| Previous changeset 8:4dd15c41d9e7 (2019-04-19) Next changeset 10:78f16bc92ba6 (2020-02-21) |
|
Commit message:
Uploaded |
|
modified:
all stuff/differenceFinder.xml |
|
added:
all stuff/.RData all stuff/.Rhistory all stuff/1RS.csv all stuff/1RSBF.csv all stuff/2RS.csv all stuff/2RSBF.csv all stuff/Difference finder for GalaxyP 2-21-20.R all stuff/Difference finder for GalaxyP working.R |
|
removed:
all stuff/Commonality and Difference finderMADE 7 TO 7 1-15-2019.R all stuff/Commonality and Difference finderMADE 7 TO 7.R all stuff/Difference finder MADE 7 TO 7 4-18-2019.R all stuff/Difference finder for GalaxyP 4-18-2019.R all stuff/Difference finderMADE 7 TO 7 1-15-2019.R all stuff/Difference finderMADE 7 TO 7 fastversion 2-14-2019.R all stuff/Difference finderMADE 7 TO 7 fastversion.R all stuff/difference finder for 2 overlaps proper names 7-7_1-15-2019.R |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/.RData |
| b |
| Binary file all stuff/.RData has changed |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/.Rhistory --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/all stuff/.Rhistory Fri Feb 21 13:07:45 2020 -0500 |
| [ |
| b'@@ -0,0 +1,288 @@\n+?rnorm\n+?rnorm\n+?rnorm\n+pwr\n+?pwr\n+??pwr\n+power.t.test(n=6, power = .7, type = "two.sample", alternative = "two.sided")\n+power.t.test(n=6, power = .9, type = "two.sample", alternative = "two.sided")\n+?power.t.test\n+power.t.test(n=5, sd=1000, power = .7, type = "paired", alternative = "one.sided")\n+10^4\n+power.t.test(n=5, sd=10000, power = .7, type = "paired", alternative = "one.sided")\n+power.t.test(n=10, delta = 7, sd=10, type = "paired", alternative = "one.sided")\n+setwd("C:/Users/John Blankenhor/Downloads/difference_finder-4dd15c41d9e7/difference_finder-4dd15c41d9e7/all stuff")\n+#put the names of your input files here\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\n+Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)\n+FirstSubstrateSet\n+EmptySubHeader<-First_unshared_motifs_table[1,]\n+First_unshared_motifs_table<-"1RS.csv"\n+First_unshared_subbackfreq<-"1RSBF.csv"\n+#put the names of your input files here\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\n+Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)\n+EmptySubHeader<-FirstSubstrateSet[1,]\n+head(Firstsubbackfreq)\n+EmptySBFHeader<-Firstsubbackfreq[,1]\n+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\n+FullMotifsOnly_questionmark<-"NO"\n+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\n+TruncatedMotifsOnly_questionmark<-"NO"\n+#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)\n+Are_You_Looking_For_Commonality<-"NO"\n+#put the names of your input files here\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\n+Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)\n+SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE)\n+Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)\n+First_unshared_motifs_table<-"1RS.csv"\n+First_unshared_subbackfreq<-"1RSBF.csv"\n+Second_unshared_motifs_table<-"2RS.csv"\n+Second_unshared_subbackfreq<-"2RSBF.csv"\n+EmptySubHeader<-FirstSubstrateSet[1,]\n+EmptySBFHeader<-Firstsubbackfreq[,1]\n+FirstCentralLetters<-FirstSubstrateSet[,11]\n+SecondCentralLetters<-SecondSubstrateSet[,11]\n+FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)\n+FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)\n+FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\n+SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)\n+SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)\n+SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")\n+FirstCentralLetters->FirstSubstrateSet[,11]\n+SecondCentralLetters->SecondSubstrateSet[,11]\n+if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){\n+FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)\n+FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)\n+for (i in 1:nrow(FirstSubstrateSet)){\n+FTLwtletters<-FirstSubstrateSet[i,4:18]\n+FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]\n+FTLwtletters<-paste(FTLwtletters, sep="", collapse="")\n+leftspaces<-c()\n+rightspaces<-c()\n+YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))\n+YYYposition <- match(x = "x", table = YYYmotif)\n+#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\n+#just 3 letters to the left of x\n+YYYLettersToTheLeft <- YYYposition - 1\n+#how many letters to th'..b're is\n+#just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1\n+YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1\n+#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\n+#variable the user puts in is\n+if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {\n+leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))\n+rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))\n+#add blank spaces if the motif has less than 4 letters to the left/right\n+motif<-c(leftspaces,YYYmotif,rightspaces)\n+#save that motif, which is the Y and +/- 4 amino acids, including truncation\n+motif<-motif[!motif %in% "x"]\n+motif<-paste(motif, sep="", collapse="")\n+D835letters<-motif\n+D835Ymotifs[i,1]<-D835letters\n+D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]\n+}\n+if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){\n+motif<-YYYmotif\n+#add blank spaces if the motif has less than 4 letters to the left/right\n+motif<-c(leftspaces,YYYmotif,rightspaces)\n+#save that motif, which is the Y and +/- 4 amino acids, including truncation\n+motif<-motif[!motif %in% "x"]\n+motif<-paste(motif, sep="", collapse="")\n+D835letters<-motif\n+D835Ymotifs[i,1]<-D835letters\n+D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]\n+}\n+}\n+names(FTLwtmotifs)<-FTLwtAccessionNumbers\n+names(D835Ymotifs)<-D835YAccessionNumbers\n+}\n+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\n+FullMotifsOnly_questionmark<-"NO"\n+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\n+TruncatedMotifsOnly_questionmark<-"NO"\n+#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)\n+Are_You_Looking_For_Commonality<-"NO"\n+#put the names of your input files here\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\n+Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)\n+SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE)\n+Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)\n+First_unshared_motifs_table<-"1RS.csv"\n+First_unshared_subbackfreq<-"1RSBF.csv"\n+Second_unshared_motifs_table<-"2RS.csv"\n+Second_unshared_subbackfreq<-"2RSBF.csv"\n+EmptySubHeader<-FirstSubstrateSet[1,]\n+EmptySBFHeader<-Firstsubbackfreq[,1]\n+FirstCentralLetters<-FirstSubstrateSet[,11]\n+SecondCentralLetters<-SecondSubstrateSet[,11]\n+FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)\n+FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)\n+FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\n+SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)\n+SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)\n+SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")\n+FirstCentralLetters->FirstSubstrateSet[,11]\n+SecondCentralLetters->SecondSubstrateSet[,11]\n+FirstSubstrateSet\n+#put the names of your input files here\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\n+FirstSubstrateSet\n+head(SecondSubstrateSet)\n+#put the names of your input files here\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\n+head(SecondSubstrateSet)\n+FirstSubstrateSet\n+#put the names of your input files here\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\n+FirstSubstrateSet\n+#put the names of your input files here\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\n+SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE)\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/1RS.csv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/all stuff/1RS.csv Fri Feb 21 13:07:45 2020 -0500 |
| b |
| b'@@ -0,0 +1,521 @@\n+Substrate,Species,Reference,-7,-6,-5,-4,-3,-2,-1,0,1,2,3,4,5,6,7,Phosphite\r\n+,,sp|P48735|IDHP_HUMAN,E,A,E,A,A,H,G,xT,V,T,R, , , , ,\r\n+,,sp|P29401|TKT_HUMAN, , , , , , ,S,xT,F,A,A,F,F,T,R,\r\n+,,sp|P30050|RL12_HUMAN, , , , , , ,L,xT,I,Q,N,R, , , ,\r\n+,,sp|P56556|NDUA6_HUMAN, , , ,Q,A,T,S,xT,A,S,T,F,V,K,P,\r\n+,,sp|Q14554|PDIA5_HUMAN, , , , ,G,F,P,xT,I,C,Y,F,E,K, ,\r\n+,,sp|P29401|TKT_HUMAN, , , , ,H,Q,P,xT,A,I,I,A,K, , ,\r\n+,,sp|P29401|TKT_HUMAN, , , , , ,N,S,xT,F,S,E,I,F,K, ,\r\n+,,sp|Q00839|HNRPU_HUMAN, , , , , , ,S,xS,G,P,T,S,L,F,A,\r\n+,,sp|Q8IXT5|RB12B_HUMAN, , , , , , , ,xS,P,T,E,D,F,R, ,\r\n+,,sp|P52566|GDIR2_HUMAN, , , , , , ,A,xT,F,M,V,G,S,Y,G,\r\n+,,sp|Q9H9T3|ELP3_HUMAN, , , , ,L,Y,P,xT,L,V,I,R, , , ,\r\n+,,sp|Q9UBT2|SAE2_HUMAN, , ,G,T,I,L,I,xS,S,E,E,G,E,T,E,\r\n+,,sp|Q9Y490|TLN1_HUMAN, , , ,E,G,T,E,xT,F,A,D,H,R, , ,\r\n+,,sp|Q9NY61|AATF_HUMAN,G,M,D,D,L,G,S,xS,E,E,E,E,D,E,E,\r\n+,,sp|P29218|IMPA1_HUMAN, , , ,Y,P,S,H,xS,F,I,G,E,E,S,V,\r\n+,,sp|P29401|TKT_HUMAN, , , , , , , ,xS,T,F,A,A,F,F,T,\r\n+,,sp|P07900|HS90A_HUMAN, , , , , , ,E,xS,E,D,K,P,E,I,E,\r\n+,,sp|P28070|PSB4_HUMAN,N,S,T,M,L,G,A,xS,G,D,Y,A,D,F,Q,\r\n+,,sp|Q13564|ULA1_HUMAN, , , , , , ,Q,xT,P,S,F,W,I,L,A,\r\n+,,sp|P09429|HMGB1_HUMAN; sp|P26583|HMGB2_HUMAN, , , , ,R,P,P,xS,A,F,F,L,F, , ,\r\n+,,sp|Q71UM5|RS27L_HUMAN; sp|P42677|RS27_HUMAN, , ,L,T,E,G,C,xS,F,R, , , , , ,\r\n+,,sp|P00505|AATM_HUMAN, , , ,V,G,A,F,xT,M,V,C,K, , , ,\r\n+,,sp|O43175|SERA_HUMAN, , , , , ,A,G,xT,G,V,D,N,V,D,L,\r\n+,,sp|P07437|TBB5_HUMAN,V,T,F,I,G,N,S,xT,A,I,Q,E,L,F,K,\r\n+,,sp|P10599|THIO_HUMAN, , , , ,C,M,P,xT,F,Q,F,F,K, , ,\r\n+,,sp|Q9UQ35|SRRM2_HUMAN, , , , , ,S,P,xS,V,S,S,P,E,P,A,\r\n+,,sp|P40926|MDHM_HUMAN, , , ,A,G,A,G,xS,A,T,L,S,M,A,Y,\r\n+,,sp|Q96FS4|SIPA1_HUMAN,A,G,E,A,R,P,P,xT,P,A,S,P,R, , ,\r\n+,,sp|Q9H0D6|XRN2_HUMAN, ,K,A,E,D,S,D,xS,E,P,E,P,E,D,N,\r\n+,,sp|P07814|SYEP_HUMAN, ,A,I,Q,G,G,T,xS,H,H,L,G,Q,N,F,\r\n+,,sp|P16403|H12_HUMAN; sp|P16401|H15_HUMAN, , , , , , ,G,xT,L,V,Q,T,K, , ,\r\n+,,sp|Q92733|PRCC_HUMAN,P,E,L,H,K,G,D,xS,D,S,E,E,D,E,P,\r\n+,,sp|Q9UHB9|SRP68_HUMAN, , , , , ,F,E,xT,F,C,L,D,P,S,L,\r\n+,,sp|P46781|RS9_HUMAN, , , , ,R,L,Q,xT,Q,V,F,K, , , ,\r\n+,,sp|Q93084|AT2A3_HUMAN; sp|P16615|AT2A2_HUMAN, , , , , ,T,G,xT,L,T,T,N,Q,M,S,\r\n+,,sp|P07237|PDIA1_HUMAN, , , , , ,V,H,xS,F,P,T,L,K, , ,\r\n+,,sp|Q9Y3T9|NOC2L_HUMAN, , , , , , , ,xS,P,D,K,P,G,G,S,\r\n+,,sp|O00264|PGRC1_HUMAN; sp|O15173|PGRC2_HUMAN, , , , ,G,L,A,xT,F,C,L,D,K, , ,\r\n+,,sp|Q9NVI7|ATD3A_HUMAN; sp|Q5T9A4|ATD3B_HUMAN, , , , , ,A,G,xT,L,F,G,E,G,F,R,\r\n+,,sp|O94903|PLPHP_HUMAN, , , , , , ,G,xS,T,I,F,G,E,R, ,\r\n+,,sp|O15530|PDPK1_HUMAN, ,A,N,S,F,V,G,xT,A,Q,Y,V,S,P,E,\r\n+,,sp|Q96RP9|EFGM_HUMAN, , , , ,K,G,D,xT,I,Y,N,T,R, , ,\r\n+,,sp|Q9UBS9|SUCO_HUMAN, , , , , ,L,G,xT,F,H,G,R, , , ,\r\n+,,sp|Q14697|GANAB_HUMAN, , , , , ,G,G,xT,I,V,P,R, , , ,\r\n+,,sp|Q13057|COASY_HUMAN, , ,G,A,V,G,G,xT,F,D,R, , , , ,\r\n+,,sp|P25205|MCM3_HUMAN, ,G,G,Y,T,S,G,xT,F,R, , , , , ,\r\n+,,sp|P08559|ODPA_HUMAN, , , , , ,G,G,xS,M,H,M,Y,A,K, ,\r\n+,,sp|Q69YN4|VIR_HUMAN, , , ,K,Q,N,T,xS,R,P,P,S,M,H,V,\r\n+,,sp|Q9UQ35|SRRM2_HUMAN, , , , , , , ,xS,P,G,M,L,E,P,L,\r\n+,,sp|P60866|RS20_HUMAN, , , , , , ,I,xT,L,T,S,R, , , ,\r\n+,,sp|P07900|HS90A_HUMAN, ,E,R,D,K,E,V,xS,D,D,E,A,E,E,K,\r\n+,,sp|O75449|KTNA1_HUMAN; sp|Q9BW62|KATL1_HUMAN, , , , , , ,T,xT,F,F,N,V,S,S,S,\r\n+,,sp|P06744|G6PI_HUMAN, , , , , ,T,F,xT,T,Q,E,T,I,T,N,\r\n+,,sp|P42166|LAP2A_HUMAN, , , , , ,S,S,xT,P,L,P,T,I,S,S,\r\n+,,sp|P39656|OST48_HUMAN, , , , , , ,S,xS,L,N,P,I,L,F,R,\r\n+,,sp|Q9H583|HEAT1_HUMAN, , , , , ,L,L,xT,F,Y,N,L,A,D,C,\r\n+,,sp|O60942|MCE1_HUMAN, ,G,H,G,E,C,P,xT,T,E,N,T,E,T,F,\r\n+,,sp|Q01469|FABP5_HUMAN, , , , , , ,K,xT,Q,T,V,C,N,F,T,\r\n+,,sp|Q9NYF8|BCLF1_HUMAN, , , , , ,Q,K,xS,P,E,I,H,R, , ,\r\n+,,sp|P17844|DDX5_HUMAN, , , , , ,T,G,xT,A,Y,T,F,F,T,P,\r\n+,,sp|Q69YN4|VIR_HUMAN,Q,N,T,S,R,P,P,xS,M,H,V,D,D,F,V,\r\n+,,sp|P28070|PSB4_HUMAN, , , ,V,N,N,S,xT,M,L,G,A,S,G,D,\r\n+,,sp|P11940|PABP1_HUMAN, , , ,A,L,Y,D,xT,F,S,A,F,G,N,I,\r\n+,,sp|Q12905|ILF2_HUMAN,P,Q,G,E,E,E,E,xS,M,E,T,Q,E, , ,\r\n+,,sp|Q7Z5L9|I2BP2_HUMAN, , , , , , , ,xS,P,P,G,A,A,A,S,\r\n+,,sp|Q69YN4|VIR_H'..b'M1_HUMAN, , , , ,D,T,D,xS,E,E,E,I,R, , ,\r\n+,,sp|O60841|IF2P_HUMAN, , , , ,I,N,S,xS,G,E,S,G,D,E,S,\r\n+,,sp|Q14676|MDC1_HUMAN, , , , ,D,S,D,xT,D,V,E,E,E,E,L,\r\n+,,sp|P06748|NPM_HUMAN, , , , , , ,E,xS,E,D,E,E,E,E,D,\r\n+,,sp|P47712|PA24A_HUMAN,V,S,N,D,S,S,D,xS,D,D,E,S,H,E,P,\r\n+,,sp|P20674|COX5A_HUMAN, , , , ,G,I,N,xT,L,V,T,Y,D,M,V,\r\n+,,sp|Q5T200|ZC3HD_HUMAN, , , , , , , ,xS,P,S,H,L,T,E,D,\r\n+,,sp|Q99733|NP1L4_HUMAN,D,A,E,S,E,W,H,xS,E,N,E,E,E,E,K,\r\n+,,sp|P51398|RT29_HUMAN, , , , , ,N,T,xS,F,A,Y,P,A,I,R,\r\n+,,sp|P62280|RS11_HUMAN, , , , , ,Q,P,xT,I,F,Q,N,K, , ,\r\n+,,sp|Q7L2H7|EIF3M_HUMAN, , , , , ,W,I,xS,D,W,N,L,T,T,E,\r\n+,,sp|Q9UQ80|PA2G4_HUMAN, , , , , , , ,xT,I,I,Q,N,P,T,D,\r\n+,,sp|Q13769|THOC5_HUMAN,S,Q,D,D,E,S,D,xS,D,A,E,E,E,Q,T,\r\n+,,sp|Q14676|MDC1_HUMAN, , , , , , ,D,xS,D,T,D,V,E,E,E,\r\n+,,sp|P01911|2B1F_HUMAN; sp|P04440|DPB1_HUMAN, , , , , ,F,D,xS,D,V,G,E,F,R, ,\r\n+,,sp|Q5H9R7|PP6R3_HUMAN,Q,Q,F,D,D,G,G,xS,D,E,E,D,I,W,E,\r\n+,,sp|P36578|RL4_HUMAN, ,L,D,E,L,Y,G,xT,W,R, , , , , ,\r\n+,,sp|Q08945|SSRP1_HUMAN, , ,E,G,M,N,P,xS,Y,D,E,Y,A,D,S,\r\n+,,sp|P49585|PCY1A_HUMAN, , , , , , , ,xS,P,S,P,S,F,R, ,\r\n+,,sp|Q15653|IKBB_HUMAN, , ,S,G,P,C,S,xS,S,S,D,S,D,S,G,\r\n+,,sp|Q53EZ4|CEP55_HUMAN, , , , , , , ,xS,P,T,A,A,L,N,E,\r\n+,,sp|P51531|SMCA2_HUMAN, , ,A,K,P,V,V,xS,D,F,D,S,D,E,E,\r\n+,,sp|Q13111|CAF1A_HUMAN, , , , ,S,P,S,xT,T,Y,L,H,T,P,T,\r\n+,,sp|Q9BVC4|LST8_HUMAN, ,T,V,Q,H,Q,D,xS,Q,V,N,A,L,E,V,\r\n+,,sp|P07900|HS90A_HUMAN, , ,N,P,D,D,I,xT,N,E,E,Y,G,E,F,\r\n+,,sp|O15530|PDPK1_HUMAN, ,Q,V,S,S,S,S,xS,S,H,S,L,S,A,S,\r\n+,,sp|Q01543|FLI1_HUMAN, , , , , , , ,xS,P,P,L,G,G,A,Q,\r\n+,,sp|P29692|EF1D_HUMAN,D,D,I,D,L,F,G,xS,D,N,E,E,E,D,K,\r\n+,,sp|P46776|RL27A_HUMAN, , , , , ,N,Q,xS,F,C,P,T,V,N,L,\r\n+,,sp|Q9NYB0|TE2IP_HUMAN, , , , , , , ,xS,P,S,S,V,T,G,N,\r\n+,,sp|P08238|HS90B_HUMAN, ,K,I,E,D,V,G,xS,D,E,E,D,D,S,G,\r\n+,,sp|Q99880|H2B1L_HUMAN; sp|Q99879|H2B1M_HUMAN; sp|Q99877|H2B1N_HUMAN; sp|Q93079|H2B1H_HUMAN; sp|P62807|H2B1C_HUMAN; sp|P58876|H2B1D_HUMAN; sp|O60814|H2B1K_HUMAN; sp|Q5QNW6|H2B2F_HUMAN; sp|P57053|H2BFS_HUMAN; sp|Q16778|H2B2E_HUMAN; sp|P33778|H2B1B_HUMAN; sp|P23527|H2B1O_HUMAN; sp|P06899|H2B1J_HUMAN; sp|Q8N257|H2B3B_HUMAN, , ,Q,V,H,P,D,xT,G,I,S,S,K, , ,\r\n+,,sp|P60484|PTEN_HUMAN, , , , ,Y,S,D,xT,T,D,S,D,P,E,N,\r\n+,,sp|P51858|HDGF_HUMAN, ,G,N,A,E,G,S,xS,D,E,E,G,K,L,V,\r\n+,,sp|Q15056|IF4H_HUMAN, , , , ,A,Y,S,xS,F,G,G,G,R, , ,\r\n+,,sp|P62308|RUXG_HUMAN; sp|A8MWD9|RUXGL_HUMAN, , , , , ,G,N,xS,I,I,M,L,E,A,L,\r\n+,,sp|P51532|SMCA4_HUMAN, , ,A,K,P,V,V,xS,D,D,D,S,E,E,E,\r\n+,,sp|Q02790|FKBP4_HUMAN, , , ,E,G,T,G,xT,E,M,P,M,I,G,D,\r\n+,,sp|Q13111|CAF1A_HUMAN, , , ,S,P,S,T,xT,Y,L,H,T,P,T,P,\r\n+,,sp|Q6UN15|FIP1_HUMAN; tr|A0A0B4J203|A0A0B4J203_HUMAN,E,D,D,S,D,S,D,xS,D,D,D,E,D,D,V,\r\n+,,sp|P05387|RLA2_HUMAN, ,K,E,E,S,E,E,xS,D,D,D,M,G,F,G,\r\n+,,sp|P52756|RBM5_HUMAN,V,A,A,Y,S,G,D,xS,D,N,E,E,E,L,V,\r\n+,,sp|O95671|ASML_HUMAN,D,S,I,P,A,A,D,xT,F,E,D,L,S,D,V,\r\n+,,sp|Q15653|IKBB_HUMAN, , , ,S,G,P,C,xS,S,S,S,D,S,D,S,\r\n+,,RRRRRsp|Q6NYC8|PPR18_HUMAN, ,E,A,L,L,E,E,xS,R,Q,Q,Q,Q,Q,Q,\r\n+,,sp|P06748|NPM_HUMAN, , , , , , ,V,xT,L,A,T,L,K, , ,\r\n+,,sp|Q13111|CAF1A_HUMAN,T,T,Y,L,H,T,P,xT,P,S,E,D,A,A,I,\r\n+,,sp|P06454|PTMA_HUMAN,S,D,A,A,V,D,T,xS,S,E,I,T,T,K, ,\r\n+,,sp|Q99439|CNN2_HUMAN, , , , , ,D,G,xT,I,L,C,T,L,M,N,\r\n+,,sp|O15530|PDPK1_HUMAN, , , ,Q,V,S,S,xS,S,S,S,H,S,L,S,\r\n+,,sp|P08238|HS90B_HUMAN, , , , ,D,N,S,xT,M,G,Y,M,M,A,K,\r\n+,,sp|P51531|SMCA2_HUMAN, ,I,A,K,E,E,E,xS,E,D,E,S,N,E,E,\r\n+,,sp|Q92608|DOCK2_HUMAN, , , , , , ,Q,xT,V,I,S,E,N,Y,L,\r\n+,,sp|O00170|AIP_HUMAN,L,H,S,D,D,E,G,xT,V,L,D,D,S,R, ,\r\n+,,sp|O15530|PDPK1_HUMAN, , ,Q,V,S,S,S,xS,S,S,H,S,L,S,A,\r\n+,,sp|P07900|HS90A_HUMAN, , , , , , , ,xT,L,V,S,V,T,K, ,\r\n+,,sp|Q99880|H2B1L_HUMAN; sp|Q99879|H2B1M_HUMAN; sp|Q99877|H2B1N_HUMAN; sp|Q93079|H2B1H_HUMAN; sp|P62807|H2B1C_HUMAN; sp|P58876|H2B1D_HUMAN; sp|O60814|H2B1K_HUMAN; sp|Q5QNW6|H2B2F_HUMAN; sp|P57053|H2BFS_HUMAN, , , , , , ,E,xS,Y,S,V,Y,V,Y,K,\r\n+,,sp|Q86UX7|URP2_HUMAN, , , , , ,Y,Y,xS,F,F,D,L,D,P,K,\r\n+,,sp|Q6KC79|NIPBL_HUMAN, , , , , ,V,D,xS,D,S,D,S,D,S,E,\r\n+,,sp|Q9NRG0|CHRC1_HUMAN,E,N,D,N,D,N,E,xS,D,H,D,E,A,D,S,\r\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/1RSBF.csv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/all stuff/1RSBF.csv Fri Feb 21 13:07:45 2020 -0500 |
| b |
| b'@@ -0,0 +1,457 @@\n+Accession Numbers,Amino Acids,A,C,D,E,F,G,H,I,K,L,M,N,P,Q,R,S,T,V,W,Y,Properties,Hydrophobic,Polar,Small,Negative,Postive,Amide,Large Aliphatic,Small Aliphatic,Aromatic,Hydroxy,X,Number of ST,Number of pST\r\n+sp|P48735|IDHP_HUMAN,7.522123894,1.769911504,7.079646018,4.646017699,4.424778761,7.743362832,2.876106195,6.415929204,7.96460177,6.85840708,2.654867257,3.318584071,4.203539823,3.982300885,5.530973451,4.867256637,6.85840708,6.194690265,1.991150442,3.097345133,,48.67256637,35.39823009,49.55752212,11.72566372,16.37168142,7.300884956,13.27433628,21.46017699,9.513274336,11.72566372,,53,2,452\r\n+sp|P29401|TKT_HUMAN,11.71749599,1.926163724,5.617977528,5.617977528,3.852327448,7.223113965,2.728731942,7.544141252,6.741573034,7.383627608,2.086677368,3.210272873,4.494382022,4.173354735,4.654895666,6.741573034,5.136436597,5.778491172,0.642054575,2.728731942,,50.88282504,32.74478331,51.8459069,11.23595506,14.12520064,7.383627608,14.92776886,24.71910112,7.223113965,11.87800963,,74,5,623\r\n+sp|P29401|TKT_HUMAN,11.71749599,1.926163724,5.617977528,5.617977528,3.852327448,7.223113965,2.728731942,7.544141252,6.741573034,7.383627608,2.086677368,3.210272873,4.494382022,4.173354735,4.654895666,6.741573034,5.136436597,5.778491172,0.642054575,2.728731942,,50.88282504,32.74478331,51.8459069,11.23595506,14.12520064,7.383627608,14.92776886,24.71910112,7.223113965,11.87800963,,74,2,623\r\n+sp|P30050|RL12_HUMAN,8.484848485,1.818181818,6.060606061,4.848484848,1.212121212,8.484848485,2.424242424,10.3030303,9.090909091,6.666666667,1.212121212,4.242424242,6.666666667,3.636363636,6.060606061,6.060606061,4.848484848,6.666666667,0.606060606,0.606060606,,46.06060606,36.36363636,53.33333333,10.90909091,17.57575758,7.878787879,16.96969697,23.63636364,2.424242424,10.90909091,,18,1,165\r\n+sp|P56556|NDUA6_HUMAN,5.46875,0,5.46875,7.03125,6.25,3.90625,3.90625,3.90625,8.59375,4.6875,4.6875,2.34375,4.6875,3.125,10.15625,3.90625,7.03125,10.9375,1.5625,2.34375,,43.75,40.625,43.75,12.5,22.65625,5.46875,8.59375,20.3125,10.15625,10.9375,,14,4,128\r\n+sp|Q14554|PDIA5_HUMAN,8.285163776,2.504816956,5.780346821,8.092485549,5.202312139,4.624277457,3.66088632,2.504816956,10.40462428,8.670520231,2.119460501,2.697495183,6.165703276,3.082851638,4.046242775,5.009633911,4.238921002,6.936416185,2.312138728,3.66088632,,46.82080925,37.76493256,46.24277457,13.87283237,18.11175337,5.780346821,11.17533719,19.84585742,11.17533719,9.248554913,,48,2,519\r\n+sp|Q00839|HNRPU_HUMAN,7.393939394,1.575757576,4.848484848,10.66666667,3.757575758,13.57575758,1.575757576,2.424242424,8.484848485,5.575757576,2.303030303,5.090909091,5.090909091,5.818181818,5.454545455,4.848484848,3.272727273,4.242424242,0.727272727,3.272727273,,44.84848485,41.93939394,49.93939394,15.51515152,15.51515152,10.90909091,8,25.21212121,7.757575758,8.121212121,,67,5,825\r\n+sp|Q00839|HNRPU_HUMAN,7.393939394,1.575757576,4.848484848,10.66666667,3.757575758,13.57575758,1.575757576,2.424242424,8.484848485,5.575757576,2.303030303,5.090909091,5.090909091,5.818181818,5.454545455,4.848484848,3.272727273,4.242424242,0.727272727,3.272727273,,44.84848485,41.93939394,49.93939394,15.51515152,15.51515152,10.90909091,8,25.21212121,7.757575758,8.121212121,,67,2,825\r\n+sp|Q8IXT5|RB12B_HUMAN,3.196803197,0.599400599,8.091908092,9.99000999,8.391608392,6.193806194,3.796203796,3.996003996,4.095904096,6.193806194,1.498501499,3.196803197,9.99000999,3.296703297,12.68731269,6.293706294,2.197802198,3.896103896,0.699300699,1.698301698,,36.36363636,45.15484515,43.65634366,18.08191808,20.57942058,6.493506494,10.18981019,13.28671329,10.78921079,8.491508492,,85,1,1001\r\n+sp|P52566|GDIR2_HUMAN,3.482587065,0.497512438,8.955223881,10.44776119,2.487562189,5.472636816,2.487562189,2.985074627,11.44278607,8.955223881,2.487562189,2.487562189,6.965174129,1.990049751,2.985074627,4.975124378,7.462686567,7.960199005,1.492537313,3.980099502,,39.80099502,40.7960199,48.25870647,19.40298507,16.91542289,4.47761194,11.94029851,16.91542289,7.960199005,12.43781095,,25,1,201\r\n'..b'3.378378378,8.783783784,0.675675676,3.378378378,,47.97297297,39.18918919,47.2972973,4.054054054,29.05405405,6.081081081,10.81081081,27.02702703,7.432432432,8.108108108,,12,1,148\r\n+sp|Q9NYB0|TE2IP_HUMAN,10.02506266,0.751879699,7.518796992,12.78195489,2.756892231,5.764411028,1.754385965,3.50877193,6.26566416,8.020050125,1.754385965,2.255639098,6.26566416,4.511278195,5.764411028,7.518796992,4.761904762,5.263157895,0.751879699,2.005012531,,40.60150376,40.85213033,50.12531328,20.30075188,13.78446115,6.766917293,11.52882206,21.05263158,5.513784461,12.28070175,,49,1,399\r\n+sp|Q15056|IF4H_HUMAN,5.241935484,0.403225806,10.48387097,6.048387097,6.048387097,14.11290323,0.403225806,2.016129032,4.435483871,5.64516129,1.612903226,2.822580645,6.451612903,3.225806452,12.09677419,7.661290323,4.032258065,4.435483871,0.403225806,2.419354839,,42.33870968,39.51612903,55.64516129,16.53225806,16.93548387,6.048387097,7.661290323,23.79032258,8.870967742,11.69354839,,29,1,248\r\n+sp|A8MWD9|RUXGL_HUMAN,3.947368421,1.315789474,3.947368421,7.894736842,5.263157895,9.210526316,2.631578947,7.894736842,9.210526316,9.210526316,6.578947368,5.263157895,3.947368421,3.947368421,5.263157895,5.263157895,2.631578947,6.578947368,0,0,,50,38.15789474,42.10526316,11.84210526,17.10526316,9.210526316,17.10526316,19.73684211,5.263157895,7.894736842,,6,1,76\r\n+sp|P62308|RUXG_HUMAN,3.947368421,1.315789474,3.947368421,6.578947368,3.947368421,9.210526316,2.631578947,7.894736842,7.894736842,10.52631579,7.894736842,6.578947368,3.947368421,3.947368421,5.263157895,5.263157895,1.315789474,7.894736842,0,0,,52.63157895,36.84210526,43.42105263,10.52631579,15.78947368,10.52631579,18.42105263,21.05263158,3.947368421,6.578947368,,5,1,76\r\n+sp|P05387|RLA2_HUMAN,17.39130435,0,9.565217391,8.695652174,1.739130435,10.43478261,0,6.086956522,8.695652174,6.956521739,1.739130435,3.47826087,4.347826087,0.869565217,1.739130435,10.43478261,0,6.086956522,0,1.739130435,,52.17391304,33.04347826,61.73913043,18.26086957,10.43478261,4.347826087,13.04347826,33.91304348,3.47826087,10.43478261,,12,1,115\r\n+sp|Q6NYC8|PPR18_HUMAN,8.482871126,0.815660685,2.77324633,14.19249592,0.652528548,7.993474715,0.815660685,1.305057096,4.078303426,9.461663948,0.815660685,0.978792822,11.58238173,6.03588907,10.60358891,8.156606852,4.241435563,4.078303426,1.794453507,1.141924959,,36.54159869,39.47797716,49.10277325,16.96574225,15.49755302,7.014681892,10.76672104,20.55464927,3.588907015,12.39804241,,76,2,613\r\n+sp|Q99439|CNN2_HUMAN,5.501618123,2.265372168,5.501618123,4.207119741,2.265372168,11.00323625,1.618122977,3.55987055,6.796116505,8.090614887,4.530744337,5.177993528,5.825242718,7.1197411,2.912621359,7.766990291,6.472491909,4.207119741,0.647249191,4.530744337,,46.60194175,33.33333333,53.72168285,9.708737864,11.32686084,12.29773463,11.65048544,20.71197411,7.443365696,14.2394822,,44,1,309\r\n+sp|Q92608|DOCK2_HUMAN,4.644808743,1.256830601,5.846994536,7.540983607,4.808743169,4.535519126,2.404371585,6.284153005,7.650273224,10.10928962,4.207650273,3.879781421,3.825136612,5.136612022,5.027322404,6.666666667,5.191256831,6.06557377,1.038251366,3.879781421,,46.83060109,37.4863388,41.91256831,13.38797814,15.08196721,9.016393443,16.39344262,15.24590164,9.726775956,11.8579235,,217,1,1830\r\n+sp|Q86UX7|URP2_HUMAN,7.346326837,1.499250375,5.847076462,7.196401799,3.898050975,6.146926537,2.548725637,4.797601199,5.097451274,11.84407796,1.79910045,2.248875562,5.547226387,5.697151424,7.346326837,7.046476762,3.5982009,5.547226387,2.248875562,2.698650675,,47.82608696,35.982009,44.82758621,13.04347826,14.99250375,7.946026987,16.64167916,19.04047976,8.845577211,10.64467766,,71,1,667\r\n+sp|Q9NRG0|CHRC1_HUMAN,7.633587786,0.763358779,7.633587786,10.6870229,2.290076336,3.816793893,1.526717557,4.580152672,9.923664122,10.6870229,2.290076336,3.816793893,2.290076336,4.580152672,3.816793893,9.923664122,4.580152672,6.106870229,0,3.053435115,,41.22137405,41.98473282,46.5648855,18.32061069,15.26717557,8.396946565,15.26717557,17.55725191,5.34351145,14.50381679,,19,1,131\r\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/2RS.csv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/all stuff/2RS.csv Fri Feb 21 13:07:45 2020 -0500 |
| b |
| b'@@ -0,0 +1,536 @@\n+Substrate,Species,Reference,-7,-6,-5,-4,-3,-2,-1,0,1,2,3,4,5,6,7,Phosphite\r\n+,,sp|Q13283|G3BP1_HUMAN, , , , , , , ,xS,S,S,P,A,P,A,D,\r\n+,,sp|Q08043|ACTN3_HUMAN; sp|P35609|ACTN2_HUMAN; sp|P12814|ACTN1_HUMAN; sp|O43707|ACTN4_HUMAN, , , , , ,T,F,xT,A,W,C,N,S,H,L,\r\n+,,sp|Q04837|SSBP_HUMAN, , , , , ,Q,A,xT,T,I,I,A,D,N,I,\r\n+,,sp|Q15738|NSDHL_HUMAN, , ,V,A,L,A,G,xT,F,H,Y,Y,S,C,E,\r\n+,,sp|Q08945|SSRP1_HUMAN, , , , ,R,P,M,xS,A,Y,M,L, , , ,\r\n+,,sp|Q9Y371|SHLB1_HUMAN, ,L,A,A,D,A,G,xT,F,L,S,R, , , ,\r\n+,,sp|P09651|ROA1_HUMAN; sp|Q32P51|RA1L2_HUMAN,S,H,F,E,Q,W,G,xT,L,T,D,C,V,V,M,\r\n+,,sp|P30740|ILEU_HUMAN, , ,T,F,H,F,N,xT,V,E,E,V,H,S,R,\r\n+,,sp|O94979|SC31A_HUMAN,R,P,V,G,A,S,F,xS,F,G,G,K, , , ,\r\n+,,sp|P07686|HEXB_HUMAN, , ,G,S,Y,S,L,xS,H,V,Y,T,P,N,D,\r\n+,,sp|P22626|ROA2_HUMAN, , ,G,F,G,F,V,xT,F,S,S,M,A,E,V,\r\n+,,sp|Q8NBS9|TXND5_HUMAN, , , , ,G,Y,P,xT,L,L,L,F,R, , ,\r\n+,,sp|P60709|ACTB_HUMAN; sp|P63261|ACTG_HUMAN, ,T,V,L,S,G,G,xT,T,M,Y,P,G,I,A,\r\n+,,sp|P49247|RPIA_HUMAN,V,L,G,I,G,S,G,xS,T,I,V,H,A,V,Q,\r\n+,,sp|Q96IU4|ABHEB_HUMAN,E,T,W,Q,N,L,G,xT,L,H,R, , , , ,\r\n+,,sp|Q96JH7|VCIP1_HUMAN, , , , , ,S,S,xT,T,F,F,E,L,Q,E,\r\n+,,sp|Q13283|G3BP1_HUMAN, , , , , , ,S,xS,S,P,A,P,A,D,I,\r\n+,,sp|Q08043|ACTN3_HUMAN; sp|P35609|ACTN2_HUMAN; sp|P12814|ACTN1_HUMAN; sp|O43707|ACTN4_HUMAN, , , , , , ,K,xT,F,T,A,W,C,N,S,\r\n+,,sp|Q13509|TBB3_HUMAN; tr|A0A0B4J269|A0A0B4J269_HUMAN, , , , ,M,S,S,xT,F,I,G,N,S,T,A,\r\n+,,sp|P49915|GUAA_HUMAN,S,F,Y,N,G,T,T,xT,L,P,I,S,D,E,D,\r\n+,,sp|Q15007|FL2D_HUMAN, , , , , , ,S,xT,M,V,D,P,A,I,N,\r\n+,,sp|P10809|CH60_HUMAN, , , , ,G,Y,I,xS,P,Y,F,I,N,T,S,\r\n+,,sp|O15294|OGT1_HUMAN,L,C,P,T,H,A,D,xS,L,N,N,L,A,N,I,\r\n+,,sp|P45880|VDAC2_HUMAN, , ,L,T,F,D,T,xT,F,S,P,N,T,G,K,\r\n+,,sp|Q9UKX7|NUP50_HUMAN, , , , ,G,I,G,xT,L,H,L,K,P,T,A,\r\n+,,sp|O43312|MTSS1_HUMAN, , , ,R,P,A,S,xT,A,G,L,P,T,T,L,\r\n+,,sp|P22314|UBA1_HUMAN, , , , , ,L,Q,xT,S,S,V,L,V,S,G,\r\n+,,sp|O75746|CMC1_HUMAN, , , , , ,L,A,xT,A,T,F,A,G,I,E,\r\n+,,sp|O43491|E41L2_HUMAN, , , , , , , ,xS,P,T,K,A,P,H,L,\r\n+,,sp|Q15005|SPCS2_HUMAN, ,F,F,D,H,S,G,xT,L,V,M,D,A,Y,E,\r\n+,,sp|P62995|TRA2B_HUMAN, , , , ,R,P,H,xT,P,T,P,G,I,Y, ,\r\n+,,sp|Q13596|SNX1_HUMAN, , ,A,V,G,T,Q,xT,L,S,G,A,G,L,L,\r\n+,,sp|Q16698|DECR_HUMAN,A,F,I,T,G,G,G,xT,G,L,G,K, , , ,\r\n+,,sp|P42166|LAP2A_HUMAN,S,D,E,E,R,E,P,xT,P,V,L,G,S,G,A,\r\n+,,sp|O43719|HTSF1_HUMAN, , ,V,F,D,D,E,xS,D,E,K,E,D,E,E,\r\n+,,sp|P34897|GLYM_HUMAN; sp|P34896|GLYC_HUMAN, , , ,I,S,A,T,xS,I,F,F,E,S,M,P,\r\n+,,sp|Q7Z422|SZRD1_HUMAN, , , , , , , ,xS,P,P,K,V,P,I,V,\r\n+,,sp|P22626|ROA2_HUMAN, , , , , , ,V,xT,F,S,S,M,A,E,V,\r\n+,,sp|P53396|ACLY_HUMAN, , , , , , ,L,xT,L,L,N,P,K, , ,\r\n+,,sp|P38606|VATA_HUMAN, , , , , ,L,A,xS,F,Y,E,R, , , ,\r\n+,,sp|Q8IX12|CCAR1_HUMAN,V,M,L,M,A,S,P,xS,M,E,D,L,Y,H,K,\r\n+,,sp|P51858|HDGF_HUMAN,A,G,D,L,L,E,D,xS,P,K,R,P,K, , ,\r\n+,,sp|Q5SW79|CE170_HUMAN,D,L,G,S,L,N,G,xT,F,V,N,D,V,R, ,\r\n+,,sp|Q9Y277|VDAC3_HUMAN, , , ,V,N,N,A,xS,L,I,G,L,G,Y,T,\r\n+,,sp|O75521|ECI2_HUMAN,P,F,S,H,L,G,Q,xS,P,E,G,C,S,S,Y,\r\n+,,sp|Q52LJ0|FA98B_HUMAN, , , , , , , ,xT,T,I,T,M,A,H,L,\r\n+,,sp|P35659|DEK_HUMAN, , , , , , ,L,xT,M,Q,V,S,S,L,Q,\r\n+,,sp|Q15052|ARHG6_HUMAN, , ,I,P,I,A,G,xT,V,V,T,R, , , ,\r\n+,,sp|P42166|LAP2A_HUMAN, ,G,P,P,D,F,S,xS,D,E,E,R,E,P,T,\r\n+,,sp|P49247|RPIA_HUMAN,N,Q,V,L,G,I,G,xS,G,S,T,I,V,H,A,\r\n+,,sp|Q9UKX7|NUP50_HUMAN, , , , , , ,S,xT,F,L,F,H,G,N,K,\r\n+,,sp|Q9UPN3|MACF1_HUMAN, , , , ,I,S,G,xT,F,S,S,G,W,T,V,\r\n+,,sp|P14618|KPYM_HUMAN, ,L,N,F,S,H,G,xT,H,E,Y,H,A,E,T,\r\n+,,sp|P49321|NASP_HUMAN, ,P,E,V,N,G,G,xS,G,D,A,V,P,S,G,\r\n+,,sp|O75064|DEN4B_HUMAN, ,Y,P,V,P,V,F,xS,T,F,V,L,T,G,A,\r\n+,,sp|Q9ULW0|TPX2_HUMAN, , , , , ,G,C,xT,I,V,K,P,F,N,L,\r\n+,,sp|Q9H6V9|LDAH_HUMAN, , , , , , ,L,xT,F,Y,Y,G,T,I,D,\r\n+,,RRRRRsp|Q8NCX0|CC150_HUMAN, , , , , ,S,H,xS,A,L,V,N,E,L,M,\r\n+,,sp|Q6ZNL6|FGD5_HUMAN, ,E,R,P,V,S,M,xS,F,P,L,S,S,P,R,\r\n+,,sp|P61981|1433G_HUMAN, , , , , , ,A,xT,V,V,E,S,S,E,K,\r\n+,,sp|Q13177|PAK2_HUMAN, , ,S,T,M,V,G,xT,P,Y,W,M,A,P,E,\r\n+,,sp|Q9Y3D7|TIM16_HUMAN, , , , , , , ,xS,V,G,G,S,F,Y,L,\r\n+,,sp|Q16778|H2B2E_HUMAN; sp|P06899|H2B1J_HUMAN; sp|P33778|H2B1B_HUMAN; sp|P23527|H2B1O_HUMAN; sp'..b'NRH2_HUMAN, , ,H,T,G,P,N,xS,P,D,T,A,N,D,G,\r\n+,,sp|O94888|UBXN7_HUMAN, , , , , , , ,xS,P,H,K,D,L,G,H,\r\n+,,sp|Q99618|CDCA3_HUMAN, , , , , ,S,P,xS,A,G,I,L,R, , ,\r\n+,,sp|Q9UQ35|SRRM2_HUMAN, , ,S,C,F,E,S,xS,P,D,P,E,L,K, ,\r\n+,,sp|Q9Y2W1|TR150_HUMAN; sp|Q9NYF8|BCLF1_HUMAN, , , , , , , ,xS,P,E,I,H,R, , ,\r\n+,,sp|Q9NWQ8|PHAG1_HUMAN, , , , , ,S,P,xS,S,C,N,D,L,Y,A,\r\n+,,sp|Q8ND76|CCNY_HUMAN, , , , , ,S,A,xS,A,D,N,L,T,L,P,\r\n+,,sp|Q9Y2W1|TR150_HUMAN, ,S,P,P,S,T,G,xS,T,Y,G,S,S,Q,K,\r\n+,,sp|P25205|MCM3_HUMAN, , , ,G,G,Y,T,xS,G,T,F,R, , , ,\r\n+,,sp|P27824|CALX_HUMAN,E,D,E,I,L,N,R,xS,P,R, , , , , ,\r\n+,,sp|P61978|HNRPK_HUMAN, , ,D,Y,D,D,M,xS,P,R, , , , , ,\r\n+,,sp|Q9Y2W1|TR150_HUMAN, , , , ,S,P,P,xS,T,G,S,T,Y,G,S,\r\n+,,sp|Q9HCE3|ZN532_HUMAN, , , , , , , ,xS,P,E,S,Q,N,L,I,\r\n+,,sp|P18615|NELFE_HUMAN, , , , , , , ,xS,I,S,A,D,D,D,L,\r\n+,,sp|P08575|PTPRC_HUMAN,D,E,S,S,D,D,D,xS,D,S,E,E,P,S,K,\r\n+,,sp|Q15036|SNX17_HUMAN, , , , , , , ,xS,P,P,L,L,E,S,P,\r\n+,,sp|Q6JBY9|CPZIP_HUMAN, , , , , ,S,Q,xS,D,C,G,E,L,G,D,\r\n+,,sp|Q96RU3|FNBP1_HUMAN, , , , , ,T,V,xS,D,N,S,L,S,N,S,\r\n+,,sp|Q9Y2W1|TR150_HUMAN,T,G,S,T,Y,G,S,xS,Q,K,E,E,S,A,A,\r\n+,,sp|P18615|NELFE_HUMAN, , , , , ,S,I,xS,A,D,D,D,L,Q,E,\r\n+,,sp|Q7Z6Z7|HUWE1_HUMAN, , , , , , ,G,xS,G,T,A,S,D,D,E,\r\n+,,sp|Q96I25|SPF45_HUMAN, , ,R,P,D,P,D,xS,D,E,D,E,D,Y,E,\r\n+,,sp|Q15366|PCBP2_HUMAN, , , , , , ,P,xS,S,S,P,V,I,F,A,\r\n+,,sp|P85037|FOXK1_HUMAN, , , , , ,E,G,xS,P,I,P,H,D,P,E,\r\n+,,sp|Q13098|CSN1_HUMAN, , , , , , , ,xS,P,P,R,E,G,S,Q,\r\n+,,sp|P08575|PTPRC_HUMAN,E,H,D,S,D,E,S,xS,D,D,D,S,D,S,E,\r\n+,,sp|P16401|H15_HUMAN; sp|P16402|H13_HUMAN; sp|Q02539|H11_HUMAN; sp|P16403|H12_HUMAN; sp|P10412|H14_HUMAN; sp|P22492|H1T_HUMAN, ,G,T,G,A,S,G,xS,F,K, , , , , ,\r\n+,,sp|P60174|TPIS_HUMAN, , , ,D,C,G,A,xT,W,V,V,L,G,H, ,\r\n+,,sp|Q9Y2W1|TR150_HUMAN,S,T,G,S,T,Y,G,xS,S,Q,K,E,E,S,A,\r\n+,,sp|Q15287|RNPS1_HUMAN, , , , , , , ,xS,P,S,P,K,P,T,K,\r\n+,,sp|Q05193|DYN1_HUMAN, , , , , , , ,xS,P,T,S,S,P,T,P,\r\n+,,sp|P07948|LYN_HUMAN, , , , ,G,K,D,xS,L,S,D,D,G,V,D,\r\n+,,sp|Q5SSJ5|HP1B3_HUMAN, , , , , ,G,A,xS,G,S,F,V,V,V,Q,\r\n+,,sp|P49585|PCY1A_HUMAN, , , , , ,S,P,xS,P,S,F,R, , , ,\r\n+,,sp|Q7Z6Z7|HUWE1_HUMAN, , , , ,G,S,G,xT,A,S,D,D,E,F,E,\r\n+,,sp|Q92610|ZN592_HUMAN, , , , , , , ,xS,P,L,E,A,T,R, ,\r\n+,,sp|Q03164|KMT2A_HUMAN, , , , , , , ,xS,P,T,V,P,S,Q,N,\r\n+,,sp|Q07666|KHDR1_HUMAN, , , , , , , ,xS,G,S,M,D,P,S,G,\r\n+,,sp|Q16629|SRSF7_HUMAN, , , , , , , ,xS,P,S,G,S,P,R, ,\r\n+,,sp|P08575|PTPRC_HUMAN,S,E,H,D,S,D,E,xS,S,D,D,D,S,D,S,\r\n+,,sp|Q5T7W0|ZN618_HUMAN, , , , , , , ,xS,P,P,A,V,V,E,E,\r\n+,,sp|Q9H0E3|SP130_HUMAN, , , , , , , ,xS,P,P,K,E,Y,I,D,\r\n+,,sp|Q5VTE0|EF1A3_HUMAN; sp|P68104|EF1A1_HUMAN, , , , , ,S,T,xT,T,G,H,L,I,Y,K,\r\n+,,sp|Q92804|RBP56_HUMAN, , , , , ,Q,S,xS,Y,S,Q,Q,P,Y,N,\r\n+,,sp|Q9Y2W1|TR150_HUMAN,S,P,P,S,T,G,S,xT,Y,G,S,S,Q,K,E,\r\n+,,sp|Q13098|CSN1_HUMAN, ,S,P,P,R,E,G,xS,Q,G,E,L,T,P,A,\r\n+,,sp|P61313|RL15_HUMAN, , , , , , ,N,xT,L,Q,L,H,R, , ,\r\n+,,tr|A0A0B4J1V8|A0A0B4J1V8_HUMAN; sp|Q9NQ55|SSF1_HUMAN, , , , ,V,G,G,xS,D,E,E,A,S,G,I,\r\n+,,sp|P49736|MCM2_HUMAN, ,G,N,D,P,L,T,xS,S,P,G,R, , , ,\r\n+,,RRRRRsp|O15229|KMO_HUMAN, , , , ,E,A,A,xT,L,L,D,K, , , ,\r\n+,,sp|P19013|K2C4_HUMAN,R,G,A,F,S,S,V,xS,M,S,G,G,A,G,R,\r\n+,,sp|O15530|PDPK1_HUMAN, , , , , , , ,xT,Q,T,E,S,S,T,P,\r\n+,,sp|P06748|NPM_HUMAN, , , , , ,G,P,xS,S,V,E,D,I,K, ,\r\n+,,sp|Q92793|CBP_HUMAN, , , , , , , ,xS,P,L,S,Q,G,D,S,\r\n+,,sp|Q9Y6K9|NEMO_HUMAN, , , , , , , ,xS,P,P,E,E,P,P,D,\r\n+,,sp|P53999|TCP4_HUMAN,V,S,S,S,S,S,G,xS,D,S,D,S,E,V,D,\r\n+,,sp|Q99613|EIF3C_HUMAN; sp|B5ME19|EIFCL_HUMAN, , , , ,T,C,H,xS,F,I,I,N,E,K, ,\r\n+,,sp|O75534|CSDE1_HUMAN, , , , , , ,G,xT,V,S,F,H,S,H,S,\r\n+,,sp|Q13547|HDAC1_HUMAN,C,E,E,E,F,S,D,xS,E,E,E,G,E,G,G,\r\n+,,sp|P53999|TCP4_HUMAN, ,E,L,V,S,S,S,xS,S,G,S,D,S,D,S,\r\n+,,sp|Q9H0F6|SHRPN_HUMAN, , , , , , , ,xS,P,G,N,L,T,E,R,\r\n+,,sp|P53999|TCP4_HUMAN,S,S,S,S,G,S,D,xS,D,S,E,V,D,K,K,\r\n+,,sp|P31930|QCR1_HUMAN, , , ,N,R,P,G,xS,A,L,E,K, , , ,\r\n+,,sp|Q05BQ5|MBTD1_HUMAN,L,I,C,V,A,T,V,xT,R, , , , , , ,\r\n+,,sp|Q5VUA4|ZN318_HUMAN, , , , , ,S,P,xT,V,L,C,Q,K, , ,\r\n+,,sp|Q92688|AN32B_HUMAN, , , , ,K,R,E,xT,D,D,E,G,E,D,D,\r\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/2RSBF.csv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/all stuff/2RSBF.csv Fri Feb 21 13:07:45 2020 -0500 |
| b |
| b'@@ -0,0 +1,437 @@\n+Accession Numbers,Amino Acids,A,C,D,E,F,G,H,I,K,L,M,N,P,Q,R,S,T,V,W,Y,Properties,Hydrophobic,Polar,Small,Negative,Postive,Amide,Large Aliphatic,Small Aliphatic,Aromatic,Hydroxy,X,Number of ST,Number of pST\r\n+sp|Q13283|G3BP1_HUMAN,4.721030043,0.214592275,5.150214592,10.30042918,4.077253219,8.369098712,2.575107296,3.004291845,4.077253219,5.364806867,2.360515021,4.506437768,10.51502146,6.43776824,7.939914163,5.793991416,3.004291845,9.442060086,0.214592275,1.931330472,,39.69957082,40.98712446,51.7167382,15.45064378,14.59227468,10.94420601,8.369098712,22.53218884,6.223175966,8.798283262,,41,4,466\r\n+sp|Q13283|G3BP1_HUMAN,4.721030043,0.214592275,5.150214592,10.30042918,4.077253219,8.369098712,2.575107296,3.004291845,4.077253219,5.364806867,2.360515021,4.506437768,10.51502146,6.43776824,7.939914163,5.793991416,3.004291845,9.442060086,0.214592275,1.931330472,,39.69957082,40.98712446,51.7167382,15.45064378,14.59227468,10.94420601,8.369098712,22.53218884,6.223175966,8.798283262,,41,3,466\r\n+sp|O43707|ACTN4_HUMAN,8.452250274,0.878155873,6.915477497,9.549945115,3.293084523,4.500548847,3.402854007,6.586169045,6.366630077,9.220636663,2.634467618,5.049396268,3.183315038,6.147091109,5.598243688,5.159165752,4.500548847,4.061470911,1.756311745,2.744237102,,44.1273326,43.02963776,42.70032931,16.46542261,15.36772777,11.19648738,15.80680571,17.01427003,7.79363337,9.659714599,,88,4,911\r\n+sp|P35609|ACTN2_HUMAN,8.389261745,1.118568233,6.040268456,10.29082774,3.131991051,3.914988814,2.572706935,7.382550336,5.928411633,9.395973154,3.243847875,5.14541387,3.131991051,6.15212528,6.711409396,4.250559284,4.8098434,3.691275168,1.789709172,2.908277405,,44.96644295,42.84116331,40.49217002,16.3310962,15.21252796,11.29753915,16.77852349,15.99552573,7.829977629,9.060402685,,81,4,894\r\n+sp|Q08043|ACTN3_HUMAN,9.10099889,1.442841287,5.882352941,9.766925638,3.32963374,5.549389567,2.219755827,5.216426193,5.216426193,10.65482797,3.107658158,4.328523862,3.218645949,5.993340733,7.325194229,4.217536071,4.439511654,4.772475028,1.886792453,2.330743618,,47.3917869,40.73251942,42.95227525,15.64927858,14.76137625,10.32186459,15.87125416,19.42286349,7.547169811,8.657047725,,78,4,901\r\n+sp|P12814|ACTN1_HUMAN,7.959641256,1.121076233,6.950672646,9.417040359,3.251121076,4.596412556,3.02690583,6.838565022,6.053811659,9.417040359,3.02690583,4.820627803,3.3632287,5.829596413,6.053811659,4.035874439,5.605381166,3.923766816,1.793721973,2.914798206,,44.84304933,42.15246637,42.37668161,16.367713,15.13452915,10.65022422,16.25560538,16.47982063,7.959641256,9.641255605,,86,4,892\r\n+sp|Q04837|SSBP_HUMAN,2.702702703,0,5.405405405,6.756756757,3.378378378,6.081081081,2.027027027,5.405405405,5.405405405,8.783783784,2.027027027,4.054054054,2.702702703,6.081081081,10.13513514,6.756756757,6.756756757,10.13513514,1.351351351,4.054054054,,43.91891892,39.86486486,44.59459459,12.16216216,17.56756757,10.13513514,14.18918919,18.91891892,8.783783784,13.51351351,,20,2,148\r\n+sp|Q15738|NSDHL_HUMAN,7.238605898,1.340482574,4.557640751,5.361930295,5.09383378,6.434316354,2.680965147,5.898123324,5.361930295,9.115281501,2.680965147,5.09383378,6.166219839,4.557640751,5.09383378,4.289544236,6.166219839,8.310991957,0.536193029,4.021447721,,50.67024129,32.7077748,49.59785523,9.919571046,13.13672922,9.651474531,15.01340483,21.98391421,9.651474531,10.45576408,,39,1,373\r\n+sp|Q08945|SSRP1_HUMAN,4.37235543,0.846262341,6.911142454,10.43723554,4.936530324,6.629055007,1.833568406,4.090267983,10.71932299,6.770098731,2.3977433,3.94922426,3.526093089,3.102961918,6.064880113,10.1551481,4.513399154,4.795486601,0.846262341,3.102961918,,38.78702398,43.01833568,45.69816643,17.348378,18.61777151,7.052186178,10.86036671,15.79689704,8.885754584,14.66854725,,104,3,709\r\n+sp|Q08945|SSRP1_HUMAN,4.37235543,0.846262341,6.911142454,10.43723554,4.936530324,6.629055007,1.833568406,4.090267983,10.71932299,6.770098731,2.3977433,3.94922426,3.526093089,3.102961918,6.064880113,10.1551481,4.513399154,4.795486601,0.846262341,3.102961918,,'..b'856115108,1.079136691,4.136690647,,44.96402878,35.61151079,46.22302158,12.41007194,14.92805755,8.273381295,14.56834532,16.90647482,10.07194245,12.58992806,,70,15,556\r\n+sp|O15530|PDPK1_HUMAN,5.935251799,1.618705036,5.035971223,7.374100719,4.856115108,6.115107914,2.697841727,4.496402878,6.834532374,10.07194245,1.798561151,3.237410072,6.834532374,5.035971223,5.395683453,7.913669065,4.676258993,4.856115108,1.079136691,4.136690647,,44.96402878,35.61151079,46.22302158,12.41007194,14.92805755,8.273381295,14.56834532,16.90647482,10.07194245,12.58992806,,70,7,556\r\n+sp|Q92793|CBP_HUMAN,7.207207207,2.047502048,3.194103194,4.2997543,2.006552007,7.084357084,2.620802621,3.071253071,4.75020475,7.084357084,3.89025389,4.873054873,11.3022113,10.97461097,4.013104013,8.927108927,5.446355446,4.873054873,0.573300573,1.760851761,,39.5986896,34.72563473,54.95495495,7.493857494,11.38411138,15.84766585,10.15561016,19.16461916,4.340704341,14.37346437,,351,1,2442\r\n+sp|Q9Y6K9|NEMO_HUMAN,10.02386635,2.625298329,3.579952267,13.8424821,1.431980907,2.625298329,2.386634845,2.14797136,7.159904535,11.69451074,2.863961814,0.954653938,4.534606205,12.88782816,7.398568019,6.205250597,1.193317422,4.77326969,0.238663484,1.431980907,,39.85680191,48.21002387,36.51551313,17.42243437,16.9451074,13.8424821,13.8424821,17.42243437,3.102625298,7.398568019,,31,1,419\r\n+sp|Q13547|HDAC1_HUMAN,5.394190871,2.074688797,6.846473029,9.958506224,4.149377593,7.676348548,2.904564315,4.771784232,8.298755187,6.43153527,3.319502075,4.564315353,4.356846473,3.112033195,4.564315353,5.601659751,4.149377593,5.601659751,0.414937759,5.809128631,,45.64315353,40.24896266,46.26556017,16.80497925,15.76763485,7.676348548,11.2033195,18.67219917,10.37344398,9.751037344,,47,1,482\r\n+sp|Q13547|HDAC1_HUMAN,5.394190871,2.074688797,6.846473029,9.958506224,4.149377593,7.676348548,2.904564315,4.771784232,8.298755187,6.43153527,3.319502075,4.564315353,4.356846473,3.112033195,4.564315353,5.601659751,4.149377593,5.601659751,0.414937759,5.809128631,,45.64315353,40.24896266,46.26556017,16.80497925,15.76763485,7.676348548,11.2033195,18.67219917,10.37344398,9.751037344,,47,2,482\r\n+sp|Q9H0F6|SHRPN_HUMAN,14.9870801,2.583979328,2.842377261,5.943152455,2.067183463,8.785529716,2.067183463,1.291989664,1.033591731,11.36950904,0.775193798,1.550387597,13.69509044,5.684754522,5.684754522,8.527131783,3.359173127,5.684754522,1.291989664,0.775193798,,49.6124031,24.80620155,62.01550388,8.785529716,8.785529716,7.235142119,12.66149871,29.45736434,4.134366925,11.88630491,,46,1,387\r\n+sp|P31930|QCR1_HUMAN,11.45833333,2.5,4.791666667,6.458333333,3.125,7.083333333,2.708333333,4.166666667,3.125,9.791666667,2.083333333,3.125,4.375,4.375,6.458333333,6.875,5.625,7.291666667,1.25,3.333333333,,52.08333333,31.04166667,53.125,11.25,12.29166667,7.5,13.95833333,25.83333333,7.708333333,12.5,,60,1,480\r\n+sp|Q05BQ5|MBTD1_HUMAN,6.52866242,3.184713376,5.414012739,6.050955414,4.458598726,6.687898089,2.547770701,4.777070064,7.643312102,7.006369427,2.388535032,3.503184713,5.732484076,4.140127389,4.299363057,8.917197452,4.777070064,6.210191083,2.229299363,3.503184713,,46.97452229,33.59872611,50.95541401,11.46496815,14.49044586,7.643312102,11.78343949,19.42675159,10.1910828,13.69426752,,86,1,628\r\n+sp|Q5VUA4|ZN318_HUMAN,5.660377358,1.272487933,5.353225099,9.039052216,2.36946029,5.748135147,2.413339184,3.641948223,7.415533129,8.205353225,1.360245722,3.027643703,9.477841158,3.598069329,6.625713032,12.76875823,4.782799473,5.089951733,0.482667837,1.667397982,,35.49802545,37.47257569,53.18121983,14.39227731,16.45458534,6.625713032,11.84730145,16.49846424,4.519526108,17.5515577,,400,2,2279\r\n+sp|Q92688|AN32B_HUMAN,2.390438247,1.195219124,15.13944223,22.31075697,2.788844622,6.374501992,0.796812749,2.390438247,6.772908367,13.14741036,1.195219124,5.179282869,2.788844622,0.796812749,3.984063745,4.38247012,2.788844622,4.38247012,0,1.195219124,,35.05976096,54.98007968,44.62151394,37.4501992,11.55378486,5.976095618,15.53784861,13.14741036,3.984063745,7.171314741,,18,1,251\r\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/Commonality and Difference finderMADE 7 TO 7 1-15-2019.R --- a/all stuff/Commonality and Difference finderMADE 7 TO 7 1-15-2019.R Fri Apr 19 16:55:29 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,1281 +0,0 @@\n-#I should make an SOP for this. Problems we encountered: no x in the xY motif, and the kilodemon\r\n-#the output files have both Y and xY, they shouldn\'t why is that happening? make it not happen\r\n-#make sure that accession numbers stay locked to each motif, somehow\r\n-#output should look just like the KALIP input\r\n-\r\n-#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n-FullMotifsOnly_questionmark<-"NO"\r\n-#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n-TruncatedMotifsOnly_questionmark<-"NO"\r\n-#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)\r\n-Are_You_Looking_For_Commonality<-"NO"\r\n-\r\n-\r\n-#put the names of your input files here\r\n-FirstSubstrateSet<- read.csv("Galaxy63-BTK_PLUS-R1_Substrates.csv", stringsAsFactors=FALSE)\r\n-Firstsubbackfreq<- read.csv("Galaxy64-BTK_PLUS-R1_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-SecondSubstrateSet<- read.csv("Galaxy65-BTK_PLUS_R2_Substrates.csv", stringsAsFactors=FALSE)\r\n-Secondsubbackfreq<- read.csv("Galaxy66-BTK_PLUS_R2_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)\r\n-Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-#then put the names of your output files here\r\n-Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"\r\n-Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"\r\n-\r\n-# Shared_motifs_table<-"Shared motifs 7-27-17.csv"\r\n-# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"\r\n-\r\n-First_unshared_motifs_table<-"R1 substrates.csv"\r\n-First_unshared_subbackfreq<-"R1 SBF.csv"\r\n-\r\n-Second_unshared_motifs_table<-"R2 subs.csv"\r\n-Second_unshared_subbackfreq<-"R2 SBf.csv"\r\n-\r\n-Third_unshared_motifs_table<-"R3 subs.csv"\r\n-Third_unshared_subbackfreq<-"R3 SBF.csv"\r\n-\r\n-#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\r\n-#other languages to see if any of them can do it.\r\n-####################################################################################################################################\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-FirstxY<-rep("xY",times=nrow(FirstSubstrateSet))\r\n-FirstSubstrateSet[,11]<-FirstxY\r\n-\r\n-SecondxY<-rep("xY",times=nrow(SecondSubstrateSet))\r\n-SecondSubstrateSet[,11]<-SecondxY\r\n-\r\n-ThirdxY<-rep("xY",times=nrow(ThirdSubstrateSet))\r\n-ThirdSubstrateSet[,11]<-ThirdxY\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two \r\n-# separate proteins thus two separate accession numbers?\r\n-# It should actually output the shared motif and BOTH accession numbers. Right now it does not, it only maps out the second\r\n-# accession number. So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-\r\n-#Create the motif sets, deciding w'..b'ly after I\'ve unduped them\r\n-# D835YnondupeAccessionNumbers<-D835YnondupeAccessionNumbers[!duplicated(D835YnondupeAccessionNumbers)]\r\n-# \r\n-# columnalheader<-c(rep(NA,35))\r\n-# D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)\r\n-# \r\n-# for (k in 1:length(D835YnondupeAccessionNumbers)) {\r\n-# #I don\'t remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is\r\n-# #destroyed immediately after use\r\n-# for (m in 1:ncol(Secondsubbackfreq)) {\r\n-# AN <- as.character(Secondsubbackfreq[1, m])\r\n-# if (grepl(pattern = AN,\r\n-# x = D835YnondupeAccessionNumbers[k],\r\n-# fixed = TRUE) == TRUE) {\r\n-# outputmatrix <- as.character(Secondsubbackfreq[, m])\r\n-# outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n-# #with that accession number, find a match in the subbackfreq file and save it here\r\n-# D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)\r\n-# }\r\n-# }\r\n-# }\r\n-# \r\n-# \r\n-# \r\n-# # FinalFTLmotifs<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]\r\n-# # FinalFTLAccessionNumbers<-FTLnondupeAccessionNumbers[!duplicated(FTLnondupeAccessionNumbers)]\r\n-# # necessaryNAs<-rep(NA,times=(length(FinalFTLmotifs)-length(FinalFTLAccessionNumbers)))\r\n-# # FinalFTLAccessionNumbers<-c(FinalFTLAccessionNumbers,necessaryNAs)\r\n-# # TRUEFTLoutputmatrix<-cbind(FinalFTLmotifs,FinalFTLAccessionNumbers)\r\n-# # TRUEFTLoutputmatrix\r\n-# \r\n-# write.table(x=FTLwtmotifsFINAL,\r\n-# file=First_unshared_motifs_table,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))\r\n-# columnalheader<-matrix(columnalheader,nrow = 1)\r\n-# write.table(x=columnalheader,\r\n-# file=First_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# write.table(x=FTLFinalMatrix,\r\n-# file=First_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# write.table(x=D835YmotifsFINAL,\r\n-# file=Second_unshared_motifs_table,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))\r\n-# columnalheader<-matrix(columnalheader,nrow = 1)\r\n-# write.table(x=columnalheader,\r\n-# file=Second_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# write.table(x=D835YFinalMatrix,\r\n-# file=Second_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# write.table(x=ITDmotifsFINAL,\r\n-# file=Third_unshared_motifs_table,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))\r\n-# columnalheader<-matrix(columnalheader,nrow = 1)\r\n-# write.table(x=columnalheader,\r\n-# file=Third_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# write.table(x=ITDFinalMatrix,\r\n-# file=Third_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# }\r\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/Commonality and Difference finderMADE 7 TO 7.R --- a/all stuff/Commonality and Difference finderMADE 7 TO 7.R Fri Apr 19 16:55:29 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,1281 +0,0 @@\n-#I should make an SOP for this. Problems we encountered: no x in the xY motif, and the kilodemon\r\n-#the output files have both Y and xY, they shouldn\'t why is that happening? make it not happen\r\n-#make sure that accession numbers stay locked to each motif, somehow\r\n-#output should look just like the KALIP input\r\n-\r\n-#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n-FullMotifsOnly_questionmark<-"NO"\r\n-#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n-TruncatedMotifsOnly_questionmark<-"NO"\r\n-#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)\r\n-Are_You_Looking_For_Commonality<-"YES"\r\n-\r\n-\r\n-#put the names of your input files here\r\n-FirstSubstrateSet<- read.csv("Galaxy63-BTK_PLUS-R1_Substrates.csv", stringsAsFactors=FALSE)\r\n-Firstsubbackfreq<- read.csv("Galaxy64-BTK_PLUS-R1_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-SecondSubstrateSet<- read.csv("Galaxy65-BTK_PLUS_R2_Substrates.csv", stringsAsFactors=FALSE)\r\n-Secondsubbackfreq<- read.csv("Galaxy66-BTK_PLUS_R2_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)\r\n-Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-#then put the names of your output files here\r\n-Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"\r\n-Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"\r\n-\r\n-# Shared_motifs_table<-"Shared motifs 7-27-17.csv"\r\n-# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"\r\n-\r\n-First_unshared_motifs_table<-"R1 substrates.csv"\r\n-First_unshared_subbackfreq<-"R1 SBF.csv"\r\n-\r\n-Second_unshared_motifs_table<-"R2 subs.csv"\r\n-Second_unshared_subbackfreq<-"R2 SBf.csv"\r\n-\r\n-Third_unshared_motifs_table<-"R3 subs.csv"\r\n-Third_unshared_subbackfreq<-"R3 SBF.csv"\r\n-\r\n-#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\r\n-#other languages to see if any of them can do it.\r\n-####################################################################################################################################\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-FirstxY<-rep("xY",times=nrow(FirstSubstrateSet))\r\n-FirstSubstrateSet[,11]<-FirstxY\r\n-\r\n-SecondxY<-rep("xY",times=nrow(SecondSubstrateSet))\r\n-SecondSubstrateSet[,11]<-SecondxY\r\n-\r\n-ThirdxY<-rep("xY",times=nrow(ThirdSubstrateSet))\r\n-ThirdSubstrateSet[,11]<-ThirdxY\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two \r\n-# separate proteins thus two separate accession numbers?\r\n-# It should actually output the shared motif and BOTH accession numbers. Right now it does not, it only maps out the second\r\n-# accession number. So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-\r\n-#Create the motif sets, deciding '..b'ly after I\'ve unduped them\r\n-# D835YnondupeAccessionNumbers<-D835YnondupeAccessionNumbers[!duplicated(D835YnondupeAccessionNumbers)]\r\n-# \r\n-# columnalheader<-c(rep(NA,35))\r\n-# D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)\r\n-# \r\n-# for (k in 1:length(D835YnondupeAccessionNumbers)) {\r\n-# #I don\'t remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is\r\n-# #destroyed immediately after use\r\n-# for (m in 1:ncol(Secondsubbackfreq)) {\r\n-# AN <- as.character(Secondsubbackfreq[1, m])\r\n-# if (grepl(pattern = AN,\r\n-# x = D835YnondupeAccessionNumbers[k],\r\n-# fixed = TRUE) == TRUE) {\r\n-# outputmatrix <- as.character(Secondsubbackfreq[, m])\r\n-# outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n-# #with that accession number, find a match in the subbackfreq file and save it here\r\n-# D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)\r\n-# }\r\n-# }\r\n-# }\r\n-# \r\n-# \r\n-# \r\n-# # FinalFTLmotifs<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]\r\n-# # FinalFTLAccessionNumbers<-FTLnondupeAccessionNumbers[!duplicated(FTLnondupeAccessionNumbers)]\r\n-# # necessaryNAs<-rep(NA,times=(length(FinalFTLmotifs)-length(FinalFTLAccessionNumbers)))\r\n-# # FinalFTLAccessionNumbers<-c(FinalFTLAccessionNumbers,necessaryNAs)\r\n-# # TRUEFTLoutputmatrix<-cbind(FinalFTLmotifs,FinalFTLAccessionNumbers)\r\n-# # TRUEFTLoutputmatrix\r\n-# \r\n-# write.table(x=FTLwtmotifsFINAL,\r\n-# file=First_unshared_motifs_table,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))\r\n-# columnalheader<-matrix(columnalheader,nrow = 1)\r\n-# write.table(x=columnalheader,\r\n-# file=First_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# write.table(x=FTLFinalMatrix,\r\n-# file=First_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# write.table(x=D835YmotifsFINAL,\r\n-# file=Second_unshared_motifs_table,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))\r\n-# columnalheader<-matrix(columnalheader,nrow = 1)\r\n-# write.table(x=columnalheader,\r\n-# file=Second_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# write.table(x=D835YFinalMatrix,\r\n-# file=Second_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# write.table(x=ITDmotifsFINAL,\r\n-# file=Third_unshared_motifs_table,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# columnalheader<-c("Accession Numbers",as.character(Thirdsubbackfreq[1:35,1]))\r\n-# columnalheader<-matrix(columnalheader,nrow = 1)\r\n-# write.table(x=columnalheader,\r\n-# file=Third_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# write.table(x=ITDFinalMatrix,\r\n-# file=Third_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# \r\n-# }\r\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/Difference finder MADE 7 TO 7 4-18-2019.R --- a/all stuff/Difference finder MADE 7 TO 7 4-18-2019.R Fri Apr 19 16:55:29 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,351 +0,0 @@\n-#I should make an SOP for this. Problems we encountered: no x in the xY motif, and the kilodemon\r\n-#the output files have both Y and xY, they shouldn\'t why is that happening? make it not happen\r\n-#make sure that accession numbers stay locked to each motif, somehow\r\n-#output should look just like the KALIP input\r\n-\r\n-#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n-FullMotifsOnly_questionmark<-"NO"\r\n-#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n-TruncatedMotifsOnly_questionmark<-"NO"\r\n-#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)\r\n-Are_You_Looking_For_Commonality<-"NO"\r\n-\r\n-\r\n-#put the names of your input files here\r\n-FirstSubstrateSet<- read.csv("Galaxy1071-(17A_TiO2_Substrates.csv).csv", stringsAsFactors=FALSE)\r\n-Firstsubbackfreq<- read.csv("Galaxy1072-(17A_TiO2_SubstrateBackgroundFrequency.csv).csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-SecondSubstrateSet<- read.csv("Galaxy1073-(17A_FeNTA_Substrates.csv) (1).csv", stringsAsFactors=FALSE)\r\n-Secondsubbackfreq<- read.csv("Galaxy1074-(17A_FeNTA_SubstrateBackgroundFrequency.csv).csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-# ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)\r\n-# Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-#then put the names of your output files here\r\n-# Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"\r\n-# Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"\r\n-\r\n-# Shared_motifs_table<-"Shared motifs 7-27-17.csv"\r\n-# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"\r\n-\r\n-First_unshared_motifs_table<-"17A TIo2 without FeNTA.csv"\r\n-First_unshared_subbackfreq<-"17A TIo2 without FeNTA sbf.csv"\r\n-\r\n-Second_unshared_motifs_table<-"17A FeNTA without TIo2.csv"\r\n-Second_unshared_subbackfreq<-"17A FeNTA without TIo2 sbf.csv"\r\n-\r\n-# Third_unshared_motifs_table<-"R3 subs.csv"\r\n-# Third_unshared_subbackfreq<-"R3 SBF.csv"\r\n-\r\n-#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\r\n-#other languages to see if any of them can do it.\r\n-####################################################################################################################################\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-# grepl(pattern = "S", x=asdf, ignore.case = TRUE)\r\n-\r\n-FirstCentralLetters<-FirstSubstrateSet[,11]\r\n-SecondCentralLetters<-SecondSubstrateSet[,11]\r\n-\r\n-FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")\r\n-\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")\r\n-\r\n-FirstCentralLetters->FirstSubstrateSet[,11]\r\n-SecondCentralLetters->SecondSubstrateSet[,11]\r\n-\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-# better version of this code written in C: what happens wh'..b'es(FTLoutputmatrix2)<-NULL\r\n- rownames(FTLoutputmatrix2)<-NULL\r\n- colnames(FLTheader)<-NULL\r\n- rownames(FLTheader)<-NULL\r\n- \r\n- \r\n- FirstCentralLettersAGAIN<-FTLoutputmatrix2[,11]\r\n- \r\n- FirstEsses<-sapply(FirstCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)\r\n- FirstTees<-sapply(FirstCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)\r\n- FirstWys<-sapply(FirstCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)\r\n- \r\n- FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstEsses,"xS")\r\n- FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstTees,"xT")\r\n- FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstWys,"xY")\r\n- \r\n- FirstCentralLettersAGAIN->FTLoutputmatrix2[,11]\r\n- \r\n- FTLoutputmatrix2<-rbind(FLTheader,FTLoutputmatrix2)\r\n- \r\n- write.table(x=FTLoutputmatrix2,\r\n- file=First_unshared_motifs_table,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n- columnalheader<-matrix(columnalheader,nrow = 1)\r\n- write.table(x=columnalheader,\r\n- file=First_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- write.table(x=FTLFinalMatrix,\r\n- file=First_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- ############################################################################################################\r\n- \r\n- D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)\r\n- \r\n- D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")\r\n- # D835Yheader<-unlist(D835Yheader)\r\n- lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n- righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n- D835Yaset<-D835Youtputmatrix[,2]\r\n- D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")\r\n- D835meat<-sapply(D835meat, unlist)\r\n- colnames(D835meat)<-NULL\r\n- D835meat<-t(D835meat)\r\n- \r\n- D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)\r\n- colnames(D835Youtputmatrix2)<-NULL\r\n- rownames(D835Youtputmatrix2)<-NULL\r\n- colnames(D835Yheader)<-NULL\r\n- rownames(D835Yheader)<-NULL\r\n- \r\n- \r\n- SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]\r\n- \r\n- SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)\r\n- SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)\r\n- SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)\r\n- \r\n- SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")\r\n- SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")\r\n- SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")\r\n- \r\n- SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]\r\n- \r\n- D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)\r\n- \r\n- write.table(x=D835Youtputmatrix2,\r\n- file=Second_unshared_motifs_table,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n- columnalheader<-matrix(columnalheader,nrow = 1)\r\n- write.table(x=columnalheader,\r\n- file=Second_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- write.table(x=D835YFinalMatrix,\r\n- file=Second_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-}\r\n-\r\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/Difference finder for GalaxyP 2-21-20.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/all stuff/Difference finder for GalaxyP 2-21-20.R Fri Feb 21 13:07:45 2020 -0500 |
| [ |
| b'@@ -0,0 +1,358 @@\n+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n+FullMotifsOnly_questionmark<-"NO"\r\n+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n+TruncatedMotifsOnly_questionmark<-"NO"\r\n+#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)\r\n+Are_You_Looking_For_Commonality<-"NO"\r\n+\r\n+\r\n+#put the names of your input files here\r\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE,colClasses = "character")\r\n+Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)\r\n+\r\n+SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE,colClasses = "character")\r\n+Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)\r\n+\r\n+\r\n+First_unshared_motifs_table<-"1RS.csv"\r\n+First_unshared_subbackfreq<-"1RSBF.csv"\r\n+\r\n+Second_unshared_motifs_table<-"2RS.csv"\r\n+Second_unshared_subbackfreq<-"2RSBF.csv"\r\n+\r\n+EmptySubHeader<-colnames(FirstSubstrateSet)\r\n+EmptySubHeader<-matrix(EmptySubHeader, nrow=1)\r\n+EmptySBFHeader<-Firstsubbackfreq[,1]\r\n+\r\n+#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\r\n+#other languages to see if any of them can do it.\r\n+####################################################################################################################################\r\n+\r\n+\r\n+FirstCentralLetters<-FirstSubstrateSet[,11]\r\n+SecondCentralLetters<-SecondSubstrateSet[,11]\r\n+\r\n+FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n+FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n+FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n+\r\n+SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n+SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n+SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n+\r\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")\r\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")\r\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")\r\n+\r\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")\r\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")\r\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")\r\n+\r\n+FirstCentralLetters->FirstSubstrateSet[,11]\r\n+SecondCentralLetters->SecondSubstrateSet[,11]\r\n+\r\n+####################################################################################################################################\r\n+####################################################################################################################################\r\n+# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two \r\n+# separate proteins thus two separate accession numbers?\r\n+# It should actually output the shared motif and BOTH accession numbers. Right now it does not, it only maps out the second\r\n+# accession number. So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number\r\n+####################################################################################################################################\r\n+####################################################################################################################################\r\n+####################################################################################################################################\r\n+####################################################################################################################################\r\n+\r\n+#Create the motif sets, deciding wether or not you\'re looking for truncated or full here\r\n+#full only\r\n+\r\n+\r\n+###############################################\r\n+#ALL motifs, full and truncated\r\n+\r\n+if (FullMotifs'..b' row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+}\r\n+\r\n+\r\n+columnalheader<-c(rep(NA,36))\r\n+D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)\r\n+\r\n+if (length(D835YmotifsFINAL)>0){\r\n+ for (k in 1:length(D835YmotifsFINAL)) {\r\n+ #I don\'t remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is\r\n+ #destroyed immediately after use\r\n+ for (m in 1:ncol(Secondsubbackfreq)) {\r\n+ AN <- as.character(Secondsubbackfreq[1, m])\r\n+ if (grepl(pattern = AN,\r\n+ x = names(D835YmotifsFINAL[k]),\r\n+ fixed = TRUE) == TRUE) {\r\n+ outputmatrix <- as.character(Secondsubbackfreq[, m])\r\n+ outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n+ #with that accession number, find a match in the subbackfreq file and save it here\r\n+ D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)\r\n+ }\r\n+ }\r\n+ }\r\n+ D835YFinalMatrix<-D835YFinalMatrix[!duplicated(D835YFinalMatrix),]\r\n+ D835YFinalMatrix<-D835YFinalMatrix[2:nrow(D835YFinalMatrix),]\r\n+ \r\n+ D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)\r\n+ \r\n+ D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")\r\n+ # D835Yheader<-unlist(D835Yheader)\r\n+ lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n+ righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n+ D835Yaset<-D835Youtputmatrix[,2]\r\n+ D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")\r\n+ D835meat<-sapply(D835meat, unlist)\r\n+ colnames(D835meat)<-NULL\r\n+ D835meat<-t(D835meat)\r\n+ \r\n+ D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)\r\n+ colnames(D835Youtputmatrix2)<-NULL\r\n+ rownames(D835Youtputmatrix2)<-NULL\r\n+ colnames(D835Yheader)<-NULL\r\n+ rownames(D835Yheader)<-NULL\r\n+ \r\n+ \r\n+ SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]\r\n+ \r\n+ SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)\r\n+ SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)\r\n+ SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)\r\n+ \r\n+ SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")\r\n+ SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")\r\n+ SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")\r\n+ \r\n+ SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]\r\n+ \r\n+ D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)\r\n+ \r\n+ write.table(x=D835Youtputmatrix2,\r\n+ file=Second_unshared_motifs_table,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+ \r\n+ columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n+ columnalheader<-matrix(columnalheader,nrow = 1)\r\n+ write.table(x=columnalheader,\r\n+ file=Second_unshared_subbackfreq,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+ \r\n+ write.table(x=D835YFinalMatrix,\r\n+ file=Second_unshared_subbackfreq,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+} else {\r\n+ D835YFinalMatrix<- columnalheader\r\n+ write.table(x=EmptySubHeader,\r\n+ file=Second_unshared_motifs_table,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+ \r\n+ columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n+ columnalheader<-matrix(columnalheader,nrow = 1)\r\n+ write.table(x=columnalheader,\r\n+ file=Second_unshared_subbackfreq,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+}\n\\ No newline at end of file\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/Difference finder for GalaxyP 4-18-2019.R --- a/all stuff/Difference finder for GalaxyP 4-18-2019.R Fri Apr 19 16:55:29 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,351 +0,0 @@\n-#I should make an SOP for this. Problems we encountered: no x in the xY motif, and the kilodemon\r\n-#the output files have both Y and xY, they shouldn\'t why is that happening? make it not happen\r\n-#make sure that accession numbers stay locked to each motif, somehow\r\n-#output should look just like the KALIP input\r\n-\r\n-#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n-FullMotifsOnly_questionmark<-"NO"\r\n-#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n-TruncatedMotifsOnly_questionmark<-"NO"\r\n-#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)\r\n-Are_You_Looking_For_Commonality<-"NO"\r\n-\r\n-\r\n-#put the names of your input files here\r\n-FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\r\n-Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE)\r\n-Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-# ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)\r\n-# Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-#then put the names of your output files here\r\n-# Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"\r\n-# Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"\r\n-\r\n-# Shared_motifs_table<-"Shared motifs 7-27-17.csv"\r\n-# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"\r\n-\r\n-First_unshared_motifs_table<-"1RS.csv"\r\n-First_unshared_subbackfreq<-"1RSBF.csv"\r\n-\r\n-Second_unshared_motifs_table<-"2RS.csv"\r\n-Second_unshared_subbackfreq<-"2RSBF.csv"\r\n-\r\n-# Third_unshared_motifs_table<-"R3 subs.csv"\r\n-# Third_unshared_subbackfreq<-"R3 SBF.csv"\r\n-\r\n-#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\r\n-#other languages to see if any of them can do it.\r\n-####################################################################################################################################\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-# grepl(pattern = "S", x=asdf, ignore.case = TRUE)\r\n-\r\n-FirstCentralLetters<-FirstSubstrateSet[,11]\r\n-SecondCentralLetters<-SecondSubstrateSet[,11]\r\n-\r\n-FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")\r\n-\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")\r\n-\r\n-FirstCentralLetters->FirstSubstrateSet[,11]\r\n-SecondCentralLetters->SecondSubstrateSet[,11]\r\n-\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two \r\n-# separate proteins thus two separate accession numbers?\r\n-# It should actually output the shared motif and BOTH accession numbers. Right now it does not, it only maps out the second\r\n-# '..b'es(FTLoutputmatrix2)<-NULL\r\n- rownames(FTLoutputmatrix2)<-NULL\r\n- colnames(FLTheader)<-NULL\r\n- rownames(FLTheader)<-NULL\r\n- \r\n- \r\n- FirstCentralLettersAGAIN<-FTLoutputmatrix2[,11]\r\n- \r\n- FirstEsses<-sapply(FirstCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)\r\n- FirstTees<-sapply(FirstCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)\r\n- FirstWys<-sapply(FirstCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)\r\n- \r\n- FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstEsses,"xS")\r\n- FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstTees,"xT")\r\n- FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstWys,"xY")\r\n- \r\n- FirstCentralLettersAGAIN->FTLoutputmatrix2[,11]\r\n- \r\n- FTLoutputmatrix2<-rbind(FLTheader,FTLoutputmatrix2)\r\n- \r\n- write.table(x=FTLoutputmatrix2,\r\n- file=First_unshared_motifs_table,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n- columnalheader<-matrix(columnalheader,nrow = 1)\r\n- write.table(x=columnalheader,\r\n- file=First_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- write.table(x=FTLFinalMatrix,\r\n- file=First_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- ############################################################################################################\r\n- \r\n- D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)\r\n- \r\n- D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")\r\n- # D835Yheader<-unlist(D835Yheader)\r\n- lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n- righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n- D835Yaset<-D835Youtputmatrix[,2]\r\n- D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")\r\n- D835meat<-sapply(D835meat, unlist)\r\n- colnames(D835meat)<-NULL\r\n- D835meat<-t(D835meat)\r\n- \r\n- D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)\r\n- colnames(D835Youtputmatrix2)<-NULL\r\n- rownames(D835Youtputmatrix2)<-NULL\r\n- colnames(D835Yheader)<-NULL\r\n- rownames(D835Yheader)<-NULL\r\n- \r\n- \r\n- SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]\r\n- \r\n- SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)\r\n- SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)\r\n- SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)\r\n- \r\n- SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")\r\n- SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")\r\n- SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")\r\n- \r\n- SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]\r\n- \r\n- D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)\r\n- \r\n- write.table(x=D835Youtputmatrix2,\r\n- file=Second_unshared_motifs_table,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n- columnalheader<-matrix(columnalheader,nrow = 1)\r\n- write.table(x=columnalheader,\r\n- file=Second_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- write.table(x=D835YFinalMatrix,\r\n- file=Second_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-}\r\n-\r\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/Difference finder for GalaxyP working.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/all stuff/Difference finder for GalaxyP working.R Fri Feb 21 13:07:45 2020 -0500 |
| [ |
| b'@@ -0,0 +1,358 @@\n+#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n+FullMotifsOnly_questionmark<-"NO"\r\n+#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n+TruncatedMotifsOnly_questionmark<-"NO"\r\n+#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)\r\n+Are_You_Looking_For_Commonality<-"NO"\r\n+\r\n+\r\n+#put the names of your input files here\r\n+FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE,colClasses = "character")\r\n+Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)\r\n+\r\n+SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE,colClasses = "character")\r\n+Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)\r\n+\r\n+\r\n+First_unshared_motifs_table<-"1RS.csv"\r\n+First_unshared_subbackfreq<-"1RSBF.csv"\r\n+\r\n+Second_unshared_motifs_table<-"2RS.csv"\r\n+Second_unshared_subbackfreq<-"2RSBF.csv"\r\n+\r\n+EmptySubHeader<-colnames(FirstSubstrateSet)\r\n+EmptySubHeader<-matrix(EmptySubHeader, nrow=1)\r\n+EmptySBFHeader<-Firstsubbackfreq[,1]\r\n+\r\n+#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\r\n+#other languages to see if any of them can do it.\r\n+####################################################################################################################################\r\n+\r\n+\r\n+FirstCentralLetters<-FirstSubstrateSet[,11]\r\n+SecondCentralLetters<-SecondSubstrateSet[,11]\r\n+\r\n+FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n+FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n+FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n+\r\n+SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n+SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n+SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n+\r\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")\r\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")\r\n+FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")\r\n+\r\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")\r\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")\r\n+SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")\r\n+\r\n+FirstCentralLetters->FirstSubstrateSet[,11]\r\n+SecondCentralLetters->SecondSubstrateSet[,11]\r\n+\r\n+####################################################################################################################################\r\n+####################################################################################################################################\r\n+# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two \r\n+# separate proteins thus two separate accession numbers?\r\n+# It should actually output the shared motif and BOTH accession numbers. Right now it does not, it only maps out the second\r\n+# accession number. So that needs to be fixed BUT you need to keep the commonality between a motif and its accession number\r\n+####################################################################################################################################\r\n+####################################################################################################################################\r\n+####################################################################################################################################\r\n+####################################################################################################################################\r\n+\r\n+#Create the motif sets, deciding wether or not you\'re looking for truncated or full here\r\n+#full only\r\n+\r\n+\r\n+###############################################\r\n+#ALL motifs, full and truncated\r\n+\r\n+if (FullMotifs'..b' row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+}\r\n+\r\n+\r\n+columnalheader<-c(rep(NA,36))\r\n+D835YFinalMatrix<-matrix(data =columnalheader,nrow = 1)\r\n+\r\n+if (length(D835YmotifsFINAL)>0){\r\n+ for (k in 1:length(D835YmotifsFINAL)) {\r\n+ #I don\'t remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is\r\n+ #destroyed immediately after use\r\n+ for (m in 1:ncol(Secondsubbackfreq)) {\r\n+ AN <- as.character(Secondsubbackfreq[1, m])\r\n+ if (grepl(pattern = AN,\r\n+ x = names(D835YmotifsFINAL[k]),\r\n+ fixed = TRUE) == TRUE) {\r\n+ outputmatrix <- as.character(Secondsubbackfreq[, m])\r\n+ outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n+ #with that accession number, find a match in the subbackfreq file and save it here\r\n+ D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)\r\n+ }\r\n+ }\r\n+ }\r\n+ D835YFinalMatrix<-D835YFinalMatrix[!duplicated(D835YFinalMatrix),]\r\n+ D835YFinalMatrix<-D835YFinalMatrix[2:nrow(D835YFinalMatrix),]\r\n+ \r\n+ D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)\r\n+ \r\n+ D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")\r\n+ # D835Yheader<-unlist(D835Yheader)\r\n+ lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n+ righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n+ D835Yaset<-D835Youtputmatrix[,2]\r\n+ D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")\r\n+ D835meat<-sapply(D835meat, unlist)\r\n+ colnames(D835meat)<-NULL\r\n+ D835meat<-t(D835meat)\r\n+ \r\n+ D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)\r\n+ colnames(D835Youtputmatrix2)<-NULL\r\n+ rownames(D835Youtputmatrix2)<-NULL\r\n+ colnames(D835Yheader)<-NULL\r\n+ rownames(D835Yheader)<-NULL\r\n+ \r\n+ \r\n+ SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]\r\n+ \r\n+ SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)\r\n+ SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)\r\n+ SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)\r\n+ \r\n+ SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")\r\n+ SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")\r\n+ SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")\r\n+ \r\n+ SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]\r\n+ \r\n+ D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)\r\n+ \r\n+ write.table(x=D835Youtputmatrix2,\r\n+ file=Second_unshared_motifs_table,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+ \r\n+ columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n+ columnalheader<-matrix(columnalheader,nrow = 1)\r\n+ write.table(x=columnalheader,\r\n+ file=Second_unshared_subbackfreq,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+ \r\n+ write.table(x=D835YFinalMatrix,\r\n+ file=Second_unshared_subbackfreq,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+} else {\r\n+ D835YFinalMatrix<- columnalheader\r\n+ write.table(x=EmptySubHeader,\r\n+ file=Second_unshared_motifs_table,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+ \r\n+ columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n+ columnalheader<-matrix(columnalheader,nrow = 1)\r\n+ write.table(x=columnalheader,\r\n+ file=Second_unshared_subbackfreq,\r\n+ quote=FALSE, sep=",",\r\n+ row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n+}\n\\ No newline at end of file\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/Difference finderMADE 7 TO 7 1-15-2019.R --- a/all stuff/Difference finderMADE 7 TO 7 1-15-2019.R Fri Apr 19 16:55:29 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,351 +0,0 @@\n-#I should make an SOP for this. Problems we encountered: no x in the xY motif, and the kilodemon\r\n-#the output files have both Y and xY, they shouldn\'t why is that happening? make it not happen\r\n-#make sure that accession numbers stay locked to each motif, somehow\r\n-#output should look just like the KALIP input\r\n-\r\n-#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n-FullMotifsOnly_questionmark<-"NO"\r\n-#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n-TruncatedMotifsOnly_questionmark<-"NO"\r\n-#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)\r\n-Are_You_Looking_For_Commonality<-"NO"\r\n-\r\n-\r\n-#put the names of your input files here\r\n-FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)\r\n-Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE)\r\n-Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-# ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)\r\n-# Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-#then put the names of your output files here\r\n-# Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"\r\n-# Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"\r\n-\r\n-# Shared_motifs_table<-"Shared motifs 7-27-17.csv"\r\n-# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"\r\n-\r\n-First_unshared_motifs_table<-"1RS.csv"\r\n-First_unshared_subbackfreq<-"1RSBF.csv"\r\n-\r\n-Second_unshared_motifs_table<-"2RS.csv"\r\n-Second_unshared_subbackfreq<-"2RSBF.csv"\r\n-\r\n-# Third_unshared_motifs_table<-"R3 subs.csv"\r\n-# Third_unshared_subbackfreq<-"R3 SBF.csv"\r\n-\r\n-#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\r\n-#other languages to see if any of them can do it.\r\n-####################################################################################################################################\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-# grepl(pattern = "S", x=asdf, ignore.case = TRUE)\r\n-\r\n-FirstCentralLetters<-FirstSubstrateSet[,11]\r\n-SecondCentralLetters<-SecondSubstrateSet[,11]\r\n-\r\n-FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")\r\n-\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")\r\n-\r\n-FirstCentralLetters->FirstSubstrateSet[,11]\r\n-SecondCentralLetters->SecondSubstrateSet[,11]\r\n-\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-# better version of this code written in C: what happens when two kinases share a motif, but they found that motif in two \r\n-# separate proteins thus two separate accession numbers?\r\n-# It should actually output the shared motif and BOTH accession numbers. Right now it does not, it only maps out the second\r\n-# '..b'es(FTLoutputmatrix2)<-NULL\r\n- rownames(FTLoutputmatrix2)<-NULL\r\n- colnames(FLTheader)<-NULL\r\n- rownames(FLTheader)<-NULL\r\n- \r\n- \r\n- FirstCentralLettersAGAIN<-FTLoutputmatrix2[,11]\r\n- \r\n- FirstEsses<-sapply(FirstCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)\r\n- FirstTees<-sapply(FirstCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)\r\n- FirstWys<-sapply(FirstCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)\r\n- \r\n- FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstEsses,"xS")\r\n- FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstTees,"xT")\r\n- FirstCentralLettersAGAIN<-replace(FirstCentralLettersAGAIN,FirstWys,"xY")\r\n- \r\n- FirstCentralLettersAGAIN->FTLoutputmatrix2[,11]\r\n- \r\n- FTLoutputmatrix2<-rbind(FLTheader,FTLoutputmatrix2)\r\n- \r\n- write.table(x=FTLoutputmatrix2,\r\n- file=First_unshared_motifs_table,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n- columnalheader<-matrix(columnalheader,nrow = 1)\r\n- write.table(x=columnalheader,\r\n- file=First_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- write.table(x=FTLFinalMatrix,\r\n- file=First_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- ############################################################################################################\r\n- \r\n- D835Youtputmatrix<-matrix(data=c(D835YmotifsFINAL,names(D835YmotifsFINAL)),ncol = 2)\r\n- \r\n- D835Yheader<-c("Substrate","Species","Reference","-7","-6","-5","-4","-3","-2","-1","0","1","2","3","4","5","6","7","Phosphite")\r\n- # D835Yheader<-unlist(D835Yheader)\r\n- lefthandD835<-matrix(data = rep(NA,times=2*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n- righthandD835<-matrix(data = rep(NA,times=1*nrow(D835Youtputmatrix)),nrow=nrow(D835Youtputmatrix))\r\n- D835Yaset<-D835Youtputmatrix[,2]\r\n- D835meat<-sapply(D835Youtputmatrix[,1], strsplit, "")\r\n- D835meat<-sapply(D835meat, unlist)\r\n- colnames(D835meat)<-NULL\r\n- D835meat<-t(D835meat)\r\n- \r\n- D835Youtputmatrix2<-cbind(lefthandD835,D835Yaset,D835meat,righthandD835)\r\n- colnames(D835Youtputmatrix2)<-NULL\r\n- rownames(D835Youtputmatrix2)<-NULL\r\n- colnames(D835Yheader)<-NULL\r\n- rownames(D835Yheader)<-NULL\r\n- \r\n- \r\n- SecondCentralLettersAGAIN<-D835Youtputmatrix2[,11]\r\n- \r\n- SecondEsses<-sapply(SecondCentralLettersAGAIN, grepl, pattern="S", ignore.case=TRUE)\r\n- SecondTees<-sapply(SecondCentralLettersAGAIN, grepl, pattern="T", ignore.case=TRUE)\r\n- SecondWys<-sapply(SecondCentralLettersAGAIN, grepl, pattern="Y", ignore.case=TRUE)\r\n- \r\n- SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondEsses,"xS")\r\n- SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondTees,"xT")\r\n- SecondCentralLettersAGAIN<-replace(SecondCentralLettersAGAIN,SecondWys,"xY")\r\n- \r\n- SecondCentralLettersAGAIN->D835Youtputmatrix2[,11]\r\n- \r\n- D835Youtputmatrix2<-rbind(D835Yheader,D835Youtputmatrix2)\r\n- \r\n- write.table(x=D835Youtputmatrix2,\r\n- file=Second_unshared_motifs_table,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- columnalheader<-c("Accession Numbers",as.character(Firstsubbackfreq[1:35,1]))\r\n- columnalheader<-matrix(columnalheader,nrow = 1)\r\n- write.table(x=columnalheader,\r\n- file=Second_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n- \r\n- write.table(x=D835YFinalMatrix,\r\n- file=Second_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-}\r\n-\r\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/Difference finderMADE 7 TO 7 fastversion 2-14-2019.R --- a/all stuff/Difference finderMADE 7 TO 7 fastversion 2-14-2019.R Fri Apr 19 16:55:29 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,453 +0,0 @@\n-#I should make an SOP for this. Problems we encountered: no x in the xY motif, and the kilodemon\r\n-#the output files have both Y and xY, they shouldn\'t why is that happening? make it not happen\r\n-#make sure that accession numbers stay locked to each motif, somehow\r\n-#output should look just like the KALIP input\r\n-#S2 is negatives\r\n-#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n-FullMotifsOnly_questionmark<-"NO"\r\n-#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n-TruncatedMotifsOnly_questionmark<-"NO"\r\n-#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)\r\n-Are_You_Looking_For_Commonality<-"NO"\r\n-\r\n-\r\n-#put the names of your input files here\r\n-FirstSubstrateSet<- read.csv("Substrates 1A TiO2 and FeNTA no duplicates.csv", stringsAsFactors=FALSE)\r\n-Firstsubbackfreq<- read.csv("SBF 1A TiO2 and FeNTA no duplicates.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-SecondSubstrateSet<- read.csv("Substrates 1B TiO2 and FeNTA no duplicates.csv", stringsAsFactors=FALSE)\r\n-Secondsubbackfreq<- read.csv("SBF 1B TiO2 and FeNTA no duplicates.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-# ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)\r\n-# Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-#then put the names of your output files here\r\n-# Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"\r\n-# Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"\r\n-\r\n-# Shared_motifs_table<-"Shared motifs 7-27-17.csv"\r\n-# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"\r\n-\r\n-First_unshared_motifs_table<-"pka_minus_wo-plus_wo_vector_subs.csv"\r\n-First_unshared_subbackfreq<-"pka_minus_wo-plus_wo_vector_sbf.csv"\r\n-\r\n-Second_unshared_motifs_table<-"pka_plus_wo-minus_wo_vector_subs.csv"\r\n-Second_unshared_subbackfreq<-"pka_plus_wo-minus_wo_vector_sbf.csv"\r\n-\r\n-# Third_unshared_motifs_table<-"R3 subs.csv"\r\n-# Third_unshared_subbackfreq<-"R3 SBF.csv"\r\n-\r\n-#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\r\n-#other languages to see if any of them can do it.\r\n-####################################################################################################################################\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-# grepl(pattern = "S", x=asdf, ignore.case = TRUE)\r\n-\r\n-FirstCentralLetters<-FirstSubstrateSet[,11]\r\n-SecondCentralLetters<-SecondSubstrateSet[,11]\r\n-\r\n-FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")\r\n-\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")\r\n-\r\n-FirstCentralLetters->FirstSubstrateSet[,11]\r\n-SecondCentralLetters->SecondSubstrateSet[,11]\r\n-\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-# better version of this code written in C: w'..b'otif, which is the Y and +/- 4 amino acids, including truncation\r\n-# motif<-motif[!motif %in% "x"]\r\n-# motif<-paste(motif, sep="", collapse="")\r\n-# FTLwtletters<-motif\r\n-# FTLwtmotifs[i,1]<-FTLwtletters\r\n-# FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]\r\n-# \r\n-# \r\n-# }\r\n-# \r\n-# }\r\n-\r\n-\r\n-\r\n-# for (i in 1:nrow(SecondSubstrateSet)){\r\n-# D835letters<-SecondSubstrateSet[i,4:18]\r\n-# D835letters<-D835letters[D835letters !="XXXXX"]\r\n-# D835letters<-paste(D835letters, sep="", collapse="")\r\n-# leftspaces<-c()\r\n-# rightspaces<-c()\r\n-# \r\n-# YYYmotif <- unlist(strsplit(D835letters, split = ""))\r\n-# YYYposition <- match(x = "x", table = YYYmotif)\r\n-# #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\r\n-# #just 3 letters to the left of x\r\n-# \r\n-# YYYLettersToTheLeft <- YYYposition - 1\r\n-# #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\r\n-# #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1\r\n-# YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1\r\n-# #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\r\n-# #variable the user puts in is\r\n-# if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {\r\n-# leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))\r\n-# rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))\r\n-# #add blank spaces if the motif has less than 4 letters to the left/right\r\n-# motif<-c(leftspaces,YYYmotif,rightspaces)\r\n-# #save that motif, which is the Y and +/- 4 amino acids, including truncation\r\n-# motif<-motif[!motif %in% "x"]\r\n-# motif<-paste(motif, sep="", collapse="")\r\n-# D835letters<-motif\r\n-# D835Ymotifs[i,1]<-D835letters\r\n-# D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]\r\n-# }\r\n-# \r\n-# if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){\r\n-# motif<-YYYmotif\r\n-# #add blank spaces if the motif has less than 4 letters to the left/right\r\n-# motif<-c(leftspaces,YYYmotif,rightspaces)\r\n-# #save that motif, which is the Y and +/- 4 amino acids, including truncation\r\n-# motif<-motif[!motif %in% "x"]\r\n-# motif<-paste(motif, sep="", collapse="")\r\n-# D835letters<-motif\r\n-# D835Ymotifs[i,1]<-D835letters\r\n-# D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]\r\n-# }\r\n-# }\r\n-\r\n-# for (k in 1:length(FTLwtmotifsFINAL)) {\r\n-# AN<-00000\r\n-# #I don\'t remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is\r\n-# #destroyed immediately after use\r\n-# for (m in 1:ncol(Firstsubbackfreq)) {\r\n-# AN <- as.character(Firstsubbackfreq[1, m])\r\n-# if (grepl(pattern = AN,\r\n-# x = names(FTLwtmotifsFINAL[k]),\r\n-# fixed = TRUE) == TRUE) {\r\n-# outputmatrix <- as.character(Firstsubbackfreq[, m])\r\n-# outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n-# #with that accession number, find a match in the subbackfreq file and save it here\r\n-# FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)\r\n-# }\r\n-# }\r\n-# }\r\n-# for (k in 1:length(D835YmotifsFINAL)) {\r\n-# #I don\'t remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is\r\n-# #destroyed immediately after use\r\n-# for (m in 1:ncol(Secondsubbackfreq)) {\r\n-# AN <- as.character(Secondsubbackfreq[1, m])\r\n-# if (grepl(pattern = AN,\r\n-# x = names(D835YmotifsFINAL[k]),\r\n-# fixed = TRUE) == TRUE) {\r\n-# outputmatrix <- as.character(Secondsubbackfreq[, m])\r\n-# outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n-# #with that accession number, find a match in the subbackfreq file and save it here\r\n-# D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)\r\n-# }\r\n-# }\r\n-# }\n\\ No newline at end of file\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/Difference finderMADE 7 TO 7 fastversion.R --- a/all stuff/Difference finderMADE 7 TO 7 fastversion.R Fri Apr 19 16:55:29 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,451 +0,0 @@\n-#I should make an SOP for this. Problems we encountered: no x in the xY motif, and the kilodemon\r\n-#the output files have both Y and xY, they shouldn\'t why is that happening? make it not happen\r\n-#make sure that accession numbers stay locked to each motif, somehow\r\n-#output should look just like the KALIP input\r\n-#S2 is negatives\r\n-#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n-FullMotifsOnly_questionmark<-"NO"\r\n-#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n-TruncatedMotifsOnly_questionmark<-"NO"\r\n-#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)\r\n-Are_You_Looking_For_Commonality<-"NO"\r\n-\r\n-\r\n-#put the names of your input files here\r\n-FirstSubstrateSet<- read.csv("pka_minus_wo_vector_subs.csv", stringsAsFactors=FALSE)\r\n-Firstsubbackfreq<- read.csv("pka_minus_wo_vector_sbf.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-SecondSubstrateSet<- read.csv("pka_plus_wo_vector_substrates.csv", stringsAsFactors=FALSE)\r\n-Secondsubbackfreq<- read.csv("pka_plus_wo_vector_sbf.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-# ThirdSubstrateSet<- read.csv("Galaxy69-BTK_PLUS_R3_Substrates.csv", stringsAsFactors=FALSE)\r\n-# Thirdsubbackfreq<- read.csv("Galaxy70-BTK_PLUS_R3_SubstrateBackgroundFrequency.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-#then put the names of your output files here\r\n-# Shared_motifs_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-substrates.csv"\r\n-# Shared_subbackfreq_table<-"180719_GALAXY-BTK-plus-rep-OVLP-7to7-SubBackFreq.csv"\r\n-\r\n-# Shared_motifs_table<-"Shared motifs 7-27-17.csv"\r\n-# Shared_subbackfreq_table<-"SubstrateBackgrounFrequency-for-shared-motifs 4 7-27-17.csv"\r\n-\r\n-First_unshared_motifs_table<-"pka_minus_wo-plus_wo_vector_subs.csv"\r\n-First_unshared_subbackfreq<-"pka_minus_wo-plus_wo_vector_sbf.csv"\r\n-\r\n-Second_unshared_motifs_table<-"pka_plus_wo-minus_wo_vector_subs.csv"\r\n-Second_unshared_subbackfreq<-"pka_plus_wo-minus_wo_vector_sbf.csv"\r\n-\r\n-# Third_unshared_motifs_table<-"R3 subs.csv"\r\n-# Third_unshared_subbackfreq<-"R3 SBF.csv"\r\n-\r\n-#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\r\n-#other languages to see if any of them can do it.\r\n-####################################################################################################################################\r\n-\r\n-\r\n-\r\n-\r\n-\r\n-# grepl(pattern = "S", x=asdf, ignore.case = TRUE)\r\n-\r\n-FirstCentralLetters<-FirstSubstrateSet[,11]\r\n-SecondCentralLetters<-SecondSubstrateSet[,11]\r\n-\r\n-FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)\r\n-SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)\r\n-SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)\r\n-\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")\r\n-FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")\r\n-\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")\r\n-SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")\r\n-\r\n-FirstCentralLetters->FirstSubstrateSet[,11]\r\n-SecondCentralLetters->SecondSubstrateSet[,11]\r\n-\r\n-####################################################################################################################################\r\n-####################################################################################################################################\r\n-# better version of this code written in C: what happens when two kinases share a motif, but they fou'..b'otif, which is the Y and +/- 4 amino acids, including truncation\r\n-# motif<-motif[!motif %in% "x"]\r\n-# motif<-paste(motif, sep="", collapse="")\r\n-# FTLwtletters<-motif\r\n-# FTLwtmotifs[i,1]<-FTLwtletters\r\n-# FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]\r\n-# \r\n-# \r\n-# }\r\n-# \r\n-# }\r\n-\r\n-\r\n-\r\n-# for (i in 1:nrow(SecondSubstrateSet)){\r\n-# D835letters<-SecondSubstrateSet[i,4:18]\r\n-# D835letters<-D835letters[D835letters !="XXXXX"]\r\n-# D835letters<-paste(D835letters, sep="", collapse="")\r\n-# leftspaces<-c()\r\n-# rightspaces<-c()\r\n-# \r\n-# YYYmotif <- unlist(strsplit(D835letters, split = ""))\r\n-# YYYposition <- match(x = "x", table = YYYmotif)\r\n-# #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\r\n-# #just 3 letters to the left of x\r\n-# \r\n-# YYYLettersToTheLeft <- YYYposition - 1\r\n-# #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\r\n-# #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1\r\n-# YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1\r\n-# #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\r\n-# #variable the user puts in is\r\n-# if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {\r\n-# leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))\r\n-# rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))\r\n-# #add blank spaces if the motif has less than 4 letters to the left/right\r\n-# motif<-c(leftspaces,YYYmotif,rightspaces)\r\n-# #save that motif, which is the Y and +/- 4 amino acids, including truncation\r\n-# motif<-motif[!motif %in% "x"]\r\n-# motif<-paste(motif, sep="", collapse="")\r\n-# D835letters<-motif\r\n-# D835Ymotifs[i,1]<-D835letters\r\n-# D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]\r\n-# }\r\n-# \r\n-# if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){\r\n-# motif<-YYYmotif\r\n-# #add blank spaces if the motif has less than 4 letters to the left/right\r\n-# motif<-c(leftspaces,YYYmotif,rightspaces)\r\n-# #save that motif, which is the Y and +/- 4 amino acids, including truncation\r\n-# motif<-motif[!motif %in% "x"]\r\n-# motif<-paste(motif, sep="", collapse="")\r\n-# D835letters<-motif\r\n-# D835Ymotifs[i,1]<-D835letters\r\n-# D835YAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]\r\n-# }\r\n-# }\r\n-\r\n-# for (k in 1:length(FTLwtmotifsFINAL)) {\r\n-# AN<-00000\r\n-# #I don\'t remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is\r\n-# #destroyed immediately after use\r\n-# for (m in 1:ncol(Firstsubbackfreq)) {\r\n-# AN <- as.character(Firstsubbackfreq[1, m])\r\n-# if (grepl(pattern = AN,\r\n-# x = names(FTLwtmotifsFINAL[k]),\r\n-# fixed = TRUE) == TRUE) {\r\n-# outputmatrix <- as.character(Firstsubbackfreq[, m])\r\n-# outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n-# #with that accession number, find a match in the subbackfreq file and save it here\r\n-# FTLFinalMatrix<-rbind(FTLFinalMatrix,outputmatrix)\r\n-# }\r\n-# }\r\n-# }\r\n-# for (k in 1:length(D835YmotifsFINAL)) {\r\n-# #I don\'t remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is\r\n-# #destroyed immediately after use\r\n-# for (m in 1:ncol(Secondsubbackfreq)) {\r\n-# AN <- as.character(Secondsubbackfreq[1, m])\r\n-# if (grepl(pattern = AN,\r\n-# x = names(D835YmotifsFINAL[k]),\r\n-# fixed = TRUE) == TRUE) {\r\n-# outputmatrix <- as.character(Secondsubbackfreq[, m])\r\n-# outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n-# #with that accession number, find a match in the subbackfreq file and save it here\r\n-# D835YFinalMatrix<-rbind(D835YFinalMatrix,outputmatrix)\r\n-# }\r\n-# }\r\n-# }\n\\ No newline at end of file\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/difference finder for 2 overlaps proper names 7-7_1-15-2019.R --- a/all stuff/difference finder for 2 overlaps proper names 7-7_1-15-2019.R Fri Apr 19 16:55:29 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,547 +0,0 @@\n-#Difference finder for only 2 \r\n-\r\n-#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps\r\n-FullMotifsOnly_questionmark<-"NO"\r\n-#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps\r\n-TruncatedMotifsOnly_questionmark<-"NO"\r\n-\r\n-FirstSubstrateSet<- read.csv("Substrates 1A TiO2 and FeNTA no duplicates.csv", stringsAsFactors=FALSE)\r\n-Firstsubbackfreq<- read.csv("SBF 1A TiO2 and FeNTA no duplicates.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-SecondSubstrateSet<- read.csv("Substrates 1B TiO2 and FeNTA no duplicates.csv", stringsAsFactors=FALSE)\r\n-Secondsubbackfreq<- read.csv("SBF 1B TiO2 and FeNTA no duplicates.csv", header=FALSE, stringsAsFactors=FALSE)\r\n-\r\n-First_unshared_motifs_table<-"Substrates 1A no duplicates no negatives.csv"\r\n-First_unshared_subbackfreq<-"SBF 1A no duplicates no negatives.csv"\r\n-\r\n-Second_unshared_motifs_table<-"Substrates 1B no duplicates no negatives.csv"\r\n-Second_unshared_subbackfreq<-"SBF 1B no duplicates no negatives.csv"\r\n-\r\n-\r\n-LeftOfYLetters<-7\r\n-RightOfYLetters<-7\r\n-\r\n-if (FullMotifsOnly_questionmark=="YES"){\r\n- FirstMotifs=rep(NA,times=nrow(FirstSubstrateSet))\r\n- FirstAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))\r\n- leftspaces<-c()\r\n- rightspaces<-c()\r\n- for (i in 1:nrow(FirstSubstrateSet)){\r\n- FirstLetters<-FirstSubstrateSet[i,7:15]\r\n- FirstLetters<-FirstLetters[FirstLetters !="XXXXX"]\r\n- FirstLetters<-paste(FirstLetters, sep="", collapse="")\r\n- \r\n- \r\n- YYYmotif <- unlist(strsplit(FirstLetters, split = ""))\r\n- YYYposition <- match(x = "x", table = YYYmotif)\r\n- #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\r\n- #just 3 letters to the left of x\r\n- \r\n- YYYLettersToTheLeft <- YYYposition - 1\r\n- #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\r\n- #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1\r\n- YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1\r\n- #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\r\n- #variable the user puts in is\r\n- \r\n- if (YYYLettersToTheLeft > 3 && YYYLettersToTheRight > 3) {\r\n- motif<-YYYmotif\r\n- #save that motif, which is the Y and +/- 4 amino acids, including truncation\r\n- motif<-motif[!motif %in% "x"]\r\n- motif<-paste(motif, sep="", collapse="")\r\n- FirstLetters<-motif\r\n- FirstMotifs[i]<-FirstLetters\r\n- FirstAccessionNumbers[i]<-FirstSubstrateSet[i,3]\r\n- }\r\n- \r\n- }\r\n- # FirstMotifs <- FirstMotifs[!is.na(FirstMotifs)]\r\n- # FirstMotifs<-matrix(FirstMotifs,ncol = 1)\r\n- # \r\n- \r\n- SecondMotifs=rep(NA,times=nrow(FirstSubstrateSet))\r\n- SecondAccessionNumbers=rep(NA,times=nrow(FirstSubstrateSet))\r\n- \r\n- for (i in 1:nrow(SecondSubstrateSet)){\r\n- SecondLetters<-SecondSubstrateSet[i,7:15]\r\n- SecondLetters<-SecondLetters[SecondLetters !="XXXXX"]\r\n- SecondLetters<-paste(SecondLetters, sep="", collapse="")\r\n- \r\n- \r\n- YYYmotif <- unlist(strsplit(SecondLetters, split = ""))\r\n- YYYposition <- match(x = "x", table = YYYmotif)\r\n- #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\r\n- #just 3 letters to the left of x\r\n- \r\n- YYYLettersToTheLeft <- YYYposition - 1\r\n- #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\r\n- #just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1\r\n- YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1\r\n- #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\r\n- #variable the user puts in is\r\n- \r\n- if (YYYLettersToTheLeft > 3 && YYYLettersToTheRigh'..b' outputmatrix <- as.character(Thirdsubbackfreq[, m])\r\n- outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n- #with that accession number, find a match in the subbackfreq file and save it here\r\n- ITDFinalMatrix<-rbind(ITDFinalMatrix,outputmatrix)\r\n- }\r\n- }\r\n- }\r\n- ITDFinalMatrix<-ITDFinalMatrix[!duplicated(ITDFinalMatrix),]\r\n-}\r\n-\r\n-columnalheader<-c(rep(NA,36))\r\n-SecondFinalMatrix<-matrix(data =columnalheader,nrow = 1)\r\n-\r\n-for (k in 1:length(SecondMotifsFINAL)) {\r\n- #I don\'t remember why, but I felt it necessary to destroy the accession number multiple times to ensure it is\r\n- #destroyed immediately after use\r\n- for (m in 1:ncol(Secondsubbackfreq)) {\r\n- AN <- as.character(Secondsubbackfreq[1, m])\r\n- if (grepl(pattern = AN,\r\n- x = names(SecondMotifsFINAL[k]),\r\n- fixed = TRUE) == TRUE) {\r\n- outputmatrix <- as.character(Secondsubbackfreq[, m])\r\n- outputmatrix <- matrix(outputmatrix, nrow = 1)\r\n- #with that accession number, find a match in the subbackfreq file and save it here\r\n- SecondFinalMatrix<-rbind(SecondFinalMatrix,outputmatrix)\r\n- }\r\n- }\r\n-}\r\n-SecondFinalMatrix<-SecondFinalMatrix[!duplicated(SecondFinalMatrix),]\r\n-FTLoutputmatrix<-matrix(data=c(FirstMotifsFINAL,names(FirstMotifsFINAL)),ncol = 2)\r\n-\r\n-\r\n-write.table(x=FTLoutputmatrix,\r\n- file=First_unshared_motifs_table,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-\r\n-columnalheader<-c(as.character(Firstsubbackfreq[1:36,1]))\r\n-columnalheader<-matrix(columnalheader,nrow = 1)\r\n-write.table(x=columnalheader,\r\n- file=First_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-FirstFinalMatrix<-FirstFinalMatrix[2:nrow(FirstFinalMatrix),]\r\n-write.table(x=FirstFinalMatrix,\r\n- file=First_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-\r\n-############################################################################################################\r\n-\r\n-D835Youtputmatrix<-matrix(data=c(SecondMotifsFINAL,names(SecondMotifsFINAL)),ncol = 2)\r\n-\r\n-write.table(x=D835Youtputmatrix,\r\n- file=Second_unshared_motifs_table,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-\r\n-columnalheader<-c(as.character(Firstsubbackfreq[1:36,1]))\r\n-columnalheader<-matrix(columnalheader,nrow = 1)\r\n-write.table(x=columnalheader,\r\n- file=Second_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-SecondFinalMatrix<-SecondFinalMatrix[2:nrow(SecondFinalMatrix),] \r\n-write.table(x=SecondFinalMatrix,\r\n- file=Second_unshared_subbackfreq,\r\n- quote=FALSE, sep=",",\r\n- row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-\r\n-############################################################################################################\r\n-\r\n-# ITDoutputmatrix<-matrix(data = c(ITDmotifsFINAL,names(ITDmotifsFINAL)),ncol = 2)\r\n-# \r\n-# write.table(x=ITDoutputmatrix,\r\n-# file=Third_unshared_motifs_table,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# \r\n-# columnalheader<-c(as.character(Thirdsubbackfreq[1:36,1]))\r\n-# columnalheader<-matrix(columnalheader,nrow = 1)\r\n-# write.table(x=columnalheader,\r\n-# file=Third_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\r\n-# ITDFinalMatrix<-ITDFinalMatrix[2:nrow(ITDFinalMatrix),]\r\n-# write.table(x=ITDFinalMatrix,\r\n-# file=Third_unshared_subbackfreq,\r\n-# quote=FALSE, sep=",",\r\n-# row.names=FALSE,col.names = FALSE, na="", append=TRUE)\n\\ No newline at end of file\n' |
| b |
| diff -r 4dd15c41d9e7 -r 033dd86d3e0c all stuff/differenceFinder.xml --- a/all stuff/differenceFinder.xml Fri Apr 19 16:55:29 2019 -0400 +++ b/all stuff/differenceFinder.xml Fri Feb 21 13:07:45 2020 -0500 |
| b |
| @@ -9,7 +9,7 @@ ln -s '$input3' S2.csv && ln -s '$input4' SBF2.csv && - Rscript '$__tool_directory__/Difference finder for GalaxyP 4-18-2019.R' + Rscript '$__tool_directory__/Difference finder for GalaxyP 2-21-20.R' ]]></command> <inputs> <param format="csv" name="input1" type="data" label="First Substrate Set"/> |