def main(alignment_file, edlevel_step, confint_p, spec_ids_str, permut_n, select_sites):
spec_ids_list = spec_ids_str.split(',')
edlevel_dict = edlevel_dict_init(edlevel_step)
for align_obj in align_parse(alignment_file):
if (spec_ids_list[0] not in align_obj.species_list) or (spec_ids_list[1] not in align_obj.species_list):
continue
align_length = len(align_obj.align_dict[spec_ids_list[0]])
for i in range(align_length):
if align_obj.align_dict[spec_ids_list[0]][i] != 'A':
continue
if align_obj.align_dict[spec_ids_list[1]][i] == "-":
continue
for j in edlevel_dict.keys():
edlevel_dict[j].n_A += 1
if align_obj.align_dict[spec_ids_list[1]][i] == 'G':
for j in edlevel_dict.keys():
edlevel_dict[j].A2G += 1
elif align_obj.align_dict[spec_ids_list[1]][i] in ('C','T'):
for j in edlevel_dict.keys():
edlevel_dict[j].A2CT += 1
if not align_obj.edinfo_dict[spec_ids_list[0]].get(i+1):
continue
if select_sites == 'syn' and align_obj.edinfo_dict[spec_ids_list[0]][i+1].codon_change != 'syn':
continue
if select_sites == 'nsyn' and align_obj.edinfo_dict[spec_ids_list[0]][i+1].codon_change == 'syn':
continue
edlevel = align_obj.edinfo_dict[spec_ids_list[0]][i+1].edlevel
for j in edlevel_dict.keys():
if j < edlevel:
edlevel_dict[j].n_A_ed += 1
if align_obj.edinfo_dict[spec_ids_list[1]].get(i+1):
continue
if align_obj.align_dict[spec_ids_list[1]][i] == 'G':
for j in edlevel_dict.keys():
if j < edlevel:
edlevel_dict[j].A_ed2G += 1
elif align_obj.align_dict[spec_ids_list[1]][i] in ('C','T'):
for j in edlevel_dict.keys():
if j < edlevel:
edlevel_dict[j].A_ed2CT += 1
print "spec_id\tedlevel_thr\tp_Aed2G\tp_A2G\tp_A_ed2CT\tp_A2CT\trf_G\trf_G_low\trf_G_high\trf_CT\trf_CT_low\trf_CT_high"
for i in sorted(edlevel_dict.keys()):
try:
edlevel_dict[i].p_and_confint_print(confint_p, spec_ids_str, permut_n)
except ZeroDivisionError:
pass
def build_subst_mat(alignment_file,
outgr_str,
spec_str,
flag,
orf_crd_table):
outgroup_ref = outgr_str.split(',')
specs = spec_str.split(',')
orf_crd_dict = make_orf_crd_dict(orf_crd_table)
subst_mat = subst_mat_init()
n_E = 0
n_A = 0
n_G = 0
n_Y = 0
n_E_anc = 0
n_A_anc = 0
n_G_anc = 0
n_Y_anc = 0
n_E2G = 0
n_A2G = 0
n_E2Y = 0
n_A2Y = 0
n_G2E = 0
n_G2A = 0
n_Y2E = 0
n_Y2A = 0
for align_obj in align_parse(alignment_file):
if specs[0] not in align_obj.species_list:
continue
if specs[1] not in align_obj.species_list:
continue
if (outgroup_ref[0] not in align_obj.species_list) and (outgroup_ref[1] not in align_obj.species_list):
continue
outgroup = [spec_id for spec_id in outgroup_ref if spec_id in align_obj.species_list]
seq_id = align_obj.seqinfo_dict[specs[0]].keys()[0]
orf_crds = orf_crd_dict[seq_id]
align_length = len(align_obj.align_dict[specs[0]])
for i in range(orf_crds[0], orf_crds[1]):
if len(outgroup) == 1:
outgroup_let = align_obj.align_dict[outgroup[0]][i]
if align_obj.edinfo_dict[outgroup[0]].get(i+1):
outgroup_let = 'E'
elif len(outgroup) == 2:
let1 = align_obj.align_dict[outgroup[0]][i]
if align_obj.edinfo_dict[outgroup[0]].get(i+1):
let1 = 'E'
let2 = align_obj.align_dict[outgroup[1]][i]
if align_obj.edinfo_dict[outgroup[1]].get(i+1):
let2 = 'E'
outgroup_let = anc_letter(let1, let2)
if outgroup_let == '-':
continue
let1 = align_obj.align_dict[specs[0]][i]
dna_let1 = let1
if align_obj.edinfo_dict[specs[0]].get(i+1):
let1 = 'E'
let2 = align_obj.align_dict[specs[1]][i]
if align_obj.edinfo_dict[specs[1]].get(i+1):
let2 = 'E'
if (let1 == '-') or (let2 == '-'):
continue
if outgroup_let != let2:
continue
subst_mat[outgroup_let][let1] += 1
if flag == "all":
if let1 == 'A':
n_A += 1
if outgroup_let == 'G':
n_G2A += 1
elif outgroup_let in ('C', 'T'):
n_Y2A += 1
elif let1 == 'E':
n_E += 1
if outgroup_let == 'G':
n_G2E += 1
elif outgroup_let in ('C', 'T'):
n_Y2E += 1
elif let1 == 'G':
n_G += 1
elif let1 in ('C', 'T'):
n_Y += 1
if outgroup_let == 'A':
n_A_anc += 1
if let1 == 'G':
n_A2G += 1
elif let1 in ('C', 'T'):
n_A2Y += 1
elif outgroup_let == 'E':
n_E_anc += 1
if let1 == 'G':
n_E2G += 1
elif let1 in ('C', 'T'):
n_E2Y += 1
elif outgroup_let == 'G':
n_G_anc += 1
elif outgroup_let in ('C', 'T'):
n_Y_anc += 1
continue
codon, aacid, shift = get_codon(align_obj, specs[0], orf_crds[0], i)
codon_new = codon[:]
codon_new[shift] = 'A'
aacid_new = str(Seq(''.join(codon_new)).translate())
codon_new_G = codon[:]
codon_new_G[shift] = 'G'
aacid_new_G = str(Seq(''.join(codon_new_G)).translate())
if aacid_new != aacid_new_G and flag == "syn":
continue
elif aacid_new == aacid_new_G and flag == "nsyn":
continue
if let1 == 'A':
n_A += 1
if outgroup_let == 'G':
n_G2A += 1
elif outgroup_let in ('C', 'T'):
n_Y2A += 1
elif let1 == 'E':
n_E += 1
if outgroup_let == 'G':
n_G2E += 1
elif outgroup_let in ('C', 'T'):
n_Y2E += 1
elif let1 == 'G':
n_G += 1
elif let1 in ('C', 'T'):
n_Y += 1
if outgroup_let == 'A':
n_A_anc += 1
if let1 == 'G':
n_A2G += 1
elif let1 in ('C', 'T'):
n_A2Y += 1
elif outgroup_let == 'E':
n_E_anc += 1
if let1 == 'G':
n_E2G += 1
elif let1 in ('C', 'T'):
n_E2Y += 1
elif outgroup_let == 'G':
n_G_anc += 1
elif outgroup_let in ('C', 'T'):
n_Y_anc += 1
print "@\tn_E\tn_A\tn_G\tn_Y\tn_E_anc\tn_A_anc\tn_G_anc\tn_Y_anc\tn_E2G\tn_A2G\tn_E2Y\tn_A2Y\tn_G2E\tn_G2A\tn_Y2E\tn_Y2A"
print '*', n_E, n_A, n_G, n_Y, n_E_anc, n_A_anc, n_G_anc, n_Y_anc, n_E2G, n_A2G, n_E2Y, n_A2Y, n_G2E, n_G2A, n_Y2E, n_Y2A
print float(n_E2G)/n_E_anc, float(n_A2G)/n_A_anc, (float(n_E2G)/n_E_anc)/(float(n_A2G)/n_A_anc)
print float(n_E2Y)/n_E_anc, float(n_A2Y)/n_A_anc, (float(n_E2Y)/n_E_anc)/(float(n_A2Y)/n_A_anc)
print ((float(n_E2G)/n_E_anc)/(float(n_A2G)/n_A_anc))/((float(n_E2Y)/n_E_anc)/(float(n_A2Y)/n_A_anc))
print float(n_G2E)/n_G_anc, float(n_G2A)/n_G_anc, (float(n_G2E)/n_G_anc)/(float(n_G2A)/n_G_anc)
print float(n_Y2E)/n_Y_anc, float(n_Y2A)/n_Y_anc, (float(n_Y2E)/n_Y_anc)/(float(n_Y2A)/n_Y_anc)
print ((float(n_G2E)/n_G_anc)/(float(n_G2A)/n_G_anc))/((float(n_Y2E)/n_Y_anc)/(float(n_Y2A)/n_Y_anc))
print (float(n_A2G))/n_A_anc
print (float(n_A2Y))/n_A_anc
print (float(n_G2A))/n_G_anc
print (float(n_Y2A))/n_Y_anc
subst_mat_print(subst_mat)
# print control_str
return subst_mat
def build_subst_mat(alignment_file, outgr_str, spec_str, select_sites, orf_crd_table):
outgroup_ref = outgr_str.split(',')
specs = spec_str.split(',')
subst_mat = subst_mat_init()
orf_crd_dict = make_orf_crd_dict(orf_crd_table)
# control_str = ""
# count = 0
for align_obj in align_parse(alignment_file):
if specs[0] not in align_obj.species_list:
continue
if specs[1] not in align_obj.species_list:
continue
if (outgroup_ref[0] not in align_obj.species_list) and (outgroup_ref[1] not in align_obj.species_list):
continue
# print align_obj.seqinfo_dict
seq_id = align_obj.seqinfo_dict[specs[0]].keys()[0]
orf_crds = orf_crd_dict[seq_id]
outgroup = [spec_id for spec_id in outgroup_ref if spec_id in align_obj.species_list]
align_length = len(align_obj.align_dict[specs[0]])
for i in range(align_length):
if len(outgroup) == 1:
outgroup_let = align_obj.align_dict[outgroup[0]][i]
if align_obj.edinfo_dict[outgroup[0]].get(i+1):
outgroup_let = codon_change_A_or_E(select_sites, align_obj.edinfo_dict[outgroup[0]][i+1].codon_change)
elif len(outgroup) == 2:
let1 = align_obj.align_dict[outgroup[0]][i]
if align_obj.edinfo_dict[outgroup[0]].get(i+1):
let1 = codon_change_A_or_E(select_sites, align_obj.edinfo_dict[outgroup[0]][i+1].codon_change)
let2 = align_obj.align_dict[outgroup[1]][i]
if align_obj.edinfo_dict[outgroup[1]].get(i+1):
let2 = codon_change_A_or_E(select_sites, align_obj.edinfo_dict[outgroup[1]][i+1].codon_change)
outgroup_let = anc_letter(let1, let2)
if outgroup_let == '-':
continue
let1 = align_obj.align_dict[specs[0]][i]
if align_obj.edinfo_dict[specs[0]].get(i+1):
let1 = codon_change_A_or_E(select_sites, align_obj.edinfo_dict[specs[0]][i+1].codon_change)
let2 = align_obj.align_dict[specs[1]][i]
if align_obj.edinfo_dict[specs[1]].get(i+1):
let2 = codon_change_A_or_E(select_sites, align_obj.edinfo_dict[specs[1]][i+1].codon_change)
if (let1 == '-') or (let2 == '-'):
continue
if outgroup_let == let2:
if select_sites == "all":
subst_mat[outgroup_let][let1] += 1
continue
if i < orf_crds[0] or i >= orf_crds[1]:
inorf = False
else:
inorf = True
# if not inorf and select_sites == "syn":
# subst_mat[outgroup_let][let1] += 1
# continue
if not inorf:
continue
codon_start = orf_crds[0] + ((i - orf_crds[0])/3)*3
codon_end = codon_start + 3
codon = align_obj.align_dict[specs[0]][codon_start:codon_end]
codon_pos = (i - orf_crds[0]) % 3
codon = list(codon)
for j in range(3):
if align_obj.edinfo_dict[specs[0]].get(codon_start + j + 1):
codon[j] = 'A'
codon_anc = codon[:]
if outgroup_let == 'E':
codon_anc[codon_pos] = 'A'
else:
codon_anc[codon_pos] = outgroup_let
codon_anc = ''.join(codon_anc)
codon = ''.join(codon)
aacid = str(Seq(codon).translate())
aacid_anc = str(Seq(codon_anc).translate())
if aacid == aacid_anc and select_sites == "syn":
subst_mat[outgroup_let][let1] += 1
if aacid != aacid_anc and select_sites == "nsyn":
subst_mat[outgroup_let][let1] += 1
# if let1 == 'E' or outgroup_let == 'E':
# print codon, codon_anc, aacid, aacid_anc
# print count
subst_mat_print(subst_mat)
# print control_str
return subst_mat
def main(alignment_file, edlevel_step, confint_p, spec_ids_str, permut_n, orf_crd_table, nucl_list):
nucl_list = list(nucl_list)
spec_ids_list = spec_ids_str.split(',')
edlevel_dict = edlevel_dict_init(edlevel_step)
orf_crd_dict = make_orf_crd_dict(orf_crd_table)
for align_obj in align_parse(alignment_file):
if (spec_ids_list[0] not in align_obj.species_list) or (spec_ids_list[1] not in align_obj.species_list):
continue
align_length = len(align_obj.align_dict[spec_ids_list[0]])
seq_id = align_obj.seqinfo_dict[spec_ids_list[0]].keys()[0]
orf_crds = orf_crd_dict[seq_id]
# print orf_crds, len(align_obj.align_dict[spec_ids_list[0]])
for i in range(orf_crds[0], orf_crds[1]):
if align_obj.align_dict[spec_ids_list[0]][i] != 'A':
if not align_obj.edinfo_dict[spec_ids_list[0]].get(i+1):
continue
if align_obj.align_dict[spec_ids_list[1]][i] == "-":
continue
if align_obj.edinfo_dict[spec_ids_list[1]].get(i+1):
continue
if align_obj.align_dict[spec_ids_list[1]][i] in nucl_list:
codon_start = orf_crds[0] + ((i - orf_crds[0])/3)*3
codon_end = codon_start + 3
shift = (i - orf_crds[0]) % 3
codon = align_obj.align_dict[spec_ids_list[0]][codon_start:codon_end]
codon = list(codon)
for j in range(3):
if align_obj.edinfo_dict[spec_ids_list[0]].get(codon_start + j + 1):
codon[j] = 'A'
codon_subst = codon[:]
codon_subst[shift] = align_obj.align_dict[spec_ids_list[1]][i]
codon = ''.join(codon)
codon_subst = ''.join(codon_subst)
aacid = str(Seq(codon).translate())
aacid_subst = str(Seq(codon_subst).translate())
if align_obj.edinfo_dict[spec_ids_list[0]].get(i+1):
edlevel = align_obj.edinfo_dict[spec_ids_list[0]][i+1].edlevel
l = len(edlevel_dict.keys())
edlevels = sorted(edlevel_dict.keys())
for j in range(1,l):
if (edlevel < edlevels[j]) and (edlevel >= edlevels[j - 1]):
if aacid == aacid_subst:
edlevel_dict[edlevels[j - 1]].dS_e += 1
else:
edlevel_dict[edlevels[j - 1]].dN_e += 1
else:
for j in edlevel_dict.keys():
if aacid == aacid_subst:
edlevel_dict[j].dS += 1
else:
edlevel_dict[j].dN += 1
# print "spec_id\tedlevel_threshold\tdN_e\tdN\tdS_e\tdS\tdN_e_dS_e\dN_dS\tdN_dS_n\tdN_dS_n_low\tdN_dS_n_high"
for i in sorted(edlevel_dict.keys()):
try:
edlevel_dict[i].p_and_confint_print(confint_p, spec_ids_str, permut_n)
except ZeroDivisionError:
pass
def build_subst_mat(alignment_file, confint_p, outgr_str, spec_str,
select_sites):
outgroup_ref = outgr_str.split(',')
specs = spec_str.split(',')
subst_mat = subst_mat_init()
# control_str = ""
# count = 0
for align_obj in align_parse(alignment_file):
if specs[0] not in align_obj.species_list:
continue
if specs[1] not in align_obj.species_list:
continue
if (outgroup_ref[0] not in align_obj.species_list) and (
outgroup_ref[1] not in align_obj.species_list):
continue
outgroup = [
spec_id for spec_id in outgroup_ref
if spec_id in align_obj.species_list
]
align_length = len(align_obj.align_dict[specs[0]])
for i in range(align_length):
if len(outgroup) == 1:
outgroup_let = align_obj.align_dict[outgroup[0]][i]
if align_obj.edinfo_dict[outgroup[0]].get(i + 1):
outgroup_let = codon_change_A_or_E(
select_sites,
align_obj.edinfo_dict[outgroup[0]][i + 1].codon_change)
elif len(outgroup) == 2:
let1 = align_obj.align_dict[outgroup[0]][i]
if align_obj.edinfo_dict[outgroup[0]].get(i + 1):
let1 = codon_change_A_or_E(
select_sites,
align_obj.edinfo_dict[outgroup[0]][i + 1].codon_change)
let2 = align_obj.align_dict[outgroup[1]][i]
if align_obj.edinfo_dict[outgroup[1]].get(i + 1):
let2 = codon_change_A_or_E(
select_sites,
align_obj.edinfo_dict[outgroup[1]][i + 1].codon_change)
outgroup_let = anc_letter(let1, let2)
if outgroup_let == '-':
continue
let1 = align_obj.align_dict[specs[0]][i]
if align_obj.edinfo_dict[specs[0]].get(i + 1):
let1 = codon_change_A_or_E(
select_sites,
align_obj.edinfo_dict[specs[0]][i + 1].codon_change)
let2 = align_obj.align_dict[specs[1]][i]
if align_obj.edinfo_dict[specs[1]].get(i + 1):
let2 = codon_change_A_or_E(
select_sites,
align_obj.edinfo_dict[specs[1]][i + 1].codon_change)
if (let1 == '-') or (let2 == '-'):
continue
if outgroup_let == let2:
subst_mat[outgroup_let][let1] += 1
# print count
subst_mat_print(subst_mat)
# print control_str
return subst_mat
def main(alignment_file, edlevel_step, confint_p, spec_ids_str, permut_n,
syn_nsyn_esites, syn_nsyn_asites, orf_crd_table):
spec_ids_list = spec_ids_str.split(',')
edlevel_dict = edlevel_dict_init(edlevel_step)
orf_crd_dict = make_orf_crd_dict(orf_crd_table)
for align_obj in align_parse(alignment_file):
if (spec_ids_list[0] not in align_obj.species_list) or (
spec_ids_list[1] not in align_obj.species_list):
continue
# print spec_ids_list
align_length = len(align_obj.align_dict[spec_ids_list[0]])
seq_id = align_obj.seqinfo_dict[spec_ids_list[0]].keys()[0]
orf_crds = orf_crd_dict[seq_id]
for i in range(orf_crds[0], orf_crds[1]):
edsite = False
let_1 = align_obj.align_dict[spec_ids_list[0]][i]
let_2 = align_obj.align_dict[spec_ids_list[1]][i]
if let_2 == "-":
continue
if let_1 != "A":
if not align_obj.edinfo_dict[spec_ids_list[0]].get(i + 1):
continue
else:
let_1 = 'A'
if align_obj.edinfo_dict[spec_ids_list[0]].get(i + 1):
let_1 = 'A'
edsite = True
if align_obj.edinfo_dict[spec_ids_list[1]].get(i + 1):
let_2 = 'A'
if edsite:
edlevel = align_obj.edinfo_dict[spec_ids_list[0]][i +
1].edlevel
if syn_nsyn_esites == 'syn' and align_obj.edinfo_dict[
spec_ids_list[0]][i + 1].codon_change != 'syn':
continue
if syn_nsyn_esites == 'nsyn' and align_obj.edinfo_dict[
spec_ids_list[0]][i + 1].codon_change == 'syn':
continue
for j in edlevel_dict.keys():
if j <= edlevel:
edlevel_dict[j].n_E += 1
if let_2 == 'G':
for j in edlevel_dict.keys():
if j <= edlevel:
edlevel_dict[j].E2G += 1
elif let_2 in ('C', 'T'):
for j in edlevel_dict.keys():
if j <= edlevel:
edlevel_dict[j].E2Y += 1
else:
codon, aacid, shift = get_codon(align_obj, spec_ids_list[0],
orf_crds[0], i)
codon_new = codon[:]
codon_new[shift] = let_2
aacid_new = str(Seq(''.join(codon_new)).translate())
codon_new_2_G = codon[:]
codon_new_2_G[shift] = 'G'
aacid_new_2_G = str(Seq(''.join(codon_new_2_G)).translate())
# codon_new_2_C = codon[:]
# codon_new_2_C[shift] = 'C'
# aacid_new_2_C = str(Seq(''.join(codon_new_2_C)).translate())
# codon_new_2_T = codon[:]
# codon_new_2_T[shift] = 'T'
# aacid_new_2_T = str(Seq(''.join(codon_new_2_T)).translate())
if aacid == aacid_new_2_G:
syn = True
else:
syn = False
if syn_nsyn_asites == 'syn' and not syn:
continue
elif syn_nsyn_asites == 'nsyn' and syn:
continue
elif syn and syn_nsyn_asites == 'syn':
for j in edlevel_dict.keys():
edlevel_dict[j].n_AG += 1
edlevel_dict[j].n_AY += 1
elif not syn and syn_nsyn_asites == 'nsyn':
for j in edlevel_dict.keys():
edlevel_dict[j].n_AG += 1
edlevel_dict[j].n_AY += 1
elif syn_nsyn_asites == 'all':
for j in edlevel_dict.keys():
edlevel_dict[j].n_AG += 1
# if aacid == aacid_new_2_C and syn_nsyn_asites == 'syn':
# if aacid == aacid_new_2_G:
# for j in edlevel_dict.keys():
# edlevel_dict[j].n_AY += 1
# elif aacid != aacid_new_2_C and syn_nsyn_asites == 'nsyn':
# if aacid != aacid_new_2_G:
# for j in edlevel_dict.keys():
# edlevel_dict[j].n_AY += 1
#
# if aacid == aacid_new_2_T and syn_nsyn_asites == 'syn':
# if aacid == aacid_new_2_G:
# for j in edlevel_dict.keys():
# edlevel_dict[j].n_AY += 1
# elif aacid != aacid_new_2_T and syn_nsyn_asites == 'nsyn':
# if aacid != aacid_new_2_G:
# for j in edlevel_dict.keys():
# edlevel_dict[j].n_AY += 1
if let_2 == 'G':
for j in edlevel_dict.keys():
edlevel_dict[j].A2G += 1
elif let_2 in ('C', 'T'):
for j in edlevel_dict.keys():
edlevel_dict[j].A2Y += 1
print "spec_id\tedlevel_thr\tp_E2G\tp_A2G\tp_E2Y\tp_A2Y\trf_G\trf_G_low\trf_G_high\trf_Y\trf_Y_low\trf_Y_high"
for i in sorted(edlevel_dict.keys()):
try:
edlevel_dict[i].p_and_confint_print(confint_p, spec_ids_str,
permut_n, syn_nsyn_asites)
except ZeroDivisionError:
pass
def main(alignment_file,
edlevel_step,
confint_p,
spec_ids_str,
permut_n,
orf_crd_table):
spec_ids_list = spec_ids_str.split(',')
edlevel_dict = edlevel_dict_init(edlevel_step)
orf_crd_dict = make_orf_crd_dict(orf_crd_table)
codon_usage_dict = dict()
for align_obj in align_parse(alignment_file):
if (spec_ids_list[0] not in align_obj.species_list) or (spec_ids_list[1] not in align_obj.species_list):
continue
align_length = len(align_obj.align_dict[spec_ids_list[0]])
seq_id = align_obj.seqinfo_dict[spec_ids_list[0]].keys()[0]
orf_crds = orf_crd_dict[seq_id]
for i in range(orf_crds[0], orf_crds[1]):
edsite = False
let_1 = align_obj.align_dict[spec_ids_list[0]][i]
let_2 = align_obj.align_dict[spec_ids_list[1]][i]
if let_2 == "-":
continue
if let_1 != "A":
if not align_obj.edinfo_dict[spec_ids_list[0]].get(i+1):
continue
else:
let_1 = 'A'
if align_obj.edinfo_dict[spec_ids_list[0]].get(i+1):
let_1 = 'A'
edsite = True
if align_obj.edinfo_dict[spec_ids_list[1]].get(i+1):
let_2 = 'A'
if edsite:
edlevel = align_obj.edinfo_dict[spec_ids_list[0]][i+1].edlevel
if align_obj.edinfo_dict[spec_ids_list[0]][i+1].codon_change == 'syn':
continue
for j in edlevel_dict.keys():
if j <= edlevel:
edlevel_dict[j].n_E_nsyn += 1
if let_2 == 'G':
for j in edlevel_dict.keys():
if j <= edlevel:
edlevel_dict[j].E_nsyn2G += 1
else:
if let_2 != 'G' and let_2 != 'A':
continue
codon, aacid, shift = get_codon(align_obj, spec_ids_list[0], orf_crds[0], i)
str_codon = ''.join(codon)
if codon_usage_dict.get(str_codon):
codon_usage_dict[str_codon] += 1
else:
codon_usage_dict[str_codon] = 1
codon_new = codon[:]
codon_new[shift] = let_2
aacid_new = str(Seq(''.join(codon_new)).translate())
codon_new_2_G = codon[:]
codon_new_2_G[shift] = 'G'
aacid_new_2_G = str(Seq(''.join(codon_new_2_G)).translate())
if aacid != aacid_new_2_G:
continue
for j in edlevel_dict.keys():
edlevel_dict[j].n_A_syn += 1
if let_2 == 'G':
for j in edlevel_dict.keys():
edlevel_dict[j].A_syn2G += 1
alpha_nsyn, alpha_syn = alpha_count(codon_usage_dict)
for i in sorted(edlevel_dict.keys()):
edlevel_dict[i].alpha_nsyn = alpha_nsyn
edlevel_dict[i].alpha_syn = alpha_syn
print "spec_id\tedlevel_thr\tE_nsyn2G\tn_E_nsyn\tA_syn2G\tn_A_syn\talpha_nsyn\talpha_syn\tcomb_coeff\tmidvalue_dnds\tdnds_low\tdnds_high"
for i in sorted(edlevel_dict.keys()):
try:
edlevel_dict[i].p_and_confint_print(confint_p, spec_ids_str, permut_n)
except ZeroDivisionError:
pass
def main(alignment_file, edlevel_step, confint_p, spec_ids_str, permut_n, orf_crd_table, nucl_list):
global aminoacids
nucl_list = list(nucl_list)
aminoacids = list(aminoacids)
spec_ids_list = spec_ids_str.split(',')
edlevel_dict = edlevel_dict_init(edlevel_step)
edlevels = sorted(edlevel_dict.keys())
l = len(edlevels)
orf_crd_dict = make_orf_crd_dict(orf_crd_table)
for align_obj in align_parse(alignment_file):
if (spec_ids_list[0] not in align_obj.species_list) or (spec_ids_list[1] not in align_obj.species_list):
continue
align_length = len(align_obj.align_dict[spec_ids_list[0]])
seq_id = align_obj.seqinfo_dict[spec_ids_list[0]].keys()[0]
orf_crds = orf_crd_dict[seq_id]
for i in range(orf_crds[0], orf_crds[1]):
if align_obj.align_dict[spec_ids_list[0]][i] != 'A':
if not align_obj.edinfo_dict[spec_ids_list[0]].get(i+1):
continue
if align_obj.align_dict[spec_ids_list[1]][i] == "-":
continue
if align_obj.edinfo_dict[spec_ids_list[1]].get(i+1):
let2 = 'A'
else:
let2 = align_obj.align_dict[spec_ids_list[1]][i]
let1 = 'A'
codon, aacid, shift = get_codon(align_obj, spec_ids_list[0], orf_crds[0], i)
syn = True
for nucl in nucl_list:
codon_new = codon[:]
codon_new[shift] = nucl
if aacid != str(Seq(''.join(codon_new)).translate()):
syn = False
if syn and aacid not in aminoacids:
continue
if align_obj.edinfo_dict[spec_ids_list[0]].get(i+1):
edlevel = align_obj.edinfo_dict[spec_ids_list[0]][i+1].edlevel
if syn:
for j in range(1, l):
if (edlevel < edlevels[j]) and (edlevel >= edlevels[j - 1]):
edlevel_dict[edlevels[j - 1]].total_S_E += 1
else:
for j in range(1, l):
if (edlevel < edlevels[j]) and (edlevel >= edlevels[j - 1]):
edlevel_dict[edlevels[j - 1]].total_N_E += 1
else:
if syn:
for j in range(1, l):
edlevel_dict[edlevels[j - 1]].total_S_A += 1
else:
for j in range(1, l):
edlevel_dict[edlevels[j - 1]].total_N_A += 1
if let1 == let2:
continue
if let2 in nucl_list:
codon_new = codon[:]
codon_new[shift] = let2
aacid_new = str(Seq(''.join(codon_new)).translate())
if aacid == aacid_new:
syn = True
else:
syn = False
if align_obj.edinfo_dict[spec_ids_list[0]].get(i+1):
edlevel = align_obj.edinfo_dict[spec_ids_list[0]][i+1].edlevel
if syn:
for j in range(1, l):
if (edlevel < edlevels[j]) and (edlevel >= edlevels[j - 1]):
edlevel_dict[edlevels[j - 1]].dS_e += 1
else:
for j in range(1, l):
if (edlevel < edlevels[j]) and (edlevel >= edlevels[j - 1]):
edlevel_dict[edlevels[j - 1]].dN_e += 1
else:
if syn:
for j in range(1, l):
edlevel_dict[edlevels[j - 1]].dS += 1
else:
for j in range(1, l):
edlevel_dict[edlevels[j - 1]].dN += 1
s = edlevel_dict[sorted(edlevel_dict.keys())[0]]
dnds_a = (float(s.dN)/s.total_N_A)/(float(s.dS)/s.total_S_A)
for i in sorted(edlevel_dict.keys()):
edlevel_dict[i].p_and_confint_print(confint_p, spec_ids_str, permut_n, dnds_a)
