614 geneIDNam <- genena %>%
615 615 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
616   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
  616 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.)))
617 617 }
618 618 } else if(soft == FALSE){
619 619 geneIDNam <- genena %>%
620 620 read_delim(delim="\t",comment = "#")%>%
621   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
  621 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$|^UCSC_RefGene_Name$",colnames(.)))
622 622 }
623 623  
624 624 ##Labeling the gene IDs without names