import re
def calculate_aminoacid_frequencies(fasta_filename, subsequences_filename, number_of_repetitions, output_filename):
	"""Create a function that, given a multi-line protein FASTA file (fasta_filename) and a “sub-sequences” file
	(subsequences_filename) (one sequence in each line), calculates the proportion of proteins in the FASTA file
	containing at least N-times (number_of_repetitions) each of the sub-sequences (exactly equal). Save it in an
	output file with the specified format, ordered by the proportion value (descending order). Overlapping sub-
	sequences are taked into account in the count."""
	file= open(fasta_filename, "r")
	subfile= open(subsequences_filename, "r")
	output= open(output_filename, "w")
	numprots=0
	function={}
	sequence=""
	proteinscontaining=0
	for element in subfile:
		function[element.strip()] = 0
	numbersubseqs=len(function)
	subfile.close()
	for line in file:
		if line.startswith(">"):
			numprots+= 1
			if sequence != "":
				for subsequence in function:
					contador=0
					contador+= len(re.findall("(?="+subsequence+")", sequence))
					if contador >= number_of_repetitions:
						function[subsequence] += 1
			sequence=""
		else:
			sequence+= line.strip()
	file.close()
	subfile= open(subsequences_filename, "r")
	output.write("{:s}\t{:>20d}\n{:s}\t{:>20d}\n{:s}\n".format("#Number of proteins:", numprots, "#Number of subsequences:", numbersubseqs, "#Subsequence proportions:"))
	for subsequence in function:
					contador=0
					contador+= len(re.findall("(?="+subsequence+")", sequence))
					if contador >= number_of_repetitions:
						function[subsequence] += 1
	for item in sorted(function.items(), key=lambda item: item[1] , reverse=True):
		output.write("{:s}\t{:>10d}\t{:.4f}\n".format(item[0], item[1], item[1]/numprots))
	subfile.close()
	output.close()

#calculate_aminoacid_frequencies("example_fasta_file.fa", "sequence_fragments.txt", 5, "prueba.txt")