Commit 7acfa60c605a052988391cb81ca9c4a3e982a80b

Authored by Efrain Gonzalez
1 parent 52de10530c
Exists in master

Update reordered questions asked

Showing 1 changed file with 2 additions and 1 deletions   Show diff stats
1 #Checking for similar genes in both data sets 1 #Checking for similar genes in both data sets
2 2
3 #Required libraries 3 #Required libraries
4 library(MASS) 4 library(MASS)
5 library(readr) 5 library(readr)
6 library(dplyr) 6 library(dplyr)
7 7
8 Check2Match <- function(){ 8 Check2Match <- function(){
9 ANDIS <- select.list(choices = list.files(),multiple = TRUE, title = "Choose the file/files you want to analyze:")
9 numrows <- "How many rows of clinical data are their in each data set (separate each number by a comma no spaces)?: " %>% 10 numrows <- "How many rows of clinical data are their in each data set (separate each number by a comma no spaces)?: " %>%
10 readline(prompt = .) %>% 11 readline(prompt = .) %>%
11 strsplit(.,split = ",") %>% 12 strsplit(.,split = ",") %>%
12 .[[1]] %>% 13 .[[1]] %>%
13 as.integer(.) 14 as.integer(.)
14 i <- 1 15 i <- 1
15 ANDIS <- select.list(choices = list.files(),multiple = TRUE, title = "Choose the file/files you want to analyze:") 16
16 17
17 for(i in 1:length(numrows)){ 18 for(i in 1:length(numrows)){
18 if( i == 1){ 19 if( i == 1){
19 edfile <- ANDIS[i] 20 edfile <- ANDIS[i]
20 ed <- edfile %>% 21 ed <- edfile %>%
21 read_delim(.,delim = "\t") 22 read_delim(.,delim = "\t")
22 ednocd <- ed[-(1:numrows[1]),] 23 ednocd <- ed[-(1:numrows[1]),]
23 #Second file brought in 24 #Second file brought in
24 eddfile <- ANDIS[i + 1] 25 eddfile <- ANDIS[i + 1]
25 edd <- eddfile %>% 26 edd <- eddfile %>%
26 read_delim(.,delim = "\t") 27 read_delim(.,delim = "\t")
27 eddnocd <- edd[-(1:numrows[2]),] 28 eddnocd <- edd[-(1:numrows[2]),]
28 29
29 ##Fully matched both data sets 30 ##Fully matched both data sets
30 eddy <- inner_join(ednocd,eddnocd) 31 eddy <- inner_join(ednocd,eddnocd)
31 #Matches 32 #Matches
32 meds <- eddy[,1] 33 meds <- eddy[,1]
33 34
34 } 35 }
35 if(i > 1 && i + 1 < length(numrows)){ 36 if(i > 1 && i + 1 < length(numrows)){
36 eddfile <- ANDIS[i + 1] 37 eddfile <- ANDIS[i + 1]
37 edd <- eddfile %>% 38 edd <- eddfile %>%
38 read_delim(.,delim = "\t") 39 read_delim(.,delim = "\t")
39 eddnocd <- edd[-(1:numrows[i + 1]),] 40 eddnocd <- edd[-(1:numrows[i + 1]),]
40 ##Fully matched both data sets 41 ##Fully matched both data sets
41 eddy <- inner_join(meds,eddnocd) 42 eddy <- inner_join(meds,eddnocd)
42 meds <- eddy[,1] 43 meds <- eddy[,1]
43 44
44 45
45 } 46 }
46 i <- i + 1 47 i <- i + 1
47 } 48 }
48 meds 49 meds
49 for(j in 1:length(numrows)){ 50 for(j in 1:length(numrows)){
50 edfile <- ANDIS[j] 51 edfile <- ANDIS[j]
51 ed <- edfile %>% 52 ed <- edfile %>%
52 read_delim(.,delim = "\t") 53 read_delim(.,delim = "\t")
53 ednocd <- ed[-(1:numrows[j]),] 54 ednocd <- ed[-(1:numrows[j]),]
54 #use meds to match 55 #use meds to match
55 eddy <- inner_join(meds,ednocd) 56 eddy <- inner_join(meds,ednocd)
56 Finedm <- rbind(ed[1:numrows[j],],eddy) 57 Finedm <- rbind(ed[1:numrows[j],],eddy)
57 nam_fil_ed <- strsplit(edfile,"[\\|/]") %>% 58 nam_fil_ed <- strsplit(edfile,"[\\|/]") %>%
58 .[[1]] %>% 59 .[[1]] %>%
59 .[length(.)] %>% 60 .[length(.)] %>%
60 gsub("\\D","",.) %>% 61 gsub("\\D","",.) %>%
61 c("GSE",.,"matched.txt") %>% 62 c("GSE",.,"matched.txt") %>%
62 paste(collapse = "") 63 paste(collapse = "")
63 write.table(Finedm,file = nam_fil_ed,sep = "\t",row.names = FALSE) 64 write.table(Finedm,file = nam_fil_ed,sep = "\t",row.names = FALSE)
64 j <- j + 1 65 j <- j + 1
65 } 66 }
66 meds 67 meds
67 } 68 }
68 69
69 Check2Match() 70 Check2Match()