def is_poly_subtree_hemiplasy(root, leaves):
"""
Returns True if the polymorphic subtree shows hemiplasy
"""
extincts = [node.data["freq"] == 0.0 for node in leaves]
return not util.equal(* extincts)
def walk(node):
if not node.isLeaf():
counts = []
for child in node.children:
walk(child)
counts.append(child.data['genes']
- child.data['appear']
- child.data['dup']
+ child.data['loss'])
assert util.equal(* counts), str(counts)
node.data['genes'] = counts[0]
def walk(node):
if node in leaves:
colors[node] = phylo.hash_tree(node, gene2species)
else:
# recurse
for child in node.children:
walk(child)
childHashes = util.mget(colors, node.children)
if len(childHashes) > 1 and util.equal(*childHashes):
nmirrors[0] += 1
childHashes.sort()
colors[node] = phylo.hash_tree_compose(childHashes)
def walk(node):
if node in leaves:
colors[node] = phylo.hash_tree(node, gene2species)
else:
# recurse
for child in node.children:
walk(child)
childHashes = util.mget(colors, node.children)
if len(childHashes) > 1 and util.equal(*childHashes):
nmirrors[0] += 1
childHashes.sort()
colors[node] = phylo.hash_tree_compose(childHashes)
def chiSquare(rows, expected=None, nparams=0):
# ex: rows = [[1,2,3],[1,4,5]]
assert (util.equal(map(len, rows)))
if 0 in map(sum, rows): return 0, 1.0
cols = zip(*rows)
if 0 in map(sum, cols): return 0, 1.0
if not expected:
expected = make_expected(rows)
chisq = 0
for obss, exps in zip(rows, expected):
for obs, exp in zip(obss, exps):
chisq += ((obs - exp)**2) / exp
df = max(len(rows) - 1, 1) * max(len(rows[0]) - 1, 1) - nparams
p = chi_square_lookup(chisq, df)
return chisq, p
def chiSquare(rows, expected=None, nparams=0):
# ex: rows = [[1,2,3],[1,4,5]]
assert util.equal(map(len, rows))
if 0 in map(sum,rows): return 0,1.0
cols = zip(* rows)
if 0 in map(sum,cols): return 0,1.0
if not expected:
expected = make_expected(rows)
chisq = 0
for obss,exps in zip(rows,expected):
for obs, exp in zip(obss, exps):
chisq += ((obs-exp)**2)/exp
df = max(len(rows)-1, 1)*max(len(rows[0])-1, 1) - nparams
p = chi_square_lookup(chisq,df)
return chisq,p
def is_contig(db, genes):
"""Returns True if genes are contiguous along chromosome"""
if len(genes) > 1:
pos = [db.get_region_pos_full(i) for i in genes if i in db.regions]
# ensure hits are on same chromosome
if not util.equal(* util.cget(pos, 1)):
return False
ind = util.cget(pos, 2)
ind.sort()
# check that each position is present
i = ind[0]
for j in ind[1:]:
if j != i+1:
return False
i += 1
return True
def is_contig(db, genes):
"""Returns True if genes are contiguous along chromosome"""
if len(genes) > 1:
pos = [db.get_region_pos_full(i) for i in genes if i in db.regions]
# ensure hits are on same chromosome
if not util.equal(*util.cget(pos, 1)):
return False
ind = util.cget(pos, 2)
ind.sort()
# check that each position is present
i = ind[0]
for j in ind[1:]:
if j != i + 1:
return False
i += 1
return True
def validate_seqs(seqs):
"""Ensures sequences are all same size"""
sizes = map(len, seqs.values())
assert util.equal(*sizes), "sequences are not same length"
def validate_seqs(seqs):
"""Ensures sequences are all same size"""
sizes = map(len, seqs.values())
assert util.equal(* sizes), "sequences are not same length"