Efrain Gonzalez / Cleaning and Fixing Data with R

Download as
Browse Code ยป

Commit 69cbaf694d196cd94f9d81b17b97da8c9b273cb4

Authored by Efrain Gonzalez
1 parent cb3deb0578
Exists in master

Updated

Showing 1 changed file with 3 additions and 0 deletions   Show diff stats
1 #Libraries required to run the code 1 #Libraries required to run the code
2 library(pryr) 2 library(pryr)
3 library(MASS) 3 library(MASS)
4 library(dplyr) 4 library(dplyr)
5 library(tidyr) 5 library(tidyr)
6 library(readr) 6 library(readr)
7 library(stringr) 7 library(stringr)
8 8
9 9
10 #Necessary Functions 10 #Necessary Functions
11 #1#Function for handling the changing of row names and column names 11 #1#Function for handling the changing of row names and column names
12 chngrownm <- function(mat){ 12 chngrownm <- function(mat){
13 row <- dim(mat)[1] 13 row <- dim(mat)[1]
14 col <- dim(mat)[2] 14 col <- dim(mat)[2]
15 j <- 1 15 j <- 1
16 x <- 1 16 x <- 1
17 p <- 1 17 p <- 1
18 a <- 1 18 a <- 1
19 b <- 1 19 b <- 1
20 g <- 1 20 g <- 1
21 for(j in 1:col){ 21 for(j in 1:col){
22 if("!Sample_source_name_ch1"==mat[1,j]){ 22 if("!Sample_source_name_ch1"==mat[1,j]){
23 colnames(mat)[j] <- "Brain_Region" 23 colnames(mat)[j] <- "Brain_Region"
24 } 24 }
25 if("!Sample_title" == mat[1,j]){ 25 if("!Sample_title" == mat[1,j]){
26 colnames(mat)[j] <- "Title" 26 colnames(mat)[j] <- "Title"
27 } 27 }
28 if("!Sample_geo_accession" == mat[1,j]){ 28 if("!Sample_geo_accession" == mat[1,j]){
29 colnames(mat)[j] <- "ID_REF" 29 colnames(mat)[j] <- "ID_REF"
30 } else{ 30 } else{
31 if(grepl("Sex|gender|Gender|sex",mat[2,j])==TRUE){ 31 if(grepl("Sex|gender|Gender|sex",mat[2,j])==TRUE){
32 colnames(mat)[j] <- paste0("Sex",x) 32 colnames(mat)[j] <- paste0("Sex",x)
33 x = x + 1 33 x = x + 1
34 } 34 }
35 if(grepl("postmorteminterval|PMI|pmi",mat[2,j])==TRUE){ 35 if(grepl("postmorteminterval|PMI|pmi",mat[2,j])==TRUE){
36 colnames(mat)[j] <- paste0("PMI",p) 36 colnames(mat)[j] <- paste0("PMI",p)
37 p = p + 1 37 p = p + 1
38 } 38 }
39 if(grepl("age|Age|AGE",mat[2,j])==TRUE){ 39 if(grepl("age|Age|AGE",mat[2,j])==TRUE){
40 colnames(mat)[j] <- paste0("Age",a) 40 colnames(mat)[j] <- paste0("Age",a)
41 a = a + 1 41 a = a + 1
42 } 42 }
43 if(grepl("braak|b&b",mat[2,j])==TRUE){ 43 if(grepl("braak|b&b",mat[2,j])==TRUE){
44 colnames(mat)[j] <- paste0("Braak",b) 44 colnames(mat)[j] <- paste0("Braak",b)
45 b = b + 1 45 b = b + 1
46 } 46 }
47 if(grepl("group|disease|control|AD|normal|diagnosis|Alzheimer|Control",mat[2,j])==TRUE){ 47 if(grepl("group|disease|control|AD|normal|diagnosis|Alzheimer|Control",mat[2,j])==TRUE){
48 colnames(mat)[j] <- paste0("Group",g) 48 colnames(mat)[j] <- paste0("Group",g)
49 g = g + 1 49 g = g + 1
50 } 50 }
51 51
52 } 52 }
53 j = j + 1 53 j = j + 1
54 } 54 }
55 mat 55 mat
56 } 56 }
57 57
58 #2#Function for reorganizing information within the columns 58 #2#Function for reorganizing information within the columns
59 cinfo <- function(mat){ 59 cinfo <- function(mat){
60 col <- dim(mat)[2] 60 col <- dim(mat)[2]
61 j <-2 61 j <-2
62 for(j in 2:col){ 62 for(j in 2:col){
63 if(grepl("Group",colnames(mat)[j]) == TRUE){ 63 if(grepl("Group",colnames(mat)[j]) == TRUE){
64 mat[,j] <- gsub(".+:\\s|\\s.+;.+","",mat[,j]) 64 mat[,j] <- gsub(".+:\\s|\\s.+;.+","",mat[,j])
65 } 65 }
66 if(grepl("Age",colnames(mat)[j])==TRUE){ 66 if(grepl("Age",colnames(mat)[j])==TRUE){
67 mat[,j] <- gsub("\\D","",mat[,j])%>% 67 mat[,j] <- gsub("\\D","",mat[,j])%>%
68 as.integer() 68 as.integer()
69 } 69 }
70 if(grepl("Sex",colnames(mat)[j])==TRUE){ 70 if(grepl("Sex",colnames(mat)[j])==TRUE){
71 mat[,j] <- gsub(".+:\\s","",mat[,j]) 71 mat[,j] <- gsub(".+:\\s","",mat[,j])
72 } 72 }
73 if(grepl("PMI",colnames(mat)[j])==TRUE){ 73 if(grepl("PMI",colnames(mat)[j])==TRUE){
74 mat[,j] <- gsub("[^0-9\\.]","",mat[,j])%>% 74 mat[,j] <- gsub("[^0-9\\.]","",mat[,j])%>%
75 as.numeric() 75 as.numeric()
76 } 76 }
77 if(grepl("Braak",colnames(mat)[j])==TRUE){ 77 if(grepl("Braak",colnames(mat)[j])==TRUE){
78 mat[,j]<-gsub(".+:\\s","",mat[,j])%>% 78 mat[,j]<-gsub(".+:\\s","",mat[,j])%>%
79 as.roman()%>% 79 as.roman()%>%
80 as.integer() 80 as.integer()
81 } 81 }
82 j=j+1 82 j=j+1
83 } 83 }
84 mat 84 mat
85 } 85 }
86 86
87 #3#Function for labeling the gene IDs without names 87 #3#Function for labeling the gene IDs without names
88 NAFIXING <- function(GIDNAM){ 88 NAFIXING <- function(GIDNAM){
89 row <- dim(GIDNAM)[1] 89 row <- dim(GIDNAM)[1]
90 i <- 1 90 i <- 1
91 for(i in 1:row){ 91 for(i in 1:row){
92 if(grepl("^NA\\s*$",GIDNAM[i,2])==TRUE||is.na(GIDNAM[i,2])==TRUE){ 92 if(grepl("^NA\\s*$",GIDNAM[i,2])==TRUE||is.na(GIDNAM[i,2])==TRUE){
93 GIDNAM[i,2] <- GIDNAM[i,1] 93 GIDNAM[i,2] <- GIDNAM[i,1]
94 } 94 }
95 i <- i + 1 95 i <- i + 1
96 } 96 }
97 GIDNAM 97 GIDNAM
98 } 98 }
99 99
100 ##4#Function for changing the gene ID to gene name 100 ##4#Function for changing the gene ID to gene name
101 ##cgeneID <- function(GeneName,DATA){ 101 ##cgeneID <- function(GeneName,DATA){
102 ## colGene <- dim(GeneName)[2] 102 ## colGene <- dim(GeneName)[2]
103 ## j <- 1 103 ## j <- 1
104 ## for(j in 1:colGene){ 104 ## for(j in 1:colGene){
105 ## chngsreq <- grep(GeneName[1,j],DATA[1,]) 105 ## chngsreq <- grep(GeneName[1,j],DATA[1,])
106 ## if(sum(chngsreq) > 0){ 106 ## if(sum(chngsreq) > 0){
107 ## #DATA[1,chngsreq] <- gsub(GeneName[1,j],GeneName[2,j],DATA[1,chngsreq]) 107 ## #DATA[1,chngsreq] <- gsub(GeneName[1,j],GeneName[2,j],DATA[1,chngsreq])
108 ## DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq]) 108 ## DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq])
109 ## } 109 ## }
110 ## j = j+1 110 ## j = j+1
111 ## } 111 ## }
112 ## DATA 112 ## DATA
113 ##} 113 ##}
114 #4#Function for changing the gene ID to gene name 114 #4#Function for changing the gene ID to gene name
115 cgeneID <- function(GeneName,DATA){ 115 cgeneID <- function(GeneName,DATA){
116 colGene <- dim(GeneName)[2] 116 colGene <- dim(GeneName)[2]
117 j <- 1 117 j <- 1
118 for(j in 1:colGene){ 118 for(j in 1:colGene){
119 chngsreq <- grep(paste0("^",GeneName[1,j],"$"),DATA[1,]) 119 chngsreq <- grep(paste0("^",GeneName[1,j],"$"),DATA[1,])
120 if(is.na(sum(chngsreq))==FALSE){ 120 if(is.na(sum(chngsreq))==FALSE){
121 if(sum(chngsreq) > 0){ 121 if(sum(chngsreq) > 0){
122 DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq]) 122 DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq])
123 } 123 }
124 } 124 }
125 #if(sum(chngsreq) > 0){ 125 #if(sum(chngsreq) > 0){
126 ##DATA[1,chngsreq] <- gsub(GeneName[1,j],GeneName[2,j],DATA[1,chngsreq]) 126 ##DATA[1,chngsreq] <- gsub(GeneName[1,j],GeneName[2,j],DATA[1,chngsreq])
127 #DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq]) 127 #DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq])
128 #} 128 #}
129 j = j+1 129 j = j+1
130 } 130 }
131 DATA 131 DATA
132 } 132 }
133 133
134 #5#Function for adjusting the gene names 134 #5#Function for adjusting the gene names
135 gcnames <- function(DiData,usecol=1){ 135 gcnames <- function(DiData,usecol=1){
136 nuruns <- dim(DiData)[2] 136 nuruns <- dim(DiData)[2]
137 i = 1 137 i = 1
138 nwnam <- rep("0",length.out=nuruns) 138 nwnam <- rep("0",length.out=nuruns)
139 for(i in 1:nuruns){ 139 for(i in 1:nuruns){
140 if(length(strsplit(colnames(DiData)[i],"///")[[1]]) >= usecol){ 140 if(length(strsplit(colnames(DiData)[i],"///")[[1]]) >= usecol){
141 nwnam[i]=strsplit(colnames(DiData)[i],"///")[[1]][usecol] 141 nwnam[i]=strsplit(colnames(DiData)[i],"///")[[1]][usecol]
142 } else{ 142 } else{
143 nwnam[i]=strsplit(colnames(DiData)[i],"///")[[1]][1] 143 nwnam[i]=strsplit(colnames(DiData)[i],"///")[[1]][1]
144 } 144 }
145 145
146 } 146 }
147 nwnam 147 nwnam
148 148
149 } 149 }
150 150
151 151
152 152
153 #The Rest of this code will be used every time you want to change a data set 153 #The Rest of this code will be used every time you want to change a data set
154 154
155 #Getting the series matrix file 155 #Getting the series matrix file
156 print("Choose the series matrix file that you want to Analyze") 156 print("Choose the series matrix file that you want to Analyze")
157 alz <- file.choose() 157 alz <- file.choose()
158 158
159 #Getting the GPL file 159 #Getting the GPL file
160 print("Choose the GPL file that correlates with the above series matrix file") 160 print("Choose the GPL file that correlates with the above series matrix file")
161 genena <- file.choose() 161 genena <- file.choose()
162 162
163 163
164 #Set working directory based on the directory of the series matrix file Currently only works for windows 164 #Set working directory based on the directory of the series matrix file Currently only works for windows
165 ##strsplit(alz,"[\\]") %>% 165 ##strsplit(alz,"[\\]") %>%
166 ## .[[1]] %>% 166 ## .[[1]] %>%
167 ## .[-length(.)] %>% 167 ## .[-length(.)] %>%
168 ## paste(.,collapse="/") %>% 168 ## paste(.,collapse="/") %>%
169 ## setwd() 169 ## setwd()
170 170
171 #Find out if it is a soft GPL file or not 171 #Find out if it is a soft GPL file or not
172 soft <- strsplit(genena,"[\\|/]") %>% 172 soft <- strsplit(genena,"[\\|/]") %>%
173 .[[1]] %>% 173 .[[1]] %>%
174 .[length(.)] %>% 174 .[length(.)] %>%
175 grepl("soft|annot",.) 175 grepl("soft|annot",.)
176 176
177 #Working with the wordy part of the document 177 #Working with the wordy part of the document
178 alzword <- alz %>% 178 alzword <- alz %>%
179 read_delim(delim ="\t",comment = "!Series",col_names = FALSE)%>% 179 read_delim(delim ="\t",comment = "!Series",col_names = FALSE)%>%
180 filter(grepl("!Sample",X1))%>% 180 filter(grepl("!Sample",X1))%>%
181 filter(!grepl("!Sample_contact",X1)) 181 filter(!grepl("!Sample_contact",X1))
182 182
183 ##Changing row names and column names: 183 ##Changing row names and column names:
184 ALZWORD <- t(alzword) 184 ALZWORD <- t(alzword)
185 rownames(ALZWORD)=NULL 185 rownames(ALZWORD)=NULL
186 colnames(ALZWORD) <- colnames(ALZWORD,do.NULL=FALSE) 186 colnames(ALZWORD) <- colnames(ALZWORD,do.NULL=FALSE)
187 ALZWORD <- chngrownm(ALZWORD)[-1,] 187 ALZWORD <- chngrownm(ALZWORD)[-1,]
188 ALZWORD <- ALZWORD%>% 188 ALZWORD <- ALZWORD%>%
189 as.data.frame()%>% 189 as.data.frame()%>%
190 dplyr::select(-starts_with("col")) 190 dplyr::select(-starts_with("col"))
191 191
192 ##Reorganizing information within the columns 192 ##Reorganizing information within the columns
193 ALZWORDF <- cinfo(ALZWORD) 193 ALZWORDF <- cinfo(ALZWORD)
194 194
195 195
196 #Working with Actual Data part of file 196 #Working with Actual Data part of file
197 alzdat <- alz %>% 197 alzdat <- alz %>%
198 read_delim(delim="\t",col_names=TRUE,comment = "!",skip=1) 198 read_delim(delim="\t",col_names=TRUE,comment = "!",skip=1)
199 ALZDAT <- t(alzdat[,-1]) 199 ALZDAT <- t(alzdat[,-1])
200 rownames(ALZDAT)=NULL 200 rownames(ALZDAT)=NULL
201 201
202 ##Is there a clean version of the GPL file available? 202 ##Is there a clean version of the GPL file available?
203 gplnum <- strsplit(genena,"[\\|/]") %>% 203 gplnum <- strsplit(genena,"[\\|/]") %>%
204 .[[1]] %>% 204 .[[1]] %>%
205 .[length(.)] %>% 205 .[length(.)] %>%
206 gsub("\\D","",.) 206 gsub("\\D","",.)
207 clfileex <- sum(grepl(paste0("Clean_GPL",gplnum),list.files())) 207 clfileex <- sum(grepl(paste0("Clean_GPL",gplnum),list.files()))
208 if(clfileex >= 1){ 208 if(clfileex >= 1){
209 #use the clean version 209 #use the clean version
210 geneIDNam <- paste0("Clean_GPL",gplnum,".txt") %>% 210 geneIDNam <- paste0("Clean_GPL",gplnum,".txt") %>%
211 read_delim(delim="\t",col_names = c("ID","Symbol"), comment = "!") 211 read_delim(delim="\t",col_names = c("ID","Symbol"), comment = "!")
212 212
213 } 213 }
214 if(clfileex == 0){ 214 if(clfileex == 0){
215 ##Lets Create a clean version 215 ##Lets Create a clean version
216 216
217 ##Gene ID to Gene Name 217 ##Gene ID to Gene Name
218 ###geneIDNam <- genena %>% 218 ###geneIDNam <- genena %>%
219 ### read_delim(delim="\t",comment = "#")%>% 219 ### read_delim(delim="\t",comment = "#")%>%
220 ### dplyr::select(.,ID,grep("Symbol|ORF",colnames(.))) 220 ### dplyr::select(.,ID,grep("Symbol|ORF",colnames(.)))
221 ###problems with the above for soft files 221 ###problems with the above for soft files
222 if(soft == TRUE){ 222 if(soft == TRUE){
223 #gplnum <- strsplit(genena,"[\\|/]") %>% 223 #gplnum <- strsplit(genena,"[\\|/]") %>%
224 # .[[1]] %>% 224 # .[[1]] %>%
225 # .[length(.)] %>% 225 # .[length(.)] %>%
226 # gsub("\\D","",.) 226 # gsub("\\D","",.)
227 #Check to see if there is already a file containing information on soft files 227 #Check to see if there is already a file containing information on soft files
228 fileex <- sum(grepl("GPL_ID_LOC.txt",list.files())) 228 fileex <- sum(grepl("GPL_ID_LOC.txt",list.files()))
229 if(fileex == 1){ 229 if(fileex == 1){
230 #Check to see if this GPL soft file has been used before 230 #Check to see if this GPL soft file has been used before
231 IDF <- read_delim("GPL_ID_LOC.txt",delim = "\t",col_names = TRUE) %>% 231 IDF <- read_delim("GPL_ID_LOC.txt",delim = "\t",col_names = TRUE) %>%
232 .$GPL_FILE_NUM%>% 232 .$GPL_FILE_NUM%>%
233 grepl(gplnum,.) %>% 233 grepl(gplnum,.) %>%
234 sum() 234 sum()
235 if(IDF == 1){ 235 if(IDF == 1){
236 IDLOCAL <- read_delim("GPL_ID_LOC.txt",delim = "\t",col_names = TRUE) %>% 236 IDLOCAL <- read_delim("GPL_ID_LOC.txt",delim = "\t",col_names = TRUE) %>%
237 .$GPL_FILE_NUM%>% 237 .$GPL_FILE_NUM%>%
238 grep(gplnum,.) 238 grep(gplnum,.)
239 idlocgpl <- read_delim("GPL_ID_LOC.txt",delim = "\t",col_names = TRUE) %>% 239 idlocgpl <- read_delim("GPL_ID_LOC.txt",delim = "\t",col_names = TRUE) %>%
240 .$LOC_ID %>% 240 .$LOC_ID %>%
241 .[IDLOCAL] 241 .[IDLOCAL]
242 geneIDNam <- genena %>% 242 geneIDNam <- genena %>%
243 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>% 243 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idlocgpl) %>%
244 dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) 244 dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
245 } 245 }
246 if(IDF == 0){ 246 if(IDF == 0){
247 #No information on this particular GPL file 247 #No information on this particular GPL file
248 idLOCGPL <- genena %>% 248 idLOCGPL <- genena %>%
249 read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>% 249 read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>%
250 t(.) %>% 250 t(.) %>%
251 .[1,] %>% 251 .[1,] %>%
252 grep("^ID\\s*$",.) %>% 252 grep("^ID\\s*$",.) %>%
253 -1 253 -1
254 cbind(as.integer(gplnum),as.integer(idLOCGPL)) %>% 254 cbind(as.integer(gplnum),as.integer(idLOCGPL)) %>%
255 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE) 255 cat(file="GPL_ID_LOC.txt",sep = "\t", fill = TRUE, append = TRUE)
256 geneIDNam <- genena %>% 256 geneIDNam <- genena %>%
257 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% 257 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
258 dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) 258 dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
259 } 259 }
260 } 260 }
261 if(fileex == 0){ 261 if(fileex == 0){
262 #We must create a file that we can access for later use 262 #We must create a file that we can access for later use
263 idLOCGPL <- genena %>% 263 idLOCGPL <- genena %>%
264 read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>% 264 read_delim(delim="\t",col_names = FALSE, comment = "!", n_max = 1000) %>%
265 t(.) %>% 265 t(.) %>%
266 .[1,] %>% 266 .[1,] %>%
267 grep("^ID\\s*$",.) %>% 267 grep("^ID\\s*$",.) %>%
268 -1 268 -1
269 Firstval <- cbind(as.integer(gplnum),as.integer(idLOCGPL)) 269 Firstval <- cbind(as.integer(gplnum),as.integer(idLOCGPL))
270 colnames(Firstval) <- c("GPL_FILE_NUM","LOC_ID") 270 colnames(Firstval) <- c("GPL_FILE_NUM","LOC_ID")
271 write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE) 271 write.table(Firstval,file = "GPL_ID_LOC.txt", sep = "\t",row.names = FALSE, col.names = TRUE)
272 geneIDNam <- genena %>% 272 geneIDNam <- genena %>%
273 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>% 273 read_delim(delim="\t",col_names = TRUE, comment = "!", skip = idLOCGPL) %>%
274 dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) 274 dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
275 } 275 }
276 } 276 }
277 if(soft == FALSE){ 277 if(soft == FALSE){
278 geneIDNam <- genena %>% 278 geneIDNam <- genena %>%
279 read_delim(delim="\t",comment = "#")%>% 279 read_delim(delim="\t",comment = "#")%>%
280 dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.))) 280 dplyr::select(.,ID,grep("Symbol|^ORF\\s*$|^gene_assignment\\s*$",colnames(.)))
281 } 281 }
282 282
283 ##Labeling the gene IDs without names 283 ##Labeling the gene IDs without names
284 geneIDNam <- NAFIXING(geneIDNam) 284 geneIDNam <- NAFIXING(geneIDNam)
285 285
286 ##remove the whitespace 286 ##remove the whitespace
287 geneIDNam <- t(rbind(str_trim(t(geneIDNam)[1,]),str_trim(t(geneIDNam)[2,]))) 287 geneIDNam <- t(rbind(str_trim(t(geneIDNam)[1,]),str_trim(t(geneIDNam)[2,])))
288 288
289 ##Here is the clean version 289 ##Here is the clean version
290 write.table(geneIDNam,file = paste0("Clean_GPL",gplnum,".txt"),sep = "\t",row.names = FALSE, col.names = FALSE) 290 write.table(geneIDNam,file = paste0("Clean_GPL",gplnum,".txt"),sep = "\t",row.names = FALSE, col.names = FALSE)
291 } 291 }
292 292
293 293
294 294
295 ##Changing the gene ID to gene name 295 ##Changing the gene ID to gene name
296 ALZDAT1 <- cgeneID(t(geneIDNam),t(alzdat)) 296 ALZDAT1 <- cgeneID(t(geneIDNam),t(alzdat))
297 colnames(ALZDAT) = ALZDAT1[1,] 297 colnames(ALZDAT) = ALZDAT1[1,]
298 298
299 299
300 ##Adjusting the column names aka the gene names 300 ##Adjusting the column names aka the gene names
301 colnames(ALZDAT) <- gcnames(ALZDAT) 301 colnames(ALZDAT) <- gcnames(ALZDAT)
302 302
303 303
304 #Full Data 304 #Full Data
305 Fullalzdw <- ALZDAT %>% 305 Fullalzdw <- ALZDAT %>%
306 as.data.frame() %>% 306 as.data.frame() %>%
307 cbind(ALZWORDF,.) 307 cbind(ALZWORDF,.)
308 308
309 309
310 #nfna <- strsplit(alz,"[\\|/]") %>% 310 #nfna <- strsplit(alz,"[\\|/]") %>%
311 # .[[1]] %>% 311 # .[[1]] %>%
312 # .[length(.)] %>% 312 # .[length(.)] %>%
313 # gsub("\\D","",.) %>% 313 # gsub("\\D","",.) %>%
314 # c("GSE",.,"after.txt") %>% 314 # c("GSE",.,"after.txt") %>%
315 # paste(collapse = "") 315 # paste(collapse = "")
316 #write.matrix(Fullalzdw,file = nfna,sep = "\t") 316 #write.matrix(Fullalzdw,file = nfna,sep = "\t")
317 317
318 #Perfect for excel viewing 318 #Perfect for excel viewing
319 nfnaex <- strsplit(alz,"[\\]") %>% 319 nfnaex <- strsplit(alz,"[\\]") %>%
320 .[[1]] %>% 320 .[[1]] %>%
321 .[length(.)] %>% 321 .[length(.)] %>%
322 gsub("\\D","",.) %>% 322 gsub("\\D","",.) %>%
323 c("GSE",.,"aftexcel.txt") %>% 323 c("GSE",.,"aftexcel.txt") %>%
324 paste(collapse = "") 324 paste(collapse = "")
325 write.table(t(Fullalzdw), file = nfnaex, sep = "\t") 325 write.table(t(Fullalzdw), file = nfnaex, sep = "\t")
326 326
327 327
328
329
330
328 331