comparison read2mut.py @ 1:3556001ff2db draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/variant_analyzer commit 60dc8db809909edf44d662683b1f392b9d5964bf"

0:8d29173d49a9

"""

from __future__ import division

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

    if trim < 0:
        sys.exit("Error: trim is '{}', but only non-negative integers allowed".format(thresh))

    # 1. read mut file
    with open(file1, 'r') as mut:
        mut_array = np.genfromtxt(mut, skip_header=1, delimiter='\t', comments='#', dtype='string')

    # 2. load dicts
    with open(json_file, "r") as f:
        (tag_dict, cvrg_dict) = json.load(f)

        alt = mut_array[m, 10]
        mut_dict[chrom_stop_pos] = {}
        mut_read_pos_dict[chrom_stop_pos] = {}
        reads_dict[chrom_stop_pos] = {}

        for pileupcolumn in bam.pileup(chrom.tobytes(), stop_pos - 2, stop_pos, max_depth=1000000000):
            if pileupcolumn.reference_pos == stop_pos - 1:
                count_alt = 0
                count_ref = 0
                count_indel = 0
                count_n = 0

    else:
        pure_tags_dict_short = pure_tags_dict

    whole_array = []
    for k in pure_tags_dict.values():
        if len(k) != 0:
            keys = k.keys()
            if len(keys) > 1:
                for k1 in keys:
                    whole_array.append(k1)
            else:
                whole_array.append(keys[0])

    # 7. output summary with threshold
    workbook = xlsxwriter.Workbook(outfile)
    ws1 = workbook.add_worksheet("Results")
    ws2 = workbook.add_worksheet("Allele frequencies")

                                    half1_mate1 = array1_half2
                                    half2_mate1 = array1_half
                                    half1_mate2 = array2_half2
                                    half2_mate2 = array2_half
                                # calculate HD of "a" in the tag to all "a's" or "b" in the tag to all "b's"
                                dist = np.array([sum(itertools.imap(operator.ne, half1_mate1, c)) for c in half1_mate2])
                                min_index = np.where(dist == dist.min())  # get index of min HD
                                # get all "b's" of the tag or all "a's" of the tag with minimum HD
                                min_tag_half2 = half2_mate2[min_index]
                                min_tag_array2 = array2[min_index]  # get whole tag with min HD
                                min_value = dist.min()
                                # calculate HD of "b" to all "b's" or "a" to all "a's"
                                dist_second_half = np.array([sum(itertools.imap(operator.ne, half2_mate1, e))
                                                             for e in min_tag_half2])

                                dist2 = dist_second_half.max()
                                max_index = np.where(dist_second_half == dist_second_half.max())[0]  # get index of max HD
                                max_tag = min_tag_array2[max_index]

1:3556001ff2db

"""

from __future__ import division

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

    if trim < 0:
        sys.exit("Error: trim is '{}', but only non-negative integers allowed".format(thresh))

    # 1. read mut file
    with open(file1, 'r') as mut:
        mut_array = np.genfromtxt(mut, skip_header=1, delimiter='\t', comments='#', dtype=str)

    # 2. load dicts
    with open(json_file, "r") as f:
        (tag_dict, cvrg_dict) = json.load(f)

        alt = mut_array[m, 10]
        mut_dict[chrom_stop_pos] = {}
        mut_read_pos_dict[chrom_stop_pos] = {}
        reads_dict[chrom_stop_pos] = {}

        for pileupcolumn in bam.pileup(chrom, stop_pos - 2, stop_pos, max_depth=1000000000):
            if pileupcolumn.reference_pos == stop_pos - 1:
                count_alt = 0
                count_ref = 0
                count_indel = 0
                count_n = 0

    else:
        pure_tags_dict_short = pure_tags_dict

    whole_array = []
    for k in pure_tags_dict.values():
        whole_array.extend(k.keys())

    # 7. output summary with threshold
    workbook = xlsxwriter.Workbook(outfile)
    ws1 = workbook.add_worksheet("Results")
    ws2 = workbook.add_worksheet("Allele frequencies")

                                    half1_mate1 = array1_half2
                                    half2_mate1 = array1_half
                                    half1_mate2 = array2_half2
                                    half2_mate2 = array2_half
                                # calculate HD of "a" in the tag to all "a's" or "b" in the tag to all "b's"
                                dist = np.array([sum(map(operator.ne, half1_mate1, c)) for c in half1_mate2])
                                min_index = np.where(dist == dist.min())  # get index of min HD
                                # get all "b's" of the tag or all "a's" of the tag with minimum HD
                                min_tag_half2 = half2_mate2[min_index]
                                min_tag_array2 = array2[min_index]  # get whole tag with min HD
                                min_value = dist.min()
                                # calculate HD of "b" to all "b's" or "a" to all "a's"
                                dist_second_half = np.array([sum(map(operator.ne, half2_mate1, e))
                                                             for e in min_tag_half2])

                                dist2 = dist_second_half.max()
                                max_index = np.where(dist_second_half == dist_second_half.max())[0]  # get index of max HD
                                max_tag = min_tag_array2[max_index]