|
0
|
1 #Difference finder for only 2
|
|
|
2
|
|
|
3 #ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
|
|
|
4 FullMotifsOnly_questionmark<-"NO"
|
|
|
5 #If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
|
|
|
6 TruncatedMotifsOnly_questionmark<-"NO"
|
|
|
7
|
|
|
8 FirstSubstrateSet<- read.csv("170922-BTK-MINUS-COMBO FILES_Substrates.csv", stringsAsFactors=FALSE)
|
|
|
9 Firstsubbackfreq<- read.csv("170922-BTK-MINUS-COMBO FILES_Substrates.csv", header=FALSE, stringsAsFactors=FALSE)
|
|
|
10
|
|
|
11 SecondSubstrateSet<- read.csv("170922-btk-rep OVLP-plus_Substrates.csv", stringsAsFactors=FALSE)
|
|
|
12 Secondsubbackfreq<- read.csv("170922-btk-rep OVLP-plus_SubBackFreq.csv", header=FALSE, stringsAsFactors=FALSE)
|
|
|
13
|
|
|
14 First_unshared_motifs_table<-"170922-BTK-MINUS-COMBO FILES_Substrates-unique.csv"
|
|
|
15 First_unshared_subbackfreq<-"170922-BTK-MINUS-COMBO FILES_SubBackFreq-unique.csv"
|
|
|
16
|
|
|
17 Second_unshared_motifs_table<-"170922-btk-rep OVLP-plus_Substrates-unique.csv"
|
|
|
18 Second_unshared_subbackfreq<-"170922-btk-rep OVLP-plus_SubBackFreq-unique.csv"
|
|
|
19
|
|
|
20
|
|
|
21 LeftOfYLetters<-7
|
|
|
22 RightOfYLetters<-7
|
|
|
23
|
|
|
24 if (FullMotifsOnly_questionmark=="YES"){
|
|
|
25 FirstMotifs=rep(NA,times=nrow(FirstSubstrateSet))
|
|
|
26 FirstAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
|
|
|
27 leftspaces<-c()
|
|
|
28 rightspaces<-c()
|
|
|
29 for (i in 1:nrow(FirstSubstrateSet)){
|
|
|
30 FirstLetters<-FirstSubstrateSet[i,7:15]
|
|
|
31 FirstLetters<-FirstLetters[FirstLetters !="XXXXX"]
|
|
|
32 FirstLetters<-paste(FirstLetters, sep="", collapse="")
|
|
|
33
|
|
|
34
|
|
|
35 YYYmotif <- unlist(strsplit(FirstLetters, split = ""))
|
|
|
36 YYYposition <- match(x = "x", table = YYYmotif)
|
|
|
37 #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
|
|
|
38 #just 3 letters to the left of x
|
|
|
39
|
|
|
40 YYYLettersToTheLeft <- YYYposition - 1
|
|
|
41 #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
|
|
|
42 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
|
|
|
43 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
|
|
|
44 #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
|
|
|
45 #variable the user puts in is
|
|
|
46
|
|
|
47 if (YYYLettersToTheLeft > 3 && YYYLettersToTheRight > 3) {
|
|
|
48 motif<-YYYmotif
|
|
|
49 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
50 motif<-motif[!motif %in% "x"]
|
|
|
51 motif<-paste(motif, sep="", collapse="")
|
|
|
52 FirstLetters<-motif
|
|
|
53 FirstMotifs[i]<-FirstLetters
|
|
|
54 FirstAccessionNumbers[i]<-FirstSubstrateSet[i,3]
|
|
|
55 }
|
|
|
56
|
|
|
57 }
|
|
|
58 # FirstMotifs <- FirstMotifs[!is.na(FirstMotifs)]
|
|
|
59 # FirstMotifs<-matrix(FirstMotifs,ncol = 1)
|
|
|
60 #
|
|
|
61
|
|
|
62 SecondMotifs=rep(NA,times=nrow(FirstSubstrateSet))
|
|
|
63 SecondAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
|
|
|
64
|
|
|
65 for (i in 1:nrow(SecondSubstrateSet)){
|
|
|
66 SecondLetters<-SecondSubstrateSet[i,7:15]
|
|
|
67 SecondLetters<-SecondLetters[SecondLetters !="XXXXX"]
|
|
|
68 SecondLetters<-paste(SecondLetters, sep="", collapse="")
|
|
|
69
|
|
|
70
|
|
|
71 YYYmotif <- unlist(strsplit(SecondLetters, split = ""))
|
|
|
72 YYYposition <- match(x = "x", table = YYYmotif)
|
|
|
73 #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
|
|
|
74 #just 3 letters to the left of x
|
|
|
75
|
|
|
76 YYYLettersToTheLeft <- YYYposition - 1
|
|
|
77 #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
|
|
|
78 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
|
|
|
79 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
|
|
|
80 #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
|
|
|
81 #variable the user puts in is
|
|
|
82
|
|
|
83 if (YYYLettersToTheLeft > 3 && YYYLettersToTheRight > 3) {
|
|
|
84 motif<-YYYmotif
|
|
|
85 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
86 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
87 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
88 motif<-motif[!motif %in% "x"]
|
|
|
89 motif<-paste(motif, sep="", collapse="")
|
|
|
90 SecondLetters<-motif
|
|
|
91 SecondMotifs[i]<-SecondLetters
|
|
|
92 SecondAccessionNumbers[i]<-SecondSubstrateSet[i,3]
|
|
|
93 }
|
|
|
94 }
|
|
|
95 names(FirstMotifs)<-FirstAccessionNumbers
|
|
|
96 names(SecondMotifs)<-SecondAccessionNumbers
|
|
|
97
|
|
|
98
|
|
|
99 # ITDmotifs=rep(NA,times=nrow(FirstSubstrateSet))
|
|
|
100 # ITDAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
|
|
|
101 if(1==0){
|
|
|
102 for (i in 1:nrow(ThirdSubstrateSet)){
|
|
|
103 ITDletters<-ThirdSubstrateSet[i,7:15]
|
|
|
104 ITDletters<-ITDletters[ITDletters !="XXXXX"]
|
|
|
105 ITDletters<-paste(ITDletters, sep="", collapse="")
|
|
|
106 YYYmotif <- unlist(strsplit(ITDletters, split = ""))
|
|
|
107 YYYposition <- match(x = "x", table = YYYmotif)
|
|
|
108 #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
|
|
|
109 #just 3 letters to the left of x
|
|
|
110
|
|
|
111 YYYLettersToTheLeft <- YYYposition - 1
|
|
|
112 #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
|
|
|
113 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
|
|
|
114 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
|
|
|
115 #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
|
|
|
116 #variable the user puts in is
|
|
|
117
|
|
|
118 if (YYYLettersToTheLeft > 3 && YYYLettersToTheRight > 3) {
|
|
|
119 motif<-YYYmotif
|
|
|
120 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
121 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
122 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
123 motif<-motif[!motif %in% "x"]
|
|
|
124 motif<-paste(motif, sep="", collapse="")
|
|
|
125 ITDletters<-motif
|
|
|
126 ITDmotifs[i]<-ITDletters
|
|
|
127 ITDAccessionNumbers[i]<-ThirdSubstrateSet[i,3]
|
|
|
128
|
|
|
129 }
|
|
|
130 }
|
|
|
131 }
|
|
|
132 #names(ITDmotifs)<-ITDAccessionNumbers
|
|
|
133 names(SecondMotifs)<-SecondAccessionNumbers
|
|
|
134 names(FirstMotifs)<-FirstAccessionNumbers
|
|
|
135 }
|
|
|
136
|
|
|
137
|
|
|
138 ##############################################3
|
|
|
139 #Truncated only
|
|
|
140 if (TruncatedMotifsOnly_questionmark=="YES"){
|
|
|
141 FirstMotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
|
|
|
142 FirstAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
|
|
|
143
|
|
|
144 for (i in 1:nrow(FirstSubstrateSet)){
|
|
|
145 FirstLetters<-FirstSubstrateSet[i,7:15]
|
|
|
146 FirstLetters<-FirstLetters[FirstLetters !="XXXXX"]
|
|
|
147 FirstLetters<-paste(FirstLetters, sep="", collapse="")
|
|
|
148
|
|
|
149
|
|
|
150 YYYmotif <- unlist(strsplit(FirstLetters, split = ""))
|
|
|
151 YYYposition <- match(x = "x", table = YYYmotif)
|
|
|
152 #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
|
|
|
153 #just 3 letters to the left of x
|
|
|
154
|
|
|
155 YYYLettersToTheLeft <- YYYposition - 1
|
|
|
156 #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
|
|
|
157 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
|
|
|
158 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
|
|
|
159 #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
|
|
|
160 #variable the user puts in is
|
|
|
161
|
|
|
162 if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
|
|
|
163 leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
|
|
|
164 rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
|
|
|
165 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
166 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
167 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
168 motif<-motif[!motif %in% "x"]
|
|
|
169 motif<-paste(motif, sep="", collapse="")
|
|
|
170 FirstLetters<-motif
|
|
|
171 FirstMotifs[i,1]<-FirstLetters
|
|
|
172 FirstAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
|
|
|
173 }
|
|
|
174
|
|
|
175 }
|
|
|
176
|
|
|
177 SecondMotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
|
|
|
178 SecondAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
|
|
|
179 i=2
|
|
|
180 for (i in 1:nrow(SecondSubstrateSet)){
|
|
|
181 SecondLetters<-SecondSubstrateSet[i,7:15]
|
|
|
182 SecondLetters<-SecondLetters[SecondLetters !="XXXXX"]
|
|
|
183 SecondLetters<-paste(SecondLetters, sep="", collapse="")
|
|
|
184
|
|
|
185
|
|
|
186 YYYmotif <- unlist(strsplit(SecondLetters, split = ""))
|
|
|
187 YYYposition <- match(x = "x", table = YYYmotif)
|
|
|
188 #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
|
|
|
189 #just 3 letters to the left of x
|
|
|
190
|
|
|
191 YYYLettersToTheLeft <- YYYposition - 1
|
|
|
192 #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
|
|
|
193 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
|
|
|
194 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
|
|
|
195 #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
|
|
|
196 #variable the user puts in is
|
|
|
197
|
|
|
198 if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
|
|
|
199 leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
|
|
|
200 rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
|
|
|
201 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
202 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
203 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
204 motif<-motif[!motif %in% "x"]
|
|
|
205 motif<-paste(motif, sep="", collapse="")
|
|
|
206 SecondLetters<-motif
|
|
|
207 SecondAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
|
|
|
208 SecondMotifs[i,1]<-SecondLetters
|
|
|
209 }
|
|
|
210 }
|
|
|
211
|
|
|
212 # ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
|
|
|
213 # ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
|
|
|
214 if(1==0){
|
|
|
215 for (i in 1:nrow(ThirdSubstrateSet)){
|
|
|
216 ITDletters<-ThirdSubstrateSet[i,7:15]
|
|
|
217 ITDletters<-ITDletters[ITDletters !="XXXXX"]
|
|
|
218 ITDletters<-paste(ITDletters, sep="", collapse="")
|
|
|
219 YYYmotif <- unlist(strsplit(ITDletters, split = ""))
|
|
|
220 YYYposition <- match(x = "x", table = YYYmotif)
|
|
|
221 #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
|
|
|
222 #just 3 letters to the left of x
|
|
|
223
|
|
|
224 YYYLettersToTheLeft <- YYYposition - 1
|
|
|
225 #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
|
|
|
226 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
|
|
|
227 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
|
|
|
228 #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
|
|
|
229 #variable the user puts in is
|
|
|
230
|
|
|
231 if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
|
|
|
232 leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
|
|
|
233 rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
|
|
|
234 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
235 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
236 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
237 motif<-motif[!motif %in% "x"]
|
|
|
238 motif<-paste(motif, sep="", collapse="")
|
|
|
239 ITDletters<-motif
|
|
|
240 ITDAccessionNumbers[i,1]<-ThirdSubstrateSet[i,3]
|
|
|
241 ITDmotifs[i,1]<-ITDletters
|
|
|
242 }
|
|
|
243 }
|
|
|
244 }
|
|
|
245 names(FirstMotifs)<-FirstAccessionNumbers
|
|
|
246 names(SecondMotifs)<-SecondAccessionNumbers
|
|
|
247 #names(ITDmotifs)<-ITDAccessionNumbers
|
|
|
248 }
|
|
|
249
|
|
|
250 ###############################################
|
|
|
251 #ALL motifs, full and truncated
|
|
|
252
|
|
|
253 if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
|
|
|
254 #print("!")}
|
|
|
255 FirstMotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
|
|
|
256 FirstAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
|
|
|
257
|
|
|
258 for (i in 1:nrow(FirstSubstrateSet)){
|
|
|
259 FirstLetters<-FirstSubstrateSet[i,7:15]
|
|
|
260 FirstLetters<-FirstLetters[FirstLetters !="XXXXX"]
|
|
|
261 FirstLetters<-paste(FirstLetters, sep="", collapse="")
|
|
|
262 leftspaces<-c()
|
|
|
263 rightspaces<-c()
|
|
|
264
|
|
|
265 YYYmotif <- unlist(strsplit(FirstLetters, split = ""))
|
|
|
266 YYYposition <- match(x = "x", table = YYYmotif)
|
|
|
267 #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
|
|
|
268 #just 3 letters to the left of x
|
|
|
269
|
|
|
270 YYYLettersToTheLeft <- YYYposition - 1
|
|
|
271 #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
|
|
|
272 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
|
|
|
273 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
|
|
|
274 #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
|
|
|
275 #variable the user puts in is
|
|
|
276
|
|
|
277
|
|
|
278 if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
|
|
|
279 leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
|
|
|
280 rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
|
|
|
281 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
282 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
283 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
284 motif<-motif[!motif %in% "x"]
|
|
|
285 motif<-paste(motif, sep="", collapse="")
|
|
|
286 FirstLetters<-motif
|
|
|
287 FirstMotifs[i,1]<-FirstLetters
|
|
|
288 FirstAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
|
|
|
289 }
|
|
|
290
|
|
|
291 if(YYYLettersToTheLeft>3 && YYYLettersToTheRight>3){
|
|
|
292 motif<-YYYmotif
|
|
|
293 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
294 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
295 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
296 motif<-motif[!motif %in% "x"]
|
|
|
297 motif<-paste(motif, sep="", collapse="")
|
|
|
298 FirstLetters<-motif
|
|
|
299 FirstMotifs[i,1]<-FirstLetters
|
|
|
300 FirstAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
|
|
|
301
|
|
|
302
|
|
|
303 }
|
|
|
304
|
|
|
305 }
|
|
|
306
|
|
|
307 SecondMotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
|
|
|
308 SecondAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
|
|
|
309
|
|
|
310 for (i in 1:nrow(SecondSubstrateSet)){
|
|
|
311 SecondLetters<-SecondSubstrateSet[i,7:15]
|
|
|
312 SecondLetters<-SecondLetters[SecondLetters !="XXXXX"]
|
|
|
313 SecondLetters<-paste(SecondLetters, sep="", collapse="")
|
|
|
314 leftspaces<-c()
|
|
|
315 rightspaces<-c()
|
|
|
316
|
|
|
317 YYYmotif <- unlist(strsplit(SecondLetters, split = ""))
|
|
|
318 YYYposition <- match(x = "x", table = YYYmotif)
|
|
|
319 #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
|
|
|
320 #just 3 letters to the left of x
|
|
|
321
|
|
|
322 YYYLettersToTheLeft <- YYYposition - 1
|
|
|
323 #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
|
|
|
324 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
|
|
|
325 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
|
|
|
326 #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
|
|
|
327 #variable the user puts in is
|
|
|
328 if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
|
|
|
329 leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
|
|
|
330 rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
|
|
|
331 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
332 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
333 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
334 motif<-motif[!motif %in% "x"]
|
|
|
335 motif<-paste(motif, sep="", collapse="")
|
|
|
336 SecondLetters<-motif
|
|
|
337 SecondMotifs[i,1]<-SecondLetters
|
|
|
338 SecondAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
|
|
|
339 }
|
|
|
340
|
|
|
341 if(YYYLettersToTheLeft>3 && YYYLettersToTheRight>3){
|
|
|
342 motif<-YYYmotif
|
|
|
343 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
344 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
345 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
346 motif<-motif[!motif %in% "x"]
|
|
|
347 motif<-paste(motif, sep="", collapse="")
|
|
|
348 SecondLetters<-motif
|
|
|
349 SecondMotifs[i,1]<-SecondLetters
|
|
|
350 SecondAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
|
|
|
351 }
|
|
|
352 }
|
|
|
353
|
|
|
354
|
|
|
355 #ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
|
|
|
356 #ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
|
|
|
357 if(1==0){
|
|
|
358 for (i in 1:nrow(ThirdSubstrateSet)){
|
|
|
359 ITDletters<-ThirdSubstrateSet[i,7:15]
|
|
|
360 ITDletters<-ITDletters[ITDletters !="XXXXX"]
|
|
|
361 ITDletters<-paste(ITDletters, sep="", collapse="")
|
|
|
362 YYYmotif <- unlist(strsplit(ITDletters, split = ""))
|
|
|
363 leftspaces<-c()
|
|
|
364 rightspaces<-c()
|
|
|
365 YYYposition <- match(x = "x", table = YYYmotif)
|
|
|
366 #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
|
|
|
367 #just 3 letters to the left of x
|
|
|
368
|
|
|
369 YYYLettersToTheLeft <- YYYposition - 1
|
|
|
370 #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
|
|
|
371 #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
|
|
|
372 YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
|
|
|
373 #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
|
|
|
374 #variable the user puts in is
|
|
|
375 if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
|
|
|
376 leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
|
|
|
377 rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
|
|
|
378 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
379 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
380 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
381 motif<-motif[!motif %in% "x"]
|
|
|
382 motif<-paste(motif, sep="", collapse="")
|
|
|
383 ITDletters<-motif
|
|
|
384 ITDmotifs[i,1]<-ITDletters
|
|
|
385 ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
|
|
|
386 }
|
|
|
387
|
|
|
388 if(YYYLettersToTheLeft>3 && YYYLettersToTheRight>3){
|
|
|
389 motif<-YYYmotif
|
|
|
390 #add blank spaces if the motif has less than 4 letters to the left/right
|
|
|
391 motif<-c(leftspaces,YYYmotif,rightspaces)
|
|
|
392 #save that motif, which is the Y and +/- 4 amino acids, including truncation
|
|
|
393 motif<-motif[!motif %in% "x"]
|
|
|
394 motif<-paste(motif, sep="", collapse="")
|
|
|
395 ITDletters<-motif
|
|
|
396 ITDmotifs[i,1]<-ITDletters
|
|
|
397 ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
|
|
|
398 }
|
|
|
399 }
|
|
|
400 }
|
|
|
401 names(FirstMotifs)<-FirstAccessionNumbers
|
|
|
402 names(SecondMotifs)<-SecondAccessionNumbers
|
|
|
403 #names(ITDmotifs)<-ITDAccessionNumbers
|
|
|
404 }
|
|
|
405
|
|
|
406
|
|
|
407 FirstMotifsFINAL<-FirstMotifs[!FirstMotifs %in% SecondMotifs]
|
|
|
408 #FirstMotifsFINAL<-FirstMotifsFINAL[!FirstMotifsFINAL %in% ITDmotifs]
|
|
|
409 FirstMotifsFINAL<-FirstMotifsFINAL[!duplicated(FirstMotifsFINAL)]
|
|
|
410
|
|
|
411
|
|
|
412 # ITDmotifsFINAL<-ITDmotifs[!ITDmotifs %in% SecondMotifs]
|
|
|
413 # ITDmotifsFINAL<-ITDmotifsFINAL[!ITDmotifsFINAL %in% FirstMotifs]
|
|
|
414 # ITDmotifsFINAL<-ITDmotifsFINAL[!duplicated(ITDmotifsFINAL)]
|
|
|
415
|
|
|
416
|
|
|
417 SecondMotifsFINAL<-SecondMotifs[!SecondMotifs %in% FirstMotifs]
|
|
|
418 #SecondMotifsFINAL<-SecondMotifsFINAL[!SecondMotifsFINAL %in% ITDmotifs]
|
|
|
419 SecondMotifsFINAL<-SecondMotifsFINAL[!duplicated(SecondMotifsFINAL)]
|
|
|
420
|
|
|
421
|
|
|
422 columnalheader<-c(rep(NA,36))
|
|
|
423 FirstFinalMatrix<-matrix(data =columnalheader,nrow = 1)
|
|
|
424
|
|
|
425 for (k in 1:length(FirstMotifsFINAL)) {
|
|
|
426 AN<-00000
|
|
|
427 #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
|
|
|
428 #destroyed immediately after use
|
|
|
429 for (m in 2:ncol(Firstsubbackfreq)) {
|
|
|
430 AN <- as.character(Firstsubbackfreq[2, m])
|
|
|
431 #print(AN)}
|
|
|
432 if (grepl(pattern = AN,
|
|
|
433 x = names(FirstMotifsFINAL[k]),
|
|
|
434 fixed = TRUE) == TRUE) {
|
|
|
435 outputmatrix <- as.character(Firstsubbackfreq[, m])
|
|
|
436 outputmatrix <- matrix(outputmatrix, nrow = 1)
|
|
|
437 #with that accession number, find a match in the subbackfreq file and save it here
|
|
|
438 FirstFinalMatrix<-rbind(FirstFinalMatrix,outputmatrix)
|
|
|
439 # print(AN,outputmatrix)}
|
|
|
440 }
|
|
|
441 }
|
|
|
442 }
|
|
|
443 FirstFinalMatrix<-FirstFinalMatrix[!duplicated(FirstFinalMatrix),]
|
|
|
444
|
|
|
445 #columnalheader<-c(rep(NA,36))
|
|
|
446 #ITDFinalMatrix<-matrix(data =columnalheader,nrow = 1)
|
|
|
447
|
|
|
448 if(1==0){
|
|
|
449 for (k in 1:length(ITDmotifsFINAL)) {
|
|
|
450 AN<-00000
|
|
|
451 #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
|
|
|
452 #destroyed immediately after use
|
|
|
453 for (m in 1:ncol(Thirdsubbackfreq)) {
|
|
|
454 AN <- as.character(Thirdsubbackfreq[1, m])
|
|
|
455 if (grepl(pattern = AN,
|
|
|
456 x = names(ITDmotifsFINAL[k]),
|
|
|
457 fixed = TRUE) == TRUE) {
|
|
|
458 outputmatrix <- as.character(Thirdsubbackfreq[, m])
|
|
|
459 outputmatrix <- matrix(outputmatrix, nrow = 1)
|
|
|
460 #with that accession number, find a match in the subbackfreq file and save it here
|
|
|
461 ITDFinalMatrix<-rbind(ITDFinalMatrix,outputmatrix)
|
|
|
462 }
|
|
|
463 }
|
|
|
464 }
|
|
|
465 ITDFinalMatrix<-ITDFinalMatrix[!duplicated(ITDFinalMatrix),]
|
|
|
466 }
|
|
|
467
|
|
|
468 columnalheader<-c(rep(NA,36))
|
|
|
469 SecondFinalMatrix<-matrix(data =columnalheader,nrow = 1)
|
|
|
470
|
|
|
471 for (k in 1:length(SecondMotifsFINAL)) {
|
|
|
472 #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
|
|
|
473 #destroyed immediately after use
|
|
|
474 for (m in 1:ncol(Secondsubbackfreq)) {
|
|
|
475 AN <- as.character(Secondsubbackfreq[1, m])
|
|
|
476 if (grepl(pattern = AN,
|
|
|
477 x = names(SecondMotifsFINAL[k]),
|
|
|
478 fixed = TRUE) == TRUE) {
|
|
|
479 outputmatrix <- as.character(Secondsubbackfreq[, m])
|
|
|
480 outputmatrix <- matrix(outputmatrix, nrow = 1)
|
|
|
481 #with that accession number, find a match in the subbackfreq file and save it here
|
|
|
482 SecondFinalMatrix<-rbind(SecondFinalMatrix,outputmatrix)
|
|
|
483 }
|
|
|
484 }
|
|
|
485 }
|
|
|
486 SecondFinalMatrix<-SecondFinalMatrix[!duplicated(SecondFinalMatrix),]
|
|
|
487 FTLoutputmatrix<-matrix(data=c(FirstMotifsFINAL,names(FirstMotifsFINAL)),ncol = 2)
|
|
|
488
|
|
|
489
|
|
|
490 write.table(x=FTLoutputmatrix,
|
|
|
491 file=First_unshared_motifs_table,
|
|
|
492 quote=FALSE, sep=",",
|
|
|
493 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
|
|
|
494
|
|
|
495 columnalheader<-c(as.character(Firstsubbackfreq[1:36,1]))
|
|
|
496 columnalheader<-matrix(columnalheader,nrow = 1)
|
|
|
497 write.table(x=columnalheader,
|
|
|
498 file=First_unshared_subbackfreq,
|
|
|
499 quote=FALSE, sep=",",
|
|
|
500 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
|
|
|
501 FirstFinalMatrix<-FirstFinalMatrix[2:nrow(FirstFinalMatrix),]
|
|
|
502 write.table(x=FirstFinalMatrix,
|
|
|
503 file=First_unshared_subbackfreq,
|
|
|
504 quote=FALSE, sep=",",
|
|
|
505 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
|
|
|
506
|
|
|
507 ############################################################################################################
|
|
|
508
|
|
|
509 D835Youtputmatrix<-matrix(data=c(SecondMotifsFINAL,names(SecondMotifsFINAL)),ncol = 2)
|
|
|
510
|
|
|
511 write.table(x=D835Youtputmatrix,
|
|
|
512 file=Second_unshared_motifs_table,
|
|
|
513 quote=FALSE, sep=",",
|
|
|
514 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
|
|
|
515
|
|
|
516 columnalheader<-c(as.character(Firstsubbackfreq[1:36,1]))
|
|
|
517 columnalheader<-matrix(columnalheader,nrow = 1)
|
|
|
518 write.table(x=columnalheader,
|
|
|
519 file=Second_unshared_subbackfreq,
|
|
|
520 quote=FALSE, sep=",",
|
|
|
521 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
|
|
|
522 SecondFinalMatrix<-SecondFinalMatrix[2:nrow(SecondFinalMatrix),]
|
|
|
523 write.table(x=SecondFinalMatrix,
|
|
|
524 file=Second_unshared_subbackfreq,
|
|
|
525 quote=FALSE, sep=",",
|
|
|
526 row.names=FALSE,col.names = FALSE, na="", append=TRUE)
|
|
|
527
|
|
|
528 ############################################################################################################
|
|
|
529
|
|
|
530 # ITDoutputmatrix<-matrix(data = c(ITDmotifsFINAL,names(ITDmotifsFINAL)),ncol = 2)
|
|
|
531 #
|
|
|
532 # write.table(x=ITDoutputmatrix,
|
|
|
533 # file=Third_unshared_motifs_table,
|
|
|
534 # quote=FALSE, sep=",",
|
|
|
535 # row.names=FALSE,col.names = FALSE, na="", append=TRUE)
|
|
|
536 #
|
|
|
537 # columnalheader<-c(as.character(Thirdsubbackfreq[1:36,1]))
|
|
|
538 # columnalheader<-matrix(columnalheader,nrow = 1)
|
|
|
539 # write.table(x=columnalheader,
|
|
|
540 # file=Third_unshared_subbackfreq,
|
|
|
541 # quote=FALSE, sep=",",
|
|
|
542 # row.names=FALSE,col.names = FALSE, na="", append=TRUE)
|
|
|
543 # ITDFinalMatrix<-ITDFinalMatrix[2:nrow(ITDFinalMatrix),]
|
|
|
544 # write.table(x=ITDFinalMatrix,
|
|
|
545 # file=Third_unshared_subbackfreq,
|
|
|
546 # quote=FALSE, sep=",",
|
|
|
547 # row.names=FALSE,col.names = FALSE, na="", append=TRUE) |
