These exercises cover the sections of Conditions and Loops in R Introduction to R.
– Calculate the factorial (factorial of 3 = 3 * 2 * 1) of 10 using a loop.
for(x in 1:10){
if(x == 1){
factorialAnswer <- 1
}else{
factorialAnswer <- factorialAnswer * x
}
}
factorialAnswer## [1] 3628800– Adjusting your answer from before, what is the first number that has a factorial greater than 1000.
factorialAnswer <- 0
count <- 0
while(factorialAnswer <= 1000){
count <- count+1
if(count == 1){
factorialAnswer <- 1
}else{
factorialAnswer <- factorialAnswer * count
}
}
count## [1] 7– Using an ifelse() expression, create a factor from a vector of 1 to 40 where all numbers less than 10 are “small”,10 to 30 are “mid”,31 to 40 are “big”
condExercise <- 1:40
condExercise## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
## [24] 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40vectorResult <- ifelse(condExercise<10,"small",ifelse(condExercise < 31,"mid","big"))
temp <- factor(vectorResult,levels=c("small","mid","big"),order=T)
temp## [1] small small small small small small small small small mid mid
## [12] mid mid mid mid mid mid mid mid mid mid mid
## [23] mid mid mid mid mid mid mid mid big big big
## [34] big big big big big big big
## Levels: small < mid < big– Read in all files from expression directory with .txt extension and create a table of gene expression results.
filesToRead <- dir("../ExpressionResults/",pattern = "*\\.txt",full.names=T)
fileRead <- vector("list",length=length(filesToRead))
for(i in 1:length(filesToRead)){
fileRead[[i]] <- read.delim(filesToRead[i],header=F,sep="\t")
colnames(fileRead[[i]]) <- c("GeneNames",basename(filesToRead[i]))
}
mergedTable <- NULL
for(i in fileRead){
if(is.null(mergedTable)){
mergedTable <- i
}else{
mergedTable <- merge(mergedTable,i,by=1,all=T)
}
print(nrow(mergedTable))
}## [1] 2000
## [1] 2000
## [1] 2000
## [1] 2000
## [1] 2000
## [1] 2000
## [1] 2000
## [1] 2000
## [1] 2000
## [1] 2000mergedTable[1:3,] ## GeneNames ExpressionResults_Sample1.txt ExpressionResults_Sample10.txt
## 1 Gene_1 3.448466 7.665488
## 2 Gene_10 5.314180 7.813501
## 3 Gene_100 5.591612 5.186500
## ExpressionResults_Sample2.txt ExpressionResults_Sample3.txt
## 1 5.250063 5.968927
## 2 5.361170 5.305980
## 3 6.840497 5.197710
## ExpressionResults_Sample4.txt ExpressionResults_Sample5.txt
## 1 6.868251 5.367100
## 2 6.742855 5.957786
## 3 5.922931 6.813154
## ExpressionResults_Sample6.txt ExpressionResults_Sample7.txt
## 1 5.189686 3.882930
## 2 6.293098 7.361497
## 3 6.228178 5.831575
## ExpressionResults_Sample8.txt ExpressionResults_Sample9.txt
## 1 5.329258 6.167451
## 2 6.649428 6.213910
## 3 6.653152 3.992555– Add annotation from Annotation.txt. How do the pathway information for genes compare between expression table and annotation table.
Annotation <- read.table("../ExpressionResults/Annotation.ann",sep="\t",h=T)
annotatedExpression <- merge(Annotation,mergedTable,by=1,all.x=F,all.y=T)
annotatedExpression[1:2,]## GeneName Ensembl Pathway ExpressionResults_Sample1.txt
## 1 Gene_1 Ens_1001 DNA_Binding 3.448466
## 2 Gene_10 Ens_10010 DNA_Binding 5.314180
## ExpressionResults_Sample10.txt ExpressionResults_Sample2.txt
## 1 7.665488 5.250063
## 2 7.813501 5.361170
## ExpressionResults_Sample3.txt ExpressionResults_Sample4.txt
## 1 5.968927 6.868251
## 2 5.305980 6.742855
## ExpressionResults_Sample5.txt ExpressionResults_Sample6.txt
## 1 5.367100 5.189686
## 2 5.957786 6.293098
## ExpressionResults_Sample7.txt ExpressionResults_Sample8.txt
## 1 3.882930 5.329258
## 2 7.361497 6.649428
## ExpressionResults_Sample9.txt
## 1 6.167451
## 2 6.213910summary(annotatedExpression$Pathway)## DNA_Binding Glycolysis TGFb WntSignaling
## 1000 500 300 200summary(Annotation$Pathway)## DNA_Binding Glycolysis TGFb WntSignaling NA's
## 1000 500 300 200 3000– Look at the correlation between samples. Do any samples show a higher degree of correlation.
cor(annotatedExpression[,grep("ExpressionResults",colnames(annotatedExpression))])## ExpressionResults_Sample1.txt
## ExpressionResults_Sample1.txt 1.0000000
## ExpressionResults_Sample10.txt 0.8620963
## ExpressionResults_Sample2.txt 0.8662458
## ExpressionResults_Sample3.txt 0.8681681
## ExpressionResults_Sample4.txt 0.8616757
## ExpressionResults_Sample5.txt 0.8643865
## ExpressionResults_Sample6.txt 0.8712424
## ExpressionResults_Sample7.txt 0.8625237
## ExpressionResults_Sample8.txt 0.8618539
## ExpressionResults_Sample9.txt 0.8686308
## ExpressionResults_Sample10.txt
## ExpressionResults_Sample1.txt 0.8620963
## ExpressionResults_Sample10.txt 1.0000000
## ExpressionResults_Sample2.txt 0.8662233
## ExpressionResults_Sample3.txt 0.8681699
## ExpressionResults_Sample4.txt 0.8701285
## ExpressionResults_Sample5.txt 0.8703278
## ExpressionResults_Sample6.txt 0.8683173
## ExpressionResults_Sample7.txt 0.8698833
## ExpressionResults_Sample8.txt 0.8660971
## ExpressionResults_Sample9.txt 0.8685996
## ExpressionResults_Sample2.txt
## ExpressionResults_Sample1.txt 0.8662458
## ExpressionResults_Sample10.txt 0.8662233
## ExpressionResults_Sample2.txt 1.0000000
## ExpressionResults_Sample3.txt 0.8724322
## ExpressionResults_Sample4.txt 0.8707259
## ExpressionResults_Sample5.txt 0.8715251
## ExpressionResults_Sample6.txt 0.8685840
## ExpressionResults_Sample7.txt 0.8697635
## ExpressionResults_Sample8.txt 0.8697318
## ExpressionResults_Sample9.txt 0.8757107
## ExpressionResults_Sample3.txt
## ExpressionResults_Sample1.txt 0.8681681
## ExpressionResults_Sample10.txt 0.8681699
## ExpressionResults_Sample2.txt 0.8724322
## ExpressionResults_Sample3.txt 1.0000000
## ExpressionResults_Sample4.txt 0.8679524
## ExpressionResults_Sample5.txt 0.8660294
## ExpressionResults_Sample6.txt 0.8699042
## ExpressionResults_Sample7.txt 0.8637106
## ExpressionResults_Sample8.txt 0.8656122
## ExpressionResults_Sample9.txt 0.8704524
## ExpressionResults_Sample4.txt
## ExpressionResults_Sample1.txt 0.8616757
## ExpressionResults_Sample10.txt 0.8701285
## ExpressionResults_Sample2.txt 0.8707259
## ExpressionResults_Sample3.txt 0.8679524
## ExpressionResults_Sample4.txt 1.0000000
## ExpressionResults_Sample5.txt 0.8749856
## ExpressionResults_Sample6.txt 0.8745045
## ExpressionResults_Sample7.txt 0.8670132
## ExpressionResults_Sample8.txt 0.8703234
## ExpressionResults_Sample9.txt 0.8697739
## ExpressionResults_Sample5.txt
## ExpressionResults_Sample1.txt 0.8643865
## ExpressionResults_Sample10.txt 0.8703278
## ExpressionResults_Sample2.txt 0.8715251
## ExpressionResults_Sample3.txt 0.8660294
## ExpressionResults_Sample4.txt 0.8749856
## ExpressionResults_Sample5.txt 1.0000000
## ExpressionResults_Sample6.txt 0.8645176
## ExpressionResults_Sample7.txt 0.8707010
## ExpressionResults_Sample8.txt 0.8716815
## ExpressionResults_Sample9.txt 0.8764503
## ExpressionResults_Sample6.txt
## ExpressionResults_Sample1.txt 0.8712424
## ExpressionResults_Sample10.txt 0.8683173
## ExpressionResults_Sample2.txt 0.8685840
## ExpressionResults_Sample3.txt 0.8699042
## ExpressionResults_Sample4.txt 0.8745045
## ExpressionResults_Sample5.txt 0.8645176
## ExpressionResults_Sample6.txt 1.0000000
## ExpressionResults_Sample7.txt 0.8721725
## ExpressionResults_Sample8.txt 0.8725429
## ExpressionResults_Sample9.txt 0.8722234
## ExpressionResults_Sample7.txt
## ExpressionResults_Sample1.txt 0.8625237
## ExpressionResults_Sample10.txt 0.8698833
## ExpressionResults_Sample2.txt 0.8697635
## ExpressionResults_Sample3.txt 0.8637106
## ExpressionResults_Sample4.txt 0.8670132
## ExpressionResults_Sample5.txt 0.8707010
## ExpressionResults_Sample6.txt 0.8721725
## ExpressionResults_Sample7.txt 1.0000000
## ExpressionResults_Sample8.txt 0.8584981
## ExpressionResults_Sample9.txt 0.8675662
## ExpressionResults_Sample8.txt
## ExpressionResults_Sample1.txt 0.8618539
## ExpressionResults_Sample10.txt 0.8660971
## ExpressionResults_Sample2.txt 0.8697318
## ExpressionResults_Sample3.txt 0.8656122
## ExpressionResults_Sample4.txt 0.8703234
## ExpressionResults_Sample5.txt 0.8716815
## ExpressionResults_Sample6.txt 0.8725429
## ExpressionResults_Sample7.txt 0.8584981
## ExpressionResults_Sample8.txt 1.0000000
## ExpressionResults_Sample9.txt 0.8692940
## ExpressionResults_Sample9.txt
## ExpressionResults_Sample1.txt 0.8686308
## ExpressionResults_Sample10.txt 0.8685996
## ExpressionResults_Sample2.txt 0.8757107
## ExpressionResults_Sample3.txt 0.8704524
## ExpressionResults_Sample4.txt 0.8697739
## ExpressionResults_Sample5.txt 0.8764503
## ExpressionResults_Sample6.txt 0.8722234
## ExpressionResults_Sample7.txt 0.8675662
## ExpressionResults_Sample8.txt 0.8692940
## ExpressionResults_Sample9.txt 1.0000000– For every gene, perform a t-test and write out the t-statistic (assuming unequal variance), log2 fold change, pvalue and gene annotation to a file.
indexGroupOne <- grep("[1-5].txt",colnames(annotatedExpression))
indexGroupTwo <- grep("[6-9,0].txt",colnames(annotatedExpression))
ttestResults <- apply(annotatedExpression,1,function(x)
t.test(as.numeric(x[indexGroupOne]),as.numeric(x[indexGroupTwo])))
str(ttestResults[[1]])## List of 9
## $ statistic : Named num -0.318
## ..- attr(*, "names")= chr "t"
## $ parameter : Named num 7.92
## ..- attr(*, "names")= chr "df"
## $ p.value : num 0.759
## $ conf.int : atomic [1:2] -2.2 1.67
## ..- attr(*, "conf.level")= num 0.95
## $ estimate : Named num [1:2] 5.38 5.65
## ..- attr(*, "names")= chr [1:2] "mean of x" "mean of y"
## $ null.value : Named num 0
## ..- attr(*, "names")= chr "difference in means"
## $ alternative: chr "two.sided"
## $ method : chr "Welch Two Sample t-test"
## $ data.name : chr "as.numeric(x[indexGroupOne]) and as.numeric(x[indexGroupTwo])"
## - attr(*, "class")= chr "htest"testResult <- sapply(ttestResults,function(x) c(log2(x$estimate[2]) - log2(x$estimate[1]), x$statistic,x$p.value))
testResult <- t(testResult)
colnames(testResult) <- c("logFC","tStatistic","pValue")
annotatedResult <- cbind(annotatedExpression[,1:3],testResult)
annotatedResult <- annotatedResult[order(annotatedResult$tStatistic),]
annotatedResult[1:2,]## GeneName Ensembl Pathway logFC tStatistic pValue
## 1491 Gene_54 Ens_10054 DNA_Binding 0.2631082 -5.3950 0.0007161659
## 1716 Gene_742 Ens_100742 Glycolysis 0.2311226 -4.5044 0.0029789595write.table(annotatedResult,file="annotatedResults.csv",sep=",",row.names=F,col.names=F)