Mercurial > repos > davidvanzessen > shm_csr
comparison new_imgt.r @ 57:cb779a45537b draft
Uploaded
author | davidvanzessen |
---|---|
date | Tue, 18 Jul 2017 04:28:11 -0400 |
parents | 6cd12c71c3d3 |
children | dc06e94bc1e3 |
comparison
equal
deleted
inserted
replaced
56:ee807645b224 | 57:cb779a45537b |
---|---|
12 | 12 |
13 if("best_match" %in% names(merged)){ | 13 if("best_match" %in% names(merged)){ |
14 merged = merged[!grepl("unmatched", merged$best_match),] | 14 merged = merged[!grepl("unmatched", merged$best_match),] |
15 } | 15 } |
16 | 16 |
17 nrow_dat = 0 | |
18 | |
17 for(f in list.files(imgt.dir, pattern="*.txt$")){ | 19 for(f in list.files(imgt.dir, pattern="*.txt$")){ |
18 #print(paste("filtering", f)) | 20 #print(paste("filtering", f)) |
19 path = file.path(imgt.dir, f) | 21 path = file.path(imgt.dir, f) |
20 dat = read.table(path, header=T, sep="\t", fill=T, quote="", stringsAsFactors=F, check.names=FALSE, comment.char="") | 22 dat = read.table(path, header=T, sep="\t", fill=T, quote="", stringsAsFactors=F, check.names=FALSE, comment.char="") |
21 | 23 |
22 dat = dat[dat[,"Sequence ID"] %in% merged$Sequence.ID,] | 24 dat = dat[dat[,"Sequence ID"] %in% merged$Sequence.ID,] |
23 | 25 |
26 nrow_dat = nrow(dat) | |
27 | |
24 if(nrow(dat) > 0 & grepl("^8_", f)){ #change the FR1 columns to 0 in the "8_..." file | 28 if(nrow(dat) > 0 & grepl("^8_", f)){ #change the FR1 columns to 0 in the "8_..." file |
25 dat[,grepl("^FR1", names(dat))] = 0 | 29 dat[,grepl("^FR1", names(dat))] = 0 |
26 } | 30 } |
27 | 31 |
28 write.table(dat, path, quote=F, sep="\t", row.names=F, col.names=T, na="") | 32 write.table(dat, path, quote=F, sep="\t", row.names=F, col.names=T, na="") |
29 } | 33 } |
34 | |
35 print(paste("Creating new zip for ", gene, "with", nrow_dat, "sequences")) |