import re
gene_dict = {}
f1 = open('human.gtf')
f2 = open('mRNAmatrix.txt')
f3 = open('sym.txt','w')
for lines in f1:
    if lines.startswith('#'):
        continue
    line = lines.strip().split('\t')
    #print(line[2])
    if line[2] == "gene":
        gene_id = re.search(r'gene_id "([^;]+)";',line[8]).group(1)
        #print(geneid)
        gene_name = re.search(r' gene_name "([^;]+)";',line[8]).group(1)
        #print(gene_name)
        gene_dict[gene_id] = gene_name

for lines in f2:
    lines = lines.strip()
    if lines.startswith('id'):
        print(lines,file = f3)
        continue
    line = lines.split('\t')
    gene_inf = line[0][:15]

    if gene_inf in gene_dict:
        print(gene_dict[gene_inf]+"\t"+'\t'.join(line[1:]),file = f3 )