def test_flatten():
assert helper.flatten([]) == []
assert helper.flatten([[]]) == []
assert helper.flatten([[1]]) == [1]
assert helper.flatten([[2], [1]]) == [2, 1]
assert helper.flatten([[1, 2], [1]]) == [1, 2, 1]
d = diffs_per_site(seqs[keys[i]].lower(), seqs[keys[j]].lower())
if d != 'NA':
num += d
den += 1
if den == 0:
return 'NA'
return float(num) / den
# read in shared regions
shared_regions, _ = \
read_table.read_table_rows('shared_introgression_nonsingleton_list.txt',
'\t')
# read in strain dirs information
s = align_helpers.get_strains(align_helpers.flatten(gp.non_ref_dirs.values()))
strain_dirs = dict(s)
# for each shared region:
# - calculate fraction of sites that are polymorphic among introgressed strains
# - for each introgressed strain, calculate:
# - number of unique variants among introgressed strains (or all strains?)
f = open('shared_introgression_nonsingleton_polymorphism.txt', 'w')
f.write('region_number\tchromosome\tstart\tend\tpi\t'
'frac_poly\tnum_poly\tnum_total\tnum_strains\tstrain_list\n')
for chrm in gp.chrms:
chrom_seqs = {}
for region_number in shared_regions.keys():
if shared_regions[region_number]['chromosome'] != chrm:
continue
def test_flatten():
assert helper.flatten([]) == []
assert helper.flatten([[]]) == []
assert helper.flatten([[1]]) == [1]
assert helper.flatten([[2], [1]]) == [2, 1]
assert helper.flatten([[1, 2], [1]]) == [1, 2, 1]
import os
from align.align_helpers import get_strains, flatten
import global_params as gp
# get all non-reference strains of cerevisiae and paradoxus
s = get_strains(flatten(gp.non_ref_dirs.values()))
gp_dir = '../'
a = []
if gp.resume_alignment:
a = os.listdir(gp_dir + gp.alignments_dir)
# need to add this on the start of each command because os.system()
# creates a new shell instance every time
cmd_string_start = 'export MUGSY_INSTALL=' + gp.mugsy_install_path + '; '
cmd_string_start += 'export PATH=$PATH:$MUGSY_INSTALL:$MUGSY_INSTALL/mapping; '
cmd_string_start += 'export PERL5LIB=$MUGSY_INSTALL/perllibs; '
ref_prefix = '_'.join(gp.alignment_ref_order) + '_'
ref_dirs = [gp.ref_dir[ref] for ref in gp.alignment_ref_order]
for strain, d in s:
print(strain)
cmd_string = cmd_string_start
for chrm in [gp.chrms[-1]]:
align_fn = ref_prefix + strain + '_chr' + chrm + gp.alignment_suffix
# if we don't already have an alignment for this strain/chromosome,
# then make one
if align_fn not in a:
# region_start = 787000
# region_end = 794000
# chrm = 'II'
region_start = 917571 - 100
region_end = 921647 + 100
chrm = 'IV'
region_length = region_end - region_start + 1
# ======
# get strains
# ======
strain_dirs = align_helpers.get_strains(
align_helpers.flatten(gp.non_ref_dirs.values()))
num_strains = len(strain_dirs)
# ======
# loop through all strains, getting appropriate sequence
# ======
# master reference and other reference seqs
master_ref = gp.alignment_ref_order[0]
master_fn = gp.ref_dir[master_ref] + gp.ref_fn_prefix[master_ref] + '_chr' + \
chrm + gp.fasta_suffix
master_seq = read_fasta.read_fasta(master_fn)[1][0][
region_start:region_end+1].lower()