My code in R is:
stage 1
x <- read.alignment("humanSeqAligned.fasta", format= "fasta")
stage 2
cleanx <- cleanAlignment(x, 30, 30)
stage3
dBin<-as.DNAbin(cleanx)
stage4
dist <- dist.dna(dBin, model = "K80", variance = FALSE, gamma = FALSE, pairwise.deletion = FALSE, base.freq = NULL, as.matrix = FALSE)
stage5
neighbor <- nj(dist)
stage6
humanSeqTreeRooted <-root(neighbor, "NC_001643.1", r=TRUE)
stage7
pdf(file='/work/projects/project3/project3tree.pdf', height=8, width=8)
plot.phylo(humanSeqTreeRooted, type='p')
dev.off()
stage 8
s <- prcomp(dist, center=TRUE, scale=TRUE)
stage9
pdf(file='/work/07950/projects/project3/project3pca.pdf', height=8, width=8)
biplot(s)
dev.off()