def main(argv):
parser = argparse.ArgumentParser(
description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
# name or flags - Either a name or a list of option strings, e.g. foo or -f, --foo.
# action - The basic type of action to be taken when this argument is encountered at the command line. (store, store_const, store_true, store_false, append, append_const, version)
# nargs - The number of command-line arguments that should be consumed. (N, ? (one or default), * (all 1 or more), + (more than 1) )
# const - A constant value required by some action and nargs selections.
# default - The value produced if the argument is absent from the command line.
# type - The type to which the command-line argument should be converted.
# choices - A container of the allowable values for the argument.
# required - Whether or not the command-line option may be omitted (optionals only).
# help - A brief description of what the argument does.
# metavar - A name for the argument in usage messages.
# dest - The name of the attribute to be added to the object returned by parse_args().
input_gr = parser.add_argument_group(
"TREE INPUT OPTIONS\n=================")
input_gr.add_argument(
'tree',
metavar='tree_file',
type=str,
nargs=1,
help='A tree file (or text string) in newick format.')
input_gr.add_argument("--raxml",
dest="raxml",
action="store_true",
help="""Process newick as raxml bootstrap values""")
img_gr = parser.add_argument_group("TREE IMAGE OPTIONS\n=================")
img_gr.add_argument("-m",
"--mode",
dest="mode",
choices=["c", "r"],
default="r",
help="""(r)ectangular or (c)ircular visualization""")
img_gr.add_argument(
"-i",
"--image",
dest="image",
type=str,
help="Render tree image instead of showing it. A filename "
" should be provided. PDF, SVG and PNG file extensions are"
" supported (i.e. -i tree.svg)")
img_gr.add_argument(
"--Iw",
"--width",
dest="width",
type=int,
default=0,
help="width of the rendered image in pixels (see --size-units).")
img_gr.add_argument(
"--Ih",
"--height",
dest="height",
type=int,
default=0,
help="height of the rendered image in pixels (see --size-units).")
img_gr.add_argument("--Ir",
"--resolution",
dest="resolution",
type=int,
default=300,
help="Resolution if the tree image (DPI)")
img_gr.add_argument("--Iu",
"--size-units",
dest="size_units",
choices=["px", "mm", "in"],
default="px",
help="Units used to specify the size of the image."
" (px:pixels, mm:millimeters, in:inches). ")
img_gr.add_argument(
"-mbs",
"--min-branch-separation",
dest="branch_separation",
type=int,
default=3,
help="Min number of pixels to separate branches vertically.")
img_gr.add_argument("--ss",
"--show-support",
dest="show_support",
action="store_true",
help="""Shows branch bootstrap/support values""")
img_gr.add_argument("--sbl",
"--branch-length",
dest="show_branch_length",
action="store_true",
help="""Show branch lengths.""")
img_gr.add_argument(
"--ft",
"--force-topology",
dest="force_topology",
action="store_true",
help="""Force branch length to have a minimum length in the image""")
img_gr.add_argument("--hln",
"--hide-leaf-names",
dest="hide_leaf_names",
action="store_true",
help="""Hide leaf names.""")
img_gr.add_argument(
"--sin",
"--show-internal-names",
dest="show_internal_names",
action="store_true",
help="""Show the name attribute of all internal nodes.""")
edit_gr = parser.add_argument_group("TREE EDIT OPTIONS\n=================")
edit_gr.add_argument(
"-r",
"--root",
dest="root",
type=str,
nargs="*",
help="Roots the tree to the node grouping the list"
" of node names provided (space separated). In example:"
"'--root human rat mouse'")
edit_gr.add_argument("-s",
"--sort-branches",
dest="sort",
action="store_true",
help="""Sort branches according to node names.""")
edit_gr.add_argument("-l",
"--ladderize",
dest="ladderize",
action="store_true",
help="""Sort branches by partition size.""")
edit_gr.add_argument("--color_by_rank",
dest="color_by_rank",
type=str,
nargs="+",
help="""If the attribute rank is present in nodes """)
phylo_gr = parser.add_argument_group(
"PHYLOGENETIC OPTIONS\n=================")
phylo_gr.add_argument("--alg",
dest="alg",
type=str,
help="""Multiple sequence alignment.""")
phylo_gr.add_argument(
"--alg-format",
dest="alg_format",
type=str,
default="fasta",
help="""fasta, phylip, iphylip, relaxed_iphylip, relaxed_phylip.""")
phylo_gr.add_argument(
"--sp-discovery",
dest="species_discovery_regexp",
type=str,
default="^[^_]+_(.+)",
help="Perl regular expression to capture species"
" code from node names. By default, node names"
" are expected to follow the NAME_SPCODE format = '^[^_]+_(.+)' ")
phylo_gr.add_argument(
"--dump-subtrees",
dest="subtrees_output_file",
type=str,
help="Returns a file containing all possible species subtrees"
" contained in a given gene tree ")
phylo_gr.add_argument(
"--newick",
dest="newick",
type=str,
help="dumps newick file after applying editing options")
args = parser.parse_args(argv)
tfile = args.tree[0]
if args.ladderize and args.sort:
raise ValueError(
"--sort-branches and --ladderize options are mutually exclusive")
if args.raxml:
nw = re.sub(":(\d+\.\d+)\[(\d+)\]", ":\\1[&&NHX:support=\\2]",
open(tfile).read())
t = PhyloTree(nw)
#for n in t.traverse():
#n.support = getattr(n, "bootstrap", -1)
#
else:
t = PhyloTree(tfile)
if args.alg:
t.link_to_alignment(args.alg, alg_format=args.alg_format)
LEAF_ATTRIBUTES["sequence"] = 1
if args.species_discovery_regexp:
SPCODE_REGEXP = re.compile(args.species_discovery_regexp)
t.set_species_naming_function(user_species_naming_function)
if args.ladderize:
t.ladderize()
if args.sort:
t.sort_descendants()
if args.root:
if len(args.root) > 1:
outgroup = t.get_common_ancestor(args.root)
else:
outgroup = t & args.root[0]
t.set_outgroup(outgroup)
# EXTRACT INFO
if args.subtrees_output_file:
ntrees, ndups, treeiter = t.get_speciation_trees()
print >> sys.stderr, "Found %d duplication nodes. Dumping %d sutrees..." % (
ndups, ntrees)
OUT = open(args.subtrees_output_file, "w")
for tree in treeiter:
print >> OUT, tree.write()
OUT.close()
# VISUALIZATION
ts = TreeStyle()
ts.mode = args.mode
ts.show_leaf_name = False
ts.branch_vertical_margin = args.branch_separation
if args.show_support:
ts.show_branch_support = True
if args.show_branch_length:
ts.show_branch_length = True
if args.force_topology:
ts.force_topology = True
if args.hide_leaf_names:
del LEAF_ATTRIBUTES["name"]
if args.show_internal_names:
INTERNAL_ATTRIBUTES["name"] = 1
# scale the tree
if not args.height:
args.height = None
if not args.width:
args.width = None
ts.layout_fn = master_layout
if args.image:
t.render(args.image,
tree_style=ts,
w=args.width,
h=args.height,
units=args.size_units)
else:
t.show(None, tree_style=ts)
if args.newick:
t.write(features=[], outfile=args.newick)
print "Processed Newick dumped into", args.newick
def main(argv):
parser = argparse.ArgumentParser(description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
# name or flags - Either a name or a list of option strings, e.g. foo or -f, --foo.
# action - The basic type of action to be taken when this argument is encountered at the command line. (store, store_const, store_true, store_false, append, append_const, version)
# nargs - The number of command-line arguments that should be consumed. (N, ? (one or default), * (all 1 or more), + (more than 1) )
# const - A constant value required by some action and nargs selections.
# default - The value produced if the argument is absent from the command line.
# type - The type to which the command-line argument should be converted.
# choices - A container of the allowable values for the argument.
# required - Whether or not the command-line option may be omitted (optionals only).
# help - A brief description of what the argument does.
# metavar - A name for the argument in usage messages.
# dest - The name of the attribute to be added to the object returned by parse_args().
input_gr = parser.add_argument_group("TREE INPUT OPTIONS\n=================")
input_gr.add_argument('tree', metavar='tree_file', type=str, nargs=1,
help='A tree file (or text string) in newick format.')
input_gr.add_argument("--raxml", dest="raxml",
action="store_true",
help="""Process newick as raxml bootstrap values""")
img_gr = parser.add_argument_group("TREE IMAGE OPTIONS\n=================")
img_gr.add_argument("-m", "--mode", dest="mode",
choices=["c", "r"], default="r",
help="""(r)ectangular or (c)ircular visualization""")
img_gr.add_argument("-i", "--image", dest="image",
type=str,
help="Render tree image instead of showing it. A filename "
" should be provided. PDF, SVG and PNG file extensions are"
" supported (i.e. -i tree.svg)"
)
img_gr.add_argument("--Iw", "--width", dest="width",
type=int, default=0,
help="width of the rendered image in pixels (see --size-units)."
)
img_gr.add_argument("--Ih", "--height", dest="height",
type=int, default=0,
help="height of the rendered image in pixels (see --size-units)."
)
img_gr.add_argument("--Ir", "--resolution", dest="resolution",
type=int, default=300,
help="Resolution if the tree image (DPI)"
)
img_gr.add_argument("--Iu", "--size-units", dest="size_units",
choices=["px", "mm", "in"], default="px",
help="Units used to specify the size of the image."
" (px:pixels, mm:millimeters, in:inches). "
)
img_gr.add_argument("-mbs", "--min-branch-separation", dest="branch_separation",
type=int, default = 3,
help="Min number of pixels to separate branches vertically."
)
img_gr.add_argument("--ss", "--show-support", dest="show_support",
action="store_true",
help="""Shows branch bootstrap/support values""")
img_gr.add_argument("--sbl", "--branch-length", dest="show_branch_length",
action="store_true",
help="""Show branch lengths.""")
img_gr.add_argument("--ft", "--force-topology", dest="force_topology",
action="store_true",
help="""Force branch length to have a minimum length in the image""")
img_gr.add_argument("--hln", "--hide-leaf-names", dest="hide_leaf_names",
action="store_true",
help="""Hide leaf names.""")
img_gr.add_argument("--sin", "--show-internal-names", dest="show_internal_names",
action="store_true",
help="""Show the name attribute of all internal nodes.""")
edit_gr = parser.add_argument_group("TREE EDIT OPTIONS\n=================")
edit_gr.add_argument("-r", "--root", dest="root",
type=str, nargs="*",
help="Roots the tree to the node grouping the list"
" of node names provided (space separated). In example:"
"'--root human rat mouse'")
edit_gr.add_argument("-s", "--sort-branches", dest="sort",
action="store_true",
help="""Sort branches according to node names.""")
edit_gr.add_argument("-l", "--ladderize", dest="ladderize",
action="store_true",
help="""Sort branches by partition size.""")
edit_gr.add_argument("--color_by_rank", dest="color_by_rank",
type=str, nargs="+",
help="""If the attribute rank is present in nodes """)
phylo_gr = parser.add_argument_group("PHYLOGENETIC OPTIONS\n=================")
phylo_gr.add_argument("--alg", dest="alg",
type=str,
help="""Multiple sequence alignment.""")
phylo_gr.add_argument("--alg-format", dest="alg_format",
type=str, default="fasta",
help="""fasta, phylip, iphylip, relaxed_iphylip, relaxed_phylip.""")
phylo_gr.add_argument("--sp-discovery", dest="species_discovery_regexp",
type=str, default="^[^_]+_(.+)",
help="Perl regular expression to capture species"
" code from node names. By default, node names"
" are expected to follow the NAME_SPCODE format = '^[^_]+_(.+)' ")
phylo_gr.add_argument("--dump-subtrees", dest="subtrees_output_file",
type=str,
help="Returns a file containing all possible species subtrees"
" contained in a given gene tree ")
phylo_gr.add_argument("--newick", dest="newick",
type=str,
help="dumps newick file after applying editing options")
args = parser.parse_args(argv)
tfile = args.tree[0]
if args.ladderize and args.sort:
raise ValueError("--sort-branches and --ladderize options are mutually exclusive")
if args.raxml:
nw = re.sub(":(\d+\.\d+)\[(\d+)\]", ":\\1[&&NHX:support=\\2]", open(tfile).read())
t = PhyloTree(nw)
#for n in t.traverse():
#n.support = getattr(n, "bootstrap", -1)
#
else:
t = PhyloTree(tfile)
if args.alg:
t.link_to_alignment(args.alg, alg_format=args.alg_format)
LEAF_ATTRIBUTES["sequence"] = 1
if args.species_discovery_regexp:
SPCODE_REGEXP = re.compile(args.species_discovery_regexp)
t.set_species_naming_function(user_species_naming_function)
if args.ladderize:
t.ladderize()
if args.sort:
t.sort_descendants()
if args.root:
if len(args.root) > 1:
outgroup = t.get_common_ancestor(args.root)
else:
outgroup = t & args.root[0]
t.set_outgroup(outgroup)
# EXTRACT INFO
if args.subtrees_output_file:
ntrees, ndups, treeiter = t.get_speciation_trees()
print >>sys.stderr, "Found %d duplication nodes. Dumping %d sutrees..." %(ndups, ntrees)
OUT = open(args.subtrees_output_file, "w")
for tree in treeiter:
print >>OUT, tree.write()
OUT.close()
# VISUALIZATION
ts = TreeStyle()
ts.mode = args.mode
ts.show_leaf_name = False
ts.branch_vertical_margin = args.branch_separation
if args.show_support:
ts.show_branch_support = True
if args.show_branch_length:
ts.show_branch_length = True
if args.force_topology:
ts.force_topology = True
if args.hide_leaf_names:
del LEAF_ATTRIBUTES["name"]
if args.show_internal_names:
INTERNAL_ATTRIBUTES["name"] = 1
# scale the tree
if not args.height:
args.height = None
if not args.width:
args.width = None
ts.layout_fn = master_layout
if args.image:
t.render(args.image, tree_style=ts, w=args.width, h=args.height, units=args.size_units)
else:
t.show(None, tree_style=ts)
if args.newick:
t.write(features=[], outfile=args.newick)
print "Processed Newick dumped into", args.newick
def main(argv):
parser = ArgumentParser(description=__DESCRIPTION__)
parser.add_argument("--db", dest="dbfile",
type=str,
help="""NCBI sqlite3 db file.""")
parser.add_argument("-t", "--taxid", dest="taxid", nargs="+",
type=int,
help="""taxids (space separated)""")
parser.add_argument("-tf", "--taxid_file", dest="taxid_file",
type=str,
help="""file containing a list of taxids (one per line)""")
parser.add_argument("-r", "--reftree", dest="reftree",
type=str,
help="""tree file containing taxids as node names.""")
parser.add_argument("--reftree_attr", dest="reftree_attr",
type=str, default="name",
help="""Where taxid should be read from""")
parser.add_argument("-n", "--name", dest="names", nargs="+",
type=str,
help="""species or taxa names (comma separated)""")
parser.add_argument("-nf", "--names_file", dest="names_file",
type=str,
help="""file containing a list of taxids (one per line)""")
parser.add_argument("-x", "--taxonomy", dest="taxonomy",
action="store_true",
help=("returns a pruned version of the NCBI taxonomy"
" tree containing target species"))
parser.add_argument("--show_tree", dest="show_tree",
action="store_true",
help="""shows the NCBI taxonomy tree of the provided species""")
parser.add_argument("--collapse_subspecies", dest="collapse_subspecies",
action="store_true",
help=("When used, all nodes under the the species rank"
" are collapsed, so all species and subspecies"
" are seen as sister nodes"))
parser.add_argument("--rank_limit", dest="rank_limit",
type=str,
help=("When used, all nodes under the provided rank"
" are discarded"))
parser.add_argument("--full_lineage", dest="full_lineage",
action="store_true",
help=("When used, topology is not pruned to avoid "
" one-child-nodes, so the complete lineage"
" track leading from root to tips is kept."))
parser.add_argument("-i", "--info", dest="info",
action="store_true",
help="""shows NCBI information about the species""")
parser.add_argument("--fuzzy", dest="fuzzy", type=float,
help=("Tries a fuzzy (and SLOW) search for those"
" species names that could not be translated"
" into taxids. A float number must be provided"
" indicating the minimum string similarity."))
args = parser.parse_args(argv)
if not args.taxonomy and not args.info and not args.reftree:
parser.print_usage()
sys.exit(0)
if args.fuzzy:
import pysqlite2.dbapi2 as sqlite3
c = sqlite3.connect(os.path.join(MODULE_PATH, args.dbfile))
else:
ncbi.connect_database(args.dbfile)
all_names = set([])
all_taxids = []
if args.names_file:
all_names.update(map(strip, open(args.names_file, "rU").read().split("\n")))
if args.names:
all_names.update(map(strip, " ".join(args.names).split(",")))
all_names.discard("")
#all_names = set([n.lower() for n in all_names])
not_found = set()
name2realname = {}
name2score = {}
if all_names:
log.info("Dumping name translations:")
name2id = ncbi.get_name_translator(all_names)
not_found = all_names - set(name2id.keys())
if args.fuzzy and not_found:
log.info("%s unknown names", len(not_found))
for name in not_found:
# enable extension loading
c.enable_load_extension(True)
c.execute("select load_extension('%s')" % os.path.join(module_path,
"SQLite-Levenshtein/levenshtein.sqlext"))
tax, realname, sim = ncbi.get_fuzzy_name_translation(name, args.fuzzy)
if tax:
name2id[name] = tax
name2realname[name] = realname
name2score[name] = "Fuzzy:%0.2f" %sim
for name in all_names:
taxid = name2id.get(name, "???")
realname = name2realname.get(name, name)
score = name2score.get(name, "Exact:1.0")
print "\t".join(map(str, [score, name, realname.capitalize(), taxid]))
if args.taxid_file:
all_taxids.extend(map(strip, open(args.taxid_file, "rU").read().split("\n")))
if args.taxid:
all_taxids.extend(args.taxid)
reftree = None
if args.reftree:
reftree = PhyloTree(args.reftree)
all_taxids.extend(list(set([getattr(n, args.reftree_attr) for n in reftree.iter_leaves()])))
if all_taxids and args.info:
all_taxids = set(all_taxids)
all_taxids.discard("")
all_taxids, merge_conversion = ncbi.translate_merged(all_taxids)
log.info("Dumping %d taxid translations:" %len(all_taxids))
all_taxids.discard("")
translator = ncbi.get_taxid_translator(all_taxids)
for taxid, name in translator.iteritems():
lineage = ncbi.get_sp_lineage(taxid)
named_lineage = ','.join(ncbi.translate_to_names(lineage))
lineage = ','.join(map(str, lineage))
print "\t".join(map(str, [merge_conversion.get(int(taxid), taxid), name, named_lineage, lineage ]))
for notfound in set(map(str, all_taxids)) - set(str(k) for k in translator.iterkeys()):
print >>sys.stderr, notfound, "NOT FOUND"
if all_taxids and args.taxonomy:
all_taxids = set(all_taxids)
all_taxids.discard("")
log.info("Dumping NCBI taxonomy of %d taxa:" %len(all_taxids))
t = ncbi.get_topology(all_taxids, args.full_lineage, args.rank_limit)
id2name = ncbi.get_taxid_translator([n.name for n in t.traverse()])
for n in t.traverse():
n.add_features(taxid=n.name)
n.add_features(sci_name=str(id2name.get(int(n.name), "?")))
if n.rank in COLOR_RANKS:
n.add_features(bgcolor=COLOR_RANKS[n.rank])
n.name = "%s{%s}" %(id2name.get(int(n.name), n.name), n.name)
lineage = ncbi.get_sp_lineage(n.taxid)
n.add_features(named_lineage = '|'.join(ncbi.translate_to_names(lineage)))
if args.collapse_subspecies:
species_nodes = [n for n in t.traverse() if n.rank == "species"
if int(n.taxid) in all_taxids]
for sp_node in species_nodes:
bellow = sp_node.get_descendants()
if bellow:
# creates a copy of the species node
connector = sp_node.__class__()
for f in sp_node.features:
connector.add_feature(f, getattr(sp_node, f))
connector.name = connector.name + "{species}"
for n in bellow:
n.detach()
n.name = n.name + "{%s}" %n.rank
sp_node.add_child(n)
sp_node.add_child(connector)
sp_node.add_feature("collapse_subspecies", "1")
if args.show_tree:
t.show()
print "\n\n ===== Newick files saved as 'your_taxa_query.*' ===== "
t.write(format=9, outfile="your_ncbi_query.nw")
t.write(format=8, outfile="your_ncbi_query.named.nw")
t.write(format=9, features=["taxid", "name", "rank", "bgcolor", "sci_name", "collapse_subspecies", "named_lineage"],
outfile="your_ncbi_query.extended.nw")
for i in t.iter_leaves():
i.name = i.taxid
t.write(format=9, outfile="your_ncbi_query.taxids.nw")
if all_taxids and reftree:
translator = ncbi.get_taxid_translator(all_taxids)
for n in reftree.iter_leaves():
if not hasattr(n, "taxid"):
n.add_features(taxid=int(getattr(n, args.reftree_attr)))
n.add_features(sci_name = translator.get(int(n.taxid), n.name))
lineage = ncbi.get_sp_lineage(n.taxid)
named_lineage = '|'.join(ncbi.translate_to_names(lineage))
n.add_features(ncbi_track=named_lineage)
print reftree.write(features=["taxid", "sci_name", "ncbi_track"])
def main(argv):
parser = ArgumentParser(description=__DESCRIPTION__)
parser.add_argument("--db",
dest="dbfile",
type=str,
help="""NCBI sqlite3 db file.""")
parser.add_argument("-t",
"--taxid",
dest="taxid",
nargs="+",
type=int,
help="""taxids (space separated)""")
parser.add_argument(
"-tf",
"--taxid_file",
dest="taxid_file",
type=str,
help="""file containing a list of taxids (one per line)""")
parser.add_argument("-r",
"--reftree",
dest="reftree",
type=str,
help="""tree file containing taxids as node names.""")
parser.add_argument("--reftree_attr",
dest="reftree_attr",
type=str,
default="name",
help="""Where taxid should be read from""")
parser.add_argument("-n",
"--name",
dest="names",
nargs="+",
type=str,
help="""species or taxa names (comma separated)""")
parser.add_argument(
"-nf",
"--names_file",
dest="names_file",
type=str,
help="""file containing a list of taxids (one per line)""")
parser.add_argument("-x",
"--taxonomy",
dest="taxonomy",
action="store_true",
help=("returns a pruned version of the NCBI taxonomy"
" tree containing target species"))
parser.add_argument(
"--show_tree",
dest="show_tree",
action="store_true",
help="""shows the NCBI taxonomy tree of the provided species""")
parser.add_argument("--collapse_subspecies",
dest="collapse_subspecies",
action="store_true",
help=("When used, all nodes under the the species rank"
" are collapsed, so all species and subspecies"
" are seen as sister nodes"))
parser.add_argument("--rank_limit",
dest="rank_limit",
type=str,
help=("When used, all nodes under the provided rank"
" are discarded"))
parser.add_argument("--full_lineage",
dest="full_lineage",
action="store_true",
help=("When used, topology is not pruned to avoid "
" one-child-nodes, so the complete lineage"
" track leading from root to tips is kept."))
parser.add_argument("-i",
"--info",
dest="info",
action="store_true",
help="""shows NCBI information about the species""")
parser.add_argument("--fuzzy",
dest="fuzzy",
type=float,
help=("Tries a fuzzy (and SLOW) search for those"
" species names that could not be translated"
" into taxids. A float number must be provided"
" indicating the minimum string similarity."))
args = parser.parse_args(argv)
if not args.taxonomy and not args.info and not args.reftree:
parser.print_usage()
sys.exit(0)
if args.fuzzy:
import pysqlite2.dbapi2 as sqlite3
c = sqlite3.connect(os.path.join(MODULE_PATH, args.dbfile))
else:
ncbi.connect_database(args.dbfile)
all_names = set([])
all_taxids = []
if args.names_file:
all_names.update(
map(strip,
open(args.names_file, "rU").read().split("\n")))
if args.names:
all_names.update(map(strip, " ".join(args.names).split(",")))
all_names.discard("")
#all_names = set([n.lower() for n in all_names])
not_found = set()
name2realname = {}
name2score = {}
if all_names:
log.info("Dumping name translations:")
name2id = ncbi.get_name_translator(all_names)
not_found = all_names - set(name2id.keys())
if args.fuzzy and not_found:
log.info("%s unknown names", len(not_found))
for name in not_found:
# enable extension loading
c.enable_load_extension(True)
c.execute("select load_extension('%s')" % os.path.join(
module_path, "SQLite-Levenshtein/levenshtein.sqlext"))
tax, realname, sim = ncbi.get_fuzzy_name_translation(
name, args.fuzzy)
if tax:
name2id[name] = tax
name2realname[name] = realname
name2score[name] = "Fuzzy:%0.2f" % sim
for name in all_names:
taxid = name2id.get(name, "???")
realname = name2realname.get(name, name)
score = name2score.get(name, "Exact:1.0")
print "\t".join(
map(str,
[score, name, realname.capitalize(), taxid]))
if args.taxid_file:
all_taxids.extend(
map(strip,
open(args.taxid_file, "rU").read().split("\n")))
if args.taxid:
all_taxids.extend(args.taxid)
reftree = None
if args.reftree:
reftree = PhyloTree(args.reftree)
all_taxids.extend(
list(
set([
getattr(n, args.reftree_attr)
for n in reftree.iter_leaves()
])))
if all_taxids and args.info:
all_taxids = set(all_taxids)
all_taxids.discard("")
all_taxids, merge_conversion = ncbi.translate_merged(all_taxids)
log.info("Dumping %d taxid translations:" % len(all_taxids))
all_taxids.discard("")
translator = ncbi.get_taxid_translator(all_taxids)
for taxid, name in translator.iteritems():
lineage = ncbi.get_sp_lineage(taxid)
named_lineage = ','.join(ncbi.translate_to_names(lineage))
lineage = ','.join(map(str, lineage))
print "\t".join(
map(str, [
merge_conversion.get(int(taxid), taxid), name,
named_lineage, lineage
]))
for notfound in set(map(str, all_taxids)) - set(
str(k) for k in translator.iterkeys()):
print >> sys.stderr, notfound, "NOT FOUND"
if all_taxids and args.taxonomy:
all_taxids = set(all_taxids)
all_taxids.discard("")
log.info("Dumping NCBI taxonomy of %d taxa:" % len(all_taxids))
t = ncbi.get_topology(all_taxids, args.full_lineage, args.rank_limit)
id2name = ncbi.get_taxid_translator([n.name for n in t.traverse()])
for n in t.traverse():
n.add_features(taxid=n.name)
n.add_features(sci_name=str(id2name.get(int(n.name), "?")))
if n.rank in COLOR_RANKS:
n.add_features(bgcolor=COLOR_RANKS[n.rank])
n.name = "%s{%s}" % (id2name.get(int(n.name), n.name), n.name)
lineage = ncbi.get_sp_lineage(n.taxid)
n.add_features(
named_lineage='|'.join(ncbi.translate_to_names(lineage)))
if args.collapse_subspecies:
species_nodes = [
n for n in t.traverse() if n.rank == "species"
if int(n.taxid) in all_taxids
]
for sp_node in species_nodes:
bellow = sp_node.get_descendants()
if bellow:
# creates a copy of the species node
connector = sp_node.__class__()
for f in sp_node.features:
connector.add_feature(f, getattr(sp_node, f))
connector.name = connector.name + "{species}"
for n in bellow:
n.detach()
n.name = n.name + "{%s}" % n.rank
sp_node.add_child(n)
sp_node.add_child(connector)
sp_node.add_feature("collapse_subspecies", "1")
if args.show_tree:
t.show()
print "\n\n ===== Newick files saved as 'your_taxa_query.*' ===== "
t.write(format=9, outfile="your_ncbi_query.nw")
t.write(format=8, outfile="your_ncbi_query.named.nw")
t.write(format=9,
features=[
"taxid", "name", "rank", "bgcolor", "sci_name",
"collapse_subspecies", "named_lineage"
],
outfile="your_ncbi_query.extended.nw")
for i in t.iter_leaves():
i.name = i.taxid
t.write(format=9, outfile="your_ncbi_query.taxids.nw")
if all_taxids and reftree:
translator = ncbi.get_taxid_translator(all_taxids)
for n in reftree.iter_leaves():
if not hasattr(n, "taxid"):
n.add_features(taxid=int(getattr(n, args.reftree_attr)))
n.add_features(sci_name=translator.get(int(n.taxid), n.name))
lineage = ncbi.get_sp_lineage(n.taxid)
named_lineage = '|'.join(ncbi.translate_to_names(lineage))
n.add_features(ncbi_track=named_lineage)
print reftree.write(features=["taxid", "sci_name", "ncbi_track"])
def main(argv):
parser = argparse.ArgumentParser(
description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('tree',
metavar='tree_file',
type=str,
nargs=1,
help='A tree file (or text string) in newick format.')
parser.add_argument(
"--sp_delimiter",
dest="species_delimiter",
type=str,
default="_",
help=("When species names are guessed from node names,"
" this argument specifies how to split node name to guess"
" the species code"))
parser.add_argument(
"--sp_field",
dest="species_field",
type=int,
default=1,
help=("When species names are guessed from node names,"
" this argument specifies the position of the species"
" name code relative to the name splitting delimiter"))
parser.add_argument(
"--root",
dest="root",
type=str,
nargs="*",
help="Roots the tree to the node grouping the list"
" of node names provided (space separated). In example:"
"'--root human rat mouse'")
parser.add_argument(
"--skip_ortholog_detection",
dest="skip_ortholog_detection",
action="store_true",
help=
("Skip automatic detection of"
" speciation and duplication events, thus relying in the"
" correct annotation of the provided tree using"
" the extended newick format (i.e. '((A, A)[&&NHX:evoltype=D], B)[&&NHX:evoltype=S];')"
))
parser.add_argument(
"--evoltype_attr",
dest="evoltype_attr",
type=str,
default="evoltype",
help=(
"When orthology detection is disabled,"
" the attribute name provided here will be expected to exist"
" in all internal nodes and read from the extended newick format"))
parser.add_argument("--database",
dest="database",
type=str,
default="",
help=("Database name"))
parser.add_argument(
"--show",
dest="show",
action="store_true",
default="",
help=(
"Show the tree and its evolutionary events before orthoXML export"
))
parser.add_argument(
"--ascii",
dest="ascii",
action="store_true",
default="",
help=(
"Show the tree using ASCII representation and all its evolutionary"
" events before orthoXML export"))
parser.add_argument(
"--newick",
dest="newick",
action="store_true",
default="",
help=("print the extended newick format for provided tree using"
" ASCII representation and all its evolutionary events"
" before orthoXML export"))
args = parser.parse_args()
newick = args.tree[0]
SPECIES_NAME_POS = args.species_field
SPECIES_NAME_DELIMITER = args.species_delimiter
# load a phylomeDB Tree provided as a newick file in the command line
t = PhyloTree(newick, sp_naming_function=extract_spname)
if args.root:
if len(args.root) > 1:
outgroup = t.get_common_ancestor(args.root)
else:
outgroup = t & args.root[0]
t.set_outgroup(outgroup)
if not args.skip_ortholog_detection:
# detect speciation and duplication events using the species overlap
# algorithm used in phylomeDB
t.get_descendant_evol_events()
if args.ascii:
print t.get_ascii(attributes=[args.evoltype_attr, "name"],
show_internal=True)
if args.newick:
print t.write(features=[args.evoltype_attr], format_root_node=True)
if args.show:
t.show()
export_as_orthoXML(t, args.database, args.evoltype_attr)
def main(argv):
parser = argparse.ArgumentParser(description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('tree', metavar='tree_file', type=str, nargs=1,
help='A tree file (or text string) in newick format.')
parser.add_argument("--sp_delimiter", dest="species_delimiter",
type=str, default="_",
help=("When species names are guessed from node names,"
" this argument specifies how to split node name to guess"
" the species code"))
parser.add_argument("--sp_field", dest="species_field",
type=int, default=1,
help=("When species names are guessed from node names,"
" this argument specifies the position of the species"
" name code relative to the name splitting delimiter"))
parser.add_argument("--root", dest="root",
type=str, nargs="*",
help="Roots the tree to the node grouping the list"
" of node names provided (space separated). In example:"
"'--root human rat mouse'")
parser.add_argument("--skip_ortholog_detection", dest="skip_ortholog_detection",
action="store_true",
help=("Skip automatic detection of"
" speciation and duplication events, thus relying in the"
" correct annotation of the provided tree using"
" the extended newick format (i.e. '((A, A)[&&NHX:evoltype=D], B)[&&NHX:evoltype=S];')"))
parser.add_argument("--evoltype_attr", dest="evoltype_attr",
type=str, default="evoltype",
help=("When orthology detection is disabled,"
" the attribute name provided here will be expected to exist"
" in all internal nodes and read from the extended newick format"))
parser.add_argument("--database", dest="database",
type=str, default="",
help=("Database name"))
parser.add_argument("--show", dest="show",
action="store_true", default="",
help=("Show the tree and its evolutionary events before orthoXML export"))
parser.add_argument("--ascii", dest="ascii",
action="store_true", default="",
help=("Show the tree using ASCII representation and all its evolutionary"
" events before orthoXML export"))
parser.add_argument("--newick", dest="newick",
action="store_true", default="",
help=("print the extended newick format for provided tree using"
" ASCII representation and all its evolutionary events"
" before orthoXML export"))
args = parser.parse_args()
newick = args.tree[0]
SPECIES_NAME_POS = args.species_field
SPECIES_NAME_DELIMITER = args.species_delimiter
# load a phylomeDB Tree provided as a newick file in the command line
t = PhyloTree(newick, sp_naming_function=extract_spname)
if args.root:
if len(args.root) > 1:
outgroup = t.get_common_ancestor(args.root)
else:
outgroup = t & args.root[0]
t.set_outgroup(outgroup)
if not args.skip_ortholog_detection:
# detect speciation and duplication events using the species overlap
# algorithm used in phylomeDB
t.get_descendant_evol_events()
if args.ascii:
print t.get_ascii(attributes=[args.evoltype_attr, "name"], show_internal=True)
if args.newick:
print t.write(features=[args.evoltype_attr], format_root_node=True)
if args.show:
t.show()
export_as_orthoXML(t, args.database, args.evoltype_attr)
