Created
January 18, 2016 04:58
-
-
Save yuifu/e0a1560ad20df363e20c to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
path_gtf = "merged.asm/merged.gtf" | |
path_ofile = "merged.asm/merged.gtf.txt" | |
arr_attr = Array{Any,1}() | |
d_attr = Dict{Any,Any}() | |
# Extract all attributes | |
f = open(path_gtf) | |
for ln in eachline(f) | |
for s in split(split(chomp(ln), "\t")[9], "; ") | |
if ! in(split(s, " ")[1], arr_attr) | |
push!(arr_attr, split(s, " ")[1]) | |
end | |
end | |
end | |
close(f) | |
for s in arr_attr | |
println(s) | |
println(typeof(s)) | |
end | |
# Convert Colmun 9 into columns | |
fw = open(path_ofile, "w") | |
write(fw, join(["chr"; "V2"; "V3"; "start"; "end"; "V6"; "strand"; "V8"; arr_attr], "\t") * "\n") | |
f = open(path_gtf) | |
for ln in eachline(f) | |
empty!(d_attr) | |
for s in split(split(chomp(ln), "\t")[9], "; ") | |
d_attr[split(s, " ")[1]] = replace(split(s, " ")[2], r"[\";]", s"") | |
end | |
res = join(split(chomp(ln), "\t")[1:8], "\t") | |
for s in arr_attr | |
if in(s, keys(d_attr)) | |
res *= "\t" * d_attr[s] | |
else | |
res *= "\t" * "." | |
end | |
end | |
write(fw, res * "\n") | |
end | |
close(f) | |
close(fw) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment