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.Subset(*list(self.cfg.partitions)) self.filtered_alignment = SubsetAlignment(self.alignment, subset_with_everything) self.filtered_alignment_path = os.path.join(self.cfg.start_tree_path, 'filtered_source.phy') self.filtered_alignment.write(self.filtered_alignment_path) # Now we've written this alignment, we need to lock everything in # place, no more adding partitions, or changing them from now on. self.cfg.partitions.check_against_alignment(self.alignment) self.cfg.partitions.finalise() # We start by copying the alignment self.alignment_path = os.path.join(self.cfg.start_tree_path, 'source.phy') # Now check for the tree tree_path = self.cfg.processor.make_tree_path( self.filtered_alignment_path) if self.need_new_tree(tree_path) == True: 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(self.cfg.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(self.cfg.start_tree_path, 'user_topology.phy') self.cfg.processor.dupfile(user_path, topology_path) else: log.debug("didn't find tree at %s, making a new one" % tree_path) topology_path = self.cfg.processor.make_topology( self.filtered_alignment_path, self.cfg.datatype, self.cfg.cmdline_extras) # Now estimate branch lengths tree_path = self.cfg.processor.make_branch_lengths( self.filtered_alignment_path, topology_path, self.cfg.datatype, self.cfg.cmdline_extras) self.tree_path = tree_path log.info("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(self.cfg.user_subsets) self.filtered_alignment = SubsetAlignment( self.alignment, subset_with_everything) self.filtered_alignment_path = os.path.join( self.cfg.start_tree_path, 'filtered_source.phy') self.filtered_alignment.write(self.filtered_alignment_path) # Now we've written this alignment, we need to lock everything in # place, no more adding partitions, or changing them from now on. # TODO: This checking should still be done... # self.cfg.partitions.check_against_alignment(self.alignment) # self.cfg.partitions.finalise() # We start by copying the alignment self.alignment_path = os.path.join( self.cfg.start_tree_path, 'source.phy') # Now check for the tree tree_path = self.cfg.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(self.cfg.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(self.cfg.start_tree_path, 'user_topology.phy') self.cfg.processor.dupfile(user_path, topology_path) else: log.debug( "didn't find tree at %s, making a new one" % tree_path) topology_path = self.cfg.processor.make_topology( self.filtered_alignment_path, self.cfg.datatype, self.cfg.cmdline_extras) # Now estimate branch lengths tree_path = self.cfg.processor.make_branch_lengths( self.filtered_alignment_path, topology_path, self.cfg.datatype, self.cfg.cmdline_extras) self.tree_path = tree_path log.info("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)
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)