comparison read2mut.py @ 13:02bf6425fc25 draft

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

12:7a418148319d

"""

from __future__ import division

import argparse
import json
import operator
import os
import re
import sys

import numpy as np
import pysam
import xlsxwriter
from cyvcf2 import VCF

                        help='JSON file with data collected by mut2read.py.')
    parser.add_argument('--sscsJson',
                        help='JSON file with SSCS counts collected by mut2sscs.py.')
    parser.add_argument('--outputFile',
                        help='Output xlsx file with summary of mutations.')
    parser.add_argument('--outputFile2',
                        help='Output xlsx file with allele frequencies of mutations.')
    parser.add_argument('--outputFile3',
                        help='Output xlsx file with examples of the tier classification.')
    parser.add_argument('--thresh', type=int, default=0,

                        help='Integer threshold for Phred score. Only reads higher than this threshold are considered. Default 20.')
    parser.add_argument('--trim', type=int, default=10,
                        help='Integer threshold for assigning mutations at start and end of reads to lower tier. Default 10.')
    parser.add_argument('--chimera_correction', action="store_true",
                        help='Count chimeric variants and correct the variant frequencies')
    return parser


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

    json_file = args.inputJson
    sscs_json = args.sscsJson
    outfile = args.outputFile
    outfile2 = args.outputFile2
    outfile3 = args.outputFile3
    thresh = args.thresh
    phred_score = args.phred
    trim = args.trim
    chimera_correction = args.chimera_correction

            if len(value) < thresh:
                pure_tags_dict_short[key] = value
    else:
        pure_tags_dict_short = pure_tags_dict

    # output summary with threshold
    workbook = xlsxwriter.Workbook(outfile)
    workbook2 = xlsxwriter.Workbook(outfile2)
    workbook3 = xlsxwriter.Workbook(outfile3)
    ws1 = workbook.add_worksheet("Results")

                   'rel. ref.ab', 'rel. ref.ba', 'rel. alt.ab', 'rel. alt.ba',
                   'na.ab', 'na.ba', 'lowq.ab', 'lowq.ba', 'trim.ab', 'trim.ba',
                   'SSCS alt.ab', 'SSCS alt.ba', 'SSCS ref.ab', 'SSCS ref.ba',
                   'in phase', 'chimeric tag')
    ws1.write_row(0, 0, header_line)
    counter_tier11 = 0
    counter_tier12 = 0
    counter_tier21 = 0
    counter_tier22 = 0
    counter_tier23 = 0

                            read_pos2 = read_len_median2 = None
                        if (read_pos3 == -1):
                            read_pos3 = read_len_median3 = None
                        line = (var_id, tier, key2[:-5], 'ab1.ba2', read_pos1, read_pos4, read_len_median1, read_len_median4, dcs_median) + details1 + (sscs_mut_ab, sscs_mut_ba, sscs_ref_ab, sscs_ref_ba, add_mut14, chimera)
                        ws1.write_row(row, 0, line)
                        line = ("", "", key2[:-5], 'ab2.ba1', read_pos2, read_pos3, read_len_median2, read_len_median3, dcs_median) + details2 + (sscs_mut_ab, sscs_mut_ba, sscs_ref_ab, sscs_ref_ba, add_mut23, chimera)
                        ws1.write_row(row + 1, 0, line)

                        ws1.conditional_format('L{}:M{}'.format(row + 1, row + 2),
                                               {'type': 'formula',
                                                'criteria': '=OR($B${}="1.1", $B${}="1.2")'.format(row + 1, row + 1),
                                                'format': format1,

                                'multi_range': 'L{}:M{} T{}:U{} 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)})
        row += 3
    workbook.close()
    workbook2.close()
    workbook3.close()


if __name__ == '__main__':
    sys.exit(read2mut(sys.argv))

13:02bf6425fc25

"""

from __future__ import division

import argparse
import csv
import json
import operator
import os
import re
import sys


import numpy as np
import pysam
import xlsxwriter
from cyvcf2 import VCF

                        help='JSON file with data collected by mut2read.py.')
    parser.add_argument('--sscsJson',
                        help='JSON file with SSCS counts collected by mut2sscs.py.')
    parser.add_argument('--outputFile',
                        help='Output xlsx file with summary of mutations.')
    parser.add_argument('--outputFile_csv',
                        help='Output csv file with summary of mutations.')
    parser.add_argument('--outputFile2',
                        help='Output xlsx file with allele frequencies of mutations.')
    parser.add_argument('--outputFile3',
                        help='Output xlsx file with examples of the tier classification.')
    parser.add_argument('--thresh', type=int, default=0,

                        help='Integer threshold for Phred score. Only reads higher than this threshold are considered. Default 20.')
    parser.add_argument('--trim', type=int, default=10,
                        help='Integer threshold for assigning mutations at start and end of reads to lower tier. Default 10.')
    parser.add_argument('--chimera_correction', action="store_true",
                        help='Count chimeric variants and correct the variant frequencies')


    return parser


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

    json_file = args.inputJson
    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

            if len(value) < thresh:
                pure_tags_dict_short[key] = value
    else:
        pure_tags_dict_short = pure_tags_dict

    csv_data = open(outputFile_csv, "w")
    csv_writer = csv.writer(csv_data)

    # output summary with threshold
    workbook = xlsxwriter.Workbook(outfile)
    workbook2 = xlsxwriter.Workbook(outfile2)
    workbook3 = xlsxwriter.Workbook(outfile3)
    ws1 = workbook.add_worksheet("Results")

                   'rel. ref.ab', 'rel. ref.ba', 'rel. alt.ab', 'rel. alt.ba',
                   'na.ab', 'na.ba', 'lowq.ab', 'lowq.ba', 'trim.ab', 'trim.ba',
                   'SSCS alt.ab', 'SSCS alt.ba', 'SSCS ref.ab', 'SSCS ref.ba',
                   'in phase', 'chimeric tag')
    ws1.write_row(0, 0, header_line)
    csv_writer.writerow(header_line)
    counter_tier11 = 0
    counter_tier12 = 0
    counter_tier21 = 0
    counter_tier22 = 0
    counter_tier23 = 0

                            read_pos2 = read_len_median2 = None
                        if (read_pos3 == -1):
                            read_pos3 = read_len_median3 = None
                        line = (var_id, tier, key2[:-5], 'ab1.ba2', read_pos1, read_pos4, read_len_median1, read_len_median4, dcs_median) + details1 + (sscs_mut_ab, sscs_mut_ba, sscs_ref_ab, sscs_ref_ba, add_mut14, chimera)
                        ws1.write_row(row, 0, line)
                        csv_writer.writerow(line)
                        line = ("", "", key2[:-5], 'ab2.ba1', read_pos2, read_pos3, read_len_median2, read_len_median3, dcs_median) + details2 + (sscs_mut_ab, sscs_mut_ba, sscs_ref_ab, sscs_ref_ba, add_mut23, chimera)
                        ws1.write_row(row + 1, 0, line)
                        csv_writer.writerow(line)

                        ws1.conditional_format('L{}:M{}'.format(row + 1, row + 2),
                                               {'type': 'formula',
                                                'criteria': '=OR($B${}="1.1", $B${}="1.2")'.format(row + 1, row + 1),
                                                'format': format1,

                                'multi_range': 'L{}:M{} T{}:U{} 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)})
        row += 3
    workbook.close()
    workbook2.close()
    workbook3.close()
    csv_data.close()


if __name__ == '__main__':
    sys.exit(read2mut(sys.argv))