diff --git a/RClean4.R b/RClean4.R index f1c1b40..a927f51 100644 --- a/RClean4.R +++ b/RClean4.R @@ -241,7 +241,7 @@ if(clfileex == 0){ .[IDLOCAL] geneIDNam <- genena %>% read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>% - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.))) + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) } if(IDF == 0){ #No information on this particular GPL file @@ -255,7 +255,7 @@ if(clfileex == 0){ cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE) geneIDNam <- genena %>% read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.))) + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) } } if(fileex == 0){ @@ -271,13 +271,13 @@ if(clfileex == 0){ write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE) geneIDNam <- genena %>% read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.))) + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) } } if(soft == FALSE){ geneIDNam <- genena %>% read_delim(delim="\t",comment = "#")%>% - dplyr::select(.,ID,grep("Symbol|^ORF\\s*$",colnames(.)) + dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)) } ##Labeling the gene IDs without names