Commit 6a66705877a70dd83cb8cff53f5b52f447b4dc76
1 parent
769f081f9b
Exists in
master
Don't use this code yet
updated else if statements
Showing
1 changed file
with
20 additions
and
38 deletions
 
Show diff stats
RAutoClDs.R
| ... | ... | @@ -27,11 +27,9 @@ chngrownm <- function(mat){ | 
| 27 | 27 | for(e in 1:col){ | 
| 28 | 28 | if("!Sample_source_name_ch1"==mat[1,e]){ | 
| 29 | 29 | colnames(mat)[e] <- "Brain_Region" | 
| 30 | - } | |
| 31 | - else if("!Sample_title" == mat[1,e]){ | |
| 30 | + } else if("!Sample_title" == mat[1,e]){ | |
| 32 | 31 | colnames(mat)[e] <- "Title" | 
| 33 | - } | |
| 34 | - else if("!Sample_geo_accession" == mat[1,e]){ | |
| 32 | + } else if("!Sample_geo_accession" == mat[1,e]){ | |
| 35 | 33 | colnames(mat)[e] <- "ID_REF" | 
| 36 | 34 | } else{ | 
| 37 | 35 | if(grepl("Sex|gender|Gender|sex",mat[2,e])==TRUE){ | 
| ... | ... | @@ -68,19 +66,15 @@ cinfo <- function(mat){ | 
| 68 | 66 | for(j in 2:col){ | 
| 69 | 67 | if(grepl("Group",colnames(mat)[j]) == TRUE){ | 
| 70 | 68 | mat[,j] <- gsub(".+:\\s|\\s.+;.+","",mat[,j]) | 
| 71 | - } | |
| 72 | - else if(grepl("Age",colnames(mat)[j])==TRUE){ | |
| 69 | + } else if(grepl("Age",colnames(mat)[j])==TRUE){ | |
| 73 | 70 | mat[,j] <- gsub("\\D","",mat[,j])%>% | 
| 74 | 71 | as.integer() | 
| 75 | - } | |
| 76 | - else if(grepl("Sex",colnames(mat)[j])==TRUE){ | |
| 72 | + } else if(grepl("Sex",colnames(mat)[j])==TRUE){ | |
| 77 | 73 | mat[,j] <- gsub(".+:\\s","",mat[,j]) | 
| 78 | - } | |
| 79 | - else if(grepl("PMI",colnames(mat)[j])==TRUE){ | |
| 74 | + } else if(grepl("PMI",colnames(mat)[j])==TRUE){ | |
| 80 | 75 | mat[,j] <- gsub("[^0-9\\.]","",mat[,j])%>% | 
| 81 | 76 | as.numeric() | 
| 82 | - } | |
| 83 | - else if(grepl("Braak",colnames(mat)[j])==TRUE){ | |
| 77 | + } else if(grepl("Braak",colnames(mat)[j])==TRUE){ | |
| 84 | 78 | mat[,j]<-gsub(".+:\\s","",mat[,j])%>% | 
| 85 | 79 | as.roman()%>% | 
| 86 | 80 | as.integer() | 
| ... | ... | @@ -168,11 +162,9 @@ dndat <- function(NDATA){ | 
| 168 | 162 | |
| 169 | 163 | if(NDATA[i,j] < -1){ | 
| 170 | 164 | DDATA[i,j]=0L | 
| 171 | - } | |
| 172 | - else if(NDATA[i,j] > 1){ | |
| 165 | + } else if(NDATA[i,j] > 1){ | |
| 173 | 166 | DDATA[i,j]=2L | 
| 174 | - } | |
| 175 | - else if(-1 <= NDATA[i,j] && NDATA[i,j] < 1){ | |
| 167 | + } else if(-1 <= NDATA[i,j] && NDATA[i,j] < 1){ | |
| 176 | 168 | DDATA[i,j]=1L | 
| 177 | 169 | } | 
| 178 | 170 | } else{ | 
| ... | ... | @@ -276,8 +268,7 @@ THEFT <- function(){ | 
| 276 | 268 | geneIDNam <- genena %>% | 
| 277 | 269 | read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>% | 
| 278 | 270 | dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) | 
| 279 | - } | |
| 280 | - else if(IDF == 0){ | |
| 271 | + } else if(IDF == 0){ | |
| 281 | 272 | #No information on this particular GPL file | 
| 282 | 273 | idLOCGPL <- genena %>% | 
| 283 | 274 | read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>% | 
| ... | ... | @@ -290,8 +281,7 @@ THEFT <- function(){ | 
| 290 | 281 | read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% | 
| 291 | 282 | dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) | 
| 292 | 283 | } | 
| 293 | - } | |
| 294 | - else if(fileex == 0){ | |
| 284 | + } else if(fileex == 0){ | |
| 295 | 285 | #We must create a file that we can access for later use | 
| 296 | 286 | idLOCGPL <- genena %>% | 
| 297 | 287 | read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>% | 
| ... | ... | @@ -305,8 +295,7 @@ THEFT <- function(){ | 
| 305 | 295 | read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% | 
| 306 | 296 | dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) | 
| 307 | 297 | } | 
| 308 | - } | |
| 309 | - else if(soft == FALSE){ | |
| 298 | + } else if(soft == FALSE){ | |
| 310 | 299 | geneIDNam <- genena %>% | 
| 311 | 300 | read_delim(delim="\t",comment = "#")%>% | 
| 312 | 301 | dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) | 
| ... | ... | @@ -407,9 +396,8 @@ THEFT <- function(){ | 
| 407 | 396 | ##Putting the ones without duplicates in their new homes | 
| 408 | 397 | if(tabRDATID[j] == 1){ | 
| 409 | 398 | NuRDATN[,j] <- RAWDATNUM[,which(RAWDATID==rownames(tabRDATID)[j])] | 
| 410 | - } | |
| 411 | - ##Averaging duplicates and putting them in their new homes | |
| 412 | - else if(tabRDATID[j] > 1){ | |
| 399 | + } else if(tabRDATID[j] > 1){ | |
| 400 | + ##Averaging duplicates and putting them in their new homes | |
| 413 | 401 | NuRDATN[,j] <- rowMeans(RAWDATNUM[,which(RAWDATID==rownames(tabRDATID)[j])],na.rm = TRUE) | 
| 414 | 402 | } | 
| 415 | 403 | j <- j + 1 | 
| ... | ... | @@ -476,10 +464,9 @@ THEFT <- function(){ | 
| 476 | 464 | write.table(Dscrtalzdw, file = nfnaex2, sep = "\t",col.names = TRUE,row.names = FALSE) | 
| 477 | 465 | n <- n +1 | 
| 478 | 466 | } | 
| 479 | - } | |
| 480 | - | |
| 467 | + } else if(numDAT == 2){ | |
| 481 | 468 | #CHOOSE A DATA FILE TO CLEAN OR SEVERAL DATA FILES TO CLEAN | 
| 482 | - else if(numDAT == 2){ | |
| 469 | + | |
| 483 | 470 | #All the files you want to analyze | 
| 484 | 471 | ANDIS <- select.list(choices = list.files()[GSEfileloc],multiple = TRUE, title = "Choose the file/files you want to analyze:") | 
| 485 | 472 | if(length(ANDIS) == 0){ | 
| ... | ... | @@ -541,8 +528,7 @@ THEFT <- function(){ | 
| 541 | 528 | geneIDNam <- paste0("Clean_GPL",gplnum,".txt") %>% | 
| 542 | 529 | read_delim(delim="\t",col_names = c("ID","Symbol"), comment = "!") | 
| 543 | 530 | |
| 544 | - } | |
| 545 | - else if(clfileex == 0){ | |
| 531 | + } else if(clfileex == 0){ | |
| 546 | 532 | ##Lets Create a clean version | 
| 547 | 533 | |
| 548 | 534 | ##Gene ID to Gene Name | 
| ... | ... | @@ -565,8 +551,7 @@ THEFT <- function(){ | 
| 565 | 551 | geneIDNam <- genena %>% | 
| 566 | 552 | read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>% | 
| 567 | 553 | dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) | 
| 568 | - } | |
| 569 | - else if(IDF == 0){ | |
| 554 | + } else if(IDF == 0){ | |
| 570 | 555 | #No information on this particular GPL file | 
| 571 | 556 | idLOCGPL <- genena %>% | 
| 572 | 557 | read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>% | 
| ... | ... | @@ -579,8 +564,7 @@ THEFT <- function(){ | 
| 579 | 564 | read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% | 
| 580 | 565 | dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) | 
| 581 | 566 | } | 
| 582 | - } | |
| 583 | - else if(fileex == 0){ | |
| 567 | + } else if(fileex == 0){ | |
| 584 | 568 | #We must create a file that we can access for later use | 
| 585 | 569 | idLOCGPL <- genena %>% | 
| 586 | 570 | read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>% | 
| ... | ... | @@ -594,8 +578,7 @@ THEFT <- function(){ | 
| 594 | 578 | read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% | 
| 595 | 579 | dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) | 
| 596 | 580 | } | 
| 597 | - } | |
| 598 | - else if(soft == FALSE){ | |
| 581 | + } else if(soft == FALSE){ | |
| 599 | 582 | geneIDNam <- genena %>% | 
| 600 | 583 | read_delim(delim="\t",comment = "#")%>% | 
| 601 | 584 | dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) | 
| ... | ... | @@ -696,9 +679,8 @@ THEFT <- function(){ | 
| 696 | 679 | ##Putting the ones without duplicates in their new homes | 
| 697 | 680 | if(tabRDATID[j] == 1){ | 
| 698 | 681 | NuRDATN[,j] <- RAWDATNUM[,which(RAWDATID==rownames(tabRDATID)[j])] | 
| 699 | - } | |
| 682 | + } else if(tabRDATID[j] > 1){ | |
| 700 | 683 | ##Averaging duplicates and putting them in their new homes | 
| 701 | - else if(tabRDATID[j] > 1){ | |
| 702 | 684 | NuRDATN[,j] <- rowMeans(RAWDATNUM[,which(RAWDATID==rownames(tabRDATID)[j])],na.rm = TRUE) | 
| 703 | 685 | } | 
| 704 | 686 | j <- j + 1 |