comparison read2mut.py @ 84:e46d5e377760 draft

planemo upload for repository https://github.com/Single-Molecule-Genetics/VariantAnalyzerGalaxy/tree/master/tools/variant_analyzer commit ee4a8e6cf290e6c8a4d55f9cd2839d60ab3b11c8-dirty

83:8cec772c0bf1

                        help='Count chimeric variants and correct the variant frequencies')
    parser.add_argument('--softclipping_dist',  type=int, default=15,
                        help='Count mutation as an artifact if mutation lies within this parameter away from the softclipping part of the read.')
    parser.add_argument('--reads_threshold',  type=float, default=1.0,
                        help='Float number which specifies the minimum percentage of softclipped reads in a family to be considered in the softclipping tiers. Default: 1.0, means all reads of a family have to be softclipped.')
    return parser


def safe_div(x, y):
    if y == 0:

    sscs_json = args.sscsJson
    outfile = args.outputFile
    outfile2 = args.outputFile2
    outfile3 = args.outputFile3
    outputFile_csv = args.outputFile_csv

    thresh = args.thresh
    phred_score = args.phred
    trim = args.trim
    chimera_correction = args.chimera_correction

    chimera_dict = {}
    for key1, value1 in sorted(mut_dict.items()):
        counts_mut = 0
        chimeric_tag_list = []
        chimeric_tag = {}
        if (key1 in pure_tags_dict_short.keys()) or (key1 in pure_tags_dict_ref.keys()):  # ref or alt

            # if key1 not in np.array(['#'.join(str(i) for i in z)
            #                        for z in zip(mut_array[:, 0], mut_array[:, 1], mut_array[:, 2], mut_array[:, 3])]):
            #     continue

            change_tier_after_print = []

                if (((key2[:-5] in tag_dict.keys()) and (key2[:-5] in pure_tags_dict_short[key1].keys()) and (key1 in tag_dict[key2[:-5]].keys()) and (key2[:-5] not in used_keys)) or ((key2[:-5] in tag_dict_ref.keys()) and (key2[:-5] in pure_tags_dict_ref[key1].keys()) and (key1 in tag_dict_ref[key2[:-5]].keys()) and (key2[:-5] not in used_keys))):
                    if key2[:-5] in tag_dict.keys():
                        variant_type = "alt"
                    elif key2[:-5] in tag_dict_ref.keys():
                        variant_type = "ref"

                    if key2[:-5] + '.ab.1' in mut_dict[key1].keys():
                        total1 = sum(mut_dict[key1][key2[:-5] + '.ab.1'].values())
                        if 'na' in mut_dict[key1][key2[:-5] + '.ab.1'].keys():
                            na1 = mut_dict[key1][key2[:-5] + '.ab.1']['na']

                    used_keys.append(key2[:-5])
                    # elif variant_type == "ref":
                    #     used_keys_ref.append(key2[:-5])
                    counts_mut += 1

                    if key2[:-5] == "CTTGAACACGTCAGCATGCATGGAGA":
                        print(key1, variant_type, (alt1f + alt2f + alt3f + alt4f) > 0.5, (ref1f + ref2f + ref3f + ref4f) > 0.5)
                    if (variant_type == "alt" and ((alt1f + alt2f + alt3f + alt4f) > 0.5)) or (variant_type == "ref" and ((ref1f + ref2f + ref3f + ref4f) > 0.5)):
                        if variant_type == "alt":
                            tier1ff, tier2ff, tier3ff, tier4ff = alt1f, alt2f, alt3f, alt4f
                            tier1ff_trim, tier2ff_trim, tier3ff_trim, tier4ff_trim = alt1f, alt2f, alt3f, alt4f
                        elif variant_type == "ref":

                                ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=$B${}>="3"'.format(row + 1), 'format': format2, 'multi_range': 'M{}:N{} U{}:V{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                            elif variant_type == "ref":
                                ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=OR($B${}="1.1", $B${}="1.2")'.format(row + 1, row + 1), 'format': format1, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                                ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=OR($B${}="2.1", $B${}="2.2", $B${}="2.3", $B${}="2.4", $B${}="2.5")'.format(row + 1, row + 1, row + 1, row + 1, row + 1), 'format': format3, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                                ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=$B${}>="3"'.format(row + 1), 'format': format2, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                        else:
                            change_tier_after_print.append((line, line2, trimmed_actual_high_tier))

                        row += 3

            if chimera_correction:
                chimeric_dcs_high_tiers = 0
                chimeric_dcs = 0
                for keys_chimera in chimeric_tag.keys():

                        ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=OR($B${}="2.1", $B${}="2.2", $B${}="2.3", $B${}="2.4", $B${}="2.5")'.format(row + 1, row + 1, row + 1, row + 1, row + 1), 'format': format3, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                        ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=$B${}>="3"'.format(row + 1), 'format': format2, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                    row += 3

    # sheet 2
    if chimera_correction:
        header_line2 = ('variant ID', 'cvrg', 'AC alt (all tiers)', 'AF (all tiers)', 'cvrg (tiers 1.1-2.5)', 'AC ref (tiers 1.1-2.5)', 'AC alt (tiers 1.1-2.5)', 'AF (tiers 1.1-2.5)', 'chimera-corrected cvrg (tiers 1.1-2.5)', 'chimeras in AC alt (tiers 1.1-2.5)', 'chimera-corrected AF (tiers 1.1-2.5)', 'AC alt (orginal DCS)', 'AF (original DCS)',
                        'tier 1.1 (alt)', 'tier 1.2 (alt)', 'tier 2.1 (alt)', 'tier 2.2 (alt)', 'tier 2.3 (alt)', 'tier 2.4 (alt)', 'tier 2.5 (alt)',
                        'tier 3.1 (alt)', 'tier 3.2 (alt)', 'tier 4 (alt)', 'tier 5.1 (alt)', 'tier 5.2 (alt)', 'tier 5.3 (alt)', 'tier 5.4 (alt)', 'tier 5.5 (alt)', 'tier 6 (alt)', 'tier 7 (alt)',
                        'tier 1.1 (ref)', 'tier 1.2 (ref)', 'tier 2.1 (ref)', 'tier 2.2 (ref)', 'tier 2.3 (ref)', 'tier 2.4 (ref)', 'tier 2.5 (ref)',
                        'tier 3.1 (ref)', 'tier 3.2 (ref)', 'tier 4 (ref)', 'tier 5.1 (ref)', 'tier 5.2 (ref)', 'tier 5.3 (ref)', 'tier 5.4 (ref)', 'tier 5.5 (ref)', 'tier 6 (ref)', 'tier 7 (ref)'
                        )
    else:
        header_line2 = ('variant ID', 'cvrg', 'AC alt (all tiers)', 'AF (all tiers)', 'cvrg (tiers 1.1-2.5)', 'AC ref (tiers 1.1-2.5)', 'AC alt (tiers 1.1-2.5)', 'AF (tiers 1.1-2.5)', 'AC alt (orginal DCS)', 'AF (original DCS)',
                        'tier 1.1 (alt)', 'tier 1.2 (alt)', 'tier 2.1 (alt)', 'tier 2.2 (alt)', 'tier 2.3 (alt)', 'tier 2.4 (alt)', 'tier 2.5 (alt)',
                        'tier 3.1 (alt)', 'tier 3.2 (alt)', 'tier 4 (alt)', 'tier 5.1 (alt)', 'tier 5.2 (alt)', 'tier 5.3 (alt)', 'tier 5.4 (alt)', 'tier 5.5 (alt)', 'tier 6 (alt)', 'tier 7 (alt)',
                        'tier 1.1 (ref)', 'tier 1.2 (ref)', 'tier 2.1 (ref)', 'tier 2.2 (ref)', 'tier 2.3 (ref)', 'tier 2.4 (ref)', 'tier 2.5 (ref)',
                        'tier 3.1 (ref)', 'tier 3.2 (ref)', 'tier 4 (ref)', 'tier 5.1 (ref)', 'tier 5.2 (ref)', 'tier 5.3 (ref)', 'tier 5.4 (ref)', 'tier 5.5 (ref)', 'tier 6 (ref)', 'tier 7 (ref)'
                        )
    ws2.write_row(0, 0, header_line2)
    row = 0

    for key1, value1 in sorted(tier_dict.items()):
        if key1 in pure_tags_dict_short.keys():

                    cum = safe_div(sum(used_tiers), cvrg)
                    cum_af.append(cum)
            if sum(used_tiers) == 0:  # skip mutations that are filtered by the VA in the first place
                continue
            lst.extend([sum(used_tiers), safe_div(sum(used_tiers), cvrg)])
            lst.extend([(sum(used_tiers_ref[0:7]) + sum(used_tiers[0:7])), sum(used_tiers_ref[0:7]), sum(used_tiers[0:7]), safe_div(sum(used_tiers[0:7]), (sum(used_tiers_ref[0:7]) + sum(used_tiers[0:7])))])
            if chimera_correction:
                chimeras_all = chimera_dict[key1][1]
                new_alt = sum(used_tiers[0:7]) - chimeras_all
                fraction_chimeras = safe_div(chimeras_all, float(sum(used_tiers[0:7])))
                if fraction_chimeras is None:
                    fraction_chimeras = 0.
                new_cvrg = (cvrg - sum(used_tiers[-10:])) * (1. - fraction_chimeras)
                lst.extend([new_cvrg, chimeras_all, safe_div(new_alt, new_cvrg)])
            lst.extend([alt_count, safe_div(alt_count, cvrg)])
            lst.extend(used_tiers)
            lst.extend(used_tiers_ref)
            # lst.extend(cum_af)
            lst = tuple(lst)
            ws2.write_row(row + 1, 0, lst)
            if chimera_correction:
                ws2.conditional_format('N{}:O{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$N$1="tier 1.1 (alt)"', 'format': format12, 'multi_range': 'N{}:O{} N1:O1 AE{}:AF{} AE1:AF1'.format(row + 2, row + 2, row + 2, row + 2)})
                ws2.conditional_format('P{}:T{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$P$1="tier 2.1 (alt)"', 'format': format32, 'multi_range': 'P{}:T{} P1:T1 AG{}:AK{} AG1:AK1'.format(row + 2, row + 2, row + 2, row + 2)})
                ws2.conditional_format('U{}:AD{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$U$1="tier 3.1 (alt)"', 'format': format22, 'multi_range': 'U{}:AD{} U1:AD1 AL{}:AU{} AL1:AU1'.format(row + 2, row + 2, row + 2, row + 2)})
            else:
                ws2.conditional_format('K{}:L{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$K$1="tier 1.1 (alt)"', 'format': format12, 'multi_range': 'K{}:L{} K1:L1 AB{}:AC{} AB1:AC1'.format(row + 2, row + 2, row + 2, row + 2)})
                ws2.conditional_format('M{}:Q{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$M$1="tier 2.1 (alt)"', 'format': format32, 'multi_range': 'M{}:Q{} M1:Q1 AD{}:AH{} AD1:AH1'.format(row + 2, row + 2, row + 2, row + 2)})
                ws2.conditional_format('R{}:AA{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$R$1="tier 3.1 (alt)"', 'format': format22, 'multi_range': 'R{}:AA{} R1:AA1 AI{}:AR{} AI1:AR1'.format(row + 2, row + 2, row + 2, row + 2)})
            row += 1

    # sheet 3
    sheet3 = [("tier 1.1", counter_tier11), ("tier 1.2", counter_tier12), ("tier 2.1", counter_tier21),
              ("tier 2.2", counter_tier22), ("tier 2.3", counter_tier23), ("tier 2.4", counter_tier24), ("tier 2.5", counter_tier25),

    for i in range(len(description_tiers)):
        ws3.write_row(start_row + 2 + row + i + 1, 0, description_tiers[i])
        ex = examples_tiers[i]
        for k in range(len(ex)):
            ws3.write_row(start_row + 2 + row + i + k + 2, 0, ex[k])
        ws3.conditional_format('M{}:N{}'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3), 
                               {'type': 'formula', 'criteria': '=OR($B${}="1.1", $B${}="1.2")'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2), 
                                'format': format13, 
                                'multi_range': 'M{}:N{} U{}:V{} B{}'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3)})
        ws3.conditional_format('M{}:N{}'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3),
                               {'type': 'formula', 'criteria': '=OR($B${}="2.1",$B${}="2.2", $B${}="2.3", $B${}="2.4", $B${}="2.5")'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2),
                                'format': format33,
                                'multi_range': 'M{}:N{} U{}:V{} B{}'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3)})

84:e46d5e377760

                        help='Count chimeric variants and correct the variant frequencies')
    parser.add_argument('--softclipping_dist',  type=int, default=15,
                        help='Count mutation as an artifact if mutation lies within this parameter away from the softclipping part of the read.')
    parser.add_argument('--reads_threshold',  type=float, default=1.0,
                        help='Float number which specifies the minimum percentage of softclipped reads in a family to be considered in the softclipping tiers. Default: 1.0, means all reads of a family have to be softclipped.')
    parser.add_argument('--refalttiers', action="store_true",
                        help='Store also information about the reference allele.')

    return parser


def safe_div(x, y):
    if y == 0:

    sscs_json = args.sscsJson
    outfile = args.outputFile
    outfile2 = args.outputFile2
    outfile3 = args.outputFile3
    outputFile_csv = args.outputFile_csv
    refalttiers = args.refalttiers

    thresh = args.thresh
    phred_score = args.phred
    trim = args.trim
    chimera_correction = args.chimera_correction

    chimera_dict = {}
    for key1, value1 in sorted(mut_dict.items()):
        counts_mut = 0
        chimeric_tag_list = []
        chimeric_tag = {}

        if (key1 in pure_tags_dict_short.keys()) or (key1 in pure_tags_dict_ref.keys()):  # ref or alt
            # if key1 not in np.array(['#'.join(str(i) for i in z)
            #                        for z in zip(mut_array[:, 0], mut_array[:, 1], mut_array[:, 2], mut_array[:, 3])]):
            #     continue

            change_tier_after_print = []

                if (((key2[:-5] in tag_dict.keys()) and (key2[:-5] in pure_tags_dict_short[key1].keys()) and (key1 in tag_dict[key2[:-5]].keys()) and (key2[:-5] not in used_keys)) or ((key2[:-5] in tag_dict_ref.keys()) and (key2[:-5] in pure_tags_dict_ref[key1].keys()) and (key1 in tag_dict_ref[key2[:-5]].keys()) and (key2[:-5] not in used_keys))):
                    if key2[:-5] in tag_dict.keys():
                        variant_type = "alt"
                    elif key2[:-5] in tag_dict_ref.keys():
                        variant_type = "ref"

                    if refalttiers is False and variant_type == "ref":  # if we only want information about alt tiers, skip all refs
                        continue

                    if key2[:-5] + '.ab.1' in mut_dict[key1].keys():
                        total1 = sum(mut_dict[key1][key2[:-5] + '.ab.1'].values())
                        if 'na' in mut_dict[key1][key2[:-5] + '.ab.1'].keys():
                            na1 = mut_dict[key1][key2[:-5] + '.ab.1']['na']

                    used_keys.append(key2[:-5])
                    # elif variant_type == "ref":
                    #     used_keys_ref.append(key2[:-5])
                    counts_mut += 1

                    if (variant_type == "alt" and ((alt1f + alt2f + alt3f + alt4f) > 0.5)) or (variant_type == "ref" and ((ref1f + ref2f + ref3f + ref4f) > 0.5)):
                        if variant_type == "alt":
                            tier1ff, tier2ff, tier3ff, tier4ff = alt1f, alt2f, alt3f, alt4f
                            tier1ff_trim, tier2ff_trim, tier3ff_trim, tier4ff_trim = alt1f, alt2f, alt3f, alt4f
                        elif variant_type == "ref":

                                ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=$B${}>="3"'.format(row + 1), 'format': format2, 'multi_range': 'M{}:N{} U{}:V{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                            elif variant_type == "ref":
                                ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=OR($B${}="1.1", $B${}="1.2")'.format(row + 1, row + 1), 'format': format1, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                                ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=OR($B${}="2.1", $B${}="2.2", $B${}="2.3", $B${}="2.4", $B${}="2.5")'.format(row + 1, row + 1, row + 1, row + 1, row + 1), 'format': format3, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                                ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=$B${}>="3"'.format(row + 1), 'format': format2, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                            row += 3
                        else:
                            change_tier_after_print.append((line, line2, trimmed_actual_high_tier))    

            if chimera_correction:
                chimeric_dcs_high_tiers = 0
                chimeric_dcs = 0
                for keys_chimera in chimeric_tag.keys():

                        ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=OR($B${}="2.1", $B${}="2.2", $B${}="2.3", $B${}="2.4", $B${}="2.5")'.format(row + 1, row + 1, row + 1, row + 1, row + 1), 'format': format3, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                        ws1.conditional_format('M{}:N{}'.format(row + 1, row + 2), {'type': 'formula', 'criteria': '=$B${}>="3"'.format(row + 1), 'format': format2, 'multi_range': 'M{}:N{} S{}:T{} B{}'.format(row + 1, row + 2, row + 1, row + 2, row + 1, row + 2)})
                    row += 3

    # sheet 2
    if refalttiers:
        if chimera_correction:
            header_line2 = ('variant ID', 'cvrg', 'AC alt (all tiers)', 'AF (all tiers)', 'cvrg (tiers 1.1-2.5)', 'AC ref (tiers 1.1-2.5)', 'AC alt (tiers 1.1-2.5)', 'AF (tiers 1.1-2.5)', 'chimera-corrected cvrg (tiers 1.1-2.5)', 'chimeras in AC alt (tiers 1.1-2.5)', 'chimera-corrected AF (tiers 1.1-2.5)', 'AC alt (orginal DCS)', 'AF (original DCS)',
                            'tier 1.1 (alt)', 'tier 1.2 (alt)', 'tier 2.1 (alt)', 'tier 2.2 (alt)', 'tier 2.3 (alt)', 'tier 2.4 (alt)', 'tier 2.5 (alt)',
                            'tier 3.1 (alt)', 'tier 3.2 (alt)', 'tier 4 (alt)', 'tier 5.1 (alt)', 'tier 5.2 (alt)', 'tier 5.3 (alt)', 'tier 5.4 (alt)', 'tier 5.5 (alt)', 'tier 6 (alt)', 'tier 7 (alt)',
                            'tier 1.1 (ref)', 'tier 1.2 (ref)', 'tier 2.1 (ref)', 'tier 2.2 (ref)', 'tier 2.3 (ref)', 'tier 2.4 (ref)', 'tier 2.5 (ref)',
                            'tier 3.1 (ref)', 'tier 3.2 (ref)', 'tier 4 (ref)', 'tier 5.1 (ref)', 'tier 5.2 (ref)', 'tier 5.3 (ref)', 'tier 5.4 (ref)', 'tier 5.5 (ref)', 'tier 6 (ref)', 'tier 7 (ref)'
                            )
        else:
            header_line2 = ('variant ID', 'cvrg', 'AC alt (all tiers)', 'AF (all tiers)', 'cvrg (tiers 1.1-2.5)', 'AC ref (tiers 1.1-2.5)', 'AC alt (tiers 1.1-2.5)', 'AF (tiers 1.1-2.5)', 'AC alt (orginal DCS)', 'AF (original DCS)',
                            'tier 1.1 (alt)', 'tier 1.2 (alt)', 'tier 2.1 (alt)', 'tier 2.2 (alt)', 'tier 2.3 (alt)', 'tier 2.4 (alt)', 'tier 2.5 (alt)',
                            'tier 3.1 (alt)', 'tier 3.2 (alt)', 'tier 4 (alt)', 'tier 5.1 (alt)', 'tier 5.2 (alt)', 'tier 5.3 (alt)', 'tier 5.4 (alt)', 'tier 5.5 (alt)', 'tier 6 (alt)', 'tier 7 (alt)',
                            'tier 1.1 (ref)', 'tier 1.2 (ref)', 'tier 2.1 (ref)', 'tier 2.2 (ref)', 'tier 2.3 (ref)', 'tier 2.4 (ref)', 'tier 2.5 (ref)',
                            'tier 3.1 (ref)', 'tier 3.2 (ref)', 'tier 4 (ref)', 'tier 5.1 (ref)', 'tier 5.2 (ref)', 'tier 5.3 (ref)', 'tier 5.4 (ref)', 'tier 5.5 (ref)', 'tier 6 (ref)', 'tier 7 (ref)'
                            )
    else:
        if chimera_correction:
            header_line2 = ('variant ID', 'cvrg', 'AC alt (all tiers)', 'AF (all tiers)', 'cvrg (tiers 1.1-2.5)', 'AC alt (tiers 1.1-2.5)', 'AF (tiers 1.1-2.5)', 'chimera-corrected cvrg (tiers 1.1-2.5)', 'chimeras in AC alt (tiers 1.1-2.5)', 'chimera-corrected AF (tiers 1.1-2.5)', 'AC alt (orginal DCS)', 'AF (original DCS)',
                            'tier 1.1 (alt)', 'tier 1.2 (alt)', 'tier 2.1 (alt)', 'tier 2.2 (alt)', 'tier 2.3 (alt)', 'tier 2.4 (alt)', 'tier 2.5 (alt)',
                            'tier 3.1 (alt)', 'tier 3.2 (alt)', 'tier 4 (alt)', 'tier 5.1 (alt)', 'tier 5.2 (alt)', 'tier 5.3 (alt)', 'tier 5.4 (alt)', 'tier 5.5 (alt)', 'tier 6 (alt)', 'tier 7 (alt)'
                            )
        else:
            header_line2 = ('variant ID', 'cvrg', 'AC alt (all tiers)', 'AF (all tiers)', 'cvrg (tiers 1.1-2.5)', 'AC alt (tiers 1.1-2.5)', 'AF (tiers 1.1-2.5)', 'AC alt (orginal DCS)', 'AF (original DCS)',
                            'tier 1.1 (alt)', 'tier 1.2 (alt)', 'tier 2.1 (alt)', 'tier 2.2 (alt)', 'tier 2.3 (alt)', 'tier 2.4 (alt)', 'tier 2.5 (alt)',
                            'tier 3.1 (alt)', 'tier 3.2 (alt)', 'tier 4 (alt)', 'tier 5.1 (alt)', 'tier 5.2 (alt)', 'tier 5.3 (alt)', 'tier 5.4 (alt)', 'tier 5.5 (alt)', 'tier 6 (alt)', 'tier 7 (alt)'
                            )
    ws2.write_row(0, 0, header_line2)
    row = 0

    for key1, value1 in sorted(tier_dict.items()):
        if key1 in pure_tags_dict_short.keys():

                    cum = safe_div(sum(used_tiers), cvrg)
                    cum_af.append(cum)
            if sum(used_tiers) == 0:  # skip mutations that are filtered by the VA in the first place
                continue
            lst.extend([sum(used_tiers), safe_div(sum(used_tiers), cvrg)])
            if refalttiers:
                lst.extend([(sum(used_tiers_ref[0:7]) + sum(used_tiers[0:7])), sum(used_tiers_ref[0:7]), sum(used_tiers[0:7]), safe_div(sum(used_tiers[0:7]), (sum(used_tiers_ref[0:7]) + sum(used_tiers[0:7])))])
            else:
                lst.extend([(cvrg - sum(used_tiers[-10:])), sum(used_tiers[0:7]), safe_div(sum(used_tiers[0:7]), (cvrg - sum(used_tiers[-10:])))])
            if chimera_correction:
                chimeras_all = chimera_dict[key1][1]
                new_alt = sum(used_tiers[0:7]) - chimeras_all
                fraction_chimeras = safe_div(chimeras_all, float(sum(used_tiers[0:7])))
                if fraction_chimeras is None:
                    fraction_chimeras = 0.
                new_cvrg = (cvrg - sum(used_tiers[-10:])) * (1. - fraction_chimeras)
                lst.extend([new_cvrg, chimeras_all, safe_div(new_alt, new_cvrg)])
            lst.extend([alt_count, safe_div(alt_count, cvrg)])
            lst.extend(used_tiers)
            if refalttiers:
                lst.extend(used_tiers_ref)
            # lst.extend(cum_af)
            lst = tuple(lst)
            ws2.write_row(row + 1, 0, lst)
            if refalttiers:
                if chimera_correction:
                    ws2.conditional_format('N{}:O{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$N$1="tier 1.1 (alt)"', 'format': format12, 'multi_range': 'N{}:O{} N1:O1 AE{}:AF{} AE1:AF1'.format(row + 2, row + 2, row + 2, row + 2)})
                    ws2.conditional_format('P{}:T{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$P$1="tier 2.1 (alt)"', 'format': format32, 'multi_range': 'P{}:T{} P1:T1 AG{}:AK{} AG1:AK1'.format(row + 2, row + 2, row + 2, row + 2)})
                    ws2.conditional_format('U{}:AD{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$U$1="tier 3.1 (alt)"', 'format': format22, 'multi_range': 'U{}:AD{} U1:AD1 AL{}:AU{} AL1:AU1'.format(row + 2, row + 2, row + 2, row + 2)})
                else:
                    ws2.conditional_format('K{}:L{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$K$1="tier 1.1 (alt)"', 'format': format12, 'multi_range': 'K{}:L{} K1:L1 AB{}:AC{} AB1:AC1'.format(row + 2, row + 2, row + 2, row + 2)})
                    ws2.conditional_format('M{}:Q{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$M$1="tier 2.1 (alt)"', 'format': format32, 'multi_range': 'M{}:Q{} M1:Q1 AD{}:AH{} AD1:AH1'.format(row + 2, row + 2, row + 2, row + 2)})
                    ws2.conditional_format('R{}:AA{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$R$1="tier 3.1 (alt)"', 'format': format22, 'multi_range': 'R{}:AA{} R1:AA1 AI{}:AR{} AI1:AR1'.format(row + 2, row + 2, row + 2, row + 2)})
            else:
                if chimera_correction:
                    ws2.conditional_format('M{}:N{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$M$1="tier 1.1 (alt)"', 'format': format12, 'multi_range': 'M{}:N{} M1:N1'.format(row + 2, row + 2)})
                    ws2.conditional_format('O{}:S{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$O$1="tier 2.1 (alt)"', 'format': format32, 'multi_range': 'O{}:S{} O1:S1'.format(row + 2, row + 2)})
                    ws2.conditional_format('T{}:AC{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$T$1="tier 3.1 (alt)"', 'format': format22, 'multi_range': 'T{}:AC{} T1:AC1'.format(row + 2, row + 2)})
                else:
                    ws2.conditional_format('J{}:K{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$J$1="tier 1.1 (alt)"', 'format': format12, 'multi_range': 'J{}:K{} J1:K1'.format(row + 2, row + 2)})
                    ws2.conditional_format('L{}:P{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$L$1="tier 2.1 (alt)"', 'format': format32, 'multi_range': 'L{}:P{} L1:P1'.format(row + 2, row + 2)})
                    ws2.conditional_format('Q{}:Z{}'.format(row + 2, row + 2), {'type': 'formula', 'criteria': '=$Q$1="tier 3.1 (alt)"', 'format': format22, 'multi_range': 'Q{}:Z{} Q1:Z1'.format(row + 2, row + 2)})
            row += 1

    # sheet 3
    sheet3 = [("tier 1.1", counter_tier11), ("tier 1.2", counter_tier12), ("tier 2.1", counter_tier21),
              ("tier 2.2", counter_tier22), ("tier 2.3", counter_tier23), ("tier 2.4", counter_tier24), ("tier 2.5", counter_tier25),

    for i in range(len(description_tiers)):
        ws3.write_row(start_row + 2 + row + i + 1, 0, description_tiers[i])
        ex = examples_tiers[i]
        for k in range(len(ex)):
            ws3.write_row(start_row + 2 + row + i + k + 2, 0, ex[k])
        ws3.conditional_format('M{}:N{}'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3),
                               {'type': 'formula', 'criteria': '=OR($B${}="1.1", $B${}="1.2")'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2),
                                'format': format13,
                                'multi_range': 'M{}:N{} U{}:V{} B{}'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3)})
        ws3.conditional_format('M{}:N{}'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3),
                               {'type': 'formula', 'criteria': '=OR($B${}="2.1",$B${}="2.2", $B${}="2.3", $B${}="2.4", $B${}="2.5")'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 2),
                                'format': format33,
                                'multi_range': 'M{}:N{} U{}:V{} B{}'.format(start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3, start_row + 2 + row + i + k + 2, start_row + 2 + row + i + k + 3)})