def write_tree_rates(rate_dict, alignment_dict, cdna_dicts, out_filename,
xfold_only, xfold_degeneracy):
outfile = file(out_filename, 'w')
outfile.write("orf\tnal\tcor\tpcor\tncor\tns\tss\tmsid\tmfal\tadn\n")
ngenes = 0
for orf in rate_dict.keys():
(length, spec_orf_list, aligned_prots) = alignment_dict[orf]
(dns, dss, tree) = rate_dict[orf]
root = phylip.parse_tree(tree)
species = root.leaves()
msid = align_stats(aligned_prots, sequence_identity, stats.Mean)
mfal = align_stats(aligned_prots, frac_aligned, min)
#msid = min_seq_id(aligned_prots)
#mfal = min_frac_aligned(aligned_prots)
if mfal < 0.5:
print "# rejected orf (mfal,msid) %s (%1.2f,%1.2f)" % (orf, mfal,
msid)
continue
num_genes = len(species)
# Compute correlation between nonsyn-syn changes
try:
#target_orf = dict(spec_orf_list)[spec_name]
((r, p, n), ns,
ss) = get_rate_correlation_windowed(dns, dss, aligned_prots,
cdna_dicts, spec_orf_list,
xfold_only, xfold_degeneracy)
outfile.write("%s\t%d\t%1.3f\t%1.3f\t%d\t%1.2f\t%1.2f\t%1.2f\t%1.2f\t%1.4f\n" % \
(orf,num_genes,r,p,n,sum(ns),sum(ss),msid,mfal,sum(ns)/float(len(dns))))
ngenes += 1
outfile.flush()
except stats.StatsError, se:
continue
def write_tree_rates(rate_dict, alignment_dict, cdna_dicts, out_filename, xfold_only, xfold_degeneracy):
outfile = file(out_filename,'w')
outfile.write("orf\tnal\tcor\tpcor\tncor\tns\tss\tmsid\tmfal\tadn\n")
ngenes = 0
for orf in rate_dict.keys():
(length, spec_orf_list, aligned_prots) = alignment_dict[orf]
(dns, dss, tree) = rate_dict[orf]
root = phylip.parse_tree(tree)
species = root.leaves()
msid = align_stats(aligned_prots, sequence_identity, stats.Mean)
mfal = align_stats(aligned_prots, frac_aligned, min)
#msid = min_seq_id(aligned_prots)
#mfal = min_frac_aligned(aligned_prots)
if mfal < 0.5:
print "# rejected orf (mfal,msid) %s (%1.2f,%1.2f)" % (orf, mfal, msid)
continue
num_genes = len(species)
# Compute correlation between nonsyn-syn changes
try:
#target_orf = dict(spec_orf_list)[spec_name]
((r,p,n), ns, ss) = get_rate_correlation_windowed(dns, dss, aligned_prots, cdna_dicts, spec_orf_list, xfold_only, xfold_degeneracy)
outfile.write("%s\t%d\t%1.3f\t%1.3f\t%d\t%1.2f\t%1.2f\t%1.2f\t%1.2f\t%1.4f\n" % \
(orf,num_genes,r,p,n,sum(ns),sum(ss),msid,mfal,sum(ns)/float(len(dns))))
ngenes += 1
outfile.flush()
except stats.StatsError, se:
continue
def get_tree_rates(ortho_dict, alignment_dict, cdna_dicts, tree_string, begin_index, end_index):
tree = phylip.parse_tree(tree_string)
tree_species = [n.name for n in tree.leaves()]
n_genes = 0
# Individual genes
rate_ancestor_cache = {}
# Assemble gene list
keys = []
for gene in ortho_dict.keys():
try:
(length, corr_keys, aligned_prots) = alignment_dict[gene]
alignment_species = [spec for (spec,orf) in corr_keys]
except KeyError, ke:
print "# Couldn't find alignments for", ke
continue
# Must have concordance between tree species and alignment species
if set(tree_species).intersection(set(alignment_species)) == set(tree_species):
keys.append(gene)
def get_tree_rates(ortho_dict, alignment_dict, cdna_dicts, tree_string,
begin_index, end_index):
tree = phylip.parse_tree(tree_string)
tree_species = [n.name for n in tree.leaves()]
n_genes = 0
# Individual genes
rate_ancestor_cache = {}
# Assemble gene list
keys = []
for gene in ortho_dict.keys():
try:
(length, corr_keys, aligned_prots) = alignment_dict[gene]
alignment_species = [spec for (spec, orf) in corr_keys]
except KeyError, ke:
print "# Couldn't find alignments for", ke
continue
# Must have concordance between tree species and alignment species
if set(tree_species).intersection(
set(alignment_species)) == set(tree_species):
keys.append(gene)
