# HG changeset patch
# User jfb
# Date 1555696846 14400
# Node ID 74ada21ceb70f8080d1d28fd2d29262fa46d6f3d
# Parent  dff99bed3f5687007b7f91bf89eb697abb731efe
Uploaded

diff -r dff99bed3f56 -r 74ada21ceb70 all stuff/Commonality and Difference finderMADE 7 TO 7 1-15-2019.R
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/all stuff/Commonality and Difference finderMADE 7 TO 7 1-15-2019.R	Fri Apr 19 14:00:46 2019 -0400
@@ -0,0 +1,1281 @@
+#I should make an SOP for this.  Problems we encountered: no x in the xY motif, and the kilodemon
+#the output files have both Y and xY, they shouldn't why is that happening?  make it not happen
+#make sure that accession numbers stay locked to each motif, somehow
+#output should look just like the KALIP input
+
+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
+FullMotifsOnly_questionmark<-"NO"
+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
+TruncatedMotifsOnly_questionmark<-"NO"
+#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)
+Are_You_Looking_For_Commonality<-"NO"
+
+
+#put the names of your input files here
+FirstSubstrateSet<- read.csv("Galaxy63-BTK_PLUS-R1_Substrates.csv", stringsAsFactors=FALSE)
+Firstsubbackfreq<- read.csv("Galaxy64-BTK_PLUS-R1_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
+
+SecondSubstrateSet<- read.csv("Galaxy65-BTK_PLUS_R2_Substrates.csv", stringsAsFactors=FALSE)
+Secondsubbackfreq<- read.csv("Galaxy66-BTK_PLUS_R2_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
+
+ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)
+Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
+
+#then put the names of your output files here
+Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"
+Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"
+
+# Shared_motifs_table<-"Shared motifs 7-27-17.csv"
+# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"
+
+First_unshared_motifs_table<-"R1 substrates.csv"
+First_unshared_subbackfreq<-"R1 SBF.csv"
+
+Second_unshared_motifs_table<-"R2 subs.csv"
+Second_unshared_subbackfreq<-"R2 SBf.csv"
+
+Third_unshared_motifs_table<-"R3 subs.csv"
+Third_unshared_subbackfreq<-"R3 SBF.csv"
+
+#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
+#other languages to see if any of them can do it.
+####################################################################################################################################
+
+
+
+
+
+FirstxY<-rep("xY",times=nrow(FirstSubstrateSet))
+FirstSubstrateSet[,11]<-FirstxY
+
+SecondxY<-rep("xY",times=nrow(SecondSubstrateSet))
+SecondSubstrateSet[,11]<-SecondxY
+
+ThirdxY<-rep("xY",times=nrow(ThirdSubstrateSet))
+ThirdSubstrateSet[,11]<-ThirdxY
+
+
+
+
+
+
+
+
+
+
+
+####################################################################################################################################
+####################################################################################################################################
+# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two 
+# separate proteins thus two separate accession numbers?
+# It should actually output the shared motif and BOTH accession numbers.  Right now it does not, it only maps out the second
+# accession number.  So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+
+#Create the motif sets, deciding wether or not you're looking for truncated or full here
+#full only
+if (Are_You_Looking_For_Commonality=="YES"){
+  if (FullMotifsOnly_questionmark=="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    leftspaces<-c()
+    rightspaces<-c()
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+        
+      }
+      
+    }
+    # FTLwtmotifs <- FTLwtmotifs[!is.na(FTLwtmotifs)]
+    # FTLwtmotifs<-matrix(FTLwtmotifs,ncol = 1)
+    # 
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
+        
+      }
+    }
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-ThirdSubstrateSet[i,3]
+        
+      }
+    }
+    
+  }
+  
+  ##############################################3
+  #Truncated only
+  if (TruncatedMotifsOnly_questionmark=="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+    }
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
+        D835Ymotifs[i,1]<-D835letters
+      }
+    }
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDAccessionNumbers[i,1]<-ThirdSubstrateSet[i,3]
+        ITDmotifs[i,1]<-ITDletters
+      }
+    }
+    
+  }
+  
+  ###############################################
+  #ALL motifs, full and truncated
+  
+  if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+        
+        
+      }
+      
+    }
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+    }
+    
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      leftspaces<-c()
+      rightspaces<-c()
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+    }
+    
+  }
+  #############################################################################################################################
+  #############################################################################################################################
+  #############################################################################################################################
+  #############################################################################################################################
+  #############################################################################################################################
+  
+  #now look for either commonality or difference.  Actually could you look for both...
+  
+  if (Are_You_Looking_For_Commonality=="YES"){
+    
+    columnalheader<-c(as.character(Thirdsubbackfreq[1:36,1]))
+    columnalheader<-matrix(columnalheader,nrow = 1)
+    write.table(x=columnalheader,
+                file=Shared_subbackfreq_table,
+                quote=FALSE, sep=",",
+                row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+    
+    FirstOverlapmotifs<-c()
+    for (i in 1:nrow(ITDmotifs)){
+      for (j in 1:nrow(D835Ymotifs)){
+        if (is.na(ITDmotifs[i,1])!=TRUE&&is.na(D835Ymotifs[j,1])!=TRUE){
+          if (ITDmotifs[i,1]==D835Ymotifs[j,1]){
+            FirstOverlapmotifs<-c(FirstOverlapmotifs,D835Ymotifs[j,1])
+          }
+        }
+      }
+    }
+    
+    AllAccessionNumbers<-c()
+    columnalheader<-c(rep(NA,36))
+    FinalMatrix<-matrix(data =columnalheader,nrow = 1)
+    
+    FinalMotifs<-c(rep(NA,20))
+    FinalMotifsMatrix<-matrix(data = FinalMotifs,nrow = 1)
+    
+    
+    for (l in 1:length(FirstOverlapmotifs)) {
+      AccessionNumber<-00000000000
+      for (k in 1:nrow(FTLwtmotifs)) {
+        AccessionNumber<-0000000000000
+        if(is.na(FTLwtmotifs[k])!=TRUE){
+          #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+          #destroyed immediately after use
+          if (FirstOverlapmotifs[l] == FTLwtmotifs[k]) {
+            substratematrix<-FirstSubstrateSet[k,1:20]
+            substratematrix<-as.matrix(substratematrix,nrow=1)
+            FinalMotifsMatrix<-rbind(FinalMotifsMatrix,substratematrix)
+            #when you find a match between the venn diagrams, save the substrate info you get into a matrix
+            
+            AccessionNumber <- as.character(FirstSubstrateSet[k, 3])
+            #then take the accession number 
+            
+            for (m in 1:ncol(Firstsubbackfreq)) {
+              AN <- as.character(Firstsubbackfreq[1, m])
+              if (grepl(pattern = AN,
+                        x = AccessionNumber,
+                        fixed = TRUE) == TRUE) {
+                outputmatrix <- as.character(Firstsubbackfreq[, m])
+                outputmatrix <- matrix(outputmatrix, nrow = 1)
+                #with that accession number, find a match in the subbackfreq file and save it here
+                FinalMatrix<-rbind(FinalMatrix,outputmatrix)
+              }
+            }
+          }
+        }
+      }
+    }
+    
+    
+    TrueMatrix<-FinalMatrix[!duplicated(FinalMatrix),]
+    TrueFinalMotifsMatrix<-FinalMotifsMatrix[!duplicated(FinalMotifsMatrix),]
+    
+    TrueFinalMotifsMatrix<-TrueFinalMotifsMatrix[2:nrow(TrueFinalMotifsMatrix),]
+    TrueMatrix<-TrueMatrix[2:nrow(TrueMatrix),]
+    
+    write.table(
+      x = TrueFinalMotifsMatrix,
+      file = Shared_motifs_table,
+      quote = FALSE,
+      sep = ",",
+      row.names = FALSE,
+      col.names = TRUE,
+      na = "",
+      append = TRUE
+    )
+    
+    
+    write.table(
+      x = TrueMatrix,
+      file = Shared_subbackfreq_table,
+      quote = FALSE,
+      sep = ",",
+      row.names = FALSE,
+      col.names = FALSE,
+      na = "",
+      append = TRUE
+    )
+  }
+}
+
+if (Are_You_Looking_For_Commonality=="NO"){
+  if (FullMotifsOnly_questionmark=="YES"){
+    FTLwtmotifs=rep(NA,times=nrow(FirstSubstrateSet))
+    FTLwtAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
+    leftspaces<-c()
+    rightspaces<-c()
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i]<-FTLwtletters
+        FTLwtAccessionNumbers[i]<-FirstSubstrateSet[i,3]
+      }
+      
+    }
+    # FTLwtmotifs <- FTLwtmotifs[!is.na(FTLwtmotifs)]
+    # FTLwtmotifs<-matrix(FTLwtmotifs,ncol = 1)
+    # 
+    
+    D835Ymotifs=rep(NA,times=nrow(FirstSubstrateSet))
+    D835YAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i]<-D835letters
+        D835YAccessionNumbers[i]<-SecondSubstrateSet[i,3]
+      }
+    }
+    
+    ITDmotifs=rep(NA,times=nrow(FirstSubstrateSet))
+    ITDAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i]<-ITDletters
+        ITDAccessionNumbers[i]<-ThirdSubstrateSet[i,3]
+        
+      }
+    }
+    names(ITDmotifs)<-ITDAccessionNumbers
+    names(D835Ymotifs)<-D835YAccessionNumbers
+    names(FTLwtmotifs)<-FTLwtAccessionNumbers
+  }
+  
+  
+  ##############################################3
+  #Truncated only
+  if (TruncatedMotifsOnly_questionmark=="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+    }
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    i=2
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
+        D835Ymotifs[i,1]<-D835letters
+      }
+    }
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDAccessionNumbers[i,1]<-ThirdSubstrateSet[i,3]
+        ITDmotifs[i,1]<-ITDletters
+      }
+    }
+    names(FTLwtmotifs)<-FTLwtAccessionNumbers
+    names(D835Ymotifs)<-D835YAccessionNumbers
+    names(ITDmotifs)<-ITDAccessionNumbers
+  }
+  
+  ###############################################
+  #ALL motifs, full and truncated
+  
+  if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+        
+        
+      }
+      
+    }
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+    }
+    
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      leftspaces<-c()
+      rightspaces<-c()
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+    }
+    names(FTLwtmotifs)<-FTLwtAccessionNumbers
+    names(D835Ymotifs)<-D835YAccessionNumbers
+    names(ITDmotifs)<-ITDAccessionNumbers
+  }
+  
+  
+  FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
+  FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!FTLwtmotifsFINAL %in% ITDmotifs]
+  FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
+  
+  
+  ITDmotifsFINAL<-ITDmotifs[!ITDmotifs %in% D835Ymotifs]
+  ITDmotifsFINAL<-ITDmotifsFINAL[!ITDmotifsFINAL %in% FTLwtmotifs]
+  ITDmotifsFINAL<-ITDmotifsFINAL[!duplicated(ITDmotifsFINAL)]
+  
+  
+  D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
+  D835YmotifsFINAL<-D835YmotifsFINAL[!D835YmotifsFINAL %in% ITDmotifs]
+  D835YmotifsFINAL<-D835YmotifsFINAL[!duplicated(D835YmotifsFINAL)]
+  
+  
+  columnalheader<-c(rep(NA,35))
+  FTLFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  for (k in 1:length(FTLwtmotifsFINAL)) {
+    AN<-00000
+    #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+    #destroyed immediately after use
+    for (m in 1:ncol(Firstsubbackfreq)) {
+      AN <- as.character(Firstsubbackfreq[1, m])
+      if (grepl(pattern = AN,
+                x = names(FTLwtmotifsFINAL[k]),
+                fixed = TRUE) == TRUE) {
+        outputmatrix <- as.character(Firstsubbackfreq[, m])
+        outputmatrix <- matrix(outputmatrix, nrow = 1)
+        #with that accession number, find a match in the subbackfreq file and save it here
+        FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)
+      }
+    }
+  }
+  FTLFinalMatrix<-FTLFinalMatrix[!duplicated(FTLFinalMatrix),]
+  
+  columnalheader<-c(rep(NA,35))
+  ITDFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  for (k in 1:length(ITDmotifsFINAL)) {
+    AN<-00000
+    #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+    #destroyed immediately after use
+    for (m in 1:ncol(Thirdsubbackfreq)) {
+      AN <- as.character(Thirdsubbackfreq[1, m])
+      if (grepl(pattern = AN,
+                x = names(ITDmotifsFINAL[k]),
+                fixed = TRUE) == TRUE) {
+        outputmatrix <- as.character(Thirdsubbackfreq[, m])
+        outputmatrix <- matrix(outputmatrix, nrow = 1)
+        #with that accession number, find a match in the subbackfreq file and save it here
+        ITDFinalMatrix<-rbind(ITDFinalMatrix,outputmatrix)
+      }
+    }
+  }
+  ITDFinalMatrix<-ITDFinalMatrix[!duplicated(ITDFinalMatrix),]
+  
+  columnalheader<-c(rep(NA,35))
+  D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  for (k in 1:length(D835YmotifsFINAL)) {
+    #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+    #destroyed immediately after use
+    for (m in 1:ncol(Secondsubbackfreq)) {
+      AN <- as.character(Secondsubbackfreq[1, m])
+      if (grepl(pattern = AN,
+                x = names(D835YmotifsFINAL[k]),
+                fixed = TRUE) == TRUE) {
+        outputmatrix <- as.character(Secondsubbackfreq[, m])
+        outputmatrix <- matrix(outputmatrix, nrow = 1)
+        #with that accession number, find a match in the subbackfreq file and save it here
+        D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)
+      }
+    }
+  }
+  D835YFinalMatrix<-D835YFinalMatrix[!duplicated(D835YFinalMatrix),]
+  
+  FTLoutputmatrix<-matrix(data=c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)),ncol = 2)
+  
+  
+  write.table(x=FTLoutputmatrix,
+              file=First_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,nrow = 1)
+  write.table(x=columnalheader,
+              file=First_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  write.table(x=FTLFinalMatrix,
+              file=First_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  ############################################################################################################
+  
+  D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)
+  
+  write.table(x=D835Youtputmatrix,
+              file=Second_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,nrow = 1)
+  write.table(x=columnalheader,
+              file=Second_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  write.table(x=D835YFinalMatrix,
+              file=Second_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  ############################################################################################################
+  
+  ITDoutputmatrix<-matrix(data = c(ITDmotifsFINAL,names(ITDmotifsFINAL)),ncol = 2)
+  
+  write.table(x=ITDoutputmatrix,
+              file=Third_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,nrow = 1)
+  write.table(x=columnalheader,
+              file=Third_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  write.table(x=ITDFinalMatrix,
+              file=Third_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+}
+
+# if (Are_You_Looking_For_Commonality=="NO"){
+#   
+#   
+#   FTLwtmotifsFULLMATRIX<-cbind(FTLwtmotifs,FTLwtAccessionNumbers)
+#   ITDmotifsFULLMATRIX<-cbind(ITDmotifs,ITDAccessionNumbers)
+#   D835YmotifsFULLMATRIX<-cbind(D835Ymotifs,D835YAccessionNumbers)
+#   # ?duplicated
+# 
+#   FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
+#   FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!FTLwtmotifsFINAL %in% ITDmotifs]
+#   FTLwtmotifsFINAL<-matrix(data=FTLwtmotifsFINAL, ncol = 1)
+# 
+#   ITDmotifsFINAL<-ITDmotifs[!ITDmotifs %in% D835Ymotifs]
+#   ITDmotifsFINAL<-ITDmotifsFINAL[!ITDmotifsFINAL %in% FTLwtmotifs]
+#   ITDmotifsFINAL<-matrix(data=ITDmotifsFINAL, ncol = 1)
+# 
+#   D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
+#   D835YmotifsFINAL<-D835YmotifsFINAL[!D835YmotifsFINAL %in% ITDmotifs]
+#   D835YmotifsFINAL<-matrix(data=D835YmotifsFINAL, ncol = 1)
+#   
+#   FTLnondupeAccessionNumbers<-c()
+#   
+#   for (z in 1:nrow(FTLwtmotifsFINAL)) {
+#     for (w in 1:nrow(FTLwtmotifsFULLMATRIX)) {
+#       if (is.na(FTLwtmotifsFULLMATRIX[w,1])!=TRUE)
+#         if (FTLwtmotifsFINAL[z]==FTLwtmotifsFULLMATRIX[w,1]){
+#           FTLnondupeAccessionNumbers<-c(FTLnondupeAccessionNumbers,FTLwtmotifsFULLMATRIX[w,2])
+#         }
+#     }  
+#   }
+# 
+#   
+#   #find accession numbers here, put a matrix of those things, amino acid %, but only after I've unduped them
+#   FTLnondupeAccessionNumbers<-FTLnondupeAccessionNumbers[!duplicated(FTLnondupeAccessionNumbers)]
+#   
+#   columnalheader<-c(rep(NA,35))
+#   FTLFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+#   
+#   for (k in 1:length(FTLnondupeAccessionNumbers)) {
+#     #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#     #destroyed immediately after use
+#     for (m in 1:ncol(Firstsubbackfreq)) {
+#       AN <- as.character(Firstsubbackfreq[1, m])
+#       if (grepl(pattern = AN,
+#                 x = FTLnondupeAccessionNumbers[k],
+#                 fixed = TRUE) == TRUE) {
+#         outputmatrix <- as.character(Firstsubbackfreq[, m])
+#         outputmatrix <- matrix(outputmatrix, nrow = 1)
+#         #with that accession number, find a match in the subbackfreq file and save it here
+#         FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)
+#       }
+#     }
+#   }
+#   ITDnondupeAccessionNumbers<-c()
+#   
+#   for (z in 1:nrow(ITDmotifsFINAL)) {
+#     for (w in 1:nrow(ITDmotifsFULLMATRIX)) {
+#       if (is.na(ITDmotifsFULLMATRIX[w,1])!=TRUE)
+#         if (ITDmotifsFINAL[z]==ITDmotifsFULLMATRIX[w,1]){
+#           ITDnondupeAccessionNumbers<-c(ITDnondupeAccessionNumbers,ITDmotifsFULLMATRIX[w,2])
+#         }
+#     }  
+#   }
+#   
+#   
+#   #find accession numbers here, put a matrix of those things, amino acid %, but only after I've unduped them
+#   ITDnondupeAccessionNumbers<-ITDnondupeAccessionNumbers[!duplicated(ITDnondupeAccessionNumbers)]
+#   
+#   columnalheader<-c(rep(NA,35))
+#   ITDFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+#   
+#   for (k in 1:length(ITDnondupeAccessionNumbers)) {
+#     #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#     #destroyed immediately after use
+#     for (m in 1:ncol(Thirdsubbackfreq)) {
+#       AN <- as.character(Thirdsubbackfreq[1, m])
+#       if (grepl(pattern = AN,
+#                 x = ITDnondupeAccessionNumbers[k],
+#                 fixed = TRUE) == TRUE) {
+#         outputmatrix <- as.character(Thirdsubbackfreq[, m])
+#         outputmatrix <- matrix(outputmatrix, nrow = 1)
+#         #with that accession number, find a match in the subbackfreq file and save it here
+#         ITDFinalMatrix<-rbind(ITDFinalMatrix,outputmatrix)
+#       }
+#     }
+#   }
+#   
+#   
+#   D835YnondupeAccessionNumbers<-c()
+#   
+#   for (z in 1:nrow(D835YmotifsFINAL)) {
+#     for (w in 1:nrow(D835YmotifsFULLMATRIX)) {
+#       if (is.na(D835YmotifsFULLMATRIX[w,1])!=TRUE)
+#         if (D835YmotifsFINAL[z]==D835YmotifsFULLMATRIX[w,1]){
+#           D835YnondupeAccessionNumbers<-c(D835YnondupeAccessionNumbers,D835YmotifsFULLMATRIX[w,2])
+#         }
+#     }  
+#   }
+#   
+#   
+#   #find accession numbers here, put a matrix of those things, amino acid %, but only after I've unduped them
+#   D835YnondupeAccessionNumbers<-D835YnondupeAccessionNumbers[!duplicated(D835YnondupeAccessionNumbers)]
+#   
+#   columnalheader<-c(rep(NA,35))
+#   D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+#   
+#   for (k in 1:length(D835YnondupeAccessionNumbers)) {
+#     #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#     #destroyed immediately after use
+#     for (m in 1:ncol(Secondsubbackfreq)) {
+#       AN <- as.character(Secondsubbackfreq[1, m])
+#       if (grepl(pattern = AN,
+#                 x = D835YnondupeAccessionNumbers[k],
+#                 fixed = TRUE) == TRUE) {
+#         outputmatrix <- as.character(Secondsubbackfreq[, m])
+#         outputmatrix <- matrix(outputmatrix, nrow = 1)
+#         #with that accession number, find a match in the subbackfreq file and save it here
+#         D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)
+#       }
+#     }
+#   }
+#   
+#   
+# 
+#   # FinalFTLmotifs<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
+#   # FinalFTLAccessionNumbers<-FTLnondupeAccessionNumbers[!duplicated(FTLnondupeAccessionNumbers)]
+#   # necessaryNAs<-rep(NA,times=(length(FinalFTLmotifs)-length(FinalFTLAccessionNumbers)))
+#   # FinalFTLAccessionNumbers<-c(FinalFTLAccessionNumbers,necessaryNAs)
+#   # TRUEFTLoutputmatrix<-cbind(FinalFTLmotifs,FinalFTLAccessionNumbers)
+#   # TRUEFTLoutputmatrix
+# 
+#   write.table(x=FTLwtmotifsFINAL,
+#               file=First_unshared_motifs_table,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+#   columnalheader<-matrix(columnalheader,nrow = 1)
+#   write.table(x=columnalheader,
+#               file=First_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   write.table(x=FTLFinalMatrix,
+#               file=First_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+# 
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   write.table(x=D835YmotifsFINAL,
+#               file=Second_unshared_motifs_table,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+#   columnalheader<-matrix(columnalheader,nrow = 1)
+#   write.table(x=columnalheader,
+#               file=Second_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   write.table(x=D835YFinalMatrix,
+#               file=Second_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   write.table(x=ITDmotifsFINAL,
+#               file=Third_unshared_motifs_table,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+#   columnalheader<-matrix(columnalheader,nrow = 1)
+#   write.table(x=columnalheader,
+#               file=Third_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   write.table(x=ITDFinalMatrix,
+#               file=Third_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   
+#   
+#   
+#   
+#   
+# }
diff -r dff99bed3f56 -r 74ada21ceb70 all stuff/Commonality and Difference finderMADE 7 TO 7.R
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/all stuff/Commonality and Difference finderMADE 7 TO 7.R	Fri Apr 19 14:00:46 2019 -0400
@@ -0,0 +1,1281 @@
+#I should make an SOP for this.  Problems we encountered: no x in the xY motif, and the kilodemon
+#the output files have both Y and xY, they shouldn't why is that happening?  make it not happen
+#make sure that accession numbers stay locked to each motif, somehow
+#output should look just like the KALIP input
+
+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
+FullMotifsOnly_questionmark<-"NO"
+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
+TruncatedMotifsOnly_questionmark<-"NO"
+#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)
+Are_You_Looking_For_Commonality<-"YES"
+
+
+#put the names of your input files here
+FirstSubstrateSet<- read.csv("Galaxy63-BTK_PLUS-R1_Substrates.csv", stringsAsFactors=FALSE)
+Firstsubbackfreq<- read.csv("Galaxy64-BTK_PLUS-R1_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
+
+SecondSubstrateSet<- read.csv("Galaxy65-BTK_PLUS_R2_Substrates.csv", stringsAsFactors=FALSE)
+Secondsubbackfreq<- read.csv("Galaxy66-BTK_PLUS_R2_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
+
+ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)
+Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
+
+#then put the names of your output files here
+Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"
+Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"
+
+# Shared_motifs_table<-"Shared motifs 7-27-17.csv"
+# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"
+
+First_unshared_motifs_table<-"R1 substrates.csv"
+First_unshared_subbackfreq<-"R1 SBF.csv"
+
+Second_unshared_motifs_table<-"R2 subs.csv"
+Second_unshared_subbackfreq<-"R2 SBf.csv"
+
+Third_unshared_motifs_table<-"R3 subs.csv"
+Third_unshared_subbackfreq<-"R3 SBF.csv"
+
+#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
+#other languages to see if any of them can do it.
+####################################################################################################################################
+
+
+
+
+
+FirstxY<-rep("xY",times=nrow(FirstSubstrateSet))
+FirstSubstrateSet[,11]<-FirstxY
+
+SecondxY<-rep("xY",times=nrow(SecondSubstrateSet))
+SecondSubstrateSet[,11]<-SecondxY
+
+ThirdxY<-rep("xY",times=nrow(ThirdSubstrateSet))
+ThirdSubstrateSet[,11]<-ThirdxY
+
+
+
+
+
+
+
+
+
+
+
+####################################################################################################################################
+####################################################################################################################################
+# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two 
+# separate proteins thus two separate accession numbers?
+# It should actually output the shared motif and BOTH accession numbers.  Right now it does not, it only maps out the second
+# accession number.  So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+
+#Create the motif sets, deciding wether or not you're looking for truncated or full here
+#full only
+if (Are_You_Looking_For_Commonality=="YES"){
+  if (FullMotifsOnly_questionmark=="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    leftspaces<-c()
+    rightspaces<-c()
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+        
+      }
+      
+    }
+    # FTLwtmotifs <- FTLwtmotifs[!is.na(FTLwtmotifs)]
+    # FTLwtmotifs<-matrix(FTLwtmotifs,ncol = 1)
+    # 
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
+        
+      }
+    }
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-ThirdSubstrateSet[i,3]
+        
+      }
+    }
+    
+  }
+  
+  ##############################################3
+  #Truncated only
+  if (TruncatedMotifsOnly_questionmark=="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+    }
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
+        D835Ymotifs[i,1]<-D835letters
+      }
+    }
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDAccessionNumbers[i,1]<-ThirdSubstrateSet[i,3]
+        ITDmotifs[i,1]<-ITDletters
+      }
+    }
+    
+  }
+  
+  ###############################################
+  #ALL motifs, full and truncated
+  
+  if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+        
+        
+      }
+      
+    }
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+    }
+    
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      leftspaces<-c()
+      rightspaces<-c()
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+    }
+    
+  }
+  #############################################################################################################################
+  #############################################################################################################################
+  #############################################################################################################################
+  #############################################################################################################################
+  #############################################################################################################################
+  
+  #now look for either commonality or difference.  Actually could you look for both...
+  
+  if (Are_You_Looking_For_Commonality=="YES"){
+    
+    columnalheader<-c(as.character(Thirdsubbackfreq[1:36,1]))
+    columnalheader<-matrix(columnalheader,nrow = 1)
+    write.table(x=columnalheader,
+                file=Shared_subbackfreq_table,
+                quote=FALSE, sep=",",
+                row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+    
+    FirstOverlapmotifs<-c()
+    for (i in 1:nrow(ITDmotifs)){
+      for (j in 1:nrow(D835Ymotifs)){
+        if (is.na(ITDmotifs[i,1])!=TRUE&&is.na(D835Ymotifs[j,1])!=TRUE){
+          if (ITDmotifs[i,1]==D835Ymotifs[j,1]){
+            FirstOverlapmotifs<-c(FirstOverlapmotifs,D835Ymotifs[j,1])
+          }
+        }
+      }
+    }
+    
+    AllAccessionNumbers<-c()
+    columnalheader<-c(rep(NA,36))
+    FinalMatrix<-matrix(data =columnalheader,nrow = 1)
+    
+    FinalMotifs<-c(rep(NA,20))
+    FinalMotifsMatrix<-matrix(data = FinalMotifs,nrow = 1)
+    
+    
+    for (l in 1:length(FirstOverlapmotifs)) {
+      AccessionNumber<-00000000000
+      for (k in 1:nrow(FTLwtmotifs)) {
+        AccessionNumber<-0000000000000
+        if(is.na(FTLwtmotifs[k])!=TRUE){
+          #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+          #destroyed immediately after use
+          if (FirstOverlapmotifs[l] == FTLwtmotifs[k]) {
+            substratematrix<-FirstSubstrateSet[k,1:20]
+            substratematrix<-as.matrix(substratematrix,nrow=1)
+            FinalMotifsMatrix<-rbind(FinalMotifsMatrix,substratematrix)
+            #when you find a match between the venn diagrams, save the substrate info you get into a matrix
+            
+            AccessionNumber <- as.character(FirstSubstrateSet[k, 3])
+            #then take the accession number 
+            
+            for (m in 1:ncol(Firstsubbackfreq)) {
+              AN <- as.character(Firstsubbackfreq[1, m])
+              if (grepl(pattern = AN,
+                        x = AccessionNumber,
+                        fixed = TRUE) == TRUE) {
+                outputmatrix <- as.character(Firstsubbackfreq[, m])
+                outputmatrix <- matrix(outputmatrix, nrow = 1)
+                #with that accession number, find a match in the subbackfreq file and save it here
+                FinalMatrix<-rbind(FinalMatrix,outputmatrix)
+              }
+            }
+          }
+        }
+      }
+    }
+    
+    
+    TrueMatrix<-FinalMatrix[!duplicated(FinalMatrix),]
+    TrueFinalMotifsMatrix<-FinalMotifsMatrix[!duplicated(FinalMotifsMatrix),]
+    
+    TrueFinalMotifsMatrix<-TrueFinalMotifsMatrix[2:nrow(TrueFinalMotifsMatrix),]
+    TrueMatrix<-TrueMatrix[2:nrow(TrueMatrix),]
+    
+    write.table(
+      x = TrueFinalMotifsMatrix,
+      file = Shared_motifs_table,
+      quote = FALSE,
+      sep = ",",
+      row.names = FALSE,
+      col.names = TRUE,
+      na = "",
+      append = TRUE
+    )
+    
+    
+    write.table(
+      x = TrueMatrix,
+      file = Shared_subbackfreq_table,
+      quote = FALSE,
+      sep = ",",
+      row.names = FALSE,
+      col.names = FALSE,
+      na = "",
+      append = TRUE
+    )
+  }
+}
+
+if (Are_You_Looking_For_Commonality=="NO"){
+  if (FullMotifsOnly_questionmark=="YES"){
+    FTLwtmotifs=rep(NA,times=nrow(FirstSubstrateSet))
+    FTLwtAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
+    leftspaces<-c()
+    rightspaces<-c()
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i]<-FTLwtletters
+        FTLwtAccessionNumbers[i]<-FirstSubstrateSet[i,3]
+      }
+      
+    }
+    # FTLwtmotifs <- FTLwtmotifs[!is.na(FTLwtmotifs)]
+    # FTLwtmotifs<-matrix(FTLwtmotifs,ncol = 1)
+    # 
+    
+    D835Ymotifs=rep(NA,times=nrow(FirstSubstrateSet))
+    D835YAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i]<-D835letters
+        D835YAccessionNumbers[i]<-SecondSubstrateSet[i,3]
+      }
+    }
+    
+    ITDmotifs=rep(NA,times=nrow(FirstSubstrateSet))
+    ITDAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 6 && YYYLettersToTheRight > 6) {
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i]<-ITDletters
+        ITDAccessionNumbers[i]<-ThirdSubstrateSet[i,3]
+        
+      }
+    }
+    names(ITDmotifs)<-ITDAccessionNumbers
+    names(D835Ymotifs)<-D835YAccessionNumbers
+    names(FTLwtmotifs)<-FTLwtAccessionNumbers
+  }
+  
+  
+  ##############################################3
+  #Truncated only
+  if (TruncatedMotifsOnly_questionmark=="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+    }
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    i=2
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
+        D835Ymotifs[i,1]<-D835letters
+      }
+    }
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDAccessionNumbers[i,1]<-ThirdSubstrateSet[i,3]
+        ITDmotifs[i,1]<-ITDletters
+      }
+    }
+    names(FTLwtmotifs)<-FTLwtAccessionNumbers
+    names(D835Ymotifs)<-D835YAccessionNumbers
+    names(ITDmotifs)<-ITDAccessionNumbers
+  }
+  
+  ###############################################
+  #ALL motifs, full and truncated
+  
+  if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+        
+        
+      }
+      
+    }
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+    }
+    
+    
+    ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+    ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+    
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,4:18]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      leftspaces<-c()
+      rightspaces<-c()
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i,1]<-ITDletters
+        ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+    }
+    names(FTLwtmotifs)<-FTLwtAccessionNumbers
+    names(D835Ymotifs)<-D835YAccessionNumbers
+    names(ITDmotifs)<-ITDAccessionNumbers
+  }
+  
+  
+  FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
+  FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!FTLwtmotifsFINAL %in% ITDmotifs]
+  FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
+  
+  
+  ITDmotifsFINAL<-ITDmotifs[!ITDmotifs %in% D835Ymotifs]
+  ITDmotifsFINAL<-ITDmotifsFINAL[!ITDmotifsFINAL %in% FTLwtmotifs]
+  ITDmotifsFINAL<-ITDmotifsFINAL[!duplicated(ITDmotifsFINAL)]
+  
+  
+  D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
+  D835YmotifsFINAL<-D835YmotifsFINAL[!D835YmotifsFINAL %in% ITDmotifs]
+  D835YmotifsFINAL<-D835YmotifsFINAL[!duplicated(D835YmotifsFINAL)]
+  
+  
+  columnalheader<-c(rep(NA,35))
+  FTLFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  for (k in 1:length(FTLwtmotifsFINAL)) {
+    AN<-00000
+    #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+    #destroyed immediately after use
+    for (m in 1:ncol(Firstsubbackfreq)) {
+      AN <- as.character(Firstsubbackfreq[1, m])
+      if (grepl(pattern = AN,
+                x = names(FTLwtmotifsFINAL[k]),
+                fixed = TRUE) == TRUE) {
+        outputmatrix <- as.character(Firstsubbackfreq[, m])
+        outputmatrix <- matrix(outputmatrix, nrow = 1)
+        #with that accession number, find a match in the subbackfreq file and save it here
+        FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)
+      }
+    }
+  }
+  FTLFinalMatrix<-FTLFinalMatrix[!duplicated(FTLFinalMatrix),]
+  
+  columnalheader<-c(rep(NA,35))
+  ITDFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  for (k in 1:length(ITDmotifsFINAL)) {
+    AN<-00000
+    #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+    #destroyed immediately after use
+    for (m in 1:ncol(Thirdsubbackfreq)) {
+      AN <- as.character(Thirdsubbackfreq[1, m])
+      if (grepl(pattern = AN,
+                x = names(ITDmotifsFINAL[k]),
+                fixed = TRUE) == TRUE) {
+        outputmatrix <- as.character(Thirdsubbackfreq[, m])
+        outputmatrix <- matrix(outputmatrix, nrow = 1)
+        #with that accession number, find a match in the subbackfreq file and save it here
+        ITDFinalMatrix<-rbind(ITDFinalMatrix,outputmatrix)
+      }
+    }
+  }
+  ITDFinalMatrix<-ITDFinalMatrix[!duplicated(ITDFinalMatrix),]
+  
+  columnalheader<-c(rep(NA,35))
+  D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  for (k in 1:length(D835YmotifsFINAL)) {
+    #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+    #destroyed immediately after use
+    for (m in 1:ncol(Secondsubbackfreq)) {
+      AN <- as.character(Secondsubbackfreq[1, m])
+      if (grepl(pattern = AN,
+                x = names(D835YmotifsFINAL[k]),
+                fixed = TRUE) == TRUE) {
+        outputmatrix <- as.character(Secondsubbackfreq[, m])
+        outputmatrix <- matrix(outputmatrix, nrow = 1)
+        #with that accession number, find a match in the subbackfreq file and save it here
+        D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)
+      }
+    }
+  }
+  D835YFinalMatrix<-D835YFinalMatrix[!duplicated(D835YFinalMatrix),]
+  
+  FTLoutputmatrix<-matrix(data=c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)),ncol = 2)
+  
+  
+  write.table(x=FTLoutputmatrix,
+              file=First_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,nrow = 1)
+  write.table(x=columnalheader,
+              file=First_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  write.table(x=FTLFinalMatrix,
+              file=First_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  ############################################################################################################
+  
+  D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)
+  
+  write.table(x=D835Youtputmatrix,
+              file=Second_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,nrow = 1)
+  write.table(x=columnalheader,
+              file=Second_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  write.table(x=D835YFinalMatrix,
+              file=Second_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  ############################################################################################################
+  
+  ITDoutputmatrix<-matrix(data = c(ITDmotifsFINAL,names(ITDmotifsFINAL)),ncol = 2)
+  
+  write.table(x=ITDoutputmatrix,
+              file=Third_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,nrow = 1)
+  write.table(x=columnalheader,
+              file=Third_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  write.table(x=ITDFinalMatrix,
+              file=Third_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+}
+
+# if (Are_You_Looking_For_Commonality=="NO"){
+#   
+#   
+#   FTLwtmotifsFULLMATRIX<-cbind(FTLwtmotifs,FTLwtAccessionNumbers)
+#   ITDmotifsFULLMATRIX<-cbind(ITDmotifs,ITDAccessionNumbers)
+#   D835YmotifsFULLMATRIX<-cbind(D835Ymotifs,D835YAccessionNumbers)
+#   # ?duplicated
+# 
+#   FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
+#   FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!FTLwtmotifsFINAL %in% ITDmotifs]
+#   FTLwtmotifsFINAL<-matrix(data=FTLwtmotifsFINAL, ncol = 1)
+# 
+#   ITDmotifsFINAL<-ITDmotifs[!ITDmotifs %in% D835Ymotifs]
+#   ITDmotifsFINAL<-ITDmotifsFINAL[!ITDmotifsFINAL %in% FTLwtmotifs]
+#   ITDmotifsFINAL<-matrix(data=ITDmotifsFINAL, ncol = 1)
+# 
+#   D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
+#   D835YmotifsFINAL<-D835YmotifsFINAL[!D835YmotifsFINAL %in% ITDmotifs]
+#   D835YmotifsFINAL<-matrix(data=D835YmotifsFINAL, ncol = 1)
+#   
+#   FTLnondupeAccessionNumbers<-c()
+#   
+#   for (z in 1:nrow(FTLwtmotifsFINAL)) {
+#     for (w in 1:nrow(FTLwtmotifsFULLMATRIX)) {
+#       if (is.na(FTLwtmotifsFULLMATRIX[w,1])!=TRUE)
+#         if (FTLwtmotifsFINAL[z]==FTLwtmotifsFULLMATRIX[w,1]){
+#           FTLnondupeAccessionNumbers<-c(FTLnondupeAccessionNumbers,FTLwtmotifsFULLMATRIX[w,2])
+#         }
+#     }  
+#   }
+# 
+#   
+#   #find accession numbers here, put a matrix of those things, amino acid %, but only after I've unduped them
+#   FTLnondupeAccessionNumbers<-FTLnondupeAccessionNumbers[!duplicated(FTLnondupeAccessionNumbers)]
+#   
+#   columnalheader<-c(rep(NA,35))
+#   FTLFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+#   
+#   for (k in 1:length(FTLnondupeAccessionNumbers)) {
+#     #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#     #destroyed immediately after use
+#     for (m in 1:ncol(Firstsubbackfreq)) {
+#       AN <- as.character(Firstsubbackfreq[1, m])
+#       if (grepl(pattern = AN,
+#                 x = FTLnondupeAccessionNumbers[k],
+#                 fixed = TRUE) == TRUE) {
+#         outputmatrix <- as.character(Firstsubbackfreq[, m])
+#         outputmatrix <- matrix(outputmatrix, nrow = 1)
+#         #with that accession number, find a match in the subbackfreq file and save it here
+#         FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)
+#       }
+#     }
+#   }
+#   ITDnondupeAccessionNumbers<-c()
+#   
+#   for (z in 1:nrow(ITDmotifsFINAL)) {
+#     for (w in 1:nrow(ITDmotifsFULLMATRIX)) {
+#       if (is.na(ITDmotifsFULLMATRIX[w,1])!=TRUE)
+#         if (ITDmotifsFINAL[z]==ITDmotifsFULLMATRIX[w,1]){
+#           ITDnondupeAccessionNumbers<-c(ITDnondupeAccessionNumbers,ITDmotifsFULLMATRIX[w,2])
+#         }
+#     }  
+#   }
+#   
+#   
+#   #find accession numbers here, put a matrix of those things, amino acid %, but only after I've unduped them
+#   ITDnondupeAccessionNumbers<-ITDnondupeAccessionNumbers[!duplicated(ITDnondupeAccessionNumbers)]
+#   
+#   columnalheader<-c(rep(NA,35))
+#   ITDFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+#   
+#   for (k in 1:length(ITDnondupeAccessionNumbers)) {
+#     #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#     #destroyed immediately after use
+#     for (m in 1:ncol(Thirdsubbackfreq)) {
+#       AN <- as.character(Thirdsubbackfreq[1, m])
+#       if (grepl(pattern = AN,
+#                 x = ITDnondupeAccessionNumbers[k],
+#                 fixed = TRUE) == TRUE) {
+#         outputmatrix <- as.character(Thirdsubbackfreq[, m])
+#         outputmatrix <- matrix(outputmatrix, nrow = 1)
+#         #with that accession number, find a match in the subbackfreq file and save it here
+#         ITDFinalMatrix<-rbind(ITDFinalMatrix,outputmatrix)
+#       }
+#     }
+#   }
+#   
+#   
+#   D835YnondupeAccessionNumbers<-c()
+#   
+#   for (z in 1:nrow(D835YmotifsFINAL)) {
+#     for (w in 1:nrow(D835YmotifsFULLMATRIX)) {
+#       if (is.na(D835YmotifsFULLMATRIX[w,1])!=TRUE)
+#         if (D835YmotifsFINAL[z]==D835YmotifsFULLMATRIX[w,1]){
+#           D835YnondupeAccessionNumbers<-c(D835YnondupeAccessionNumbers,D835YmotifsFULLMATRIX[w,2])
+#         }
+#     }  
+#   }
+#   
+#   
+#   #find accession numbers here, put a matrix of those things, amino acid %, but only after I've unduped them
+#   D835YnondupeAccessionNumbers<-D835YnondupeAccessionNumbers[!duplicated(D835YnondupeAccessionNumbers)]
+#   
+#   columnalheader<-c(rep(NA,35))
+#   D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+#   
+#   for (k in 1:length(D835YnondupeAccessionNumbers)) {
+#     #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#     #destroyed immediately after use
+#     for (m in 1:ncol(Secondsubbackfreq)) {
+#       AN <- as.character(Secondsubbackfreq[1, m])
+#       if (grepl(pattern = AN,
+#                 x = D835YnondupeAccessionNumbers[k],
+#                 fixed = TRUE) == TRUE) {
+#         outputmatrix <- as.character(Secondsubbackfreq[, m])
+#         outputmatrix <- matrix(outputmatrix, nrow = 1)
+#         #with that accession number, find a match in the subbackfreq file and save it here
+#         D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)
+#       }
+#     }
+#   }
+#   
+#   
+# 
+#   # FinalFTLmotifs<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
+#   # FinalFTLAccessionNumbers<-FTLnondupeAccessionNumbers[!duplicated(FTLnondupeAccessionNumbers)]
+#   # necessaryNAs<-rep(NA,times=(length(FinalFTLmotifs)-length(FinalFTLAccessionNumbers)))
+#   # FinalFTLAccessionNumbers<-c(FinalFTLAccessionNumbers,necessaryNAs)
+#   # TRUEFTLoutputmatrix<-cbind(FinalFTLmotifs,FinalFTLAccessionNumbers)
+#   # TRUEFTLoutputmatrix
+# 
+#   write.table(x=FTLwtmotifsFINAL,
+#               file=First_unshared_motifs_table,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+#   columnalheader<-matrix(columnalheader,nrow = 1)
+#   write.table(x=columnalheader,
+#               file=First_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   write.table(x=FTLFinalMatrix,
+#               file=First_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+# 
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   write.table(x=D835YmotifsFINAL,
+#               file=Second_unshared_motifs_table,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+#   columnalheader<-matrix(columnalheader,nrow = 1)
+#   write.table(x=columnalheader,
+#               file=Second_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   write.table(x=D835YFinalMatrix,
+#               file=Second_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   
+#   write.table(x=ITDmotifsFINAL,
+#               file=Third_unshared_motifs_table,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))
+#   columnalheader<-matrix(columnalheader,nrow = 1)
+#   write.table(x=columnalheader,
+#               file=Third_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   write.table(x=ITDFinalMatrix,
+#               file=Third_unshared_subbackfreq,
+#               quote=FALSE, sep=",",
+#               row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+#   
+#   
+#   
+#   
+#   
+#   
+# }
diff -r dff99bed3f56 -r 74ada21ceb70 all stuff/Difference finderMADE 7 TO 7 1-15-2019.R
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/all stuff/Difference finderMADE 7 TO 7 1-15-2019.R	Fri Apr 19 14:00:46 2019 -0400
@@ -0,0 +1,351 @@
+#I should make an SOP for this.  Problems we encountered: no x in the xY motif, and the kilodemon
+#the output files have both Y and xY, they shouldn't why is that happening?  make it not happen
+#make sure that accession numbers stay locked to each motif, somehow
+#output should look just like the KALIP input
+
+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
+FullMotifsOnly_questionmark<-"NO"
+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
+TruncatedMotifsOnly_questionmark<-"NO"
+#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)
+Are_You_Looking_For_Commonality<-"NO"
+
+
+#put the names of your input files here
+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)
+Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)
+
+SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE)
+Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)
+
+# ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)
+# Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
+
+#then put the names of your output files here
+# Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"
+# Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"
+
+# Shared_motifs_table<-"Shared motifs 7-27-17.csv"
+# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"
+
+First_unshared_motifs_table<-"1RS.csv"
+First_unshared_subbackfreq<-"1RSBF.csv"
+
+Second_unshared_motifs_table<-"2RS.csv"
+Second_unshared_subbackfreq<-"2RSBF.csv"
+
+# Third_unshared_motifs_table<-"R3 subs.csv"
+# Third_unshared_subbackfreq<-"R3 SBF.csv"
+
+#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
+#other languages to see if any of them can do it.
+####################################################################################################################################
+
+
+
+
+
+# grepl(pattern = "S", x=asdf, ignore.case = TRUE)
+
+FirstCentralLetters<-FirstSubstrateSet[,11]
+SecondCentralLetters<-SecondSubstrateSet[,11]
+
+FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)
+FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)
+FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
+
+SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)
+SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)
+SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
+
+FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")
+FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")
+FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")
+
+SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")
+SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")
+SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")
+
+FirstCentralLetters->FirstSubstrateSet[,11]
+SecondCentralLetters->SecondSubstrateSet[,11]
+
+####################################################################################################################################
+####################################################################################################################################
+# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two 
+# separate proteins thus two separate accession numbers?
+# It should actually output the shared motif and BOTH accession numbers.  Right now it does not, it only maps out the second
+# accession number.  So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+
+#Create the motif sets, deciding wether or not you're looking for truncated or full here
+#full only
+
+
+if (Are_You_Looking_For_Commonality=="NO"){
+  
+  ###############################################
+  #ALL motifs, full and truncated
+  
+  if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
+    FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    for (i in 1:nrow(FirstSubstrateSet)){
+      FTLwtletters<-FirstSubstrateSet[i,4:18]
+      FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+      FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        FTLwtletters<-motif
+        FTLwtmotifs[i,1]<-FTLwtletters
+        FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+        
+        
+      }
+      
+    }
+    
+    D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    for (i in 1:nrow(SecondSubstrateSet)){
+      D835letters<-SecondSubstrateSet[i,4:18]
+      D835letters<-D835letters[D835letters !="XXXXX"]
+      D835letters<-paste(D835letters, sep="", collapse="")
+      leftspaces<-c()
+      rightspaces<-c()
+      
+      YYYmotif <- unlist(strsplit(D835letters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+        leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+      
+      if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        D835letters<-motif
+        D835Ymotifs[i,1]<-D835letters
+        D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      }
+    }
+    
+    names(FTLwtmotifs)<-FTLwtAccessionNumbers
+    names(D835Ymotifs)<-D835YAccessionNumbers
+    
+  }
+  
+  
+  FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
+  FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
+  
+  D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
+  D835YmotifsFINAL<-D835YmotifsFINAL[!duplicated(D835YmotifsFINAL)]
+  
+  
+  columnalheader<-c(rep(NA,36))
+  FTLFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  for (k in 1:length(FTLwtmotifsFINAL)) {
+    AN<-00000
+    #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+    #destroyed immediately after use
+    for (m in 1:ncol(Firstsubbackfreq)) {
+      AN <- as.character(Firstsubbackfreq[1, m])
+      if (grepl(pattern = AN,
+                x = names(FTLwtmotifsFINAL[k]),
+                fixed = TRUE) == TRUE) {
+        outputmatrix <- as.character(Firstsubbackfreq[, m])
+        outputmatrix <- matrix(outputmatrix, nrow = 1)
+        #with that accession number, find a match in the subbackfreq file and save it here
+        FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)
+      }
+    }
+  }
+  FTLFinalMatrix<-FTLFinalMatrix[!duplicated(FTLFinalMatrix),]
+  FTLFinalMatrix<-FTLFinalMatrix[2:nrow(FTLFinalMatrix),]
+  
+  columnalheader<-c(rep(NA,36))
+  D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  for (k in 1:length(D835YmotifsFINAL)) {
+    #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+    #destroyed immediately after use
+    for (m in 1:ncol(Secondsubbackfreq)) {
+      AN <- as.character(Secondsubbackfreq[1, m])
+      if (grepl(pattern = AN,
+                x = names(D835YmotifsFINAL[k]),
+                fixed = TRUE) == TRUE) {
+        outputmatrix <- as.character(Secondsubbackfreq[, m])
+        outputmatrix <- matrix(outputmatrix, nrow = 1)
+        #with that accession number, find a match in the subbackfreq file and save it here
+        D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)
+      }
+    }
+  }
+  D835YFinalMatrix<-D835YFinalMatrix[!duplicated(D835YFinalMatrix),]
+  D835YFinalMatrix<-D835YFinalMatrix[2:nrow(D835YFinalMatrix),]
+  
+  FTLoutputmatrix<-matrix(data=c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)),ncol = 2)
+  
+  
+  FLTheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
+  # FLTheader<-unlist(FLTheader)
+  lefthandFLT<-matrix(data = rep(NA,times=2*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
+  righthandFLT<-matrix(data = rep(NA,times=1*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
+  FLTaccessionset<-FTLoutputmatrix[,2]
+  FTLmeat<-sapply(FTLoutputmatrix[,1], strsplit, "")
+  FTLmeat<-sapply(FTLmeat, unlist)
+  colnames(FTLmeat)<-NULL
+  FTLmeat<-t(FTLmeat)
+  
+  FTLoutputmatrix2<-cbind(lefthandFLT,FLTaccessionset,FTLmeat,righthandFLT)
+  colnames(FTLoutputmatrix2)<-NULL
+  rownames(FTLoutputmatrix2)<-NULL
+  colnames(FLTheader)<-NULL
+  rownames(FLTheader)<-NULL
+  
+  
+  FirstCentralLettersAGAIN<-FTLoutputmatrix2[,11]
+  
+  FirstEsses<-sapply(FirstCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
+  FirstTees<-sapply(FirstCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
+  FirstWys<-sapply(FirstCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
+  
+  FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstEsses,"xS")
+  FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstTees,"xT")
+  FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstWys,"xY")
+  
+  FirstCentralLettersAGAIN->FTLoutputmatrix2[,11]
+  
+  FTLoutputmatrix2<-rbind(FLTheader,FTLoutputmatrix2)
+  
+  write.table(x=FTLoutputmatrix2,
+              file=First_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,nrow = 1)
+  write.table(x=columnalheader,
+              file=First_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  write.table(x=FTLFinalMatrix,
+              file=First_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  ############################################################################################################
+  
+  D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)
+  
+  D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
+  # D835Yheader<-unlist(D835Yheader)
+  lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
+  righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
+  D835Yaset<-D835Youtputmatrix[,2]
+  D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")
+  D835meat<-sapply(D835meat, unlist)
+  colnames(D835meat)<-NULL
+  D835meat<-t(D835meat)
+  
+  D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)
+  colnames(D835Youtputmatrix2)<-NULL
+  rownames(D835Youtputmatrix2)<-NULL
+  colnames(D835Yheader)<-NULL
+  rownames(D835Yheader)<-NULL
+  
+  
+  SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]
+  
+  SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
+  SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
+  SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
+  
+  SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")
+  SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")
+  SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")
+  
+  SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]
+  
+  D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)
+  
+  write.table(x=D835Youtputmatrix2,
+              file=Second_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,nrow = 1)
+  write.table(x=columnalheader,
+              file=Second_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  write.table(x=D835YFinalMatrix,
+              file=Second_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+}
+
diff -r dff99bed3f56 -r 74ada21ceb70 all stuff/Difference finderMADE 7 TO 7 fastversion 2-14-2019.R
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/all stuff/Difference finderMADE 7 TO 7 fastversion 2-14-2019.R	Fri Apr 19 14:00:46 2019 -0400
@@ -0,0 +1,453 @@
+#I should make an SOP for this.  Problems we encountered: no x in the xY motif, and the kilodemon
+#the output files have both Y and xY, they shouldn't why is that happening?  make it not happen
+#make sure that accession numbers stay locked to each motif, somehow
+#output should look just like the KALIP input
+#S2 is negatives
+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
+FullMotifsOnly_questionmark<-"NO"
+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
+TruncatedMotifsOnly_questionmark<-"NO"
+#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)
+Are_You_Looking_For_Commonality<-"NO"
+
+
+#put the names of your input files here
+FirstSubstrateSet<- read.csv("Substrates 1A TiO2 and FeNTA no duplicates.csv", stringsAsFactors=FALSE)
+Firstsubbackfreq<- read.csv("SBF 1A TiO2 and FeNTA no duplicates.csv", header=FALSE, stringsAsFactors=FALSE)
+
+SecondSubstrateSet<- read.csv("Substrates 1B TiO2 and FeNTA no duplicates.csv", stringsAsFactors=FALSE)
+Secondsubbackfreq<- read.csv("SBF 1B TiO2 and FeNTA no duplicates.csv", header=FALSE, stringsAsFactors=FALSE)
+
+# ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)
+# Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
+
+#then put the names of your output files here
+# Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"
+# Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"
+
+# Shared_motifs_table<-"Shared motifs 7-27-17.csv"
+# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"
+
+First_unshared_motifs_table<-"pka_minus_wo-plus_wo_vector_subs.csv"
+First_unshared_subbackfreq<-"pka_minus_wo-plus_wo_vector_sbf.csv"
+
+Second_unshared_motifs_table<-"pka_plus_wo-minus_wo_vector_subs.csv"
+Second_unshared_subbackfreq<-"pka_plus_wo-minus_wo_vector_sbf.csv"
+
+# Third_unshared_motifs_table<-"R3 subs.csv"
+# Third_unshared_subbackfreq<-"R3 SBF.csv"
+
+#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
+#other languages to see if any of them can do it.
+####################################################################################################################################
+
+
+
+
+
+# grepl(pattern = "S", x=asdf, ignore.case = TRUE)
+
+FirstCentralLetters<-FirstSubstrateSet[,11]
+SecondCentralLetters<-SecondSubstrateSet[,11]
+
+FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)
+FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)
+FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
+
+SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)
+SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)
+SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
+
+FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")
+FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")
+FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")
+
+SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")
+SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")
+SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")
+
+FirstCentralLetters->FirstSubstrateSet[,11]
+SecondCentralLetters->SecondSubstrateSet[,11]
+
+####################################################################################################################################
+####################################################################################################################################
+# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two 
+# separate proteins thus two separate accession numbers?
+# It should actually output the shared motif and BOTH accession numbers.  Right now it does not, it only maps out the second
+# accession number.  So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+
+#Create the motif sets, deciding wether or not you're looking for truncated or full here
+#full only
+
+
+if (Are_You_Looking_For_Commonality=="NO"){
+  
+  ###############################################
+  #ALL motifs, full and truncated
+  
+  if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
+    # FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    # FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    #so what this does is
+    #find the central phospho position and add spaces to either side of it
+    #create a pasted together motif which will be used for difference finding
+    #keep motifs and accession numbers in the same index position of two vectors
+    
+    #so instead just take the FLTwt[i,4:18], and replace "" with "O"
+    #then perform paste function
+    #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
+    
+    FTLwtmotifs<-FirstSubstrateSet[,4:18]
+    # FTLwtmotifs<-sapply(FTLwtmotifs, gsub, pattern=" ", replacement="O",ignore.case=TRUE)
+    FTLwtmotifs<-replace(FTLwtmotifs, FTLwtmotifs=="", "O")
+    FTLwtmotifs<-apply(FTLwtmotifs, 1, paste, sep="", collapse="")
+    FTLwtAccessionNumbers<-FirstSubstrateSet[,3]
+    
+    # D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    # D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    D835Ymotifs<-SecondSubstrateSet[,4:18]
+    # D835Ymotifs<-sapply(D835Ymotifs, gsub, patter="", replacement="O",ignore.case=TRUE)
+    D835Ymotifs<-replace(D835Ymotifs, D835Ymotifs=="", "O")
+    D835Ymotifs<-replace(D835Ymotifs, D835Ymotifs=="", "O")
+    D835Ymotifs<-apply(D835Ymotifs, 1, paste, sep="", collapse="")
+    D835YAccessionNumbers<-SecondSubstrateSet[,3]
+    
+    names(FTLwtmotifs)<-FTLwtAccessionNumbers
+    names(D835Ymotifs)<-D835YAccessionNumbers
+    
+  }
+  
+  
+  FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
+  FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
+  
+  D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
+  D835YmotifsFINAL<-D835YmotifsFINAL[!duplicated(D835YmotifsFINAL)]
+  
+  
+  
+  # columnalheader<-c(rep(NA,36))
+  # FTLFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  # 
+  #how to make this an apply
+  #actual first turn names(motifsFINAL) into a vector, then gsub to replace all "|" pipe characters with "*" star characters
+  #first take the accession numbers as Firstsubbackfreq[1,], then gsub to replace all "|" pipe characters with "*" star characters
+  #then use AccessionNumbers as a vector and use 
+  #matches <- unique (grep(paste(toMatch,collapse="|"), names(motifsFINAL), value=TRUE))
+  
+  FLTwtNames<-names(FTLwtmotifsFINAL)
+  FLTwtNames<-FLTwtNames[!duplicated(FLTwtNames)]
+  #the problem is the names includes a lot of things that are multi names separated by ;
+  #I need to do soem paper writing and poster writing
+  
+  FLTwtNames<-gsub(pattern = '\\|', replacement = "*", x=FLTwtNames)
+  FLTwtNames<-paste(FLTwtNames,collapse = "|")
+  
+  AccNums<-as.character(Firstsubbackfreq[1,])
+  AccNums<-gsub(pattern = "\\|", replacement = "*", x=AccNums)
+  
+  
+  firstthree123<-gsub(pattern = "\\|", replacement = "", x=FLTwtNames)
+  lastthree123<-gsub(pattern = "\\|", replacement = "", x=AccNums)
+
+  pasty<-paste(lastthree123,collapse = "|")
+  
+  my_matches<-unique(grep(pattern = FLTwtNames, x=AccNums, value = TRUE))
+  # matches <- unique (grep(paste(FLTwtNames,collapse="|"), AccNums, value=TRUE))
+  My_matches<- AccNums %in% FLTwtNames #use apply grep function
+  My_matches<-grep(pattern = pasty, x=firstthree123, ignore.case = TRUE)
+  sensation<-firstthree123[My_matches]
+  what<-firstthree123[!firstthree123 %in% sensation]
+  
+  #my matches are which columns in the SBF file still have a motif with them
+  FirstFINALSBF<-Firstsubbackfreq[My_matches]
+  FTLFinalMatrix<-FirstFINALSBF
+  duped<-FTLFinalMatrix[1,]
+  duped<-duped[!duplicated(duped)]
+  names(duped)<-NULL
+  duped<-unlist(duped)
+  unduped<-FTLFinalMatrix[,!duplicated(duped)]
+  FTLFinalMatrix<-unduped
+  # FTLFinalMatrix<-FTLFinalMatrix[2:nrow(FTLFinalMatrix),]
+  
+  # columnalheader<-c(rep(NA,36))
+  # D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  D835names<-names(D835YmotifsFINAL)
+  D835names<-D835names[!duplicated(D835names)]
+  AccNums<-as.character(Secondsubbackfreq[1,])
+  My_matches<-AccNums %in% D835names
+  SecondFINALSBF<-Secondsubbackfreq[My_matches]
+  D835YFinalMatrix<-SecondFINALSBF
+  duped<-D835YFinalMatrix[1,]
+  duped<-duped[!duplicated(duped)]
+  names(duped)<-NULL
+  duped<-unlist(duped)
+  unduped<-D835YFinalMatrix[,!duplicated(duped)]
+  D835YFinalMatrix<-unduped
+  #there's a problem, accession numbers are duplicated
+  
+  # FTLoutputmatrix<-matrix(data=c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)),ncol = 2)
+  
+  FTLwtmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=FTLwtmotifsFINAL)
+  FTLwtmotifsFINAL<-gsub(pattern = "x", replacement = "", x=FTLwtmotifsFINAL)
+  FTLoutputmatrix<-matrix(data = c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)), ncol=2)
+  
+  # FTLwtmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=FTLwtmotifsFINAL)
+  # FTLwtmotifsFINAL<-gsub(pattern = "x", replacement = "", x=FTLwtmotifsFINAL)
+  # FTLoutputmatrix<-matrix(data = c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)), ncol=2)
+  
+  FLTheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
+  # FLTheader<-unlist(FLTheader)
+  lefthandFLT<-matrix(data = rep(NA,times=2*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
+  righthandFLT<-matrix(data = rep(NA,times=1*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
+  FLTaccessionset<-FTLoutputmatrix[,2]
+  FTLmeat<-sapply(FTLoutputmatrix[,1], strsplit, "")
+  FTLmeat<-sapply(FTLmeat, unlist)
+  colnames(FTLmeat)<-NULL
+  FTLmeat<-t(FTLmeat)
+  
+  FTLoutputmatrix2<-cbind(lefthandFLT,FLTaccessionset,FTLmeat,righthandFLT)
+  colnames(FTLoutputmatrix2)<-NULL
+  rownames(FTLoutputmatrix2)<-NULL
+  colnames(FLTheader)<-NULL
+  rownames(FLTheader)<-NULL
+  
+  
+  FirstCentralLettersAGAIN<-FTLoutputmatrix2[,11]
+  
+  FirstEsses<-sapply(FirstCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
+  FirstTees<-sapply(FirstCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
+  FirstWys<-sapply(FirstCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
+  
+  FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstEsses,"xS")
+  FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstTees,"xT")
+  FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstWys,"xY")
+  
+  FirstCentralLettersAGAIN->FTLoutputmatrix2[,11]
+  
+  FTLoutputmatrix2<-rbind(FLTheader,FTLoutputmatrix2)
+  
+  write.table(x=FTLoutputmatrix2,
+              file=First_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,ncol = 1)
+  # write.table(x=columnalheader,
+  #             file=First_unshared_subbackfreq,
+  #             quote=FALSE, sep=",",
+  #             row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  FTLFinalMatrix<-cbind(columnalheader,FTLFinalMatrix)
+  
+  write.table(x=FTLFinalMatrix,
+              file=First_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  ############################################################################################################
+  
+  D835YmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=D835YmotifsFINAL)
+  D835YmotifsFINAL<-gsub(pattern = "x", replacement = "", x=D835YmotifsFINAL)
+  D835Youtputmatrix<-matrix(data = c(D835YmotifsFINAL,names(D835YmotifsFINAL)), ncol=2)
+  
+  # D835YmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=D835YoutputmatrixL)
+  # D835YmotifsFINAL<-gsub(pattern = "x", replacement = "", x=D835Youtputmatrix)
+  # D835Youtputmatrix<-matrix(data = c(D835Youtputmatrix,names(D835Youtputmatrix)), ncol=2)
+  # 
+
+  # D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)
+  
+  D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
+  # D835Yheader<-unlist(D835Yheader)
+  lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
+  righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
+  D835Yaset<-D835Youtputmatrix[,2]
+  D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")
+  D835meat<-sapply(D835meat, unlist)
+  colnames(D835meat)<-NULL
+  D835meat<-t(D835meat)
+
+  # FTLmeat<-sapply(FTLoutputmatrix[,1], strsplit, "")
+  # FTLmeat<-sapply(FTLmeat, unlist)
+  # colnames(FTLmeat)<-NULL
+  # FTLmeat<-t(FTLmeat)
+
+
+  D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)
+  colnames(D835Youtputmatrix2)<-NULL
+  rownames(D835Youtputmatrix2)<-NULL
+  colnames(D835Yheader)<-NULL
+  rownames(D835Yheader)<-NULL
+
+
+  SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]
+
+  SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
+  SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
+  SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
+
+  SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")
+  SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")
+  SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")
+
+  SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]
+
+  D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)
+
+  write.table(x=D835Youtputmatrix2,
+              file=Second_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,ncol = 1)
+  # write.table(x=columnalheader,
+  #             file=Second_unshared_subbackfreq,
+  #             quote=FALSE, sep=",",
+  #             row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  D835YFinalMatrix<-cbind(columnalheader,D835YFinalMatrix)
+  
+  write.table(x=D835YFinalMatrix,
+              file=Second_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+}
+
+
+
+#  for (i in 1:nrow(FirstSubstrateSet)){
+#   FTLwtletters<-FirstSubstrateSet[i,4:18]
+#   FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+#   FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+#   leftspaces<-c()
+#   rightspaces<-c()
+#   
+#   YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+#   YYYposition <- match(x = "x", table = YYYmotif)
+#   #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
+#   #just 3 letters to the left of x
+#   
+#   YYYLettersToTheLeft <- YYYposition - 1
+#   #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
+#   #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+#   YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+#   #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
+#   #variable the user puts in is
+#   
+#   
+#   if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+#     leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+#     rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+#     #add blank spaces if the motif has less than 4 letters to the left/right
+#     motif<-c(leftspaces,YYYmotif,rightspaces)
+#     #save that motif, which is the Y and +/- 4 amino acids, including truncation
+#     motif<-motif[!motif %in% "x"]
+#     motif<-paste(motif, sep="", collapse="")
+#     FTLwtletters<-motif
+#     FTLwtmotifs[i,1]<-FTLwtletters
+#     FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+#   }
+#   
+#   if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+#     motif<-YYYmotif
+#     #add blank spaces if the motif has less than 4 letters to the left/right
+#     motif<-c(leftspaces,YYYmotif,rightspaces)
+#     #save that motif, which is the Y and +/- 4 amino acids, including truncation
+#     motif<-motif[!motif %in% "x"]
+#     motif<-paste(motif, sep="", collapse="")
+#     FTLwtletters<-motif
+#     FTLwtmotifs[i,1]<-FTLwtletters
+#     FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+#     
+#     
+#   }
+#   
+# }
+
+
+
+# for (i in 1:nrow(SecondSubstrateSet)){
+#   D835letters<-SecondSubstrateSet[i,4:18]
+#   D835letters<-D835letters[D835letters !="XXXXX"]
+#   D835letters<-paste(D835letters, sep="", collapse="")
+#   leftspaces<-c()
+#   rightspaces<-c()
+#   
+#   YYYmotif <- unlist(strsplit(D835letters, split = ""))
+#   YYYposition <- match(x = "x", table = YYYmotif)
+#   #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
+#   #just 3 letters to the left of x
+#   
+#   YYYLettersToTheLeft <- YYYposition - 1
+#   #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
+#   #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+#   YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+#   #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
+#   #variable the user puts in is
+#   if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+#     leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+#     rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+#     #add blank spaces if the motif has less than 4 letters to the left/right
+#     motif<-c(leftspaces,YYYmotif,rightspaces)
+#     #save that motif, which is the Y and +/- 4 amino acids, including truncation
+#     motif<-motif[!motif %in% "x"]
+#     motif<-paste(motif, sep="", collapse="")
+#     D835letters<-motif
+#     D835Ymotifs[i,1]<-D835letters
+#     D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+#   }
+#   
+#   if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+#     motif<-YYYmotif
+#     #add blank spaces if the motif has less than 4 letters to the left/right
+#     motif<-c(leftspaces,YYYmotif,rightspaces)
+#     #save that motif, which is the Y and +/- 4 amino acids, including truncation
+#     motif<-motif[!motif %in% "x"]
+#     motif<-paste(motif, sep="", collapse="")
+#     D835letters<-motif
+#     D835Ymotifs[i,1]<-D835letters
+#     D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+#   }
+# }
+
+# for (k in 1:length(FTLwtmotifsFINAL)) {
+#   AN<-00000
+#   #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#   #destroyed immediately after use
+#   for (m in 1:ncol(Firstsubbackfreq)) {
+#     AN <- as.character(Firstsubbackfreq[1, m])
+#     if (grepl(pattern = AN,
+#               x = names(FTLwtmotifsFINAL[k]),
+#               fixed = TRUE) == TRUE) {
+#       outputmatrix <- as.character(Firstsubbackfreq[, m])
+#       outputmatrix <- matrix(outputmatrix, nrow = 1)
+#       #with that accession number, find a match in the subbackfreq file and save it here
+#       FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)
+#     }
+#   }
+# }
+# for (k in 1:length(D835YmotifsFINAL)) {
+#   #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#   #destroyed immediately after use
+#   for (m in 1:ncol(Secondsubbackfreq)) {
+#     AN <- as.character(Secondsubbackfreq[1, m])
+#     if (grepl(pattern = AN,
+#               x = names(D835YmotifsFINAL[k]),
+#               fixed = TRUE) == TRUE) {
+#       outputmatrix <- as.character(Secondsubbackfreq[, m])
+#       outputmatrix <- matrix(outputmatrix, nrow = 1)
+#       #with that accession number, find a match in the subbackfreq file and save it here
+#       D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)
+#     }
+#   }
+# }
\ No newline at end of file
diff -r dff99bed3f56 -r 74ada21ceb70 all stuff/Difference finderMADE 7 TO 7 fastversion.R
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/all stuff/Difference finderMADE 7 TO 7 fastversion.R	Fri Apr 19 14:00:46 2019 -0400
@@ -0,0 +1,451 @@
+#I should make an SOP for this.  Problems we encountered: no x in the xY motif, and the kilodemon
+#the output files have both Y and xY, they shouldn't why is that happening?  make it not happen
+#make sure that accession numbers stay locked to each motif, somehow
+#output should look just like the KALIP input
+#S2 is negatives
+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
+FullMotifsOnly_questionmark<-"NO"
+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
+TruncatedMotifsOnly_questionmark<-"NO"
+#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)
+Are_You_Looking_For_Commonality<-"NO"
+
+
+#put the names of your input files here
+FirstSubstrateSet<- read.csv("pka_minus_wo_vector_subs.csv", stringsAsFactors=FALSE)
+Firstsubbackfreq<- read.csv("pka_minus_wo_vector_sbf.csv", header=FALSE, stringsAsFactors=FALSE)
+
+SecondSubstrateSet<- read.csv("pka_plus_wo_vector_substrates.csv", stringsAsFactors=FALSE)
+Secondsubbackfreq<- read.csv("pka_plus_wo_vector_sbf.csv", header=FALSE, stringsAsFactors=FALSE)
+
+# ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)
+# Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)
+
+#then put the names of your output files here
+# Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"
+# Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"
+
+# Shared_motifs_table<-"Shared motifs 7-27-17.csv"
+# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"
+
+First_unshared_motifs_table<-"pka_minus_wo-plus_wo_vector_subs.csv"
+First_unshared_subbackfreq<-"pka_minus_wo-plus_wo_vector_sbf.csv"
+
+Second_unshared_motifs_table<-"pka_plus_wo-minus_wo_vector_subs.csv"
+Second_unshared_subbackfreq<-"pka_plus_wo-minus_wo_vector_sbf.csv"
+
+# Third_unshared_motifs_table<-"R3 subs.csv"
+# Third_unshared_subbackfreq<-"R3 SBF.csv"
+
+#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
+#other languages to see if any of them can do it.
+####################################################################################################################################
+
+
+
+
+
+# grepl(pattern = "S", x=asdf, ignore.case = TRUE)
+
+FirstCentralLetters<-FirstSubstrateSet[,11]
+SecondCentralLetters<-SecondSubstrateSet[,11]
+
+FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)
+FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)
+FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
+
+SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)
+SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)
+SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
+
+FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")
+FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")
+FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")
+
+SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")
+SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")
+SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")
+
+FirstCentralLetters->FirstSubstrateSet[,11]
+SecondCentralLetters->SecondSubstrateSet[,11]
+
+####################################################################################################################################
+####################################################################################################################################
+# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two 
+# separate proteins thus two separate accession numbers?
+# It should actually output the shared motif and BOTH accession numbers.  Right now it does not, it only maps out the second
+# accession number.  So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+####################################################################################################################################
+
+#Create the motif sets, deciding wether or not you're looking for truncated or full here
+#full only
+
+
+if (Are_You_Looking_For_Commonality=="NO"){
+  
+  ###############################################
+  #ALL motifs, full and truncated
+  
+  if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
+    # FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    # FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+    
+    #so what this does is
+    #find the central phospho position and add spaces to either side of it
+    #create a pasted together motif which will be used for difference finding
+    #keep motifs and accession numbers in the same index position of two vectors
+    
+    #so instead just take the FLTwt[i,4:18], and replace "" with "O"
+    #then perform paste function
+    #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
+    
+    FTLwtmotifs<-FirstSubstrateSet[,4:18]
+    # FTLwtmotifs<-sapply(FTLwtmotifs, gsub, pattern=" ", replacement="O",ignore.case=TRUE)
+    FTLwtmotifs<-replace(FTLwtmotifs, FTLwtmotifs=="", "O")
+    FTLwtmotifs<-apply(FTLwtmotifs, 1, paste, sep="", collapse="")
+    FTLwtAccessionNumbers<-FirstSubstrateSet[,3]
+    
+    # D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+    # D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+    
+    D835Ymotifs<-SecondSubstrateSet[,4:18]
+    # D835Ymotifs<-sapply(D835Ymotifs, gsub, patter="", replacement="O",ignore.case=TRUE)
+    D835Ymotifs<-replace(D835Ymotifs, D835Ymotifs=="", "O")
+    D835Ymotifs<-replace(D835Ymotifs, D835Ymotifs=="", "O")
+    D835Ymotifs<-apply(D835Ymotifs, 1, paste, sep="", collapse="")
+    D835YAccessionNumbers<-SecondSubstrateSet[,3]
+    
+    names(FTLwtmotifs)<-FTLwtAccessionNumbers
+    names(D835Ymotifs)<-D835YAccessionNumbers
+    
+  }
+  
+  
+  FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
+  FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
+  
+  D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
+  D835YmotifsFINAL<-D835YmotifsFINAL[!duplicated(D835YmotifsFINAL)]
+  
+  
+  
+  # columnalheader<-c(rep(NA,36))
+  # FTLFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  # 
+  #how to make this an apply
+  #actual first turn names(motifsFINAL) into a vector, then gsub to replace all "|" pipe characters with "*" star characters
+  #first take the accession numbers as Firstsubbackfreq[1,], then gsub to replace all "|" pipe characters with "*" star characters
+  #then use AccessionNumbers as a vector and use 
+  #matches <- unique (grep(paste(toMatch,collapse="|"), names(motifsFINAL), value=TRUE))
+  
+  FLTwtNames<-names(FTLwtmotifsFINAL)
+  FLTwtNames<-FLTwtNames[!duplicated(FLTwtNames)]
+  #the problem is the names includes a lot of things that are multi names separated by ;
+  #I need to do soem paper writing and poster writing
+  
+  # FLTwtNames<-gsub(pattern = '\\|', replacement = "*", x=FLTwtNames)
+  # FLTwtNames<-paste(FLTwtNames,collapse = "|")
+  
+  AccNums<-as.character(Firstsubbackfreq[1,])
+  # AccNums<-gsub(pattern = "\\|", replacement = "*", x=AccNums)
+  
+  
+  firstthree123<-gsub(pattern = "\\|", replacement = "", x=FLTwtNames)
+  lastthree123<-gsub(pattern = "\\|", replacement = "", x=AccNums)
+
+  pasty<-paste(lastthree123,collapse = "|")
+  
+  # my_matches<-unique(grep(pattern = FLTwtNames, x=AccNums, value = TRUE))
+  # matches <- unique (grep(paste(FLTwtNames,collapse="|"), AccNums, value=TRUE))
+  My_matches<- AccNums %in% FLTwtNames #use apply grep function
+  # My_matches<-grep(pattern = pasty, x=lastthree123, ignore.case = TRUE)
+  
+  #my matches are which columns in the SBF file still have a motif with them
+  FirstFINALSBF<-Firstsubbackfreq[My_matches]
+  FTLFinalMatrix<-FirstFINALSBF
+  duped<-FTLFinalMatrix[1,]
+  duped<-duped[!duplicated(duped)]
+  names(duped)<-NULL
+  duped<-unlist(duped)
+  unduped<-FTLFinalMatrix[,!duplicated(duped)]
+  FTLFinalMatrix<-unduped
+  # FTLFinalMatrix<-FTLFinalMatrix[2:nrow(FTLFinalMatrix),]
+  
+  # columnalheader<-c(rep(NA,36))
+  # D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+  
+  D835names<-names(D835YmotifsFINAL)
+  D835names<-D835names[!duplicated(D835names)]
+  AccNums<-as.character(Secondsubbackfreq[1,])
+  My_matches<-AccNums %in% D835names
+  SecondFINALSBF<-Secondsubbackfreq[My_matches]
+  D835YFinalMatrix<-SecondFINALSBF
+  duped<-D835YFinalMatrix[1,]
+  duped<-duped[!duplicated(duped)]
+  names(duped)<-NULL
+  duped<-unlist(duped)
+  unduped<-D835YFinalMatrix[,!duplicated(duped)]
+  D835YFinalMatrix<-unduped
+  #there's a problem, accession numbers are duplicated
+  
+  # FTLoutputmatrix<-matrix(data=c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)),ncol = 2)
+  
+  FTLwtmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=FTLwtmotifsFINAL)
+  FTLwtmotifsFINAL<-gsub(pattern = "x", replacement = "", x=FTLwtmotifsFINAL)
+  FTLoutputmatrix<-matrix(data = c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)), ncol=2)
+  
+  # FTLwtmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=FTLwtmotifsFINAL)
+  # FTLwtmotifsFINAL<-gsub(pattern = "x", replacement = "", x=FTLwtmotifsFINAL)
+  # FTLoutputmatrix<-matrix(data = c(FTLwtmotifsFINAL,names(FTLwtmotifsFINAL)), ncol=2)
+  
+  FLTheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
+  # FLTheader<-unlist(FLTheader)
+  lefthandFLT<-matrix(data = rep(NA,times=2*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
+  righthandFLT<-matrix(data = rep(NA,times=1*nrow(FTLoutputmatrix)),nrow=nrow(FTLoutputmatrix))
+  FLTaccessionset<-FTLoutputmatrix[,2]
+  FTLmeat<-sapply(FTLoutputmatrix[,1], strsplit, "")
+  FTLmeat<-sapply(FTLmeat, unlist)
+  colnames(FTLmeat)<-NULL
+  FTLmeat<-t(FTLmeat)
+  
+  FTLoutputmatrix2<-cbind(lefthandFLT,FLTaccessionset,FTLmeat,righthandFLT)
+  colnames(FTLoutputmatrix2)<-NULL
+  rownames(FTLoutputmatrix2)<-NULL
+  colnames(FLTheader)<-NULL
+  rownames(FLTheader)<-NULL
+  
+  
+  FirstCentralLettersAGAIN<-FTLoutputmatrix2[,11]
+  
+  FirstEsses<-sapply(FirstCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
+  FirstTees<-sapply(FirstCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
+  FirstWys<-sapply(FirstCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
+  
+  FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstEsses,"xS")
+  FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstTees,"xT")
+  FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstWys,"xY")
+  
+  FirstCentralLettersAGAIN->FTLoutputmatrix2[,11]
+  
+  FTLoutputmatrix2<-rbind(FLTheader,FTLoutputmatrix2)
+  
+  write.table(x=FTLoutputmatrix2,
+              file=First_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,ncol = 1)
+  # write.table(x=columnalheader,
+  #             file=First_unshared_subbackfreq,
+  #             quote=FALSE, sep=",",
+  #             row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  FTLFinalMatrix<-cbind(columnalheader,FTLFinalMatrix)
+  
+  write.table(x=FTLFinalMatrix,
+              file=First_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  ############################################################################################################
+  
+  D835YmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=D835YmotifsFINAL)
+  D835YmotifsFINAL<-gsub(pattern = "x", replacement = "", x=D835YmotifsFINAL)
+  D835Youtputmatrix<-matrix(data = c(D835YmotifsFINAL,names(D835YmotifsFINAL)), ncol=2)
+  
+  # D835YmotifsFINAL<-gsub(pattern = "O", replacement = " ", x=D835YoutputmatrixL)
+  # D835YmotifsFINAL<-gsub(pattern = "x", replacement = "", x=D835Youtputmatrix)
+  # D835Youtputmatrix<-matrix(data = c(D835Youtputmatrix,names(D835Youtputmatrix)), ncol=2)
+  # 
+
+  # D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)
+  
+  D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")
+  # D835Yheader<-unlist(D835Yheader)
+  lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
+  righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))
+  D835Yaset<-D835Youtputmatrix[,2]
+  D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")
+  D835meat<-sapply(D835meat, unlist)
+  colnames(D835meat)<-NULL
+  D835meat<-t(D835meat)
+
+  # FTLmeat<-sapply(FTLoutputmatrix[,1], strsplit, "")
+  # FTLmeat<-sapply(FTLmeat, unlist)
+  # colnames(FTLmeat)<-NULL
+  # FTLmeat<-t(FTLmeat)
+
+
+  D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)
+  colnames(D835Youtputmatrix2)<-NULL
+  rownames(D835Youtputmatrix2)<-NULL
+  colnames(D835Yheader)<-NULL
+  rownames(D835Yheader)<-NULL
+
+
+  SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]
+
+  SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)
+  SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)
+  SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)
+
+  SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")
+  SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")
+  SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")
+
+  SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]
+
+  D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)
+
+  write.table(x=D835Youtputmatrix2,
+              file=Second_unshared_motifs_table,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))
+  columnalheader<-matrix(columnalheader,ncol = 1)
+  # write.table(x=columnalheader,
+  #             file=Second_unshared_subbackfreq,
+  #             quote=FALSE, sep=",",
+  #             row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+  
+  D835YFinalMatrix<-cbind(columnalheader,D835YFinalMatrix)
+  
+  write.table(x=D835YFinalMatrix,
+              file=Second_unshared_subbackfreq,
+              quote=FALSE, sep=",",
+              row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+}
+
+
+
+#  for (i in 1:nrow(FirstSubstrateSet)){
+#   FTLwtletters<-FirstSubstrateSet[i,4:18]
+#   FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
+#   FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
+#   leftspaces<-c()
+#   rightspaces<-c()
+#   
+#   YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
+#   YYYposition <- match(x = "x", table = YYYmotif)
+#   #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
+#   #just 3 letters to the left of x
+#   
+#   YYYLettersToTheLeft <- YYYposition - 1
+#   #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
+#   #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+#   YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+#   #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
+#   #variable the user puts in is
+#   
+#   
+#   if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+#     leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+#     rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+#     #add blank spaces if the motif has less than 4 letters to the left/right
+#     motif<-c(leftspaces,YYYmotif,rightspaces)
+#     #save that motif, which is the Y and +/- 4 amino acids, including truncation
+#     motif<-motif[!motif %in% "x"]
+#     motif<-paste(motif, sep="", collapse="")
+#     FTLwtletters<-motif
+#     FTLwtmotifs[i,1]<-FTLwtletters
+#     FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+#   }
+#   
+#   if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+#     motif<-YYYmotif
+#     #add blank spaces if the motif has less than 4 letters to the left/right
+#     motif<-c(leftspaces,YYYmotif,rightspaces)
+#     #save that motif, which is the Y and +/- 4 amino acids, including truncation
+#     motif<-motif[!motif %in% "x"]
+#     motif<-paste(motif, sep="", collapse="")
+#     FTLwtletters<-motif
+#     FTLwtmotifs[i,1]<-FTLwtletters
+#     FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+#     
+#     
+#   }
+#   
+# }
+
+
+
+# for (i in 1:nrow(SecondSubstrateSet)){
+#   D835letters<-SecondSubstrateSet[i,4:18]
+#   D835letters<-D835letters[D835letters !="XXXXX"]
+#   D835letters<-paste(D835letters, sep="", collapse="")
+#   leftspaces<-c()
+#   rightspaces<-c()
+#   
+#   YYYmotif <- unlist(strsplit(D835letters, split = ""))
+#   YYYposition <- match(x = "x", table = YYYmotif)
+#   #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
+#   #just 3 letters to the left of x
+#   
+#   YYYLettersToTheLeft <- YYYposition - 1
+#   #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
+#   #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+#   YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+#   #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
+#   #variable the user puts in is
+#   if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
+#     leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
+#     rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
+#     #add blank spaces if the motif has less than 4 letters to the left/right
+#     motif<-c(leftspaces,YYYmotif,rightspaces)
+#     #save that motif, which is the Y and +/- 4 amino acids, including truncation
+#     motif<-motif[!motif %in% "x"]
+#     motif<-paste(motif, sep="", collapse="")
+#     D835letters<-motif
+#     D835Ymotifs[i,1]<-D835letters
+#     D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+#   }
+#   
+#   if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
+#     motif<-YYYmotif
+#     #add blank spaces if the motif has less than 4 letters to the left/right
+#     motif<-c(leftspaces,YYYmotif,rightspaces)
+#     #save that motif, which is the Y and +/- 4 amino acids, including truncation
+#     motif<-motif[!motif %in% "x"]
+#     motif<-paste(motif, sep="", collapse="")
+#     D835letters<-motif
+#     D835Ymotifs[i,1]<-D835letters
+#     D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+#   }
+# }
+
+# for (k in 1:length(FTLwtmotifsFINAL)) {
+#   AN<-00000
+#   #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#   #destroyed immediately after use
+#   for (m in 1:ncol(Firstsubbackfreq)) {
+#     AN <- as.character(Firstsubbackfreq[1, m])
+#     if (grepl(pattern = AN,
+#               x = names(FTLwtmotifsFINAL[k]),
+#               fixed = TRUE) == TRUE) {
+#       outputmatrix <- as.character(Firstsubbackfreq[, m])
+#       outputmatrix <- matrix(outputmatrix, nrow = 1)
+#       #with that accession number, find a match in the subbackfreq file and save it here
+#       FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)
+#     }
+#   }
+# }
+# for (k in 1:length(D835YmotifsFINAL)) {
+#   #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+#   #destroyed immediately after use
+#   for (m in 1:ncol(Secondsubbackfreq)) {
+#     AN <- as.character(Secondsubbackfreq[1, m])
+#     if (grepl(pattern = AN,
+#               x = names(D835YmotifsFINAL[k]),
+#               fixed = TRUE) == TRUE) {
+#       outputmatrix <- as.character(Secondsubbackfreq[, m])
+#       outputmatrix <- matrix(outputmatrix, nrow = 1)
+#       #with that accession number, find a match in the subbackfreq file and save it here
+#       D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)
+#     }
+#   }
+# }
\ No newline at end of file
diff -r dff99bed3f56 -r 74ada21ceb70 all stuff/difference finder for 2 overlaps proper names 7-7_1-15-2019.R
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/all stuff/difference finder for 2 overlaps proper names 7-7_1-15-2019.R	Fri Apr 19 14:00:46 2019 -0400
@@ -0,0 +1,547 @@
+#Difference finder for only 2 
+
+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
+FullMotifsOnly_questionmark<-"NO"
+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
+TruncatedMotifsOnly_questionmark<-"NO"
+
+FirstSubstrateSet<- read.csv("Substrates 1A TiO2 and FeNTA no duplicates.csv", stringsAsFactors=FALSE)
+Firstsubbackfreq<- read.csv("SBF 1A TiO2 and FeNTA no duplicates.csv", header=FALSE, stringsAsFactors=FALSE)
+
+SecondSubstrateSet<- read.csv("Substrates 1B TiO2 and FeNTA no duplicates.csv", stringsAsFactors=FALSE)
+Secondsubbackfreq<- read.csv("SBF 1B TiO2 and FeNTA no duplicates.csv", header=FALSE, stringsAsFactors=FALSE)
+
+First_unshared_motifs_table<-"Substrates 1A no duplicates no negatives.csv"
+First_unshared_subbackfreq<-"SBF 1A no duplicates no negatives.csv"
+
+Second_unshared_motifs_table<-"Substrates 1B no duplicates no negatives.csv"
+Second_unshared_subbackfreq<-"SBF 1B no duplicates no negatives.csv"
+
+
+LeftOfYLetters<-7
+RightOfYLetters<-7
+
+if (FullMotifsOnly_questionmark=="YES"){
+  FirstMotifs=rep(NA,times=nrow(FirstSubstrateSet))
+  FirstAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
+  leftspaces<-c()
+  rightspaces<-c()
+  for (i in 1:nrow(FirstSubstrateSet)){
+    FirstLetters<-FirstSubstrateSet[i,7:15]
+    FirstLetters<-FirstLetters[FirstLetters !="XXXXX"]
+    FirstLetters<-paste(FirstLetters, sep="", collapse="")
+    
+    
+    YYYmotif <- unlist(strsplit(FirstLetters, split = ""))
+    YYYposition <- match(x = "x", table = YYYmotif)
+    #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
+    #just 3 letters to the left of x
+    
+    YYYLettersToTheLeft <- YYYposition - 1
+    #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
+    #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+    YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+    #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
+    #variable the user puts in is
+    
+    if (YYYLettersToTheLeft > 3 && YYYLettersToTheRight > 3) {
+      motif<-YYYmotif
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      FirstLetters<-motif
+      FirstMotifs[i]<-FirstLetters
+      FirstAccessionNumbers[i]<-FirstSubstrateSet[i,3]
+    }
+    
+  }
+  # FirstMotifs <- FirstMotifs[!is.na(FirstMotifs)]
+  # FirstMotifs<-matrix(FirstMotifs,ncol = 1)
+  # 
+  
+  SecondMotifs=rep(NA,times=nrow(FirstSubstrateSet))
+  SecondAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
+  
+  for (i in 1:nrow(SecondSubstrateSet)){
+    SecondLetters<-SecondSubstrateSet[i,7:15]
+    SecondLetters<-SecondLetters[SecondLetters !="XXXXX"]
+    SecondLetters<-paste(SecondLetters, sep="", collapse="")
+    
+    
+    YYYmotif <- unlist(strsplit(SecondLetters, split = ""))
+    YYYposition <- match(x = "x", table = YYYmotif)
+    #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
+    #just 3 letters to the left of x
+    
+    YYYLettersToTheLeft <- YYYposition - 1
+    #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
+    #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+    YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+    #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
+    #variable the user puts in is
+    
+    if (YYYLettersToTheLeft > 3 && YYYLettersToTheRight > 3) {
+      motif<-YYYmotif
+      #add blank spaces if the motif has less than 4 letters to the left/right
+      motif<-c(leftspaces,YYYmotif,rightspaces)
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      SecondLetters<-motif
+      SecondMotifs[i]<-SecondLetters
+      SecondAccessionNumbers[i]<-SecondSubstrateSet[i,3]
+    }
+  }
+  names(FirstMotifs)<-FirstAccessionNumbers
+  names(SecondMotifs)<-SecondAccessionNumbers
+  
+  
+#  ITDmotifs=rep(NA,times=nrow(FirstSubstrateSet))
+#  ITDAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))
+  if(1==0){
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,7:15]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft > 3 && YYYLettersToTheRight > 3) {
+        motif<-YYYmotif
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDmotifs[i]<-ITDletters
+        ITDAccessionNumbers[i]<-ThirdSubstrateSet[i,3]
+        
+      }
+    }
+  }  
+  #names(ITDmotifs)<-ITDAccessionNumbers
+  names(SecondMotifs)<-SecondAccessionNumbers
+  names(FirstMotifs)<-FirstAccessionNumbers
+}
+
+
+##############################################3
+#Truncated only
+if (TruncatedMotifsOnly_questionmark=="YES"){
+  FirstMotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+  FirstAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+  
+  for (i in 1:nrow(FirstSubstrateSet)){
+    FirstLetters<-FirstSubstrateSet[i,7:15]
+    FirstLetters<-FirstLetters[FirstLetters !="XXXXX"]
+    FirstLetters<-paste(FirstLetters, sep="", collapse="")
+    
+    
+    YYYmotif <- unlist(strsplit(FirstLetters, split = ""))
+    YYYposition <- match(x = "x", table = YYYmotif)
+    #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
+    #just 3 letters to the left of x
+    
+    YYYLettersToTheLeft <- YYYposition - 1
+    #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
+    #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+    YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+    #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
+    #variable the user puts in is
+    
+    if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
+      leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
+      rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
+      #add blank spaces if the motif has less than 4 letters to the left/right
+      motif<-c(leftspaces,YYYmotif,rightspaces)
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      FirstLetters<-motif
+      FirstMotifs[i,1]<-FirstLetters
+      FirstAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+    }
+    
+  }
+  
+  SecondMotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+  SecondAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+  i=2
+  for (i in 1:nrow(SecondSubstrateSet)){
+    SecondLetters<-SecondSubstrateSet[i,7:15]
+    SecondLetters<-SecondLetters[SecondLetters !="XXXXX"]
+    SecondLetters<-paste(SecondLetters, sep="", collapse="")
+    
+    
+    YYYmotif <- unlist(strsplit(SecondLetters, split = ""))
+    YYYposition <- match(x = "x", table = YYYmotif)
+    #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
+    #just 3 letters to the left of x
+    
+    YYYLettersToTheLeft <- YYYposition - 1
+    #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
+    #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+    YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+    #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
+    #variable the user puts in is
+    
+    if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
+      leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
+      rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
+      #add blank spaces if the motif has less than 4 letters to the left/right
+      motif<-c(leftspaces,YYYmotif,rightspaces)
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      SecondLetters<-motif
+      SecondAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
+      SecondMotifs[i,1]<-SecondLetters
+    }
+  }
+  
+#  ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+#  ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+  if(1==0){
+    for (i in 1:nrow(ThirdSubstrateSet)){
+      ITDletters<-ThirdSubstrateSet[i,7:15]
+      ITDletters<-ITDletters[ITDletters !="XXXXX"]
+      ITDletters<-paste(ITDletters, sep="", collapse="")
+      YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+      YYYposition <- match(x = "x", table = YYYmotif)
+      #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
+      #just 3 letters to the left of x
+      
+      YYYLettersToTheLeft <- YYYposition - 1
+      #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
+      #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+      YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+      #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
+      #variable the user puts in is
+      
+      if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
+        leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
+        rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
+        #add blank spaces if the motif has less than 4 letters to the left/right
+        motif<-c(leftspaces,YYYmotif,rightspaces)
+        #save that motif, which is the Y and +/- 4 amino acids, including truncation
+        motif<-motif[!motif %in% "x"]
+        motif<-paste(motif, sep="", collapse="")
+        ITDletters<-motif
+        ITDAccessionNumbers[i,1]<-ThirdSubstrateSet[i,3]
+        ITDmotifs[i,1]<-ITDletters
+      }
+    }
+  }
+  names(FirstMotifs)<-FirstAccessionNumbers
+  names(SecondMotifs)<-SecondAccessionNumbers
+  #names(ITDmotifs)<-ITDAccessionNumbers
+}
+
+###############################################
+#ALL motifs, full and truncated
+
+if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
+  #print("!")}
+  FirstMotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+  FirstAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
+  
+  for (i in 1:nrow(FirstSubstrateSet)){
+    FirstLetters<-FirstSubstrateSet[i,7:15]
+    FirstLetters<-FirstLetters[FirstLetters !="XXXXX"]
+    FirstLetters<-paste(FirstLetters, sep="", collapse="")
+    leftspaces<-c()
+    rightspaces<-c()
+    
+    YYYmotif <- unlist(strsplit(FirstLetters, split = ""))
+    YYYposition <- match(x = "x", table = YYYmotif)
+    #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
+    #just 3 letters to the left of x
+    
+    YYYLettersToTheLeft <- YYYposition - 1
+    #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
+    #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+    YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+    #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
+    #variable the user puts in is
+    
+    
+    if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
+      leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
+      rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
+      #add blank spaces if the motif has less than 4 letters to the left/right
+      motif<-c(leftspaces,YYYmotif,rightspaces)
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      FirstLetters<-motif
+      FirstMotifs[i,1]<-FirstLetters
+      FirstAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+    }
+    
+    if(YYYLettersToTheLeft>3 && YYYLettersToTheRight>3){
+      motif<-YYYmotif
+      #add blank spaces if the motif has less than 4 letters to the left/right
+      motif<-c(leftspaces,YYYmotif,rightspaces)
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      FirstLetters<-motif
+      FirstMotifs[i,1]<-FirstLetters
+      FirstAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+      
+      
+    }
+    
+  }
+  
+  SecondMotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
+  SecondAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
+  
+  for (i in 1:nrow(SecondSubstrateSet)){
+    SecondLetters<-SecondSubstrateSet[i,7:15]
+    SecondLetters<-SecondLetters[SecondLetters !="XXXXX"]
+    SecondLetters<-paste(SecondLetters, sep="", collapse="")
+    leftspaces<-c()
+    rightspaces<-c()
+    
+    YYYmotif <- unlist(strsplit(SecondLetters, split = ""))
+    YYYposition <- match(x = "x", table = YYYmotif)
+    #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
+    #just 3 letters to the left of x
+    
+    YYYLettersToTheLeft <- YYYposition - 1
+    #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
+    #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+    YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+    #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
+    #variable the user puts in is
+    if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
+      leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
+      rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
+      #add blank spaces if the motif has less than 4 letters to the left/right
+      motif<-c(leftspaces,YYYmotif,rightspaces)
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      SecondLetters<-motif
+      SecondMotifs[i,1]<-SecondLetters
+      SecondAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
+    }
+    
+    if(YYYLettersToTheLeft>3 && YYYLettersToTheRight>3){
+      motif<-YYYmotif
+      #add blank spaces if the motif has less than 4 letters to the left/right
+      motif<-c(leftspaces,YYYmotif,rightspaces)
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      SecondLetters<-motif
+      SecondMotifs[i,1]<-SecondLetters
+      SecondAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
+    }
+  }
+  
+  
+  #ITDmotifs=matrix(,nrow = nrow(ThirdSubstrateSet),ncol=1)
+  #ITDAccessionNumbers<-matrix(,nrow = nrow(ThirdSubstrateSet))
+  if(1==0){
+  for (i in 1:nrow(ThirdSubstrateSet)){
+    ITDletters<-ThirdSubstrateSet[i,7:15]
+    ITDletters<-ITDletters[ITDletters !="XXXXX"]
+    ITDletters<-paste(ITDletters, sep="", collapse="")
+    YYYmotif <- unlist(strsplit(ITDletters, split = ""))
+    leftspaces<-c()
+    rightspaces<-c()
+    YYYposition <- match(x = "x", table = YYYmotif)
+    #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
+    #just 3 letters to the left of x
+    
+    YYYLettersToTheLeft <- YYYposition - 1
+    #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
+    #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
+    YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
+    #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
+    #variable the user puts in is
+    if (YYYLettersToTheLeft < 4 | YYYLettersToTheRight < 4) {
+      leftspaces<-rep(" ",times=(4-YYYLettersToTheLeft))
+      rightspaces<-rep(" ",times=4-(YYYLettersToTheRight))
+      #add blank spaces if the motif has less than 4 letters to the left/right
+      motif<-c(leftspaces,YYYmotif,rightspaces)
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      ITDletters<-motif
+      ITDmotifs[i,1]<-ITDletters
+      ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+    }
+    
+    if(YYYLettersToTheLeft>3 && YYYLettersToTheRight>3){
+      motif<-YYYmotif
+      #add blank spaces if the motif has less than 4 letters to the left/right
+      motif<-c(leftspaces,YYYmotif,rightspaces)
+      #save that motif, which is the Y and +/- 4 amino acids, including truncation
+      motif<-motif[!motif %in% "x"]
+      motif<-paste(motif, sep="", collapse="")
+      ITDletters<-motif
+      ITDmotifs[i,1]<-ITDletters
+      ITDAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
+    }
+  }
+  }
+  names(FirstMotifs)<-FirstAccessionNumbers
+  names(SecondMotifs)<-SecondAccessionNumbers
+  #names(ITDmotifs)<-ITDAccessionNumbers
+}
+
+
+FirstMotifsFINAL<-FirstMotifs[!FirstMotifs %in% SecondMotifs]
+#FirstMotifsFINAL<-FirstMotifsFINAL[!FirstMotifsFINAL %in% ITDmotifs]
+FirstMotifsFINAL<-FirstMotifsFINAL[!duplicated(FirstMotifsFINAL)]
+
+
+# ITDmotifsFINAL<-ITDmotifs[!ITDmotifs %in% SecondMotifs]
+# ITDmotifsFINAL<-ITDmotifsFINAL[!ITDmotifsFINAL %in% FirstMotifs]
+# ITDmotifsFINAL<-ITDmotifsFINAL[!duplicated(ITDmotifsFINAL)]
+
+
+SecondMotifsFINAL<-SecondMotifs[!SecondMotifs %in% FirstMotifs]
+#SecondMotifsFINAL<-SecondMotifsFINAL[!SecondMotifsFINAL %in% ITDmotifs]
+SecondMotifsFINAL<-SecondMotifsFINAL[!duplicated(SecondMotifsFINAL)]
+
+
+columnalheader<-c(rep(NA,36))
+FirstFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+
+for (k in 1:length(FirstMotifsFINAL)) {
+  AN<-00000
+  #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+  #destroyed immediately after use
+  for (m in 2:ncol(Firstsubbackfreq)) {
+    AN <- as.character(Firstsubbackfreq[2, m])
+    #print(AN)}
+    if (grepl(pattern = AN,
+              x = names(FirstMotifsFINAL[k]),
+              fixed = TRUE) == TRUE) {
+      outputmatrix <- as.character(Firstsubbackfreq[, m])
+      outputmatrix <- matrix(outputmatrix, nrow = 1)
+      #with that accession number, find a match in the subbackfreq file and save it here
+      FirstFinalMatrix<-rbind(FirstFinalMatrix,outputmatrix)
+      #      print(AN,outputmatrix)}
+    }
+  }
+}
+FirstFinalMatrix<-FirstFinalMatrix[!duplicated(FirstFinalMatrix),]
+
+#columnalheader<-c(rep(NA,36))
+#ITDFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+
+if(1==0){
+  for (k in 1:length(ITDmotifsFINAL)) {
+    AN<-00000
+    #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+    #destroyed immediately after use
+    for (m in 1:ncol(Thirdsubbackfreq)) {
+      AN <- as.character(Thirdsubbackfreq[1, m])
+      if (grepl(pattern = AN,
+                x = names(ITDmotifsFINAL[k]),
+                fixed = TRUE) == TRUE) {
+        outputmatrix <- as.character(Thirdsubbackfreq[, m])
+        outputmatrix <- matrix(outputmatrix, nrow = 1)
+        #with that accession number, find a match in the subbackfreq file and save it here
+        ITDFinalMatrix<-rbind(ITDFinalMatrix,outputmatrix)
+      }
+    }
+  }
+  ITDFinalMatrix<-ITDFinalMatrix[!duplicated(ITDFinalMatrix),]
+}
+
+columnalheader<-c(rep(NA,36))
+SecondFinalMatrix<-matrix(data =columnalheader,nrow = 1)
+
+for (k in 1:length(SecondMotifsFINAL)) {
+  #I don't remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is
+  #destroyed immediately after use
+  for (m in 1:ncol(Secondsubbackfreq)) {
+    AN <- as.character(Secondsubbackfreq[1, m])
+    if (grepl(pattern = AN,
+              x = names(SecondMotifsFINAL[k]),
+              fixed = TRUE) == TRUE) {
+      outputmatrix <- as.character(Secondsubbackfreq[, m])
+      outputmatrix <- matrix(outputmatrix, nrow = 1)
+      #with that accession number, find a match in the subbackfreq file and save it here
+      SecondFinalMatrix<-rbind(SecondFinalMatrix,outputmatrix)
+    }
+  }
+}
+SecondFinalMatrix<-SecondFinalMatrix[!duplicated(SecondFinalMatrix),]
+FTLoutputmatrix<-matrix(data=c(FirstMotifsFINAL,names(FirstMotifsFINAL)),ncol = 2)
+
+
+write.table(x=FTLoutputmatrix,
+            file=First_unshared_motifs_table,
+            quote=FALSE, sep=",",
+            row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+
+columnalheader<-c(as.character(Firstsubbackfreq[1:36,1]))
+columnalheader<-matrix(columnalheader,nrow = 1)
+write.table(x=columnalheader,
+            file=First_unshared_subbackfreq,
+            quote=FALSE, sep=",",
+            row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+FirstFinalMatrix<-FirstFinalMatrix[2:nrow(FirstFinalMatrix),]
+write.table(x=FirstFinalMatrix,
+            file=First_unshared_subbackfreq,
+            quote=FALSE, sep=",",
+            row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+
+############################################################################################################
+
+D835Youtputmatrix<-matrix(data=c(SecondMotifsFINAL,names(SecondMotifsFINAL)),ncol = 2)
+
+write.table(x=D835Youtputmatrix,
+            file=Second_unshared_motifs_table,
+            quote=FALSE, sep=",",
+            row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+
+columnalheader<-c(as.character(Firstsubbackfreq[1:36,1]))
+columnalheader<-matrix(columnalheader,nrow = 1)
+write.table(x=columnalheader,
+            file=Second_unshared_subbackfreq,
+            quote=FALSE, sep=",",
+            row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+SecondFinalMatrix<-SecondFinalMatrix[2:nrow(SecondFinalMatrix),]  
+write.table(x=SecondFinalMatrix,
+            file=Second_unshared_subbackfreq,
+            quote=FALSE, sep=",",
+            row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+
+############################################################################################################
+
+# ITDoutputmatrix<-matrix(data = c(ITDmotifsFINAL,names(ITDmotifsFINAL)),ncol = 2)
+# 
+# write.table(x=ITDoutputmatrix,
+#             file=Third_unshared_motifs_table,
+#             quote=FALSE, sep=",",
+#             row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+# 
+# columnalheader<-c(as.character(Thirdsubbackfreq[1:36,1]))
+# columnalheader<-matrix(columnalheader,nrow = 1)
+# write.table(x=columnalheader,
+#             file=Third_unshared_subbackfreq,
+#             quote=FALSE, sep=",",
+#             row.names=FALSE,col.names = FALSE, na="", append=TRUE)
+# ITDFinalMatrix<-ITDFinalMatrix[2:nrow(ITDFinalMatrix),]
+# write.table(x=ITDFinalMatrix,
+#             file=Third_unshared_subbackfreq,
+#             quote=FALSE, sep=",",
+#             row.names=FALSE,col.names = FALSE, na="", append=TRUE)
\ No newline at end of file
diff -r dff99bed3f56 -r 74ada21ceb70 all stuff/differenceFinder.xml
--- a/all stuff/differenceFinder.xml	Fri Apr 19 10:57:28 2019 -0400
+++ b/all stuff/differenceFinder.xml	Fri Apr 19 14:00:46 2019 -0400
@@ -1,4 +1,4 @@
-<tool id="commonality_r" name="difference_finder" version="1.0.0">
+<tool id="commonality_r" name="difference_finder" version="17.0.0">
     <description>finds differences</description>
     <requirements>
        <requirement type="package">R</requirement>