comparison vcf_gff.py @ 3:402c3f0fe807 draft

Uploaded revised vcf_gff.py from Github to fix bug

2:ea2117a7b363

                gen = "HET"
            if genotypes == "0/0":
                gen = "HOM_ref"
        else:
            gen = "NA"
        geno = ("%s:%s;" % (reads, gen))
        genos += geno
        sample_dict = {}
    return genos
    
attributes = {}
"""
Get relevant info from vcf file and put to proper gff columns
"""

for line in in_vcf_file:
    if line.startswith("#") == False:
        info = line.split()
        seqid = info[0].strip()
        source = "SAMTOOLS"

        else:
            end = start 
        gen = get_gen(info[8:], reference)
        out_gff_file.write(
            ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\tID=%s:%s:%d;Variant" +
             "_seq=%s;Reference_seq=%s;Total_reads=%s:Zygosity=%s\n") %
            ( seqid, source,record_type, start, end, score, strand, phase,seqid, 
              record_type, start, variant, reference, reads, gen))
    
out_gff_file.close()    

3:402c3f0fe807

                gen = "HET"
            if genotypes == "0/0":
                gen = "HOM_ref"
        else:
            gen = "NA"
        geno = ("%s:%s " % (reads, gen))
        genos += geno
        sample_dict = {}
    return genos
    
attributes = {}
"""
Get relevant info from vcf file and put to proper gff columns
"""

out_gff_file.write("#gff-version 3\n")
for line in in_vcf_file:
    if line.startswith("#") == False:
        info = line.split()
        seqid = info[0].strip()
        source = "SAMTOOLS"

        else:
            end = start 
        gen = get_gen(info[8:], reference)
        out_gff_file.write(
            ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\tID=%s:%s:%d;Variant" +
             "_seq=%s;Reference_seq=%s;Total_reads=%s;Zygosity=%s\n") %
            ( seqid, source,record_type, start, end, score, strand, phase,seqid, 
              record_type, start, variant, reference, reads, gen))
    
out_gff_file.close()