Mercurial > repos > jfb > difference_finder

comparison all stuff/Difference finderMADE 7 TO 7 fastversion.R @ 4:74ada21ceb70 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jfb
date Fri, 19 Apr 2019 14:00:46 -0400
parents
children
comparison
equal deleted inserted replaced
3:dff99bed3f56 4:74ada21ceb70
1 #I should make an SOP for this. Problems we encountered: no x in the xY motif, and the kilodemon
2 #the output files have both Y and xY, they shouldn't why is that happening? make it not happen
3 #make sure that accession numbers stay locked to each motif, somehow
4 #output should look just like the KALIP input
5 #S2 is negatives
6 #ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
7 FullMotifsOnly_questionmark<-"NO"
8 #If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
9 TruncatedMotifsOnly_questionmark<-"NO"
10 #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)
11 Are_You_Looking_For_Commonality<-"NO"
12
13
14 #put the names of your input files here
15 FirstSubstrateSet<- read.csv("pka_minus_wo_vector_subs.csv", stringsAsFactors=FALSE)
16 Firstsubbackfreq<- read.csv("pka_minus_wo_vector_sbf.csv", header=FALSE, stringsAsFactors=FALSE)
17
18 SecondSubstrateSet<- read.csv("pka_plus_wo_vector_substrates.csv", stringsAsFactors=FALSE)
19 Secondsubbackfreq<- read.csv("pka_plus_wo_vector_sbf.csv", header=FALSE, stringsAsFactors=FALSE)
20
21 # ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)
22 # Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
23
24 #then put the names of your output files here
25 # Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"
26 # Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"
27
28 # Shared_motifs_table<-"Shared motifs 7-27-17.csv"
29 # Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"
30
31 First_unshared_motifs_table<-"pka_minus_wo-plus_wo_vector_subs.csv"
32 First_unshared_subbackfreq<-"pka_minus_wo-plus_wo_vector_sbf.csv"
33
34 Second_unshared_motifs_table<-"pka_plus_wo-minus_wo_vector_subs.csv"
35 Second_unshared_subbackfreq<-"pka_plus_wo-minus_wo_vector_sbf.csv"
36
37 # Third_unshared_motifs_table<-"R3 subs.csv"
38 # Third_unshared_subbackfreq<-"R3 SBF.csv"
39
40 #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
41 #other languages to see if any of them can do it.
42 ####################################################################################################################################
43
44
45
46
47
48 # grepl(pattern = "S", x=asdf, ignore.case = TRUE)
49
50 FirstCentralLetters<-FirstSubstrateSet[,11]
51 SecondCentralLetters<-SecondSubstrateSet[,11]
52
53 FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)
54 FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)
55 FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
56
57 SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)
58 SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)
59 SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
60
61 FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")
62 FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")
63 FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")
64
65 SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")
66 SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")
67 SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")
68
69 FirstCentralLetters->FirstSubstrateSet[,11]
70 SecondCentralLetters->SecondSubstrateSet[,11]
71
72 ####################################################################################################################################
73 ####################################################################################################################################
74 # better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two
75 # separate proteins thus two separate accession numbers?
76 # It should actually output the shared motif and BOTH accession numbers. Right now it does not, it only maps out the second
77 # accession number. So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number
78 ####################################################################################################################################
79 ####################################################################################################################################
80 ####################################################################################################################################
81 ####################################################################################################################################
82
83 #Create the motif sets, deciding wether or not you're looking for truncated or full here
84 #full only
85
86
87 if (Are_You_Looking_For_Commonality=="NO"){
88
89 ###############################################
90 #ALL motifs, full and truncated
91
92 if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
93 # FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
94 # FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
95
96 #so what this does is
97 #find the central phospho position and add spaces to either side of it
98 #create a pasted together motif which will be used for difference finding
99 #keep motifs and accession numbers in the same index position of two vectors
100
101 #so instead just take the FLTwt[i,4:18], and replace "" with "O"
102 #then perform paste function
103 #then FLTwt with "O" can be the motif that will get printed to the CSV (after re-removing the "O") and the pasted motif is in its own vector that follows the A #s
104
105 FTLwtmotifs<-FirstSubstrateSet[,4:18]
106 # FTLwtmotifs<-sapply(FTLwtmotifs, gsub, pattern=" ", replacement="O",ignore.case=TRUE)
107 FTLwtmotifs<-replace(FTLwtmotifs, FTLwtmotifs=="", "O")
108 FTLwtmotifs<-apply(FTLwtmotifs, 1, paste, sep="", collapse="")
109 FTLwtAccessionNumbers<-FirstSubstrateSet[,3]
110
111 # D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
112 # D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
113
114 D835Ymotifs<-SecondSubstrateSet[,4:18]
115 # D835Ymotifs<-sapply(D835Ymotifs, gsub, patter="", replacement="O",ignore.case=TRUE)
116 D835Ymotifs<-replace(D835Ymotifs, D835Ymotifs=="", "O")
117 D835Ymotifs<-replace(D835Ymotifs, D835Ymotifs=="", "O")
118 D835Ymotifs<-apply(D835Ymotifs, 1, paste, sep="", collapse="")
119 D835YAccessionNumbers<-SecondSubstrateSet[,3]
120
121 names(FTLwtmotifs)<-FTLwtAccessionNumbers
122 names(D835Ymotifs)<-D835YAccessionNumbers
123
124 }
125
126
127 FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
128 FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
129
130 D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
131 D835YmotifsFINAL<-D835YmotifsFINAL[!duplicated(D835YmotifsFINAL)]
132
133
134
135 # columnalheader<-c(rep(NA,36))
136 # FTLFinalMatrix<-matrix(data =columnalheader,nrow = 1)
137 #
138 #how to make this an apply
139 #actual first turn names(motifsFINAL) into a vector, then gsub to replace all "|" pipe characters with "*" star characters
140 #first take the accession numbers as Firstsubbackfreq[1,], then gsub to replace all "|" pipe characters with "*" star characters
141 #then use AccessionNumbers as a vector and use
142 #matches <- unique (grep(paste(toMatch,collapse="|"), names(motifsFINAL), value=TRUE))
143
144 FLTwtNames<-names(FTLwtmotifsFINAL)
145 FLTwtNames<-FLTwtNames[!duplicated(FLTwtNames)]
146 #the problem is the names includes a lot of things that are multi names separated by ;
147 #I need to do soem paper writing and poster writing
148
149 # FLTwtNames<-gsub(pattern = '\\|', replacement = "*", x=FLTwtNames)
150 # FLTwtNames<-paste(FLTwtNames,collapse = "|")
151
152 AccNums<-as.character(Firstsubbackfreq[1,])
153 # AccNums<-gsub(pattern = "\\|", replacement = "*", x=AccNums)
154
155
156 firstthree123<-gsub(pattern = "\\|", replacement = "", x=FLTwtNames)
157 lastthree123<-gsub(pattern = "\\|", replacement = "", x=AccNums)
158
159 pasty<-paste(lastthree123,collapse = "|")
160
161 # my_matches<-unique(grep(pattern = FLTwtNames, x=AccNums, value = TRUE))
162 # matches <- unique (grep(paste(FLTwtNames,collapse="|"), AccNums, value=TRUE))
163 My_matches<- AccNums %in% FLTwtNames #use apply grep function
164 # My_matches<-grep(pattern = pasty, x=lastthree123, ignore.case = TRUE)
165
166 #my matches are which columns in the SBF file still have a motif with them
167 FirstFINALSBF<-Firstsubbackfreq[My_matches]
168 FTLFinalMatrix<-FirstFINALSBF
169 duped<-FTLFinalMatrix[1,]
170 duped<-duped[!duplicated(duped)]
171 names(duped)<-NULL
172 duped<-unlist(duped)
173 unduped<-FTLFinalMatrix[,!duplicated(duped)]
174 FTLFinalMatrix<-unduped
175 # FTLFinalMatrix<-FTLFinalMatrix[2:nrow(FTLFinalMatrix),]
176
177 # columnalheader<-c(rep(NA,36))
178 # D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)
179
180 D835names<-names(D835YmotifsFINAL)
181 D835names<-D835names[!duplicated(D835names)]
182 AccNums<-as.character(Secondsubbackfreq[1,])
183 My_matches<-AccNums %in% D835names
184 SecondFINALSBF<-Secondsubbackfreq[My_matches]
185 D835YFinalMatrix<-SecondFINALSBF
186 duped<-D835YFinalMatrix[1,]
187 duped<-duped[!duplicated(duped)]
188 names(duped)<-NULL
189 duped<-unlist(duped)
190 unduped<-D835YFinalMatrix[,!duplicated(duped)]
191 D835YFinalMatrix<-unduped
192 #there's a problem, accession numbers are duplicated
193
194 # FTLoutputmatrix<-matrix(data=c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)),ncol = 2)
195
196 FTLwtmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=FTLwtmotifsFINAL)
197 FTLwtmotifsFINAL<-gsub(pattern = "x", replacement = "", x=FTLwtmotifsFINAL)
198 FTLoutputmatrix<-matrix(data = c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)), ncol=2)
199
200 # FTLwtmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=FTLwtmotifsFINAL)
201 # FTLwtmotifsFINAL<-gsub(pattern = "x", replacement = "", x=FTLwtmotifsFINAL)
202 # FTLoutputmatrix<-matrix(data = c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)), ncol=2)
203
204 FLTheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
205 # FLTheader<-unlist(FLTheader)
206 lefthandFLT<-matrix(data = rep(NA,times=2*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
207 righthandFLT<-matrix(data = rep(NA,times=1*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
208 FLTaccessionset<-FTLoutputmatrix[,2]
209 FTLmeat<-sapply(FTLoutputmatrix[,1], strsplit, "")
210 FTLmeat<-sapply(FTLmeat, unlist)
211 colnames(FTLmeat)<-NULL
212 FTLmeat<-t(FTLmeat)
213
214 FTLoutputmatrix2<-cbind(lefthandFLT,FLTaccessionset,FTLmeat,righthandFLT)
215 colnames(FTLoutputmatrix2)<-NULL
216 rownames(FTLoutputmatrix2)<-NULL
217 colnames(FLTheader)<-NULL
218 rownames(FLTheader)<-NULL
219
220
221 FirstCentralLettersAGAIN<-FTLoutputmatrix2[,11]
222
223 FirstEsses<-sapply(FirstCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
224 FirstTees<-sapply(FirstCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
225 FirstWys<-sapply(FirstCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
226
227 FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstEsses,"xS")
228 FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstTees,"xT")
229 FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstWys,"xY")
230
231 FirstCentralLettersAGAIN->FTLoutputmatrix2[,11]
232
233 FTLoutputmatrix2<-rbind(FLTheader,FTLoutputmatrix2)
234
235 write.table(x=FTLoutputmatrix2,
236 file=First_unshared_motifs_table,
237 quote=FALSE, sep=",",
238 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
239
240 columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
241 columnalheader<-matrix(columnalheader,ncol = 1)
242 # write.table(x=columnalheader,
243 # file=First_unshared_subbackfreq,
244 # quote=FALSE, sep=",",
245 # row.names=FALSE,col.names = FALSE, na="", append=TRUE)
246
247 FTLFinalMatrix<-cbind(columnalheader,FTLFinalMatrix)
248
249 write.table(x=FTLFinalMatrix,
250 file=First_unshared_subbackfreq,
251 quote=FALSE, sep=",",
252 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
253
254 ############################################################################################################
255
256 D835YmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=D835YmotifsFINAL)
257 D835YmotifsFINAL<-gsub(pattern = "x", replacement = "", x=D835YmotifsFINAL)
258 D835Youtputmatrix<-matrix(data = c(D835YmotifsFINAL,names(D835YmotifsFINAL)), ncol=2)
259
260 # D835YmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=D835YoutputmatrixL)
261 # D835YmotifsFINAL<-gsub(pattern = "x", replacement = "", x=D835Youtputmatrix)
262 # D835Youtputmatrix<-matrix(data = c(D835Youtputmatrix,names(D835Youtputmatrix)), ncol=2)
263 #
264
265 # D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)
266
267 D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
268 # D835Yheader<-unlist(D835Yheader)
269 lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
270 righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
271 D835Yaset<-D835Youtputmatrix[,2]
272 D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")
273 D835meat<-sapply(D835meat, unlist)
274 colnames(D835meat)<-NULL
275 D835meat<-t(D835meat)
276
277 # FTLmeat<-sapply(FTLoutputmatrix[,1], strsplit, "")
278 # FTLmeat<-sapply(FTLmeat, unlist)
279 # colnames(FTLmeat)<-NULL
280 # FTLmeat<-t(FTLmeat)
281
282
283 D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)
284 colnames(D835Youtputmatrix2)<-NULL
285 rownames(D835Youtputmatrix2)<-NULL
286 colnames(D835Yheader)<-NULL
287 rownames(D835Yheader)<-NULL
288
289
290 SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]
291
292 SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
293 SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
294 SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
295
296 SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")
297 SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")
298 SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")
299
300 SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]
301
302 D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)
303
304 write.table(x=D835Youtputmatrix2,
305 file=Second_unshared_motifs_table,
306 quote=FALSE, sep=",",
307 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
308
309 columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
310 columnalheader<-matrix(columnalheader,ncol = 1)
311 # write.table(x=columnalheader,
312 # file=Second_unshared_subbackfreq,
313 # quote=FALSE, sep=",",
314 # row.names=FALSE,col.names = FALSE, na="", append=TRUE)
315
316 D835YFinalMatrix<-cbind(columnalheader,D835YFinalMatrix)
317
318 write.table(x=D835YFinalMatrix,
319 file=Second_unshared_subbackfreq,
320 quote=FALSE, sep=",",
321 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
322 }
323
324
325
326 # for (i in 1:nrow(FirstSubstrateSet)){
327 # FTLwtletters<-FirstSubstrateSet[i,4:18]
328 # FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
329 # FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
330 # leftspaces<-c()
331 # rightspaces<-c()
332 #
333 # YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
334 # YYYposition <- match(x = "x", table = YYYmotif)
335 # #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
336 # #just 3 letters to the left of x
337 #
338 # YYYLettersToTheLeft <- YYYposition - 1
339 # #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
340 # #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
341 # YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
342 # #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
343 # #variable the user puts in is
344 #
345 #
346 # if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
347 # leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
348 # rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
349 # #add blank spaces if the motif has less than 4 letters to the left/right
350 # motif<-c(leftspaces,YYYmotif,rightspaces)
351 # #save that motif, which is the Y and +/- 4 amino acids, including truncation
352 # motif<-motif[!motif %in% "x"]
353 # motif<-paste(motif, sep="", collapse="")
354 # FTLwtletters<-motif
355 # FTLwtmotifs[i,1]<-FTLwtletters
356 # FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
357 # }
358 #
359 # if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
360 # motif<-YYYmotif
361 # #add blank spaces if the motif has less than 4 letters to the left/right
362 # motif<-c(leftspaces,YYYmotif,rightspaces)
363 # #save that motif, which is the Y and +/- 4 amino acids, including truncation
364 # motif<-motif[!motif %in% "x"]
365 # motif<-paste(motif, sep="", collapse="")
366 # FTLwtletters<-motif
367 # FTLwtmotifs[i,1]<-FTLwtletters
368 # FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
369 #
370 #
371 # }
372 #
373 # }
374
375
376
377 # for (i in 1:nrow(SecondSubstrateSet)){
378 # D835letters<-SecondSubstrateSet[i,4:18]
379 # D835letters<-D835letters[D835letters !="XXXXX"]
380 # D835letters<-paste(D835letters, sep="", collapse="")
381 # leftspaces<-c()
382 # rightspaces<-c()
383 #
384 # YYYmotif <- unlist(strsplit(D835letters, split = ""))
385 # YYYposition <- match(x = "x", table = YYYmotif)
386 # #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
387 # #just 3 letters to the left of x
388 #
389 # YYYLettersToTheLeft <- YYYposition - 1
390 # #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
391 # #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
392 # YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
393 # #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
394 # #variable the user puts in is
395 # if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
396 # leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
397 # rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
398 # #add blank spaces if the motif has less than 4 letters to the left/right
399 # motif<-c(leftspaces,YYYmotif,rightspaces)
400 # #save that motif, which is the Y and +/- 4 amino acids, including truncation
401 # motif<-motif[!motif %in% "x"]
402 # motif<-paste(motif, sep="", collapse="")
403 # D835letters<-motif
404 # D835Ymotifs[i,1]<-D835letters
405 # D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
406 # }
407 #
408 # if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
409 # motif<-YYYmotif
410 # #add blank spaces if the motif has less than 4 letters to the left/right
411 # motif<-c(leftspaces,YYYmotif,rightspaces)
412 # #save that motif, which is the Y and +/- 4 amino acids, including truncation
413 # motif<-motif[!motif %in% "x"]
414 # motif<-paste(motif, sep="", collapse="")
415 # D835letters<-motif
416 # D835Ymotifs[i,1]<-D835letters
417 # D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
418 # }
419 # }
420
421 # for (k in 1:length(FTLwtmotifsFINAL)) {
422 # AN<-00000
423 # #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
424 # #destroyed immediately after use
425 # for (m in 1:ncol(Firstsubbackfreq)) {
426 # AN <- as.character(Firstsubbackfreq[1, m])
427 # if (grepl(pattern = AN,
428 # x = names(FTLwtmotifsFINAL[k]),
429 # fixed = TRUE) == TRUE) {
430 # outputmatrix <- as.character(Firstsubbackfreq[, m])
431 # outputmatrix <- matrix(outputmatrix, nrow = 1)
432 # #with that accession number, find a match in the subbackfreq file and save it here
433 # FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)
434 # }
435 # }
436 # }
437 # for (k in 1:length(D835YmotifsFINAL)) {
438 # #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
439 # #destroyed immediately after use
440 # for (m in 1:ncol(Secondsubbackfreq)) {
441 # AN <- as.character(Secondsubbackfreq[1, m])
442 # if (grepl(pattern = AN,
443 # x = names(D835YmotifsFINAL[k]),
444 # fixed = TRUE) == TRUE) {
445 # outputmatrix <- as.character(Secondsubbackfreq[, m])
446 # outputmatrix <- matrix(outputmatrix, nrow = 1)
447 # #with that accession number, find a match in the subbackfreq file and save it here
448 # D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)
449 # }
450 # }
451 # }