def RunModule(fasta_file, fulllist_file, blast_file, report_file, tcsfile):
'''Runs the Module'''
blast = open(blast_file, 'r')
report = open(report_file, 'w')
Dict = FASTA_parser(fasta_file)
LargeDict = FASTA_parser(fulllist_file)
Blasts = BLASTparser(blast)
Characterize(Dict, Blasts, LargeDict, report, tcsfile)
FASTAsplitter(Dict, LargeDict, report_file)
def Read_metrics(fasta_file):
'''Calculate metrics from fasta files.'''
fasta_dict = FASTA_parser(fasta_file)
values = list(map(len, fasta_dict.values()))
max_len = max(values)
avg_len = "%.2f" % (sum(values)/len(values))
values.sort()
medianpos = len(values) / 2
if len(values) % 2 == 0:
median = (values[int(medianpos)] + values[int(medianpos - 1)]) / 2
else:
median = values[int(medianpos - 0.5)]
return(avg_len, max_len, median)
def Read_metrics(fasta_file):
'''Calculate metrics from fasta files.'''
fasta_dict = FASTA_parser(fasta_file)
values = list(map(len, fasta_dict.values()))
max_len = max(values)
avg_len = "%.2f" % (sum(values)/len(values))
values.sort()
medianpos = len(values) / 2
if len(values) % 2 == 0:
median = (values[int(medianpos)] + values[int(medianpos - 1)]) / 2
else:
median = values[int(medianpos - 0.5)]
return(avg_len, max_len, median)
def SNP_gather(snp_file, orf_file):
'''Gather SNP data from the fasta files:'''
snps = FASTA_parser(snp_file)
ammount = 0
for titles in snps.keys():
ammount += titles.count("#")
num_contigs = len(snps)
avg_snps_per_contig = "%.2f" % (ammount/num_contigs)
contig_sizes = list(map(len, snps.values()))
max_contig_size = max(contig_sizes)
min_contig_size = min(contig_sizes)
avg_contig_size = "%.2f" % (sum(contig_sizes)/len(contig_sizes))
# This part counts how many SNPs are inside ORFs
orfs = FASTA_parser(orf_file)
contig_names = []
for contigs in orfs.keys():
if "REVERSE" in contigs:
start = int(re.search('\[\d*', contigs).group()[1:])
end = re.findall('\d+(?=:)', contigs)
end = list(map(int, end))
for items in end:
suffix = str(start-items+2)
contig = re.sub(' .*$', '', contigs) + ';' + suffix
contig_names.append(contig)
else:
start = int(re.search('\[\d*', contigs).group()[1:])
end = re.findall('\d+(?=:)', contigs)
end = list(map(int, end))
for items in end:
suffix = str(start+items)
contig = re.sub(' .*$', '', contigs) + ';' + suffix
contig_names.append(contig)
snps_in_orfs = len(set(contig_names))
return(ammount, num_contigs, avg_snps_per_contig, max_contig_size,
min_contig_size, avg_contig_size, snps_in_orfs)
def SNP_gather(snp_file, orf_file):
'''Gather SNP data from the fasta files:'''
snps = FASTA_parser(snp_file)
ammount = 0
for titles in snps.keys():
ammount += titles.count("#")
num_contigs = len(snps)
avg_snps_per_contig = "%.2f" % (ammount/num_contigs)
contig_sizes = list(map(len, snps.values()))
max_contig_size = max(contig_sizes)
min_contig_size = min(contig_sizes)
avg_contig_size = "%.2f" % (sum(contig_sizes)/len(contig_sizes))
# This part counts how many SNPs are inside ORFs
orfs = FASTA_parser(orf_file)
contig_names = []
for contigs in orfs.keys():
if "REVERSE" in contigs:
start = int(re.search('\[\d*', contigs).group()[1:])
end = re.findall('\d+(?=:)', contigs)
end = list(map(int, end))
for items in end:
suffix = str(start-items+2)
contig = re.sub(' .*$', '', contigs) + ';' + suffix
contig_names.append(contig)
else:
start = int(re.search('\[\d*', contigs).group()[1:])
end = re.findall('\d+(?=:)', contigs)
end = list(map(int, end))
for items in end:
suffix = str(start+items)
contig = re.sub(' .*$', '', contigs) + ';' + suffix
contig_names.append(contig)
snps_in_orfs = len(set(contig_names))
return(ammount, num_contigs, avg_snps_per_contig, max_contig_size,
min_contig_size, avg_contig_size, snps_in_orfs)
def RunModule(fasta_file, fasta_qual_file, endreport_file, etandem, minqual):
endreport = open(endreport_file, 'w')
FDict = FASTA_parser(fasta_file)
QDict = FASTA_parser(fasta_qual_file)
SmallFiles(FDict, QDict, etandem, endreport, minqual)
def RunModule(tcs_file, fasta_file, snp_fasta, minqual):
'''Runs the module:'''
Names = TCStoDict(tcs_file, minqual)
Sequences = FASTA_parser(fasta_file)
ShortListFASTA(Names, Sequences, tcs_file, snp_fasta)
def RunModule(bamfile_name, padded_fasta_name):
"""Run the module."""
TCSwriter(bamfile_name, FASTA_parser(padded_fasta_name))