def evaluate_directory(data_dir,
eval_limit=50000,
lim=5,
limited_expand=False):
'''
Processes a directory of FASTA files, generating and evaluating trees
using branch and bound with early stopping and limited expansion (optional)
Args:
data_dir: str, the path to the data directory which stores fasta files
eval_limit: int, max number of trees to evaluate for each file. Good
setting depends on seq length and time you're willing to wait.
lim: int, number of files in the data directory to process
limited_expand: bool, whether or not to use limited expansion
Returns:
List[Tree], a list of BioPython Phylo trees with tied best scores
'''
scorer = TreeConstruction.ParsimonyScorer()
all_best = []
files = os.listdir(data_dir)
for i, file in enumerate(files[:lim]):
# Load and sort file
print(f"Processing {file} ({i+1}/{len(files[:lim])})")
aln = AlignIO.read(open(data_dir + os.path.sep + file), 'fasta')
aln.sort(key=lambda a: a.id)
result_trees = get_best_trees(aln, scorer, eval_limit, limited_expand)
print(f"Found {len(result_trees)} trees.")
all_best.extend(result_trees)
return [tr[0] for tr in all_best]
def find_good_tree(trees, data_dir, lim=25):
'''
Evaluates a list of trees against multiple alignments, returning the best
scoring tree across all alignments. Requires tree terminal names and
alignment names in data_dir are the same.
Args:
trees: List[Tree], a list of BioPython Phylo trees to evaluate
data_dir: str, the path to the data directory
lim: int, number of alignments to evaluate against (more is slower)
'''
best_trees = []
scorer = TreeConstruction.ParsimonyScorer()
files = os.listdir(data_dir)
alns = []
for i, file in enumerate(files[:lim]):
aln = AlignIO.read(open(data_dir + os.path.sep + file), 'fasta')
for rec in aln:
rec.name = rec.id = rec.name[:5]
alns.append(aln)
scores = {}
max_aln = {}
# Score trees and track highest score for each alignment to normalize later
print(f"Processing {len(trees)} trees...")
for i, tree in enumerate(trees):
print(f"\t{i+1}/{len(trees)}")
for j, aln in enumerate(alns[:lim]):
try:
sco = scorer.get_score(copy.deepcopy(tree), aln)
except Exception as e:
print(e)
print(
"Scoring failed. Did you ensure that terminal names and alignment names match?"
)
return None
scores[(i, j)] = sco
if sco > max_aln.get(j, 0): max_aln[j] = sco
# Computes normalized scores for each tree
fin_scores = {}
for i in range(len(trees)):
for j in range(len(alns[:lim])):
m_aln = max_aln.get(j, 0)
if m_aln <= 0: continue
normalized_score = scores.get((i, j), 0) / m_aln
if not normalized_score:
print(f"Error for tree {i} and alignment {j}.")
fin_scores[i] = fin_scores.get(i, 0) + normalized_score
# Finds final best tree
best_tree = -1
for key in fin_scores.keys():
if best_tree < 0 or fin_scores[key] < fin_scores[best_tree]:
best_tree = key
if best_tree < 0:
print("No best tree found.")
return None
return trees[best_tree]
