def generate_slices(args): vcf = VCF.VCF() vcf.populations = args.populations vcf.set_chrms(args.input) chrm_2_windows = vcf.chrm2length.fromkeys(vcf.chrm2length.keys(),None) for count, chrm in enumerate(vcf.chrm2length.keys()): length = vcf.chrm2length[chrm] window_size = args.window_size overlap = args.overlap # Skip contigs that are to short if length <= window_size: continue # Fit windows into remaining space if (length % window_size) > overlap: start = (length % window_size)/2 stop = (length - window_size) - overlap/2 # Prevent windows from invading remaining space if (length % window_size) <= overlap: start = (length % window_size)/2 stop = length - overlap*2 starts = range(start, stop, overlap) stops = [i+window_size for i in starts] windows = zip(starts, stops) chrm_2_windows[chrm] = windows return chrm_2_windows
def make_dadi_fs(args, region):
vcf = VCF.VCF()
vcf.populations = args.populations
vcf.set_header(args.input)
pop_ids = args.populations.keys()
# Get slice and setup output dictionaries
chunk = vcf.slice_vcf(args.input, *region)
if chunk == None:
return None
else:
g = count_alleles(chunk, args.populations)
final_dadi = {}
population_level_dadis = dict.fromkeys(pop_ids,{})
for row_count, row in enumerate(g):
raw_calls = chunk[row_count]
row['outgroups'] = {'ALT': 0, 'REF': 0} # set empty outgroup
# To Do: Need to create a function to fill outgroup if one is defined.
# The heliconius dataset, for example, has this.
if check_outgroup(row) == False: continue # skip outgroup not fixed at one value
if len(raw_calls['REF']) > 1 or len(raw_calls["ALT"]) > 1: continue # skip multi allelic sites
# CALL BASE FOR OUTGROUP
outgroup_allele = get_outgroup_base(row, raw_calls)
# CALL MAJOR ALLELE (BASE) FOR INGROUP
major_allele = get_ingroup_major_allele(row, raw_calls, outgroup_allele)
# POLORIZE REF AND ALT FOR INGROUP
if major_allele != raw_calls['REF']:
ref, alt = ('ALT','REF')
else:
ref, alt = ('REF','ALT')
calls = {}
for count, pop in enumerate(pop_ids):
calls[pop] = (row[pop][ref], row[pop][alt])
row_id = "{0}_{1}".format(raw_calls['CHROM'],raw_calls['POS'])
dadi_site = {'calls': calls,
'context': make_triplet(major_allele),
'outgroup_context': make_triplet(outgroup_allele),
'outgroup_allele': outgroup_allele,
'segregating': (raw_calls[ref], raw_calls[alt])
}
final_dadi[row_id] = dadi_site
return (final_dadi, pop_ids)
def main(args):
vcf = VCF.VCF()
vcf.populations = args.populations
vcf.set_header(args.input)
pop_ids = args.populations.keys()
# get slice and setup output dictionaries
chunk = vcf.vcf_chunk_2_dadi(args.input, args.populations, *args.region)
g = count_alleles(chunk, args.populations)
# Create Header Row
dadi_header = create_dadi_header(args)
fout = open(args.output,'w')
fout.write(dadi_header + "\n")
for row_count, row in enumerate(g):
raw_calls = chunk[row_count]
row['outgroups'] = {'ALT': 0, 'REF': 0} # set empty outgroup
# To Do: Need to create a function to fill outgroup if one is defined.
# The heliconius dataset, for example, has this.
if check_outgroup(row) == False: continue # skip outgroup not fixed at one value
if len(raw_calls['REF']) > 1 or len(raw_calls["ALT"]) > 1: continue # skip multi allelic sites
# CALL BASE FOR OUTGROUP
outgroup_allele = get_outgroup_base(row, raw_calls)
# CALL MAJOR ALLELE (BASE) FOR INGROUP
major_allele = get_ingroup_major_allele(row, raw_calls, outgroup_allele)
# POLORIZE REF AND ALT FOR INGROUP
if major_allele != raw_calls['REF']:
ref, alt = ('ALT','REF')
else:
ref, alt = ('REF','ALT')
# CREATE DADI ROW
dadi_row = [make_triplet(major_allele), make_triplet(outgroup_allele)]
for count, pop in enumerate(pop_ids):
if count == 0:
dadi_row.append(chunk[row_count][ref])
dadi_row.append(row[pop][ref])
else:
dadi_row.append(row[pop][ref])
for count, pop in enumerate(pop_ids):
if count == 0:
dadi_row.append(chunk[row_count][alt])
dadi_row.append(row[pop][alt])
else:
dadi_row.append(row[pop][alt])
dadi_row.append(raw_calls['CHROM'])
dadi_row.append(raw_calls['POS'])
dadi_row = " ".join([str(item) for item in dadi_row])
fout.write(dadi_row + "\n")
