Das deutsche Python-Forum

Code: Alles auswählen

class Count(object):
    def __init__(self,vcfFile):
        #threading.Thread.__init__(self)
        self.vcfFile = vcfFile
    
    def count(self):
        print(self.vcfFile)
        fileOne = open(self.vcfFile,'rb')
        fileOneOne = open(self.vcfFile,'rb')

        #Den Header in der VCF Datei auslassen
        iSetRowOne = int(SetFirstRow(fileOneOne))

        #Die Spaltennamen aus der VCF Datei holen
        readerVCF = csv.reader(fileOne, delimiter="\t")
        for i in range(iSetRowOne):
            strTitlesFirst = readerVCF.next()

        readerVCFtoDict = csv.DictReader(fileOne, strTitlesFirst, delimiter="\t")
        
        #VCF Datei Zeile für Zeile durchgehen.
        try:
            for rowBase in readerVCFtoDict:
                #Die Zeile Info enthält mehrere Informationen und diese Spalte ich auf
                dictData = rowBase['INFO'][:].strip()
                if rowBase['ALT'] == 'X':
                    if rowBase['REF'] != 'N':
                        #Statistiken in die jeweiligen Dict schreiben
                        ddRowBaseInfo = constructStrToDict(dictData,';','=')                 
                        dictHistBase[rowBase['REF']] += 1
                        dictHistCoverage[int(ddRowBaseInfo['DP'])] += 1
                        dictHistCoveragePerChr[rowBase['#CHROM']][int(ddRowBaseInfo['DP'])] += 1
                        iMergeTrue += 1
        finally:
            print("Statistik generiert!")

Code: Alles auswählen

def constructStrToDict(strInput,seperatorOne,seperatorTwo):
    ddInfoRow = {}
    strItems = strInput.split(seperatorOne)
    for item in strItems:
        #print(item)
        a = 0
        a = item.find(seperatorTwo)
        if a > 0 :
            key,value = item.split(seperatorTwo)
        else:
            key,value = item.split('I')
        ddInfoRow[key] = value
    return ddInfoRow

Code: Alles auswählen

import csv
from collections import defaultdict
from functools import partial
from itertools import islice

# ...

def count(vcf_filename):
    header_length = get_header_length(vcf_filename)
    vcf_file = open(vcf_filename, 'rb')
    for _ in islice(csv.reader(vcf_file, delimiter='\t'), header_length):
        pass

    rows = (
        row for row in csv.DictReader(vcf_file, delimiter='\t')
        if row['ALT'] == 'X' and row['REF'] != 'N'
    )
    base_histogram = defaultdict(int)
    coverage_per_chromosome_histogram = defaultdict(partial(defaultdict, int))
    for row in rows:
        dp_value = int(parse_info(row['INFO'])['DP'])
        base_histogram[row['REF']] += 1
        coverage_per_chromosome_histogram[row['#CHROM']][dp_value] += 1

    coverage_histogram = defaultdict(int)
    for histogram in coverage_per_chromosome_histogram.itervalues():
        for key, value in histogram.iteritems():
            coverage_histogram[key] += value
    
    return (
        sum(base_histogram.itervalues()),
        base_histogram,
        coverage_histogram,
        coverage_per_chromosome_histogram
    )


def parse_info(string, separator_a=';', separator_b='='):
    return dict(
        item.split((separator_b if separator_b in item else 'I'), 1)
        for item in string.split(separator_a)
    )

Code: Alles auswählen

##fileformat=VCFv4.1
##samtoolsVersion=0.1.18 (r982:295)
#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	1_Testrun
chr1	114813	.	G	X	0	.	DP=1;I16=1,0,0,0,36,1296,0,0,0,0,0,0,13,169,0,0	PL	0,3,4
chr1	572208	.	T	X	0	.	DP=1;I16=1,0,0,0,41,1681,0,0,1,1,0,0,22,484,0,0	PL	0,3,4

Code: Alles auswählen

Anweisung: ('countBlackJack', {'vcfFile': '2011_08_19_Testrun_01-1-Idx_11-7.bam/2011_08_19_Testrun_01-1-Idx_11-7.bam.small.vcf'})
Programm beendet in 0.0160757025083 min.
Anweisung: ('countNork', {'vcfFile': '2011_08_19_Testrun_01-1-Idx_11-7.bam/2011_08_19_Testrun_01-1-Idx_11-7.bam.small.vcf'})
Programm beendet in 0.0105002363523 min.