comparison ensembl_variant_report.py @ 8:fd612f8119a2 draft

planemo upload for repository https://github.com/jj-umn/galaxytools/tree/master/ensembl_variant_report commit f003aece24587f68b883449f278f1e601110e2ec-dirty

7:d5cb252c68da

            ref = fields[ri]
            alts = fields[ai]
            dp = int(fields[di])
            dpr = [int(x) for x in fields[fi].split(',')]
            for i,alt in enumerate(alts.split(',')):
                freq = float(dpr[i+1])/float(sum(dpr)) if dpr else None
                yield (transcript,pos,ref,alt,dp,freq)

    def parse_snpeff_vcf():
        for linenum,line in enumerate(inputFile):
            if line.startswith('##'): 

                                (alt,eff,impact,gene_name,gene_id,feature_type,transcript,biotype,exon,c_hgvs,p_hgvs,cdna,cds,aa,distance,info) = effect.split('|')
                            elif key == 'EFF':
                                (eff, effs) = effect.rstrip(')').split('(')
                                (impact, functional_class, codon_change, aa_change, aa_len, gene_name, biotype, coding, transcript, exon, alt) = effs.split('|')[0:11]
                            i = alt_list.index(alt) if alt in alt_list else 0
                            freq = float(dpr[i+1])/float(sum(dpr)) if dpr else None
                            yield (transcript,pos,ref,alt,dp,freq)


    #Process gene model
    ens_ref = None

8:fd612f8119a2

            ref = fields[ri]
            alts = fields[ai]
            dp = int(fields[di])
            dpr = [int(x) for x in fields[fi].split(',')]
            for i,alt in enumerate(alts.split(',')):
                freq = float(dpr[i+1])/float(dp) if dp and dpr else \
                    float(dpr[i+1])/float(sum(dpr)) if dpr else None
                yield (transcript,pos,ref,alt,dp,freq)

    def parse_snpeff_vcf():
        for linenum,line in enumerate(inputFile):
            if line.startswith('##'): 

                                (alt,eff,impact,gene_name,gene_id,feature_type,transcript,biotype,exon,c_hgvs,p_hgvs,cdna,cds,aa,distance,info) = effect.split('|')
                            elif key == 'EFF':
                                (eff, effs) = effect.rstrip(')').split('(')
                                (impact, functional_class, codon_change, aa_change, aa_len, gene_name, biotype, coding, transcript, exon, alt) = effs.split('|')[0:11]
                            i = alt_list.index(alt) if alt in alt_list else 0
                            freq = float(dpr[i+1])/float(dp) if dp and dpr else \
                                float(dpr[i+1])/float(sum(dpr)) if dpr else None
                            yield (transcript,pos,ref,alt,dp,freq)


    #Process gene model
    ens_ref = None