def make_branch_lengths(alignment_path, topology_path, datatype, cmdline_extras):
# Now we re-estimate branchlengths using a GTR+I+G model on the
# (unpartitioned) dataset
cmdline_extras = check_defaults(cmdline_extras)
dir_path, fname = os.path.split(topology_path)
tree_path = os.path.join(dir_path, 'topology_tree.phy')
log.debug("Copying %s to %s", topology_path, tree_path)
util.dupfile(topology_path, tree_path)
if datatype == "DNA":
log.info("Estimating GTR+I+G branch lengths on tree")
command = "-i '%s' -u '%s' -m GTR -c 4 -a e -v e -o lr -b 0 %s" % (
alignment_path, tree_path, cmdline_extras)
run_phyml(command)
if datatype == "protein":
log.info("Estimating LG+F branch lengths on tree")
command = "-i '%s' -u '%s' -m LG -c 1 -v 0 -f m -d aa -o lr -b 0 %s" % (
alignment_path, tree_path, cmdline_extras)
run_phyml(command)
tree_path = make_tree_path(alignment_path)
log.info("Branchlength estimation finished")
# Now return the path of the final tree alignment
return tree_path
def make_branch_lengths(alignment_path, topology_path, datatype,
cmdline_extras):
# Now we re-estimate branchlengths using a GTR+I+G model on the
# (unpartitioned) dataset
cmdline_extras = check_defaults(cmdline_extras)
dir_path, fname = os.path.split(topology_path)
tree_path = os.path.join(dir_path, 'topology_tree.phy')
log.debug("Copying %s to %s", topology_path, tree_path)
util.dupfile(topology_path, tree_path)
if datatype == "DNA":
log.info("Estimating GTR+I+G branch lengths on tree")
command = "-i '%s' -u '%s' -m GTR -c 4 -a e -v e -o lr -b 0 %s" % (
alignment_path, tree_path, cmdline_extras)
run_phyml(command)
if datatype == "protein":
log.info("Estimating LG+F branch lengths on tree")
command = "-i '%s' -u '%s' -m LG -c 1 -v 0 -f m -d aa -o lr -b 0 %s" % (
alignment_path, tree_path, cmdline_extras)
run_phyml(command)
tree_path = make_tree_path(alignment_path)
log.info("Branchlength estimation finished")
# Now return the path of the final tree alignment
return tree_path
def make_branch_lengths(alignment_path, topology_path, datatype,
cmdline_extras):
# Now we re-estimate branchlengths using a GTR+G model on the
# (unpartitioned) dataset
cmdline_extras = check_defaults(cmdline_extras)
dir_path, fname = os.path.split(topology_path)
tree_path = os.path.join(dir_path, 'topology_tree.phy')
log.debug("Copying %s to %s", topology_path, tree_path)
util.dupfile(topology_path, tree_path)
os.remove(topology_path) # saves headaches later...
if datatype == "DNA":
log.info("Estimating GTR+G branch lengths on tree using RAxML")
command = "-f e -s '%s' -t '%s' -m GTRGAMMA -n BLTREE -w '%s' %s " % (
alignment_path, tree_path, os.path.abspath(dir_path),
cmdline_extras)
elif datatype == "protein":
log.info("Estimating LG+G branch lengths on tree using RAxML")
command = "-f e -s '%s' -t '%s' -m PROTGAMMALG -n BLTREE -w '%s' %s " % (
alignment_path, tree_path, os.path.abspath(dir_path),
cmdline_extras)
elif datatype == "morphology":
# LOOK OUT: this relies on the assumption that we can only specify a single
# model for morphology analyses...
# choose a model for the data - necessary for RAxML to load the data properly
model = models.get_model_commandline(the_config.models[0])
log.info("Estimating %s branch lengths on tree using RAxML",
the_config.models[0])
command = "-f e -s %s -t %s %s -K MK -n BLTREE -w %s %s" % (
alignment_path, tree_path, model, os.path.abspath(dir_path),
cmdline_extras)
else:
log.error("Unrecognised datatype: '%s'" % (datatype))
raise util.PartitionFinderError
run_raxml(command)
dir, aln = os.path.split(alignment_path)
tree_path = os.path.join(dir, "RAxML_result.BLTREE")
if not os.path.exists(tree_path):
log.error(
"RAxML tree topology should be here but can't be be found: '%s'" %
(tree_path))
raise util.PartitionFinderError
else:
log.debug("RAxML tree with branch lengths ('%s') looks like this: ",
tree_path)
with open(tree_path, 'r') as fin:
log.debug('%s', fin.read())
log.info("Branchlength estimation finished")
# Now return the path of the final tree with branch lengths
return tree_path
def make_branch_lengths(alignment_path, topology_path, datatype, cmdline_extras):
# Now we re-estimate branchlengths using a GTR+G model on the
# (unpartitioned) dataset
cmdline_extras = check_defaults(cmdline_extras)
dir_path, fname = os.path.split(topology_path)
tree_path = os.path.join(dir_path, 'topology_tree.phy')
log.debug("Copying %s to %s", topology_path, tree_path)
util.dupfile(topology_path, tree_path)
os.remove(topology_path) # saves headaches later...
if datatype == "DNA":
log.info("Estimating GTR+G branch lengths on tree using RAxML")
command = "-f e -s '%s' -t '%s' -m GTRGAMMA -n BLTREE -w '%s' %s " % (
alignment_path, tree_path, os.path.abspath(dir_path), cmdline_extras)
elif datatype == "protein":
log.info("Estimating LG+G branch lengths on tree using RAxML")
command = "-f e -s '%s' -t '%s' -m PROTGAMMALG -n BLTREE -w '%s' %s " % (
alignment_path, tree_path, os.path.abspath(dir_path), cmdline_extras)
elif datatype == "morphology":
# LOOK OUT: this relies on the assumption that we can only specify a single
# model for morphology analyses...
# choose a model for the data - necessary for RAxML to load the data properly
model = models.get_model_commandline(the_config.models[0])
log.info("Estimating %s branch lengths on tree using RAxML", the_config.models[0])
command = "-f e -s '%s' -t '%s' %s -K MK -n BLTREE -w '%s' %s" % (
alignment_path, tree_path, model, os.path.abspath(dir_path), cmdline_extras)
else:
log.error("Unrecognised datatype: '%s'" % (datatype))
raise util.PartitionFinderError
run_raxml(command)
dir, aln = os.path.split(alignment_path)
tree_path = os.path.join(dir, "RAxML_result.BLTREE")
if not os.path.exists(tree_path):
log.error("RAxML tree topology should be here but can't be be found: '%s'" % (tree_path))
raise util.PartitionFinderError
else:
log.debug("RAxML tree with branch lengths ('%s') looks like this: ", tree_path)
with open(tree_path, 'r') as fin:
log.debug('%s', fin.read())
log.info("Branchlength estimation finished")
# Now return the path of the final tree with branch lengths
return tree_path
def make_branch_lengths(alignment_path, topology_path, datatype,
cmdline_extras):
# Now we re-estimate branchlengths using a GTR+G model on the
# (unpartitioned) dataset
cmdline_extras = check_defaults(cmdline_extras)
dir_path, fname = os.path.split(topology_path)
tree_path = os.path.join(dir_path, 'topology_tree.phy')
log.debug("Copying %s to %s", topology_path, tree_path)
util.dupfile(topology_path, tree_path)
os.remove(topology_path) # saves headaches later...
if datatype == "DNA":
log.info("Estimating GTR+G branch lengths on tree using RAxML")
command = "-f e -s '%s' -t '%s' -m GTRGAMMA -n BLTREE -w '%s' %s " % (
alignment_path, tree_path, os.path.abspath(dir_path),
cmdline_extras)
run_raxml(command)
if datatype == "protein":
log.info("Estimating LG+G branch lengths on tree using RAxML")
command = "-f e -s '%s' -t '%s' -m PROTGAMMALG -n BLTREE -w '%s' %s " % (
alignment_path, tree_path, os.path.abspath(dir_path),
cmdline_extras)
run_raxml(command)
dir, aln = os.path.split(alignment_path)
tree_path = os.path.join(dir, "RAxML_result.BLTREE")
if not os.path.exists(tree_path):
log.error(
"RAxML tree topology should be here but can't be be found: '%s'" %
(tree_path))
raise (RaxmlError)
else:
log.debug("RAxML tree with branch lengths ('%s') looks like this: ",
tree_path)
with open(tree_path, 'r') as fin:
log.debug('%s', fin.read())
log.info("Branchlength estimation finished")
# Now return the path of the final tree with branch lengths
return tree_path
def make_branch_lengths(alignment_path, topology_path, datatype, cmdline_extras):
# Now we re-estimate branchlengths using a GTR+G model on the
# (unpartitioned) dataset
cmdline_extras = check_defaults(cmdline_extras)
dir_path, fname = os.path.split(topology_path)
tree_path = os.path.join(dir_path, 'topology_tree.phy')
log.debug("Copying %s to %s", topology_path, tree_path)
util.dupfile(topology_path, tree_path)
os.remove(topology_path) # saves headaches later...
if datatype == "DNA":
log.info("Estimating GTR+G branch lengths on tree using RAxML")
command = "-f e -s '%s' -t '%s' -m GTRGAMMA -n BLTREE -w '%s' %s " % (
alignment_path, tree_path, os.path.abspath(dir_path), cmdline_extras)
run_raxml(command)
if datatype == "protein":
log.info("Estimating LG+G branch lengths on tree using RAxML")
command = "-f e -s '%s' -t '%s' -m PROTGAMMALG -n BLTREE -w '%s' %s " % (
alignment_path, tree_path, os.path.abspath(dir_path), cmdline_extras)
run_raxml(command)
dir, aln = os.path.split(alignment_path)
tree_path = os.path.join(dir, "RAxML_result.BLTREE")
if not os.path.exists(tree_path):
log.error("RAxML tree topology should be here but can't be be found: '%s'" % (tree_path))
raise(RaxmlError)
else:
log.debug("RAxML tree with branch lengths ('%s') looks like this: ", tree_path)
with open(tree_path, 'r') as fin:
log.debug('%s', fin.read())
log.info("Branchlength estimation finished")
# Now return the path of the final tree with branch lengths
return tree_path
def make_tree(self, user_path):
# Begin by making a filtered alignment, containing ONLY those columns
# that are defined in the subsets
subset_with_everything = subset_ops.merge_subsets(
the_config.user_subsets)
self.filtered_alignment = SubsetAlignment(self.alignment,
subset_with_everything)
self.filtered_alignment_path = os.path.join(the_config.start_tree_path,
'filtered_source.phy')
self.filtered_alignment.write(self.filtered_alignment_path)
# Check the full subset against the alignment
subset_ops.check_against_alignment(subset_with_everything,
self.alignment, the_config)
# We start by copying the alignment
self.alignment_path = os.path.join(the_config.start_tree_path,
'source.phy')
# Now check for the tree
tree_path = the_config.processor.make_tree_path(
self.filtered_alignment_path)
if self.need_new_tree(tree_path):
log.debug("Estimating new starting tree, no old tree found")
# If we have a user tree, then use that, otherwise, create a topology
util.clean_out_folder(the_config.start_tree_path,
keep=["filtered_source.phy", "source.phy"])
if user_path is not None and user_path != "":
# Copy it into the start tree folder
log.info("Using user supplied topology at %s" % user_path)
topology_path = os.path.join(the_config.start_tree_path,
'user_topology.phy')
util.dupfile(user_path, topology_path)
need_bl = True
elif the_config.no_ml_tree == True:
log.debug("didn't find tree at %s, making a new one" %
tree_path)
topology_path = the_config.processor.make_topology(
self.filtered_alignment_path, the_config.datatype,
the_config.cmdline_extras)
need_bl = True
elif the_config.no_ml_tree == False:
log.debug(
"didn't find tree at %s, making an ML tree with RAxML" %
tree_path)
tree_scheme = scheme.create_scheme(
the_config, "tree_scheme",
range(len(the_config.user_subsets)))
topology_path = raxml.make_ml_topology(
self.filtered_alignment_path, the_config.datatype,
the_config.cmdline_extras, tree_scheme, self.threads)
# here we copy the ML tree topology so it can be used with PhyML too
# TODO: this is a hack, and it would be better to decide on a universal
# name for the different types of tree we might have.
phyml_tree = os.path.join(
os.path.dirname(topology_path),
"filtered_source.phy_phyml_tree.txt")
copyfile(topology_path, phyml_tree)
need_bl = False
if need_bl == True:
# Now estimate branch lengths
tree_path = the_config.processor.make_branch_lengths(
self.filtered_alignment_path, topology_path,
the_config.datatype, the_config.cmdline_extras)
self.tree_path = tree_path
log.debug("Starting tree with branch lengths is here: %s" %
self.tree_path)
def make_tree(self, user_path):
# Begin by making a filtered alignment, containing ONLY those columns
# that are defined in the subsets
subset_with_everything = subset_ops.merge_subsets(the_config.user_subsets)
self.filtered_alignment = SubsetAlignment(
self.alignment, subset_with_everything)
self.filtered_alignment_path = os.path.join(
the_config.start_tree_path, 'filtered_source.phy')
self.filtered_alignment.write(self.filtered_alignment_path)
# Check the full subset against the alignment
subset_ops.check_against_alignment(subset_with_everything, self.alignment, the_config)
# We start by copying the alignment
self.alignment_path = os.path.join(
the_config.start_tree_path, 'source.phy')
# Now check for the tree
tree_path = the_config.processor.make_tree_path(
self.filtered_alignment_path)
if self.need_new_tree(tree_path):
log.debug("Estimating new starting tree, no old tree found")
# If we have a user tree, then use that, otherwise, create a topology
util.clean_out_folder(the_config.start_tree_path,
keep=["filtered_source.phy", "source.phy"])
if user_path is not None and user_path != "":
# Copy it into the start tree folder
log.info("Using user supplied topology at %s" % user_path)
topology_path = os.path.join(the_config.start_tree_path, 'user_topology.phy')
util.dupfile(user_path, topology_path)
need_bl = True
elif the_config.no_ml_tree == True:
log.debug(
"didn't find tree at %s, making a new one" % tree_path)
topology_path = the_config.processor.make_topology(
self.filtered_alignment_path, the_config.datatype, the_config.cmdline_extras)
need_bl = True
elif the_config.no_ml_tree == False:
log.debug(
"didn't find tree at %s, making an ML tree with RAxML" % tree_path)
tree_scheme = scheme.create_scheme(
the_config, "tree_scheme", range(len(the_config.user_subsets)))
topology_path = raxml.make_ml_topology(
self.filtered_alignment_path, the_config.datatype, the_config.cmdline_extras, tree_scheme, self.threads)
# here we copy the ML tree topology so it can be used with PhyML too
# TODO: this is a hack, and it would be better to decide on a universal
# name for the different types of tree we might have.
phyml_tree = os.path.join(os.path.dirname(topology_path), "filtered_source.phy_phyml_tree.txt")
copyfile(topology_path, phyml_tree)
need_bl = False
if need_bl == True:
# Now estimate branch lengths
tree_path = the_config.processor.make_branch_lengths(
self.filtered_alignment_path,
topology_path,
the_config.datatype,
the_config.cmdline_extras)
self.tree_path = tree_path
log.debug("Starting tree with branch lengths is here: %s" %
self.tree_path)
