Mercurial > repos > jfb > difference_finder

comparison all stuff/Difference finder for GalaxyP 2-21-20.R @ 9:033dd86d3e0c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jfb
date Fri, 21 Feb 2020 13:07:45 -0500
parents
children 78f16bc92ba6
comparison
equal deleted inserted replaced
8:4dd15c41d9e7 9:033dd86d3e0c
1 #ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
2 FullMotifsOnly_questionmark<-"NO"
3 #If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
4 TruncatedMotifsOnly_questionmark<-"NO"
5 #if you want to find the overlap, put a "YES" here (all caps), if you want to find the non-overlap, put "NO" (all caps)
6 Are_You_Looking_For_Commonality<-"NO"
7
8
9 #put the names of your input files here
10 FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE,colClasses = "character")
11 Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)
12
13 SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE,colClasses = "character")
14 Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)
15
16
17 First_unshared_motifs_table<-"1RS.csv"
18 First_unshared_subbackfreq<-"1RSBF.csv"
19
20 Second_unshared_motifs_table<-"2RS.csv"
21 Second_unshared_subbackfreq<-"2RSBF.csv"
22
23 EmptySubHeader<-colnames(FirstSubstrateSet)
24 EmptySubHeader<-matrix(EmptySubHeader, nrow=1)
25 EmptySBFHeader<-Firstsubbackfreq[,1]
26
27 #final note, this code is going to be unworkable if you want to make a Venn diagram of more than 3 circles. I think I'll poke around
28 #other languages to see if any of them can do it.
29 ####################################################################################################################################
30
31
32 FirstCentralLetters<-FirstSubstrateSet[,11]
33 SecondCentralLetters<-SecondSubstrateSet[,11]
34
35 FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)
36 FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)
37 FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
38
39 SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)
40 SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)
41 SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
42
43 FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")
44 FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")
45 FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")
46
47 SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")
48 SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")
49 SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")
50
51 FirstCentralLetters->FirstSubstrateSet[,11]
52 SecondCentralLetters->SecondSubstrateSet[,11]
53
54 ####################################################################################################################################
55 ####################################################################################################################################
56 # better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two
57 # separate proteins thus two separate accession numbers?
58 # It should actually output the shared motif and BOTH accession numbers. Right now it does not, it only maps out the second
59 # accession number. So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number
60 ####################################################################################################################################
61 ####################################################################################################################################
62 ####################################################################################################################################
63 ####################################################################################################################################
64
65 #Create the motif sets, deciding wether or not you're looking for truncated or full here
66 #full only
67
68
69 ###############################################
70 #ALL motifs, full and truncated
71
72 if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
73 FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
74 FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
75
76 for (i in 1:nrow(FirstSubstrateSet)){
77 FTLwtletters<-FirstSubstrateSet[i,4:18]
78 FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
79 FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
80 leftspaces<-c()
81 rightspaces<-c()
82
83 YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
84 YYYposition <- match(x = "x", table = YYYmotif)
85 #position itself tells me how much is to the left of that X by what it's number is. x at position 4 tells me that there are
86 #just 3 letters to the left of x
87
88 YYYLettersToTheLeft <- YYYposition - 1
89 #how many letters to the right SHOULD just be length(motif)-position-1 if it's 5 long and x is at 3 then Y is at 4 and there is
90 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
91 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
92 #then sanity check, we're currently looking only at +/-4, but this spot allows for up to +/- 7 as well, just depends on what the
93 #variable the user puts in is
94
95
96 if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
97 leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
98 rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
99 #add blank spaces if the motif has less than 4 letters to the left/right
100 motif<-c(leftspaces,YYYmotif,rightspaces)
101 #save that motif, which is the Y and +/- 4 amino acids, including truncation
102 motif<-motif[!motif %in% "x"]
103 motif<-paste(motif, sep="", collapse="")
104 FTLwtletters<-motif
105 FTLwtmotifs[i,1]<-FTLwtletters
106 FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
107 }
108
109 if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
110 motif<-YYYmotif
111 #add blank spaces if the motif has less than 4 letters to the left/right
112 motif<-c(leftspaces,YYYmotif,rightspaces)
113 #save that motif, which is the Y and +/- 4 amino acids, including truncation
114 motif<-motif[!motif %in% "x"]
115 motif<-paste(motif, sep="", collapse="")
116 FTLwtletters<-motif
117 FTLwtmotifs[i,1]<-FTLwtletters
118 FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
119
120
121 }
122
123 }
124
125 D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
126 D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
127
128 for (i in 1:nrow(SecondSubstrateSet)){
129 D835letters<-SecondSubstrateSet[i,4:18]
130 D835letters<-D835letters[D835letters !="XXXXX"]
131 D835letters<-paste(D835letters, sep="", collapse="")
132 leftspaces<-c()
133 rightspaces<-c()
134
135 YYYmotif <- unlist(strsplit(D835letters, split = ""))
136 YYYposition <- match(x = "x", table = YYYmotif)
137 #position itself tells me how much is to the left of that X by what it's number is. x at position 4 tells me that there are
138 #just 3 letters to the left of x
139
140 YYYLettersToTheLeft <- YYYposition - 1
141 #how many letters to the right SHOULD just be length(motif)-position-1 if it's 5 long and x is at 3 then Y is at 4 and there is
142 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
143 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
144 #then sanity check, we're currently looking only at +/-4, but this spot allows for up to +/- 7 as well, just depends on what the
145 #variable the user puts in is
146 if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
147 leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
148 rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
149 #add blank spaces if the motif has less than 4 letters to the left/right
150 motif<-c(leftspaces,YYYmotif,rightspaces)
151 #save that motif, which is the Y and +/- 4 amino acids, including truncation
152 motif<-motif[!motif %in% "x"]
153 motif<-paste(motif, sep="", collapse="")
154 D835letters<-motif
155 D835Ymotifs[i,1]<-D835letters
156 D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
157 }
158
159 if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
160 motif<-YYYmotif
161 #add blank spaces if the motif has less than 4 letters to the left/right
162 motif<-c(leftspaces,YYYmotif,rightspaces)
163 #save that motif, which is the Y and +/- 4 amino acids, including truncation
164 motif<-motif[!motif %in% "x"]
165 motif<-paste(motif, sep="", collapse="")
166 D835letters<-motif
167 D835Ymotifs[i,1]<-D835letters
168 D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
169 }
170 }
171
172 names(FTLwtmotifs)<-FTLwtAccessionNumbers
173 names(D835Ymotifs)<-D835YAccessionNumbers
174
175 }
176
177
178 FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
179 FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
180
181 D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
182 D835YmotifsFINAL<-D835YmotifsFINAL[!duplicated(D835YmotifsFINAL)]
183
184
185 columnalheader<-c(rep(NA,36))
186 FTLFinalMatrix<-matrix(data =columnalheader,nrow = 1)
187
188 FLTheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
189
190 if (length(FTLwtmotifsFINAL)>0){
191 for (k in 1:length(FTLwtmotifsFINAL)) {
192 AN<-00000
193 #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
194 #destroyed immediately after use
195 for (m in 1:ncol(Firstsubbackfreq)) {
196 AN <- as.character(Firstsubbackfreq[1, m])
197 if (grepl(pattern = AN,
198 x = names(FTLwtmotifsFINAL[k]),
199 fixed = TRUE) == TRUE) {
200 outputmatrix <- as.character(Firstsubbackfreq[, m])
201 outputmatrix <- matrix(outputmatrix, nrow = 1)
202 #with that accession number, find a match in the subbackfreq file and save it here
203 FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)
204 }
205 }
206 }
207 FTLFinalMatrix<-FTLFinalMatrix[!duplicated(FTLFinalMatrix),]
208 FTLFinalMatrix<-FTLFinalMatrix[2:nrow(FTLFinalMatrix),]
209
210
211 FTLoutputmatrix<-matrix(data=c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)),ncol = 2)
212 # FLTheader<-unlist(FLTheader)
213 lefthandFLT<-matrix(data = rep(NA,times=2*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
214 righthandFLT<-matrix(data = rep(NA,times=1*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
215 FLTaccessionset<-FTLoutputmatrix[,2]
216 FTLmeat<-sapply(FTLoutputmatrix[,1], strsplit, "")
217 FTLmeat<-sapply(FTLmeat, unlist)
218 colnames(FTLmeat)<-NULL
219 FTLmeat<-t(FTLmeat)
220
221 FTLoutputmatrix2<-cbind(lefthandFLT,FLTaccessionset,FTLmeat,righthandFLT)
222 colnames(FTLoutputmatrix2)<-NULL
223 rownames(FTLoutputmatrix2)<-NULL
224 colnames(FLTheader)<-NULL
225 rownames(FLTheader)<-NULL
226
227
228 FirstCentralLettersAGAIN<-FTLoutputmatrix2[,11]
229
230 FirstEsses<-sapply(FirstCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
231 FirstTees<-sapply(FirstCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
232 FirstWys<-sapply(FirstCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
233
234 FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstEsses,"xS")
235 FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstTees,"xT")
236 FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstWys,"xY")
237
238 FirstCentralLettersAGAIN->FTLoutputmatrix2[,11]
239
240 FTLoutputmatrix2<-rbind(FLTheader,FTLoutputmatrix2)
241
242 write.table(x=FTLoutputmatrix2,
243 file=First_unshared_motifs_table,
244 quote=FALSE, sep=",",
245 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
246
247 columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
248 columnalheader<-matrix(columnalheader,nrow = 1)
249 write.table(x=columnalheader,
250 file=First_unshared_subbackfreq,
251 quote=FALSE, sep=",",
252 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
253
254 write.table(x=FTLFinalMatrix,
255 file=First_unshared_subbackfreq,
256 quote=FALSE, sep=",",
257 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
258 } else{
259 FTLFinalMatrix<-columnalheader
260 write.table(x=EmptySubHeader,
261 file=First_unshared_motifs_table,
262 quote=FALSE, sep=",",
263 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
264
265 columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
266 columnalheader<-matrix(columnalheader,nrow = 1)
267 write.table(x=columnalheader,
268 file=First_unshared_subbackfreq,
269 quote=FALSE, sep=",",
270 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
271 }
272
273
274 columnalheader<-c(rep(NA,36))
275 D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)
276
277 if (length(D835YmotifsFINAL)>0){
278 for (k in 1:length(D835YmotifsFINAL)) {
279 #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
280 #destroyed immediately after use
281 for (m in 1:ncol(Secondsubbackfreq)) {
282 AN <- as.character(Secondsubbackfreq[1, m])
283 if (grepl(pattern = AN,
284 x = names(D835YmotifsFINAL[k]),
285 fixed = TRUE) == TRUE) {
286 outputmatrix <- as.character(Secondsubbackfreq[, m])
287 outputmatrix <- matrix(outputmatrix, nrow = 1)
288 #with that accession number, find a match in the subbackfreq file and save it here
289 D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)
290 }
291 }
292 }
293 D835YFinalMatrix<-D835YFinalMatrix[!duplicated(D835YFinalMatrix),]
294 D835YFinalMatrix<-D835YFinalMatrix[2:nrow(D835YFinalMatrix),]
295
296 D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)
297
298 D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
299 # D835Yheader<-unlist(D835Yheader)
300 lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
301 righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
302 D835Yaset<-D835Youtputmatrix[,2]
303 D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")
304 D835meat<-sapply(D835meat, unlist)
305 colnames(D835meat)<-NULL
306 D835meat<-t(D835meat)
307
308 D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)
309 colnames(D835Youtputmatrix2)<-NULL
310 rownames(D835Youtputmatrix2)<-NULL
311 colnames(D835Yheader)<-NULL
312 rownames(D835Yheader)<-NULL
313
314
315 SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]
316
317 SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
318 SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
319 SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
320
321 SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")
322 SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")
323 SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")
324
325 SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]
326
327 D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)
328
329 write.table(x=D835Youtputmatrix2,
330 file=Second_unshared_motifs_table,
331 quote=FALSE, sep=",",
332 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
333
334 columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
335 columnalheader<-matrix(columnalheader,nrow = 1)
336 write.table(x=columnalheader,
337 file=Second_unshared_subbackfreq,
338 quote=FALSE, sep=",",
339 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
340
341 write.table(x=D835YFinalMatrix,
342 file=Second_unshared_subbackfreq,
343 quote=FALSE, sep=",",
344 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
345 } else {
346 D835YFinalMatrix<- columnalheader
347 write.table(x=EmptySubHeader,
348 file=Second_unshared_motifs_table,
349 quote=FALSE, sep=",",
350 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
351
352 columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
353 columnalheader<-matrix(columnalheader,nrow = 1)
354 write.table(x=columnalheader,
355 file=Second_unshared_subbackfreq,
356 quote=FALSE, sep=",",
357 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
358 }