def open_folder(folder):
sim = Simulation(folder)
sim.extant_genomes = file_ops.open_genome_file(
os.path.join(folder, cfg.sim_extant_genomes()))
sim.ancestral_genomes = file_ops.open_genome_file(
os.path.join(folder, cfg.sim_ancestral_genomes()))
sim.sim_tree = file_ops.open_newick_tree(
os.path.join(folder, cfg.sim_tree()))
sim.folder = folder
# events:
try:
with open(os.path.join(sim.folder, cfg.sim_events_file())) as f:
l = f.readline()
header = l.strip().split()
for l in f:
fields = l.strip().split()
node = sim.sim_tree.find_node_with_label(fields[0])
events = {
field: int(r)
for field, r in zip(header[1:], fields[1:])
}
node.edge.events = events
except IOError:
pass
sim.sim_parameters = SimParameters()
# Reading data back
sim.sim_parameters.__dict__ = file_ops.read_simulation_parameters(
folder)
return sim
def main(treefile, ignore_weights, marker_file, kT=0.1, minimum=0.0, write_output=False, output_folder="."):
# Config:
declone = cfg.declone_path()
# nhx output:
nhxFile = os.path.splitext(treefile)[0] + ".nhx"
# open tree:
t = file_ops.open_newick_tree(treefile)
# Newick to NHX:
parse_NEWICK_to_nhx(t, ignore_weights, nhxFile, minimum)
listOfInternalNodes = [node.label for node in t.internal_nodes()]
extantAdjacencies = findAdjacencies(read_Marker_file(marker_file))
singleLeafAdj, adjacenciesPerNode, extantWeightedAdjacencies = deCloneProbabilities(declone, extantAdjacencies, kT, listOfInternalNodes, nhxFile)
if write_output:
file_ops.write_declone_weights(singleLeafAdj, adjacenciesPerNode, extantWeightedAdjacencies, kT, folder=output_folder)
return singleLeafAdj, adjacenciesPerNode, extantWeightedAdjacencies
def open_folder(folder):
sim = Simulation(folder)
sim.extant_genomes = file_ops.open_genome_file(os.path.join(folder, cfg.sim_extant_genomes()))
sim.ancestral_genomes = file_ops.open_genome_file(os.path.join(folder, cfg.sim_ancestral_genomes()))
sim.sim_tree = file_ops.open_newick_tree(os.path.join(folder, cfg.sim_tree()))
sim.folder = folder
# events:
try:
with open(os.path.join(sim.folder, cfg.sim_events_file())) as f:
l = f.readline()
header = l.strip().split()
for l in f:
fields = l.strip().split()
node = sim.sim_tree.find_node_with_label(fields[0])
events = {field: int(r) for field, r in zip(header[1:], fields[1:])}
node.edge.events = events
except IOError:
pass
sim.sim_parameters = SimParameters()
# Reading data back
sim.sim_parameters.__dict__ = file_ops.read_simulation_parameters(folder)
return sim
action="store_true",
default=False,
help="adds adjacencies from 2-cycles that are AA- or BB-open directly."
)
# PARSE params:
param = parser.parse_args()
# test if blossom5 is needed:
if param.perfect:
if not file_ops.blossom5_is_available():
print >> sys.stderr, "Blossom5 not found, it is needed for perfect matching. Either install blossom5 or do not use the '-p' perfect matching option."
sys.exit(-1)
extant_genomes = file_ops.open_genome_file(param.input_genomes)
tree = file_ops.open_newick_tree(param.tree, label_internal_nodes=True)
# estimate lenghts:
if param.estimate_lenghts is not None:
if param.estimate_lenghts == "lp":
algorithms.estimate_branch_lengths_lp(tree, extant_genomes)
elif param.estimate_lenghts == "least_squares":
algorithms.estimate_branch_lengths_least_squares(
tree, extant_genomes)
else:
# default is to run it anyway, if the tree has no branch lengths:
if any([node.edge.length is None for node in tree.leaf_nodes()]):
algorithms.estimate_branch_lengths_lp(tree, extant_genomes)
# Fix multibranching trees:
changed = resolve_tree(tree)
# DEBUG:
parser.add_argument("--add_open_2_cycles", action="store_true", default=False,
help="adds adjacencies from 2-cycles that are AA- or BB-open directly.")
# PARSE params:
param = parser.parse_args()
# test if blossom5 is needed:
if param.perfect:
if not file_ops.blossom5_is_available():
print >> sys.stderr, "Blossom5 not found, it is needed for perfect matching. Either install blossom5 or do not use the '-p' perfect matching option."
sys.exit(-1)
extant_genomes = file_ops.open_genome_file(param.input_genomes)
tree = file_ops.open_newick_tree(param.tree, label_internal_nodes=True)
# estimate lenghts:
if param.estimate_lenghts is not None:
if param.estimate_lenghts == "lp":
algorithms.estimate_branch_lengths_lp(tree, extant_genomes)
elif param.estimate_lenghts == "least_squares":
algorithms.estimate_branch_lengths_least_squares(tree, extant_genomes)
else:
# default is to run it anyway, if the tree has no branch lengths:
if any([node.edge.length is None for node in tree.leaf_nodes()]):
algorithms.estimate_branch_lengths_lp(tree, extant_genomes)
# Fix multibranching trees:
changed = resolve_tree(tree)
# if the tree changed, it might be a good idea to rerun the branch length detection?