SPLIT MULTIPLE FASTA FILE into separate fasta files with id as filename

split_fasta.rb

require 'bio' # you have to install bioruby - gem install bio
require 'fileutils'

# Run by running:
## ruby split_fasta.rb FASTA_FILE MIN MAX OUTPUT_DIR



fasta = ARGV[0]
min = ARGV[1]
max = ARGV[2]
output_dir = ARGV[3]

biofastafile = Bio::FlatFile.open(Bio::FastaFormat, fasta)
biofastafile.each_entry do |entry|
	id = entry.definition.gsub(/[\/\\:*?"<>|]/, '_')
	id = id[0..50]
	out_file = File.join(output_dir, "#{id}.fa")
	FileUtils.mkdir(output_dir) unless File.directory?(output_dir)
	seq = entry.seq
	next if seq.length > max.to_i || seq.length < min.to_i
	File.open(out_file, 'w') { |f| f.puts entry.entry }
end