Config = ConfigParser.ConfigParser() Config.read(configfile) members=ConfigSectionMap("Inputs")["sample_id"] target_pattern=ConfigSectionMap("Inputs")["target"] stress_cutoff=ConfigSectionMap("Inputs")["stress_cutoff"] freq_cutoff=ConfigSectionMap("Inputs")["qaf_cutoff"] candidate_cutoff=ConfigSectionMap("Inputs")["score_cutoff"] snpeff_file=ConfigSectionMap("Inputs")["snpeff_file"] snpeff_file=snpeff_file.replace('"','') ### Creating objects for annotater and ## segregation classes segregation_object = segregation() annotation_object = annotater() ## Reading input mergedVCF file vcf_Reader=vcf.Reader(open(inputfile),'r') target = open(outputfile, 'w') target.write("#Chromosome\tPosition\tReference\tAllele\tcandidate_stress\tmax_score\tmin_score\tavg_score\tCount\tKaviar\tUCSC_gene\tclinvar\tcms_annotation\tcadd_annotation\tsnpeff_annotation\tcandidate_score\n") ## The following reads the mergedVCF using python's VCF tools ## All positions that are homozygous reference [ALT=.] are skipped here. ## Every line is then passed onto the process_genotype function to get information ## about sample specific genotypes and quality scores. ## Next the script calls the compute_sequence_quality_score_statistics function to get ## maximum,minimum and average scores. In the further steps unique alleles at every position
target_inheritance = targets.split(",") target_hash = {} for pattern in target_inheritance: completeName = os.path.join(outdir, 'candidate_pattern_' + pattern + '.txt') writer_pattern = open(completeName, 'w') target_hash[pattern] = writer_pattern header_out(pattern, writer_pattern) ##Database connection to Impala conn = connect(host='glados19', port=21050, database=db_user) DB = conn.cursor() DB.execute("SELECT VERSION()") results = DB.fetchone() segregation_object = segregation() #Object for the segregation class """ Vividict allows creation of perl like hashes of hashes or multi key level hash User would always have to point their hash/dict to Vividict Eg: hash_dict=Vividict() """ class Vividict(dict): def __missing__(self, key): value = self[key] = type(self)() return value
writer_pattern = open(completeName, 'w') target_hash[pattern]=writer_pattern header_out(pattern,writer_pattern) ##Database connection to Impala try: conn=connect(host='glados19', port=21050,database=db_user) DB = conn.cursor() DB.execute("SELECT VERSION()") results=DB.fetchone() print ("Connection successful") except: print("Connection failed, check if connection parameters are correct") sys.exit() segregation_object=segregation() #Object for the segregation class """ Vividict allows creation of perl like hashes of hashes or multi key level hash User would always have to point their hash/dict to Vividict Eg: hash_dict=Vividict() """ class Vividict(dict): def __missing__(self, key): value= self[key] = type(self)() return value """ The compute_sequence_quality_score_statistics returns