Efrain Gonzalez / Cleaning and Fixing Data with R

Download as
Browse Code ยป

Commit 52de10530cfd98c52f52fed69b65639431a650d0

Authored by Efrain Gonzalez
1 parent 77a0d64ff0
Exists in master

Updated: added |^GENE_SYMBOL$ to glossary

Showing 1 changed file with 4 additions and 4 deletions   Show diff stats
... ... @@ -258,7 +258,7 @@ geneIDNam <- paste0("Clean_GPL",gplnum,".txt") %>%
258 258 .[IDLOCAL]
259 259 geneIDNam <- genena %>%
260 260 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>%
261   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  261 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
262 262 } else if(IDF == 0){
263 263 #No information on this particular GPL file
264 264 idLOCGPL <- genena %>%
... ... @@ -270,7 +270,7 @@ geneIDNam &lt;- paste0(&quot;Clean_GPL&quot;,gplnum,&quot;.txt&quot;) %&gt;%
270 270 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE)
271 271 geneIDNam <- genena %>%
272 272 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
273   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  273 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
274 274 }
275 275 } else if(fileex == 0){
276 276 #We must create a file that we can access for later use
... ... @@ -284,12 +284,12 @@ geneIDNam &lt;- paste0(&quot;Clean_GPL&quot;,gplnum,&quot;.txt&quot;) %&gt;%
284 284 write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE)
285 285 geneIDNam <- genena %>%
286 286 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
287   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  287 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
288 288 }
289 289 } else if(soft == FALSE){
290 290 geneIDNam <- genena %>%
291 291 read_delim(delim="\t",comment = "#")%>%
292   - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$",colnames(.)))
  292 + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$|^Gene symbol$|^GENE_SYMBOL$",colnames(.)))
293 293 }
294 294  
295 295 ##Labeling the gene IDs without names