Mercurial > repos > jfb > difference_finder

view all stuff/.Rhistory @ 9:033dd86d3e0c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jfb
date Fri, 21 Feb 2020 13:07:45 -0500
parents
children
line wrap: on
line source

?rnorm
?rnorm
?rnorm
pwr
?pwr
??pwr
power.t.test(n=6, power = .7, type = "two.sample", alternative = "two.sided")
power.t.test(n=6, power = .9, type = "two.sample", alternative = "two.sided")
?power.t.test
power.t.test(n=5, sd=1000, power = .7, type = "paired", alternative = "one.sided")
10^4
power.t.test(n=5, sd=10000, power = .7, type = "paired", alternative = "one.sided")
power.t.test(n=10, delta = 7, sd=10, type = "paired", alternative = "one.sided")
setwd("C:/Users/John Blankenhor/Downloads/difference_finder-4dd15c41d9e7/difference_finder-4dd15c41d9e7/all stuff")
#put the names of your input files here
FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)
Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)
FirstSubstrateSet
EmptySubHeader<-First_unshared_motifs_table[1,]
First_unshared_motifs_table<-"1RS.csv"
First_unshared_subbackfreq<-"1RSBF.csv"
#put the names of your input files here
FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)
Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)
EmptySubHeader<-FirstSubstrateSet[1,]
head(Firstsubbackfreq)
EmptySBFHeader<-Firstsubbackfreq[,1]
#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
FullMotifsOnly_questionmark<-"NO"
#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
TruncatedMotifsOnly_questionmark<-"NO"
#if you want to find the overlap, put a "YES" here (all caps), if you want to find the non-overlap, put "NO" (all caps)
Are_You_Looking_For_Commonality<-"NO"
#put the names of your input files here
FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)
Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)
SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE)
Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)
First_unshared_motifs_table<-"1RS.csv"
First_unshared_subbackfreq<-"1RSBF.csv"
Second_unshared_motifs_table<-"2RS.csv"
Second_unshared_subbackfreq<-"2RSBF.csv"
EmptySubHeader<-FirstSubstrateSet[1,]
EmptySBFHeader<-Firstsubbackfreq[,1]
FirstCentralLetters<-FirstSubstrateSet[,11]
SecondCentralLetters<-SecondSubstrateSet[,11]
FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)
FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)
FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)
SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)
SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")
FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")
FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")
SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")
SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")
SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")
FirstCentralLetters->FirstSubstrateSet[,11]
SecondCentralLetters->SecondSubstrateSet[,11]
if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
for (i in 1:nrow(FirstSubstrateSet)){
FTLwtletters<-FirstSubstrateSet[i,4:18]
FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
leftspaces<-c()
rightspaces<-c()
YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
YYYposition <- match(x = "x", table = YYYmotif)
#position itself tells me how much is to the left of that X by what it's number is.  x at position 4 tells me that there are
#just 3 letters to the left of x
YYYLettersToTheLeft <- YYYposition - 1
#how many letters to the right SHOULD just be length(motif)-position-1 if it's 5 long and x is at 3 then Y is at 4 and there is
#just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
#then sanity check, we're currently looking only at +/-4, but this spot allows for up to +/- 7 as well, just depends on what the
#variable the user puts in is
if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
#add blank spaces if the motif has less than 4 letters to the left/right
motif<-c(leftspaces,YYYmotif,rightspaces)
#save that motif, which is the Y and +/- 4 amino acids, including truncation
motif<-motif[!motif %in% "x"]
motif<-paste(motif, sep="", collapse="")
FTLwtletters<-motif
FTLwtmotifs[i,1]<-FTLwtletters
FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
}
if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
motif<-YYYmotif
#add blank spaces if the motif has less than 4 letters to the left/right
motif<-c(leftspaces,YYYmotif,rightspaces)
#save that motif, which is the Y and +/- 4 amino acids, including truncation
motif<-motif[!motif %in% "x"]
motif<-paste(motif, sep="", collapse="")
FTLwtletters<-motif
FTLwtmotifs[i,1]<-FTLwtletters
FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
}
}
D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
for (i in 1:nrow(SecondSubstrateSet)){
D835letters<-SecondSubstrateSet[i,4:18]
D835letters<-D835letters[D835letters !="XXXXX"]
D835letters<-paste(D835letters, sep="", collapse="")
leftspaces<-c()
rightspaces<-c()
YYYmotif <- unlist(strsplit(D835letters, split = ""))
YYYposition <- match(x = "x", table = YYYmotif)
#position itself tells me how much is to the left of that X by what it's number is.  x at position 4 tells me that there are
#just 3 letters to the left of x
YYYLettersToTheLeft <- YYYposition - 1
#how many letters to the right SHOULD just be length(motif)-position-1 if it's 5 long and x is at 3 then Y is at 4 and there is
#just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
#then sanity check, we're currently looking only at +/-4, but this spot allows for up to +/- 7 as well, just depends on what the
#variable the user puts in is
if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
#add blank spaces if the motif has less than 4 letters to the left/right
motif<-c(leftspaces,YYYmotif,rightspaces)
#save that motif, which is the Y and +/- 4 amino acids, including truncation
motif<-motif[!motif %in% "x"]
motif<-paste(motif, sep="", collapse="")
D835letters<-motif
D835Ymotifs[i,1]<-D835letters
D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
}
if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
motif<-YYYmotif
#add blank spaces if the motif has less than 4 letters to the left/right
motif<-c(leftspaces,YYYmotif,rightspaces)
#save that motif, which is the Y and +/- 4 amino acids, including truncation
motif<-motif[!motif %in% "x"]
motif<-paste(motif, sep="", collapse="")
D835letters<-motif
D835Ymotifs[i,1]<-D835letters
D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
}
}
names(FTLwtmotifs)<-FTLwtAccessionNumbers
names(D835Ymotifs)<-D835YAccessionNumbers
}
FTLwtmotifsFINAL<-FTLwtmotifs[!FTLwtmotifs %in% D835Ymotifs]
FTLwtmotifsFINAL<-FTLwtmotifsFINAL[!duplicated(FTLwtmotifsFINAL)]
D835YmotifsFINAL<-D835Ymotifs[!D835Ymotifs %in% FTLwtmotifs]
D835YmotifsFINAL<-D835YmotifsFINAL[!duplicated(D835YmotifsFINAL)]
if (FullMotifsOnly_questionmark!="YES"&&TruncatedMotifsOnly_questionmark!="YES"){
FTLwtmotifs=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
FTLwtAccessionNumbers=matrix(,nrow = nrow(FirstSubstrateSet),ncol=1)
for (i in 1:nrow(FirstSubstrateSet)){
FTLwtletters<-FirstSubstrateSet[i,4:18]
FTLwtletters<-FTLwtletters[FTLwtletters !="XXXXX"]
FTLwtletters<-paste(FTLwtletters, sep="", collapse="")
leftspaces<-c()
rightspaces<-c()
YYYmotif <- unlist(strsplit(FTLwtletters, split = ""))
YYYposition <- match(x = "x", table = YYYmotif)
#position itself tells me how much is to the left of that X by what it's number is.  x at position 4 tells me that there are
#just 3 letters to the left of x
YYYLettersToTheLeft <- YYYposition - 1
#how many letters to the right SHOULD just be length(motif)-position-1 if it's 5 long and x is at 3 then Y is at 4 and there is
#just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
#then sanity check, we're currently looking only at +/-4, but this spot allows for up to +/- 7 as well, just depends on what the
#variable the user puts in is
if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
#add blank spaces if the motif has less than 4 letters to the left/right
motif<-c(leftspaces,YYYmotif,rightspaces)
#save that motif, which is the Y and +/- 4 amino acids, including truncation
motif<-motif[!motif %in% "x"]
motif<-paste(motif, sep="", collapse="")
FTLwtletters<-motif
FTLwtmotifs[i,1]<-FTLwtletters
FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
}
if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
motif<-YYYmotif
#add blank spaces if the motif has less than 4 letters to the left/right
motif<-c(leftspaces,YYYmotif,rightspaces)
#save that motif, which is the Y and +/- 4 amino acids, including truncation
motif<-motif[!motif %in% "x"]
motif<-paste(motif, sep="", collapse="")
FTLwtletters<-motif
FTLwtmotifs[i,1]<-FTLwtletters
FTLwtAccessionNumbers[i,1]<-FirstSubstrateSet[i,3]
}
}
D835Ymotifs=matrix(,nrow = nrow(SecondSubstrateSet),ncol=1)
D835YAccessionNumbers<-matrix(,nrow = nrow(SecondSubstrateSet),ncol = 1)
for (i in 1:nrow(SecondSubstrateSet)){
D835letters<-SecondSubstrateSet[i,4:18]
D835letters<-D835letters[D835letters !="XXXXX"]
D835letters<-paste(D835letters, sep="", collapse="")
leftspaces<-c()
rightspaces<-c()
YYYmotif <- unlist(strsplit(D835letters, split = ""))
YYYposition <- match(x = "x", table = YYYmotif)
#position itself tells me how much is to the left of that X by what it's number is.  x at position 4 tells me that there are
#just 3 letters to the left of x
YYYLettersToTheLeft <- YYYposition - 1
#how many letters to the right SHOULD just be length(motif)-position-1 if it's 5 long and x is at 3 then Y is at 4 and there is
#just 1 spot to the right of Y so LettersToTheRight<-1 because 5-3-1=1
YYYLettersToTheRight <- length(YYYmotif) - YYYposition - 1
#then sanity check, we're currently looking only at +/-4, but this spot allows for up to +/- 7 as well, just depends on what the
#variable the user puts in is
if (YYYLettersToTheLeft < 7 | YYYLettersToTheRight < 7) {
leftspaces<-rep(" ",times=(7-YYYLettersToTheLeft))
rightspaces<-rep(" ",times=7-(YYYLettersToTheRight))
#add blank spaces if the motif has less than 4 letters to the left/right
motif<-c(leftspaces,YYYmotif,rightspaces)
#save that motif, which is the Y and +/- 4 amino acids, including truncation
motif<-motif[!motif %in% "x"]
motif<-paste(motif, sep="", collapse="")
D835letters<-motif
D835Ymotifs[i,1]<-D835letters
D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
}
if(YYYLettersToTheLeft>6 && YYYLettersToTheRight>6){
motif<-YYYmotif
#add blank spaces if the motif has less than 4 letters to the left/right
motif<-c(leftspaces,YYYmotif,rightspaces)
#save that motif, which is the Y and +/- 4 amino acids, including truncation
motif<-motif[!motif %in% "x"]
motif<-paste(motif, sep="", collapse="")
D835letters<-motif
D835Ymotifs[i,1]<-D835letters
D835YAccessionNumbers[i,1]<-SecondSubstrateSet[i,3]
}
}
names(FTLwtmotifs)<-FTLwtAccessionNumbers
names(D835Ymotifs)<-D835YAccessionNumbers
}
#ff you want ONLY FULL MOTIFS, put "YES" here, please use all caps
FullMotifsOnly_questionmark<-"NO"
#If you want ONLY TRUNCATED MOTIFS, put "YES" here, please use all caps
TruncatedMotifsOnly_questionmark<-"NO"
#if you want to find the overlap, put a "YES" here (all caps), if you want to find the non-overlap, put "NO" (all caps)
Are_You_Looking_For_Commonality<-"NO"
#put the names of your input files here
FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)
Firstsubbackfreq<- read.csv("SBF1.csv", header=FALSE, stringsAsFactors=FALSE)
SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE)
Secondsubbackfreq<- read.csv("SBF2.csv", header=FALSE, stringsAsFactors=FALSE)
First_unshared_motifs_table<-"1RS.csv"
First_unshared_subbackfreq<-"1RSBF.csv"
Second_unshared_motifs_table<-"2RS.csv"
Second_unshared_subbackfreq<-"2RSBF.csv"
EmptySubHeader<-FirstSubstrateSet[1,]
EmptySBFHeader<-Firstsubbackfreq[,1]
FirstCentralLetters<-FirstSubstrateSet[,11]
SecondCentralLetters<-SecondSubstrateSet[,11]
FirstEsses<-sapply(FirstCentralLetters, grepl, pattern="S", ignore.case=TRUE)
FirstTees<-sapply(FirstCentralLetters, grepl, pattern="T", ignore.case=TRUE)
FirstWys<-sapply(FirstCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
SecondEsses<-sapply(SecondCentralLetters, grepl, pattern="S", ignore.case=TRUE)
SecondTees<-sapply(SecondCentralLetters, grepl, pattern="T", ignore.case=TRUE)
SecondWys<-sapply(SecondCentralLetters, grepl, pattern="Y", ignore.case=TRUE)
FirstCentralLetters<-replace(FirstCentralLetters,FirstEsses,"xS")
FirstCentralLetters<-replace(FirstCentralLetters,FirstTees,"xT")
FirstCentralLetters<-replace(FirstCentralLetters,FirstWys,"xY")
SecondCentralLetters<-replace(SecondCentralLetters,SecondEsses,"xS")
SecondCentralLetters<-replace(SecondCentralLetters,SecondTees,"xT")
SecondCentralLetters<-replace(SecondCentralLetters,SecondWys,"xY")
FirstCentralLetters->FirstSubstrateSet[,11]
SecondCentralLetters->SecondSubstrateSet[,11]
FirstSubstrateSet
#put the names of your input files here
FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)
FirstSubstrateSet
head(SecondSubstrateSet)
#put the names of your input files here
FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)
head(SecondSubstrateSet)
FirstSubstrateSet
#put the names of your input files here
FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)
FirstSubstrateSet
#put the names of your input files here
FirstSubstrateSet<- read.csv("S1.csv", stringsAsFactors=FALSE)
SecondSubstrateSet<- read.csv("S2.csv", stringsAsFactors=FALSE)