def reconstruct_discrete_traits(tree, traits, missing_data='?', pc=1.0, sampling_bias_correction=None,
weights=None, verbose=0, iterations=5):
"""take a set of discrete states associated with tips of a tree
and reconstruct their ancestral states along with a GTR model that
approximately maximizes the likelihood of the states on the tree.
Parameters
----------
tree : str, Bio.Phylo.Tree
name of tree file or Biopython tree object
traits : dict
dictionary linking tips to straits
missing_data : str, optional
string indicating missing data
pc : float, optional
number of pseudo-counts to be used during GTR inference, default 1.0
sampling_bias_correction : float, optional
factor to inflate overall switching rate by to counteract sampling bias
weights : str, optional
name of file with equilibirum frequencies
verbose : int, optional
level of verbosity in output
iterations : int, optional
number of times non-linear optimization of overall rate and
transmission estimation are iterated
Returns
-------
tuple
tuple of treeanc object, forward and reverse alphabets
Raises
------
TreeTimeError
raise error if ancestral reconstruction errors out
"""
###########################################################################
### make a single character alphabet that maps to discrete states
###########################################################################
unique_states = set(traits.values())
n_observed_states = len(unique_states)
# load weights from file and convert to dict if supplied as string
if type(weights)==str:
try:
tmp_weights = pd.read_csv(weights, sep='\t' if weights[-3:]=='tsv' else ',',
skipinitialspace=True)
weight_dict = {row[0]:row[1] for ri,row in tmp_weights.iterrows() if not np.isnan(row[1])}
except:
raise ValueError("Loading of weights file '%s' failed!"%weights)
elif type(weights)==dict:
weight_dict = weights
else:
weight_dict = None
# add weights to unique states for alphabet construction
if weight_dict is not None:
unique_states.update(weight_dict.keys())
missing_weights = [c for c in unique_states if c not in weight_dict and c is not missing_data]
if len(missing_weights):
print("Missing weights for values: " + ", ".join(missing_weights))
if len(missing_weights)>0.5*n_observed_states:
print("More than half of discrete states missing from the weights file")
print("Weights read from file are:", weights)
raise TreeTimeError("More than half of discrete states missing from the weights file")
unique_states=sorted(unique_states)
# make a map from states (excluding missing data) to characters in the alphabet
# note that gap character '-' is chr(45) and will never be included here
reverse_alphabet = {state:chr(65+i) for i,state in enumerate(unique_states) if state!=missing_data}
alphabet = list(reverse_alphabet.values())
# construct a look up from alphabet character to states
letter_to_state = {v:k for k,v in reverse_alphabet.items()}
# construct the vector with weights to be used as equilibrium frequency
if weight_dict is not None:
mean_weight = np.mean(list(weight_dict.values()))
weights = np.array([weight_dict[letter_to_state[c]] if letter_to_state[c] in weight_dict else mean_weight
for c in alphabet], dtype=float)
weights/=weights.sum()
# consistency checks
if len(alphabet)<2:
print("mugration: only one or zero states found -- this doesn't make any sense", file=sys.stderr)
return None, None, None
n_states = len(alphabet)
missing_char = chr(65+n_states)
reverse_alphabet[missing_data]=missing_char
letter_to_state[missing_char]=missing_data
###########################################################################
### construct gtr model
###########################################################################
# set up dummy matrix
W = np.ones((n_states,n_states), dtype=float)
mugration_GTR = GTR.custom(pi = weights, W=W, alphabet = np.array(alphabet))
mugration_GTR.profile_map[missing_char] = np.ones(n_states)
mugration_GTR.ambiguous=missing_char
###########################################################################
### set up treeanc
###########################################################################
treeanc = TreeAnc(tree, gtr=mugration_GTR, verbose=verbose,
convert_upper=False, one_mutation=0.001)
treeanc.use_mutation_length = False
pseudo_seqs = [SeqRecord(id=n.name,name=n.name,
seq=Seq(reverse_alphabet[traits[n.name]]
if n.name in traits else missing_char))
for n in treeanc.tree.get_terminals()]
valid_seq = np.array([str(s.seq)!=missing_char for s in pseudo_seqs])
print("Assigned discrete traits to %d out of %d taxa.\n"%(np.sum(valid_seq),len(valid_seq)))
treeanc.aln = MultipleSeqAlignment(pseudo_seqs)
try:
ndiff = treeanc.infer_ancestral_sequences(method='ml', infer_gtr=True,
store_compressed=False, pc=pc, marginal=True, normalized_rate=False,
fixed_pi=weights, reconstruct_tip_states=True)
treeanc.optimize_gtr_rate()
except TreeTimeError as e:
print("\nAncestral reconstruction failed, please see above for error messages and/or rerun with --verbose 4\n")
raise e
for i in range(iterations):
treeanc.infer_gtr(marginal=True, normalized_rate=False, pc=pc, fixed_pi=weights)
treeanc.optimize_gtr_rate()
if sampling_bias_correction:
treeanc.gtr.mu *= sampling_bias_correction
treeanc.infer_ancestral_sequences(infer_gtr=False, store_compressed=False,
marginal=True, normalized_rate=False,
reconstruct_tip_states=True)
print(fill("NOTE: previous versions (<0.7.0) of this command made a 'short-branch length assumption. "
"TreeTime now optimizes the overall rate numerically and thus allows for long branches "
"along which multiple changes accumulated. This is expected to affect estimates of the "
"overall rate while leaving the relative rates mostly unchanged."))
return treeanc, letter_to_state, reverse_alphabet
def reconstruct_discrete_traits(tree, traits, missing_data='?', pc=1.0, sampling_bias_correction=None,
weights=None, verbose=0, iterations=5):
"""take a set of discrete states associated with tips of a tree
and reconstruct their ancestral states along with a GTR model that
approximately maximizes the likelihood of the states on the tree.
Parameters
----------
tree : str, Bio.Phylo.Tree
name of tree file or Biopython tree object
traits : dict
dictionary linking tips to straits
missing_data : str, optional
string indicating missing data
pc : float, optional
number of pseudo-counts to be used during GTR inference, default 1.0
sampling_bias_correction : float, optional
factor to inflate overall switching rate by to counteract sampling bias
weights : str, optional
name of file with equilibirum frequencies
verbose : int, optional
level of verbosity in output
iterations : int, optional
number of times non-linear optimization of overall rate and
transmission estimation are iterated
Returns
-------
tuple
tuple of treeanc object, forward and reverse alphabets
Raises
------
TreeTimeError
raise error if ancestral reconstruction errors out
"""
unique_states = sorted(set(traits.values()))
nc = len(unique_states)
if nc>180:
print("mugration: can't have more than 180 states!", file=sys.stderr)
return None, None, None
elif nc<2:
print("mugration: only one or zero states found -- this doesn't make any sense", file=sys.stderr)
return None, None, None
###########################################################################
### make a single character alphabet that maps to discrete states
###########################################################################
alphabet = [chr(65+i) for i,state in enumerate(unique_states)]
missing_char = chr(65+nc)
letter_to_state = {a:unique_states[i] for i,a in enumerate(alphabet)}
letter_to_state[missing_char]=missing_data
reverse_alphabet = {v:k for k,v in letter_to_state.items()}
###########################################################################
### construct gtr model
###########################################################################
if type(weights)==str:
tmp_weights = pd.read_csv(weights, sep='\t' if weights[-3:]=='tsv' else ',',
skipinitialspace=True)
weights = {row[0]:row[1] for ri,row in tmp_weights.iterrows()}
mean_weight = np.mean(list(weights.values()))
weights = np.array([weights[c] if c in weights else mean_weight for c in unique_states], dtype=float)
weights/=weights.sum()
else:
weights = None
# set up dummy matrix
W = np.ones((nc,nc), dtype=float)
mugration_GTR = GTR.custom(pi = weights, W=W, alphabet = np.array(alphabet))
mugration_GTR.profile_map[missing_char] = np.ones(nc)
mugration_GTR.ambiguous=missing_char
###########################################################################
### set up treeanc
###########################################################################
treeanc = TreeAnc(tree, gtr=mugration_GTR, verbose=verbose,
convert_upper=False, one_mutation=0.001)
treeanc.use_mutation_length = False
pseudo_seqs = [SeqRecord(id=n.name,name=n.name,
seq=Seq(reverse_alphabet[traits[n.name]]
if n.name in traits else missing_char))
for n in treeanc.tree.get_terminals()]
treeanc.aln = MultipleSeqAlignment(pseudo_seqs)
try:
ndiff = treeanc.infer_ancestral_sequences(method='ml', infer_gtr=True,
store_compressed=False, pc=pc, marginal=True, normalized_rate=False,
fixed_pi=weights, reconstruct_tip_states=True)
treeanc.optimize_gtr_rate()
except TreeTimeError as e:
print("\nAncestral reconstruction failed, please see above for error messages and/or rerun with --verbose 4\n")
raise e
for i in range(iterations):
treeanc.infer_gtr(marginal=True, normalized_rate=False, pc=pc)
treeanc.optimize_gtr_rate()
if sampling_bias_correction:
treeanc.gtr.mu *= sampling_bias_correction
treeanc.infer_ancestral_sequences(infer_gtr=False, store_compressed=False,
marginal=True, normalized_rate=False, reconstruct_tip_states=True)
print(fill("NOTE: previous versions (<0.7.0) of this command made a 'short-branch length assumption. "
"TreeTime now optimizes the overall rate numerically and thus allows for long branches "
"along which multiple changes accumulated. This is expected to affect estimates of the "
"overall rate while leaving the relative rates mostly unchanged."))
return treeanc, letter_to_state, reverse_alphabet
