def get_best_TC_tree(
dv_file,
gm_file,
label_file,
tree_files,
name='unnamed_tree',
):
"""
Given a distance-variance file, a genome-map file, a label file
and a number of tree files
"""
if not isinstance(tree_files, list):
return Tree.new_treecollection_tree(dv_file, gm_file,
label_file, tree_files, name)
best_score = float('inf')
best_tree = None
starts = len(tree_files)
for i in range(starts):
guide = tree_files[i]
current_tree = Tree.new_treecollection_tree(dv_file, gm_file,
label_file, guide, name)
if current_tree.score < best_score:
best_score = current_tree.score
best_tree = current_tree
return best_tree
def _put_best_TC_trees(self, tmpdir="/tmp", overwrite=True, max_guide_trees=-1):
rec_list = self.get_cluster_records_with_memberships()
for (rec, members) in rec_list:
print "Calculating treecollection tree for {0}".format(rec.name),
if rec.name in self.inferred_trees and overwrite == False:
print "Skipping - already calculated (overwrite set to False)"
continue
guidetrees = [self.keys_to_records[member].tree for member in members]
if max_guide_trees > 0:
guidetrees = guidetrees[:max_guide_trees]
TCtrees = []
pref = rec._write_temp_tc(make_guide_tree=False, tmpdir=tmpdir)
pref = "{0}/{1}".format(tmpdir, pref)
dv_file = pref + "_dv.txt"
labels_file = pref + "_labels.txt"
map_file = pref + "_map.txt"
if len(guidetrees) > 1:
print "(using best of {0} guidetrees)".format(len(guidetrees))
else:
print "(using single guidetree)"
for t in guidetrees:
guidetree_file = "{0}/{1}.nwk".format(tmpdir, t.name)
n = t.reroot_newick()
with open(guidetree_file, "w") as writer:
writer.write(n)
TCtrees.append(Tree.new_treecollection_tree(dv_file, map_file, labels_file, guidetree_file, rec.name))
best = min(TCtrees, key=lambda x: x.score)
rec.tree = best
self.inferred_trees[rec.name] = best
self.update_scores()
def _put_best_TC_trees(
self,
tmpdir='/tmp',
overwrite=True,
max_guide_trees=-1,
):
rec_list = self.get_cluster_records_with_memberships()
for (rec, members) in rec_list:
print 'Calculating treecollection tree for {0}'.format(rec.name),
if rec.name in self.inferred_trees and overwrite == False:
print 'Skipping - already calculated (overwrite set to False)'
continue
guidetrees = [
self.keys_to_records[member].tree for member in members
]
if max_guide_trees > 0:
guidetrees = guidetrees[:max_guide_trees]
TCtrees = []
pref = rec._write_temp_tc(make_guide_tree=False, tmpdir=tmpdir)
pref = '{0}/{1}'.format(tmpdir, pref)
dv_file = pref + '_dv.txt'
labels_file = pref + '_labels.txt'
map_file = pref + '_map.txt'
if len(guidetrees) > 1:
print '(using best of {0} guidetrees)'.format(len(guidetrees))
else:
print '(using single guidetree)'
for t in guidetrees:
guidetree_file = '{0}/{1}.nwk'.format(tmpdir, t.name)
n = t.reroot_newick()
with open(guidetree_file, 'w') as writer:
writer.write(n)
TCtrees.append(
Tree.new_treecollection_tree(dv_file, map_file,
labels_file, guidetree_file,
rec.name))
best = min(TCtrees, key=lambda x: x.score)
rec.tree = best
self.inferred_trees[rec.name] = best
self.update_scores()
