ydeng/bch441-work-abc-units
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update: FASTA files may contain gap and stop characters

Browse Source
This commit is contained in:
hyginn 2017-10-14 18:26:16 -04:00
parent d9e7813d27
commit 153e7dcf00
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/ABC-dbUtilities.R
View File

@ -33,7 +33,7 @@ if (!require(xml2, quietly = TRUE)) {
dbSanitizeSequence <- function(s, unambiguous = TRUE) { dbSanitizeSequence <- function(s, unambiguous = TRUE) {
# Remove FASTA header lines, if any, # Remove FASTA header lines, if any,
# flatten any structure that s has, # flatten any structure that s has,
# remove all non-letters, # remove all non-letters except "-" (gap) and "*" (stop),
# convert to uppercase. # convert to uppercase.
# #
# Parameters: # Parameters:
@ -51,7 +51,7 @@ dbSanitizeSequence <- function(s, unambiguous = TRUE) {
s <- unlist(strsplit(s, "\n")) # split up at linebreaks, if any s <- unlist(strsplit(s, "\n")) # split up at linebreaks, if any
s <- s[! grepl("^>", s)] # drop all lines beginning">" (FASTA header) s <- s[! grepl("^>", s)] # drop all lines beginning">" (FASTA header)
s <- paste(s, collapse="") # combine into single string s <- paste(s, collapse="") # combine into single string
s <- toupper(gsub("[^a-zA-Z]", "", s)) s <- toupper(gsub("[^a-zA-Z*-]", "", s))
if (unambiguous) { if (unambiguous) {
amb <- "([bjouxzBJOUXZ])" # parentheses capture the match amb <- "([bjouxzBJOUXZ])" # parentheses capture the match
ambChar <- unlist(regmatches(s, regexec(amb, s)))[1] ambChar <- unlist(regmatches(s, regexec(amb, s)))[1]