i replaced the low quality position with "N"
and then trimmed N from 5' and 3'
i got the reads which only contain the "N" in the middle
if i want to find those reads before replacement by "N"
WHAT CAN I DO?
THX
such is coding
library(ShortRead)
reads <- readFastq(fastqfile);#
ids<- id(reads); #
seqs <- sread(reads);
nCount<-alphabetFrequency(seqs)[,"N"]
nDist<- table(nCount)
qualityCutoff <- 20
qual <- PhredQuality(quality(quality(reads)))
myqual_mat <- matrix(charToRaw(as.character(unlist(qual))),
nrow=length(qual), byrow=TRUE) # convert quality score to matrix
at <- myqual_mat <
charToRaw(as.character(PhredQuality(as.integer(qualityCutoff))))
letter_subject <- DNAString(paste(rep.int("N", width(seqs)[1]),
collapse=""))
letter <- as(Views(letter_subject, start=1, end=rowSums(at)),
"DNAStringSet")
injectedseqs <- replaceLetterAt(seqs, at, letter)
trimmed <-trimLRPatterns(Rpattern = letter_subject, Lpattern =
letter_subject,subject = injectedseqs)
nCount<-alphabetFrequency(trimmed)[,"N"]
nDist<- table(nCount)
thank u
shan gao
[[alternative HTML version deleted]]
_______________________________________________
Bioc-sig-sequencing mailing list
Bioc-sig-sequencing@r-project.org
https://stat.ethz.ch/mailman/listinfo/bioc-sig-sequencing
