mycoplasma.py

data = open("Mycoplasma_hominis.fasta", "r").read()
data2 = open("Mycoplasma_hominis.csv", "r").readlines()
result = open("genes.fasta", "w")

def complement(dna):
    d = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A'}
    return "".join([d[nucleotide] for nucleotide in dna][::-1])

contig_dict = {}

lines = data.splitlines()

for line in lines:
    if line.startswith(">"):
        contig_dict[line] = ""
    else:
        contig_dict[list(contig_dict.keys())[len(contig_dict) - 1]] += line


for line in data2:
    line = line.split(",")
    print(line)
    if line[1] == "gene":
        start_pos = int(line[2]) - 1
        end_pos = int(line[3])
        result.write(f">{line[0]}|gene|{line[5]}|{line[2]}:{line[3]}|{line[4]}\n")
        if line[4] == "-":
            result.write(f"{complement(contig_dict[">" + line[0]][start_pos:end_pos])}\n")
        else:
            result.write(f"{contig_dict[">" + line[0]][start_pos:end_pos]}\n")