my first ever Julia script - reads fasta from stdin and prints mean length of sequences

meanfaslen.jl

# julia shebang here

# mean fasta length
# non-fasta input may lead to division by zero !!
# use at your own risk

# add global constants for vars in loop below
# actually - requires julia v1.8+
nseq::Int = 0
len::Int = 0

# read STDIN
for line in eachline(stdin)
	#print("Found $line")
	if(occursin(">", line) == true)
		global nseq += 1
	else
		global len += length(line)
	end
end
println(len/nseq) # float, possibly

## apply function to a file
# function read_and_capitalize(f::IOStream)
#     return uppercase(read(f, String))
# end
## call
# open(read_and_capitalize, "hello.txt")


## OPEN FILE
# open("lom300tf.fasta", "r") do fasta
# 	for line in eachline(fasta)
#			#println(line)
# 		# the following block can be in a function
# 		if(occursin(">", line) == true)
# 			nseq += 1
# 		else
# 			len += length(line)
# 		end
# 	end
# 	println(len/nseq) # float, possibly
# end

## DOCS
## https://docs.julialang.org/en/v1/manual/networking-and-streams/
## https://docs.julialang.org/en/v1/manual/strings/#Common-Operations
## https://syl1.gitbook.io/julia-language-a-concise-tutorial/language-core/input-output

meanfaslen.jl

Use like this:

julia meanfaslen.jl < genes.fa

Try parallelism

With the @threads macro and atomic assignments!

https://docs.julialang.org/en/v1/manual/multi-threading/#Atomic-Operations

julia> using Base.Threads

julia> nthreads()
4

julia> acc = Ref(0)
Base.RefValue{Int64}(0)

julia> @threads for i in 1:1000
          acc[] += 1
       end

julia> acc[]
926

julia> acc = Atomic{Int64}(0)
Atomic{Int64}(0)

julia> @threads for i in 1:1000
          atomic_add!(acc, 1)
       end

julia> acc[]
1000

Update

Doesn't work - stdin doesn't support the method. I would probably need to create an iterator that collects from stdin, but that sounds advanced for now.

CSV.Rows

https://csv.juliadata.org/stable/reading.html#CSV.Rows

Code example:

for row in CSV.Rows(file)
    println("a=$(row.a), b=$(row.b), c=$(row.c)")
end

Options:

• reusebuffer=true
• header=1