def load_ncbi_tree_from_dump(tar):
# Download: ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz
parent2child = {}
name2node = {}
node2taxname = {}
synonyms = set()
name2rank = {}
print "Loading node names..."
for line in tar.extractfile("names.dmp"):
fields = map(strip, line.split("|"))
nodename = fields[0]
name_type = fields[3].lower()
taxname = fields[1]
if name_type == "scientific name":
node2taxname[nodename] = taxname
elif name_type in set(["synonym", "equivalent name", "genbank equivalent name",
"anamorph", "genbank synonym", "genbank anamorph", "teleomorph"]):
synonyms.add( (nodename, taxname) )
print len(node2taxname), "names loaded."
print len(synonyms), "synonyms loaded."
print "Loading nodes..."
for line in tar.extractfile("nodes.dmp"):
fields = line.split("|")
nodename = fields[0].strip()
parentname = fields[1].strip()
n = Tree()
n.name = nodename
n.taxname = node2taxname[nodename]
n.rank = fields[2].strip()
parent2child[nodename] = parentname
name2node[nodename] = n
print len(name2node), "nodes loaded."
print "Linking nodes..."
for node in name2node:
if node == "1":
t = name2node[node]
else:
parent = parent2child[node]
parent_node = name2node[parent]
parent_node.add_child(name2node[node])
print "Tree is loaded."
return t, synonyms
def main(argv):
parser = argparse.ArgumentParser(
description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("--tf",
dest='target_trees_file',
type=str,
help='target_trees')
parser.add_argument("-t",
dest='target_trees',
type=str,
nargs="+",
help='target_trees')
parser.add_argument(
"--unique",
dest='unique',
type=str,
help=
'When used, all the provided trees are compared and unique topologies are dumped in the specified file.'
)
parser.add_argument("--stats",
dest='stats',
type=str,
help='Show general stats for the provided trees')
parser.add_argument(
"--distmatrix",
dest='distmatrix',
type=str,
help='Dump a distance matrix (robinson foulds) among all topologies')
args = parser.parse_args(argv)
print __DESCRIPTION__
unique_topo = {}
stats_table = []
for tfile in itertrees(args.target_trees, args.target_trees_file):
t = Tree(tfile)
if args.unique:
tid = t.get_topology_id()
if tid not in unique_topo:
unique_topo[tid] = t
if args.stats:
most_distance_node, tree_length = t.get_farthest_leaf()
supports = []
names = []
distances = []
leaves = 0
for n in t.traverse():
names.append(n.name)
if n.up:
supports.append(n.support)
distances.append(n.dist)
if n.is_leaf():
leaves += 1
min_support, max_support = min(supports), max(supports)
mean_support, std_support = mean_std_dev(supports)
min_dist, max_dist = min(distances), max(distances)
mean_dist, std_dist = mean_std_dev(distances)
stats_table.append([
str(t.children <= 2),
leaves,
tree_length,
most_distance_node.name,
min_support,
max_support,
mean_support,
std_support,
min_dist,
max_dist,
mean_dist,
std_dist,
])
if stats_table:
header = [
'rooted', '#tips', 'tree length', 'most distant tip',
'min support', 'max support', 'min support', 'std support',
'max dist', 'min dist', 'mean dist', 'std dist'
]
print_table(stats_table, header=header, max_col_width=12)
if unique_topo:
print '%d unique topologies found' % len(unique_topo)
topos = unique_topo.values()
open(args.unique + '.trees',
'w').write('\n'.join([topo.write(format=9)
for topo in topos]) + '\n')
import itertools
for a, b in itertools.product(topos, topos):
print a.diff(b, output='diffs_tab')
def main(argv):
parser = argparse.ArgumentParser(
description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("target_trees",
metavar='target_trees',
type=str,
nargs="*",
help='a list of target tree files')
parser.add_argument(
"--targets_file",
dest="targets_file",
type=str,
help="""path to a file containing target trees, one per line""")
parser.add_argument("-o",
dest="output",
type=str,
help="""Path to the tab delimited report file""")
parser.add_argument("-r",
dest="reftree",
type=str,
required=True,
help="""Reference tree""")
parser.add_argument(
"--outgroup",
dest="outgroup",
nargs="+",
help=
"""outgroup used to root reference and target trees before distance computation"""
)
parser.add_argument("--expand_polytomies",
dest="polytomies",
action="store_true",
help="""expand politomies if necessary""")
parser.add_argument("--unrooted",
dest="unrooted",
action="store_true",
help="""compare trees as unrooted""")
parser.add_argument(
"--min_support",
dest="min_support",
type=float,
default=0.0,
help=
("min support value for branches to be counted in the distance computation (RF, treeko and refTree/targeGene compatibility)"
))
parser.add_argument(
"--extract_species",
dest="extract_species",
action="store_true",
help=
"""When used, reference tree is assumed to contain species names, while target trees as expected to be gene trees. Species name will be extracted from gene tree nodes and treeko will be used if duplication events are found."""
)
parser.add_argument("--spname_delimiter",
dest="spname_delimiter",
type=str,
default="_",
help=("species code delimiter in node names"))
parser.add_argument(
"--spname_field",
dest="spname_field",
type=int,
default=-1,
help=
("position of the species code extracted from node names. -1 = last field"
))
parser.add_argument("--collateral",
dest="collateral",
action='store_true',
help=(""))
parser.add_argument("--ref_attr",
dest="ref_attr",
type=str,
help=("attribute in ref tree used as leaf name"))
parser.add_argument("--target_attr",
dest="target_attr",
type=str,
help=("attribute in target tree used as leaf name"))
args = parser.parse_args(argv)
print __DESCRIPTION__
reftree = args.reftree
if args.targets_file and args.target_trees:
print >> sys.stderr, 'The use of targets_file and targets at the same time is not supported.'
sys.exit(1)
if args.targets_file:
target_trees = tree_iterator(args.targets_file)
else:
target_trees = args.target_trees
t = Tree(reftree)
if args.ref_attr:
for lf in t.iter_leaves():
lf._origname = lf.name
if args.ref_attr not in lf.features:
print lf
lf.name = getattr(lf, args.ref_attr)
if args.outgroup:
if len(args.outgroup) > 1:
out = t.get_common_ancestor(args.outgroup)
else:
out = t.search_nodes(name=args.outgroup[0])[0]
t.set_outgroup(out)
ref_names = set(t.get_leaf_names())
reftree_len = len(t)
reftree_edges = (reftree_len * 2) - 2
ncollapsed_branches = len([
n for n in t.traverse() if n.children and n.support < args.min_support
])
#reftree_edges -= ncollapsed_branches
#if ncollapsed_branches:
# print '%d branches collapsed in reference tree' %ncollapsed_branches
HEADER = ("target tree", 'dups', 'subtrees', 'used trees', 'treeko', "RF",
"maxRF", 'normRF', "%reftree", "%genetree", "avgSize", "minSize",
"common tips", "refSize", "targetSize")
if args.output:
OUT = open(args.output, "w")
print >> OUT, '# ' + ctime()
print >> OUT, '# ' + ' '.join(sys.argv)
print >> OUT, '#' + '\t'.join(HEADER)
else:
print '# ' + ctime()
print '# ' + ' '.join(sys.argv)
COL_WIDTHS = [20, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7]
print_table([HEADER], fix_col_width=COL_WIDTHS, wrap_style='wrap')
prev_tree = None
for counter, tfile in enumerate(target_trees):
if args.targets_file:
seedid, tfile = tfile
else:
seedid = None
if args.extract_species:
tt = PhyloTree(tfile,
sp_naming_function=lambda name: name.split(
args.spname_delimiter)[args.spname_field])
else:
tt = Tree(tfile)
if args.target_attr:
for lf in tt.iter_leaves():
lf._origname = lf.name
lf.name = getattr(lf, args.target_attr)
if args.outgroup:
if len(args.outgroup) > 1:
out = tt.get_common_ancestor(args.outgroup)
else:
out = tt.search_nodes(name=args.outgroup[0])[0]
tt.set_outgroup(out)
if args.target_trees:
fname = os.path.basename(tfile)
else:
fname = '%05d' % counter
max_size, min_size, avg_size, common = -1, -1, -1, -1
total_rf, max_rf, norm_rf = -1, -1, -1
treeko_d = -1
ref_branches_in_target, target_branches_in_ref = -1, -1
target_tree_len = -1
used_subtrees = -1
if args.extract_species:
orig_target_size = len(tt)
ntrees, ndups, sp_trees = tt.get_speciation_trees(
autodetect_duplications=True, newick_only=True)
if ntrees < 1000:
all_rf = []
ref_found = []
target_found = []
tree_sizes = []
all_max_rf = []
common_names = 0
for subtree_nw in sp_trees:
if seedid and not args.collateral and (seedid
not in subtree_nw):
continue
subtree = PhyloTree(
subtree_nw,
sp_naming_function=lambda name: name.split(
args.spname_delimiter)[args.spname_field])
# only necessary if rf function is going to filter by support value. It slows downs the analysis, obviously
if args.min_support:
subtree_content = subtree.get_cached_content(
store_attr='name')
for n in subtree.traverse():
if n.children:
n.support = tt.get_common_ancestor(
subtree_content[n]).support
rf, maxr, common, p1, p2, d1, d2 = t.robinson_foulds(
subtree,
expand_polytomies=args.polytomies,
unrooted_trees=args.unrooted,
attr_t2='species',
min_support_t2=args.min_support)
if maxr > 0 and p1 and p2:
all_rf.append(rf)
tree_sizes.append(len(common))
all_max_rf.append(maxr)
common_names = max(common_names, len(common))
ref_found.append(float(len(p2 & p1)) / reftree_edges)
p2bis = set([
p for p in (p2 - d2)
if len(p[0]) > 1 and len(p[1]) > 1
]) # valid edges in target not leaves
if p2bis:
incompatible_target_branches = float(
len((p2 - d2) - p1))
target_found.append(1 -
(incompatible_target_branches /
(len(p2 - d2))))
# valid_target = p2-d2
# valid_ref = p1-d1
# ref_found.append(float(len(valid_target & valid_ref)) / reftree_edges)
# p2bis = set([p for p in (p2-d2) if len(p[0])>1 and len(p[1])>1])
# if p2bis-d2:
# incompatible_target_branches = float(len((p2-d2) - p1))
# target_found.append(1 - (incompatible_target_branches / (len(p2-d2))))
if all_rf:
# Treeko speciation distance
alld = [(all_rf[i] / float(all_max_rf[i]))
for i in xrange(len(all_rf))]
a = numpy.sum(
[alld[i] * tree_sizes[i] for i in xrange(len(all_rf))])
b = float(numpy.sum(tree_sizes))
treeko_d = a / b
total_rf = numpy.mean(all_rf)
norm_rf = numpy.mean([(all_rf[i] / float(all_max_rf[i]))
for i in xrange(len(all_rf))])
max_rf = numpy.max(all_max_rf)
ref_branches_in_target = numpy.mean(ref_found)
target_branches_in_ref = numpy.mean(
target_found) if target_found else -1
target_tree_len = numpy.mean(tree_sizes)
used_subtrees = len(all_rf)
else:
target_tree_len = len(tt)
ndups, ntrees, used_subtrees = 0, 1, 1
treeko_d = -1
total_rf, max_rf, common, p1, p2, d1, d2 = tt.robinson_foulds(
t,
expand_polytomies=args.polytomies,
unrooted_trees=args.unrooted)
common_names = len(common)
if max_rf:
norm_rf = total_rf / float(max_rf)
if p1 and p2:
sizes = [len(p) for p in p2 ^ p1]
if sizes:
avg_size = sum(sizes) / float(len(sizes))
max_size, min_size = max(sizes), min(sizes)
else:
max_size, min_size, avg_size = 0, 0, 0
ref_branches_in_target = float(len(p2 & p1)) / reftree_edges
#if p2-d2:
# incompatible_target_branches = float(len((p2-d2) - p1))
# target_found.append(1 - (incompatible_target_branches / (len(p2-d2))))
else:
ref_branches_in_target = 0.0
target_branches_in_ref = 0.0
max_size, min_size, avg_size = -1, -1, -1
if args.output:
print >> OUT, '\t'.join(
map(str, (fname, ndups, ntrees, used_subtrees, treeko_d,
total_rf, max_rf, norm_rf, ref_branches_in_target,
target_branches_in_ref, avg_size, min_size,
common_names, reftree_len, target_tree_len)))
else:
print_table([
map(istr,
(fname[-30:], ndups, ntrees, used_subtrees, treeko_d,
total_rf, max_rf, norm_rf,
'%0.4f' % ref_branches_in_target,
'%0.4f' % target_branches_in_ref, avg_size, min_size,
common_names, reftree_len, target_tree_len))
],
fix_col_width=COL_WIDTHS,
wrap_style='cut')
if args.output:
OUT.close()
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().
parser.add_argument("--show",
dest="show_tree",
action="store_true",
help="""Display tree after the analysis.""")
parser.add_argument("--render",
dest="render",
action="store_true",
help="""Render tree.""")
parser.add_argument("--dump",
dest="dump",
action="store_true",
help="""Dump analysis""")
parser.add_argument(
"--explore",
dest="explore",
type=str,
help="""Reads a previously analyzed tree and visualize it""")
input_args = parser.add_mutually_exclusive_group()
input_args.required = True
input_args.add_argument("-t",
"--tree",
dest="target_tree",
nargs="+",
type=str,
help="""Tree file in newick format""")
input_args.add_argument("-tf",
dest="tree_list_file",
type=str,
help="File with the list of tree files")
parser.add_argument("--tax",
dest="tax_info",
type=str,
help="If the taxid attribute is not set in the"
" newick file for all leaf nodes, a tab file file"
" with the translation of name and taxid can be"
" provided with this option.")
parser.add_argument(
"--sp_delimiter",
dest="sp_delimiter",
type=str,
help=
"If taxid is part of the leaf name, delimiter used to split the string"
)
parser.add_argument(
"--sp_field",
dest="sp_field",
type=int,
default=0,
help="field position for taxid after splitting leaf names")
parser.add_argument("--ref",
dest="ref_tree",
type=str,
help="Uses ref tree to compute robinson foulds"
" distances of the different subtrees")
parser.add_argument("--rf-only",
dest="rf_only",
action="store_true",
help="Skip ncbi consensus analysis")
parser.add_argument(
"--outgroup",
dest="outgroup",
type=str,
nargs="+",
help="A list of node names defining the trees outgroup")
parser.add_argument("--is_sptree",
dest="is_sptree",
action="store_true",
help="Assumes no duplication nodes in the tree")
parser.add_argument("-o",
dest="output",
type=str,
help="Writes result into a file")
parser.add_argument("--tax2name", dest="tax2name", type=str, help="")
parser.add_argument("--tax2track", dest="tax2track", type=str, help="")
parser.add_argument("--dump_tax_info",
dest="dump_tax_info",
action="store_true",
help="")
args = parser.parse_args(argv)
if args.sp_delimiter:
GET_TAXID = lambda x: x.split(args.sp_delimiter)[args.sp_field]
else:
GET_TAXID = None
reftree_name = os.path.basename(args.ref_tree) if args.ref_tree else ""
if args.explore:
print >> sys.stderr, "Reading tree from file:", args.explore
t = cPickle.load(open(args.explore))
ts = TreeStyle()
ts.force_topology = True
ts.show_leaf_name = False
ts.layout_fn = ncbi_layout
ts.mode = "r"
t.show(tree_style=ts)
print >> sys.stderr, "dumping color config"
cPickle.dump(name2color, open("ncbi_colors.pkl", "w"))
sys.exit()
if args.output:
OUT = open(args.output, "w")
else:
OUT = sys.stdout
print >> sys.stderr, "Dumping results into", OUT
target_trees = []
if args.tree_list_file:
target_trees = [line.strip() for line in open(args.tree_list_file)]
if args.target_tree:
target_trees += args.target_tree
prev_tree = None
if args.tax2name:
tax2name = cPickle.load(open(args.tax2name))
else:
tax2name = {}
if args.tax2track:
tax2track = cPickle.load(open(args.tax2track))
else:
tax2track = {}
print len(tax2track), len(tax2name)
header = ("TargetTree", "Subtrees", "Ndups", "Broken subtrees",
"Broken clades", "Clade sizes", "RF (avg)", "RF (med)",
"RF (std)", "RF (max)", "Shared tips")
print >> OUT, '|'.join([h.ljust(15) for h in header])
if args.ref_tree:
print >> sys.stderr, "Reading ref tree from", args.ref_tree
reft = Tree(args.ref_tree, format=1)
else:
reft = None
SHOW_TREE = False
if args.show_tree or args.render:
SHOW_TREE = True
prev_broken = set()
ENTRIES = []
ncbi.connect_database()
for tfile in target_trees:
#print tfile
t = PhyloTree(tfile, sp_naming_function=None)
if GET_TAXID:
for n in t.iter_leaves():
n.name = GET_TAXID(n.name)
if args.outgroup:
if len(args.outgroup) == 1:
out = t & args.outgroup[0]
else:
out = t.get_common_ancestor(args.outgroup)
if set(out.get_leaf_names()) ^ set(args.outgroup):
raise ValueError("Outgroup is not monophyletic")
t.set_outgroup(out)
t.ladderize()
if prev_tree:
tree_compare(t, prev_tree)
prev_tree = t
if args.tax_info:
tax2name, tax2track = annotate_tree_with_taxa(
t, args.tax_info, tax2name, tax2track)
if args.dump_tax_info:
cPickle.dump(tax2track, open("tax2track.pkl", "w"))
cPickle.dump(tax2name, open("tax2name.pkl", "w"))
print "Tax info written into pickle files"
else:
for n in t.iter_leaves():
spcode = n.name
n.add_features(taxid=spcode)
n.add_features(species=spcode)
tax2name, tax2track = annotate_tree_with_taxa(
t, None, tax2name, tax2track)
# Split tree into species trees
#subtrees = t.get_speciation_trees()
if not args.rf_only:
#print "Calculating tree subparts..."
t1 = time.time()
if not args.is_sptree:
subtrees = t.split_by_dups()
#print "Subparts:", len(subtrees), time.time()-t1
else:
subtrees = [t]
valid_subtrees, broken_subtrees, ncbi_mistakes, broken_branches, total_rf, broken_clades, broken_sizes = analyze_subtrees(
t, subtrees, show_tree=SHOW_TREE)
#print valid_subtrees, broken_subtrees, ncbi_mistakes, total_rf
else:
subtrees = []
valid_subtrees, broken_subtrees, ncbi_mistakes, broken_branches, total_rf, broken_clades, broken_sizes = 0, 0, 0, 0, 0, 0
ndups = 0
nsubtrees = len(subtrees)
rf = 0
rf_max = 0
rf_std = 0
rf_med = 0
common_names = 0
max_size = 0
if reft and len(subtrees) == 1:
rf = t.robinson_foulds(reft, attr_t1="realname")
rf_max = rf[1]
rf = rf[0]
rf_med = rf
elif reft:
#print "Calculating avg RF..."
nsubtrees, ndups, subtrees = t.get_speciation_trees(
map_features=["taxid"])
#print len(subtrees), "Sub-Species-trees found"
avg_rf = []
rf_max = 0.0 # reft.robinson_foulds(reft)[1]
sum_size = 0.0
print nsubtrees, "subtrees", ndups, "duplications"
for ii, subt in enumerate(subtrees):
print "\r%d" % ii,
sys.stdout.flush()
try:
partial_rf = subt.robinson_foulds(reft, attr_t1="taxid")
except ValueError:
pass
else:
sptree_size = len(
set([n.taxid for n in subt.iter_leaves()]))
sum_size += sptree_size
avg_rf.append(
(partial_rf[0] / float(partial_rf[1])) * sptree_size)
common_names = len(partial_rf[3])
max_size = max(max_size, sptree_size)
rf_max = max(rf_max, partial_rf[1])
#print partial_rf[:2]
rf = numpy.sum(avg_rf) / float(sum_size) # Treeko dist
rf_std = numpy.std(avg_rf)
rf_med = numpy.median(avg_rf)
sizes_info = "%0.1f/%0.1f +- %0.1f" % (numpy.mean(broken_sizes),
numpy.median(broken_sizes),
numpy.std(broken_sizes))
iter_values = [
os.path.basename(tfile), nsubtrees, ndups, broken_subtrees,
ncbi_mistakes, broken_branches, sizes_info, rf, rf_med, rf_std,
rf_max, common_names
]
print >> OUT, '|'.join(
map(lambda x: str(x).strip().ljust(15), iter_values))
fixed = sorted([n for n in prev_broken if n not in broken_clades])
new_problems = sorted(broken_clades - prev_broken)
fixed_string = color(', '.join(fixed), "green") if fixed else ""
problems_string = color(', '.join(new_problems),
"red") if new_problems else ""
OUT.write(" Fixed clades: %s\n" % fixed_string) if fixed else None
OUT.write(" New broken: %s\n" %
problems_string) if new_problems else None
prev_broken = broken_clades
ENTRIES.append([
os.path.basename(tfile), nsubtrees, ndups, broken_subtrees,
ncbi_mistakes, broken_branches, sizes_info, fixed_string,
problems_string
])
OUT.flush()
if args.show_tree or args.render:
ts = TreeStyle()
ts.force_topology = True
#ts.tree_width = 500
ts.show_leaf_name = False
ts.layout_fn = ncbi_layout
ts.mode = "r"
t.dist = 0
if args.show_tree:
#if args.hide_monophyletic:
# tax2monophyletic = {}
# n2content = t.get_node2content()
# for node in t.traverse():
# term2count = defaultdict(int)
# for leaf in n2content[node]:
# if leaf.lineage:
# for term in leaf.lineage:
# term2count[term] += 1
# expected_size = len(n2content)
# for term, count in term2count.iteritems():
# if count > 1
print "Showing tree..."
t.show(tree_style=ts)
else:
t.render("img.svg", tree_style=ts, dpi=300)
print "dumping color config"
cPickle.dump(name2color, open("ncbi_colors.pkl", "w"))
if args.dump:
cPickle.dump(t, open("ncbi_analysis.pkl", "w"))
print
print
HEADER = ("TargetTree", "Subtrees", "Ndups", "Broken subtrees",
"Broken clades", "Broken branches", "Clade sizes",
"Fixed Groups", "New Broken Clades")
print_table(ENTRIES, max_col_width=50, row_line=True, header=HEADER)
if args.output:
OUT.close()
def main(argv):
global args
parser = argparse.ArgumentParser(
description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("-r",
dest="reftree",
type=str,
required=True,
help="""Reference tree""")
parser.add_argument(
"--source_trees",
dest="source_trees",
type=str,
required=True,
help=
("A list of *rooted* genetrees, one per line, in the format: TreeID/SeedID [TAB] newick "
))
parser.add_argument("--plot_newick",
dest="plot_newick",
type=str,
help=(""))
parser.add_argument("--spname_delimiter",
dest="spname_delimiter",
type=str,
default="_",
help=("species code delimiter in node names"))
parser.add_argument(
"--spname_field",
dest="spname_field",
type=int,
default=-1,
help=
("position of the species code extracted from node names. -1 = last field"
))
parser.add_argument(
"--collateral",
dest="use_collateral",
action="store_true",
help=("If enabled, collateral information will be used as"
" equally qualified data. Otherwise, such data will"
" be reported separatedly. Use this if your set of"
" trees are not overlaping. "))
parser.add_argument(
"--skip_dup_detection",
dest="skip_dup_detection",
action="store_true",
help=('If used, duplications will be expected to be annotated'
' in the source gene trees with the evoltype="D" tag.'
' Otherwise they will be inferred on the fly using'
' the species overlap algorithm.'))
parser.add_argument(
"--spoverlap",
dest="species_overlap",
type=float,
default=0.0,
help=("Species overlap cutoff. A number between 0 and 1 "
"representing the percentage of species that should be "
"shared between two sister partitions to be considered a"
" duplication. 0 = any overlap represents a duplication. "))
parser.add_argument(
"--debug",
dest="debug",
action="store_true",
help=
("generate an image of every input gene tree tree, so the result can be inspected"
))
parser.add_argument(
"--snapshot_step",
dest="snapshot_step",
type=int,
default=1000,
help=("How many trees should be processed between snapshots dumps?"))
parser.add_argument(
"--reftree_constraint",
dest="reftree_constraint",
type=str,
help=("A python module from from which a function called "
"*is_valid_treeid(treeid, refbranch)* should be importable. "
"The function will be used to decide if the info of a given "
"source tree is informative or not for each reftree branch. "))
parser.add_argument("-o",
dest="output",
type=str,
required=True,
help=("output tag name (extensions will be added)"))
parser.add_argument("--cpu",
dest="cpu",
type=int,
default=1,
help=("enable parallel computation"))
parser.add_argument(
"--img_report",
dest="img_report",
action="store_true",
help=
("If true, it generates a summary image results with all the computed data"
))
parser.add_argument(
"--report_supports",
dest="report_supports",
action="store_true",
help=
("If used, supported ref tree branches are individually reported for each gene tree "
))
args = parser.parse_args(argv)
if args.plot_newick:
t = Tree(args.plot_newick)
ts = TreeStyle()
ts.layout_fn = info_layout
t.render("tree_analysis.png", tree_style=ts)
sys.exit(0)
SPNAME_FIELD, SPNAME_DELIMITER = args.spname_field, args.spname_delimiter
USE_COLLATERAL = args.use_collateral
DETECT_DUPLICATIONS = True if not args.skip_dup_detection else False
REPORT_PER_TREE_SUPPORTS = True if args.report_supports else False
SP_OVERLAP = args.species_overlap
DEBUG = args.debug
IMG_REPORT = args.img_report
reftree = PhyloTree(args.reftree, sp_naming_function=None)
for nid, n in enumerate(reftree.traverse()):
n.add_features(nid=nid)
REFTREE_SPECIES = set(reftree.get_leaf_names())
print __DESCRIPTION__
if REPORT_PER_TREE_SUPPORTS:
REPORT_SUPPORT_FILE = open("%s.gentree_supports" % args.output, "w")
print >> REPORT_SUPPORT_FILE, '#' + '\t'.join(
map(str, [
"treeId", "spCoverage", "mean_support", "mean_coll_support",
"tested_branches", 'tested_coll_branches'
]))
TOTAL_TREES = int(
commands.getoutput("wc -l %s" % args.source_trees).split()[0]) + 1
print >> sys.stderr, "Processing %d source trees" % TOTAL_TREES
if args.reftree_constraint:
import imp
constraint = imp.load_source('constraint', args.reftree_constraint)
IS_VALID_TREEID = constraint.is_valid_treeid
else:
IS_VALID_TREEID = None
if args.cpu > 1:
MONITOR_STEP = 0
#return (informed_branches, dup_per_branch, losses_per_branch, losses_per_dup_branch, refbranch_supports,
# coll_dup_per_branch, coll_losses_per_branch, coll_losses_per_dup_branch, coll_refbranch_supports)
# The output of the process_trees function are 9 dictionaries in which keys are refbranches
target_dicts = [{} for x in range(9)]
def merge_dict_results(target, source):
def merge_dict(target, source):
for k, v in source.iteritems():
if k not in target:
target[k] = v
elif isinstance(v, list):
target[k].extend(v)
elif isinstance(v, set):
target[k].update(v)
elif isinstance(v, int):
target[k] += v
else:
raise ValueError("Impossible to merge str results")
for index in xrange(len(target)):
merge_dict(target[index], out[index])
from multiprocessing import Process, Queue
from Queue import Empty as QueueEmpty
outputs_queue = Queue()
if TOTAL_TREES > args.cpu:
trees_per_cpu = TOTAL_TREES / args.cpu
trees_per_cpu += 1 if TOTAL_TREES % args.cpu else 0
else:
trees_per_cpu = 1
args.cpu = TOTAL_TREES
all_workers = set()
for cpu_num in xrange(args.cpu):
sline = (cpu_num * trees_per_cpu)
eline = (cpu_num * trees_per_cpu) + trees_per_cpu
data_iter = tree_iterator(args.source_trees,
restrict_species=REFTREE_SPECIES,
start_line=sline,
end_line=eline)
print >> sys.stderr, "Launching worker %d from %d to %d" % (
cpu_num, sline, eline)
worker = Process(target=run_parallel,
args=(cpu_num, outputs_queue, process_trees,
data_iter, reftree, trees_per_cpu))
worker.name = "Worker_%d" % cpu_num
all_workers.add(worker)
worker.start()
while all_workers:
# clear done threads
for w in list(all_workers):
if not w.is_alive():
print >> sys.stderr, "%s thread is done!" % w.name
all_workers.discard(w)
# get and merge results
while 1:
try:
out = outputs_queue.get(False)
except QueueEmpty:
break
else:
# This merge depends on process_trees return output!!!!!
merge_dict_results(target_dicts, out)
# Dump a snapshot
dump_results(reftree, *target_dicts)
time.sleep(0.1)
if all_workers:
time.sleep(1)
# collected data
(informed_branches, dup_per_branch, losses_per_branch,
losses_per_dup_branch, refbranch_supports, coll_dup_per_branch,
coll_losses_per_branch, coll_losses_per_dup_branch,
coll_refbranch_supports) = target_dicts
else:
MONITOR_STEP = args.snapshot_step
data_iter = tree_iterator(args.source_trees,
restrict_species=REFTREE_SPECIES)
(informed_branches, dup_per_branch, losses_per_branch,
losses_per_dup_branch, refbranch_supports, coll_dup_per_branch,
coll_losses_per_branch, coll_losses_per_dup_branch,
coll_refbranch_supports) = process_trees(data_iter, reftree,
TOTAL_TREES)
if REPORT_PER_TREE_SUPPORTS:
REPORT_SUPPORT_FILE.close()
dump_results(reftree, informed_branches, dup_per_branch, losses_per_branch,
losses_per_dup_branch, refbranch_supports,
coll_dup_per_branch, coll_losses_per_branch,
coll_losses_per_dup_branch, coll_refbranch_supports)
print >> sys.stderr, "Dumping full analysis..."
# Full dump, including duplication details
cPickle.dump(reftree, open("%s.pkl" % args.output, "w"))
def test():
#print_table([[3,2, {"whatever":1, "bla":[1,2]}], [5,"this is a test of wrapping text with the new function",777], [88, 9, 00]],
# header=[ "hola", "otor que no veas", "blas"], wrap=True, max_col_width=10, wrap_style='wrap',
# row_line=True, fix_col_width=True)
print "RUNNING UNITEST..."
# Test code
for x in xrange(100):
t1 = Tree()
t2 = Tree()
t1.populate(
20,
names_library=
"abcdefghijklmnopqrstuvwxyz1234567890ABCDEFGHIJKLMNOPQRSTUVWXYZ")
t2.populate(
20,
names_library=
"abcdefghijklmnopqrstuvwxyz1234567890ABCDEFGHIJKLMNOPQRSTUVWXYZ")
#t2 = t1.copy()
t1.set_outgroup("Z")
t2.set_outgroup("Z")
show_difftable_summary(treediff(t1, t2, "name", "name", EUCL_DIST))
show_difftable_summary(
treediff(t1, t2, "name", "name", EUCL_DIST, True))
#show_difftable(treediff(t1, t2, "name", "name", RF_DIST), "name", "name")
t1 = Tree("(((a, b), (c,d))j, (e, (f, g)h )i );", format=1)
t2 = Tree("(((a, c), (b,d))j, (e, (f, g)h )i );", format=1)
show_difftable_topo(treediff(t1, t2, "name", "name", EUCL_DIST), "name",
"name")
print "\n\n"
def main(argv):
global args
#test()
parser = argparse.ArgumentParser(
description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("target_trees",
type=str,
nargs="+",
help='a list of target tree files')
parser.add_argument("-r",
dest='reftree',
type=str,
help='The reference tree to compare with')
parser.add_argument(
"--ref_attr",
dest="ref_attr",
default="name",
help=("Defines the attribute in REFERENCE tree that will be used"
" to perform the comparison"))
parser.add_argument(
"--target_attr",
dest="target_attr",
default="name",
help=("Defines the attribute in TARGET tree that will be used"
" to perform the comparison"))
parser.add_argument(
"--fullsearch",
dest="fullsearch",
action="store_false",
help=("Enable this option if duplicated attributes (i.e. name)"
"exist in reference or target trees."))
parser.add_argument("--quite",
dest="quite",
action="store_true",
help="Do not show process information")
parser.add_argument("--report",
dest="report",
choices=["topology", "diffs", "diffs_tab", "summary"],
default="topology",
help="Different format for the comparison results")
parser.add_argument(
"--ncbi",
dest="ncbi",
action="store_true",
help=
"If enabled, it will use the ETE ncbi_taxonomy module to for ncbi taxid translation"
)
parser.add_argument(
"--color",
dest="color",
action="store_true",
help="If enabled, it will use colors in some of the report")
args = parser.parse_args(argv)
if args.quite:
logging.basicConfig(format='%(message)s', level=logging.WARNING)
else:
logging.basicConfig(format='%(message)s', level=logging.INFO)
log = logging
t1 = Tree(args.reftree)
if args.ncbi:
from common import ncbi
ncbi.connect_database()
for ttree in args.target_trees:
t2 = Tree(ttree)
if args.ncbi:
taxids = set(
[getattr(leaf, args.ref_attr) for leaf in t1.iter_leaves()])
taxids.update(
[getattr(leaf, args.target_attr) for leaf in t2.iter_leaves()])
taxid2name = ncbi.get_taxid_translator(taxids)
for leaf in t1.get_leaves() + t2.get_leaves():
try:
leaf.name = taxid2name.get(int(leaf.name), leaf.name)
except ValueError:
pass
difftable = treediff(t1,
t2,
args.ref_attr,
args.target_attr,
reduce_matrix=args.fullsearch)
if args.report == "topology":
show_difftable_topo(difftable,
args.ref_attr,
args.target_attr,
usecolor=args.color)
elif args.report == "diffs":
show_difftable(difftable)
elif args.report == "diffs_tab":
show_difftable_tab(difftable)
elif args.report == 'table':
rf, rf_max, _, _, _, _, _ = t1.robinson_foulds(
t2, attr_t1=args.ref_attr, attr_t2=args.target_attr)[:2]
show_difftable_summary(difftable, rf, rf_max)
def show_difftable_topo(difftable, attr1, attr2, usecolor=False):
if not difftable:
return
showtable = []
maxcolwidth = 80
total_dist = 0
for dist, side1, side2, diff, n1, n2 in sorted(difftable, reverse=True):
total_dist += dist
n1 = Tree(n1.write(features=[attr1]))
n2 = Tree(n2.write(features=[attr2]))
n1.ladderize()
n2.ladderize()
for leaf in n1.iter_leaves():
leaf.name = getattr(leaf, attr1)
if leaf.name in diff:
leaf.name += " ***"
if usecolor:
leaf.name = color(leaf.name, "red")
for leaf in n2.iter_leaves():
leaf.name = getattr(leaf, attr2)
if leaf.name in diff:
leaf.name += " ***"
if usecolor:
leaf.name = color(leaf.name, "red")
topo1 = n1.get_ascii(show_internal=False, compact=False)
topo2 = n2.get_ascii(show_internal=False, compact=False)
# This truncates too large topology strings pretending to be
# scrolled to the right margin
topo1_lines = topo1.split("\n")
topowidth1 = max([len(l) for l in topo1_lines])
if topowidth1 > maxcolwidth:
start = topowidth1 - maxcolwidth
topo1 = '\n'.join([line[start + 1:] for line in topo1_lines])
topo2_lines = topo2.split("\n")
topowidth2 = max([len(l) for l in topo2_lines])
if topowidth2 > maxcolwidth:
start = topowidth2 - maxcolwidth
topo2 = '\n'.join([line[start + 1:] for line in topo2_lines])
showtable.append([
"%0.2g" % dist,
"%d vs %d tips\n(%d diffs)" % (len(side1), len(side2), len(diff)),
topo1, topo2
])
print_table(showtable,
header=["Dist", "#diffs", "Tree1", "Tree2"],
max_col_width=maxcolwidth,
wrap_style="wrap",
row_line=True)
log.info("Total euclidean distance:\t%0.4f\tMismatching nodes:\t%d" %
(total_dist, len(difftable)))
def test():
# print_table([[3,2, {"whatever":1, "bla":[1,2]}], [5,"this is a test of wrapping text with the new function",777], [88, 9, 00]],
# header=[ "hola", "otor que no veas", "blas"], wrap=True, max_col_width=10, wrap_style='wrap',
# row_line=True, fix_col_width=True)
print "RUNNING UNITEST..."
# Test code
for x in xrange(100):
t1 = Tree()
t2 = Tree()
t1.populate(20, names_library="abcdefghijklmnopqrstuvwxyz1234567890ABCDEFGHIJKLMNOPQRSTUVWXYZ")
t2.populate(20, names_library="abcdefghijklmnopqrstuvwxyz1234567890ABCDEFGHIJKLMNOPQRSTUVWXYZ")
# t2 = t1.copy()
t1.set_outgroup("Z")
t2.set_outgroup("Z")
show_difftable_summary(treediff(t1, t2, "name", "name", EUCL_DIST))
show_difftable_summary(treediff(t1, t2, "name", "name", EUCL_DIST, True))
# show_difftable(treediff(t1, t2, "name", "name", RF_DIST), "name", "name")
t1 = Tree("(((a, b), (c,d))j, (e, (f, g)h )i );", format=1)
t2 = Tree("(((a, c), (b,d))j, (e, (f, g)h )i );", format=1)
show_difftable_topo(treediff(t1, t2, "name", "name", EUCL_DIST), "name", "name")
print "\n\n"
def main(argv):
parser = argparse.ArgumentParser(description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("-r", dest="reftree",
type=str, required=True,
help="""Reference tree""")
parser.add_argument("source_trees", metavar='source_trees',
type=str, nargs="+",
help='A list of newick tree files used as a source for node annotations')
parser.add_argument("--discard", dest="discard",
type=str, nargs="+", default=[],
help=("A list of attributes that should be ignored from source trees. "
"Node dist, name and support values are always ignored unless they"
" are explicitly passed as target features"))
parser.add_argument("--features", dest="features",
type=str, nargs="+", default = [],
help=("A list of attributes that should be transferred from source trees."))
parser.add_argument("-o", dest="output",
type=str, required=True,
help=("output file name for the annotated tree"))
args = parser.parse_args(argv)
ref = Tree(args.reftree)
TARGET_FEATURES = args.features
DISCARD_FEATURES = args.discard + ["support", "name", "dist"]
key2node = {}
for node in ref.traverse():
nodekey = frozenset(node.get_leaf_names())
key2node[nodekey] = node
out = ref.children[0].get_leaf_names()
out2 = ref.children[1].get_leaf_names()
transferred_features = defaultdict(int)
for target in args.source_trees:
print target
tt = Tree(target)
tt.prune(ref.get_leaf_names())
if len(out) > 1:
try:
tt.set_outgroup(tt.get_common_ancestor(out))
except ValueError:
tt.set_outgroup(tt.get_common_ancestor(out2))
else:
tt.set_outgroup(tt.search_nodes(name=out[0])[0])
for node in tt.traverse():
nodekey = frozenset([n.name for n in node.get_leaves()])
target_node = key2node.get(nodekey, None)
if target_node:
for f in node.features:
if f in DISCARD_FEATURES and not TARGET_FEATURES:
continue
elif TARGET_FEATURES and f not in TARGET_FEATURES:
continue
else:
transferred_features[f] += 1
target_node.add_feature(f, getattr(node, f))
ref.write(outfile=args.output, features=[], format_root_node=True)
print
print_table(transferred_features.items(), header=["feature name", "#nodes"])
def main(argv):
global args
# test()
parser = argparse.ArgumentParser(description=__DESCRIPTION__, formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("target_trees", type=str, nargs="+", help="a list of target tree files")
parser.add_argument("-r", dest="reftree", type=str, help="The reference tree to compare with")
parser.add_argument(
"--ref_attr",
dest="ref_attr",
default="name",
help=("Defines the attribute in REFERENCE tree that will be used" " to perform the comparison"),
)
parser.add_argument(
"--target_attr",
dest="target_attr",
default="name",
help=("Defines the attribute in TARGET tree that will be used" " to perform the comparison"),
)
parser.add_argument(
"--fullsearch",
dest="fullsearch",
action="store_false",
help=("Enable this option if duplicated attributes (i.e. name)" "exist in reference or target trees."),
)
parser.add_argument("--quite", dest="quite", action="store_true", help="Do not show process information")
parser.add_argument(
"--report",
dest="report",
choices=["topology", "diffs", "diffs_tab", "summary"],
default="topology",
help="Different format for the comparison results",
)
parser.add_argument(
"--ncbi",
dest="ncbi",
action="store_true",
help="If enabled, it will use the ETE ncbi_taxonomy module to for ncbi taxid translation",
)
parser.add_argument(
"--color", dest="color", action="store_true", help="If enabled, it will use colors in some of the report"
)
args = parser.parse_args(argv)
if args.quite:
logging.basicConfig(format="%(message)s", level=logging.WARNING)
else:
logging.basicConfig(format="%(message)s", level=logging.INFO)
log = logging
t1 = Tree(args.reftree)
if args.ncbi:
from common import ncbi
ncbi.connect_database()
for ttree in args.target_trees:
t2 = Tree(ttree)
if args.ncbi:
taxids = set([getattr(leaf, args.ref_attr) for leaf in t1.iter_leaves()])
taxids.update([getattr(leaf, args.target_attr) for leaf in t2.iter_leaves()])
taxid2name = ncbi.get_taxid_translator(taxids)
for leaf in t1.get_leaves() + t2.get_leaves():
try:
leaf.name = taxid2name.get(int(leaf.name), leaf.name)
except ValueError:
pass
difftable = treediff(t1, t2, args.ref_attr, args.target_attr, reduce_matrix=args.fullsearch)
if args.report == "topology":
show_difftable_topo(difftable, args.ref_attr, args.target_attr, usecolor=args.color)
elif args.report == "diffs":
show_difftable(difftable)
elif args.report == "diffs_tab":
show_difftable_tab(difftable)
elif args.report == "table":
rf, rf_max, _, _, _, _, _ = t1.robinson_foulds(t2, attr_t1=args.ref_attr, attr_t2=args.target_attr)[:2]
show_difftable_summary(difftable, rf, rf_max)
def show_difftable_topo(difftable, attr1, attr2, usecolor=False):
if not difftable:
return
showtable = []
maxcolwidth = 80
total_dist = 0
for dist, side1, side2, diff, n1, n2 in sorted(difftable, reverse=True):
total_dist += dist
n1 = Tree(n1.write(features=[attr1]))
n2 = Tree(n2.write(features=[attr2]))
n1.ladderize()
n2.ladderize()
for leaf in n1.iter_leaves():
leaf.name = getattr(leaf, attr1)
if leaf.name in diff:
leaf.name += " ***"
if usecolor:
leaf.name = color(leaf.name, "red")
for leaf in n2.iter_leaves():
leaf.name = getattr(leaf, attr2)
if leaf.name in diff:
leaf.name += " ***"
if usecolor:
leaf.name = color(leaf.name, "red")
topo1 = n1.get_ascii(show_internal=False, compact=False)
topo2 = n2.get_ascii(show_internal=False, compact=False)
# This truncates too large topology strings pretending to be
# scrolled to the right margin
topo1_lines = topo1.split("\n")
topowidth1 = max([len(l) for l in topo1_lines])
if topowidth1 > maxcolwidth:
start = topowidth1 - maxcolwidth
topo1 = "\n".join([line[start + 1 :] for line in topo1_lines])
topo2_lines = topo2.split("\n")
topowidth2 = max([len(l) for l in topo2_lines])
if topowidth2 > maxcolwidth:
start = topowidth2 - maxcolwidth
topo2 = "\n".join([line[start + 1 :] for line in topo2_lines])
showtable.append(
["%0.2g" % dist, "%d vs %d tips\n(%d diffs)" % (len(side1), len(side2), len(diff)), topo1, topo2]
)
print_table(
showtable,
header=["Dist", "#diffs", "Tree1", "Tree2"],
max_col_width=maxcolwidth,
wrap_style="wrap",
row_line=True,
)
log.info("Total euclidean distance:\t%0.4f\tMismatching nodes:\t%d" % (total_dist, len(difftable)))
def main(argv):
parser = argparse.ArgumentParser(description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("target_trees", metavar='target_trees', type=str, nargs="*",
help='a list of target tree files')
parser.add_argument("--targets_file", dest="targets_file",
type=str,
help="""path to a file containing target trees, one per line""")
parser.add_argument("-o", dest="output",
type=str,
help="""Path to the tab delimited report file""")
parser.add_argument("-r", dest="reftree",
type=str, required=True,
help="""Reference tree""")
parser.add_argument("--outgroup", dest="outgroup",
nargs = "+",
help="""outgroup used to root reference and target trees before distance computation""")
parser.add_argument("--expand_polytomies", dest="polytomies",
action = "store_true",
help="""expand politomies if necessary""")
parser.add_argument("--unrooted", dest="unrooted",
action = "store_true",
help="""compare trees as unrooted""")
parser.add_argument("--min_support", dest="min_support",
type=float, default=0.0,
help=("min support value for branches to be counted in the distance computation (RF, treeko and refTree/targeGene compatibility)"))
parser.add_argument("--extract_species", dest="extract_species",
action = "store_true",
help="""When used, reference tree is assumed to contain species names, while target trees as expected to be gene trees. Species name will be extracted from gene tree nodes and treeko will be used if duplication events are found.""")
parser.add_argument("--spname_delimiter", dest="spname_delimiter",
type=str, default="_",
help=("species code delimiter in node names"))
parser.add_argument("--spname_field", dest="spname_field",
type=int, default=-1,
help=("position of the species code extracted from node names. -1 = last field"))
parser.add_argument("--collateral", dest="collateral",
action='store_true',
help=(""))
parser.add_argument("--ref_attr", dest="ref_attr",
type=str,
help=("attribute in ref tree used as leaf name"))
parser.add_argument("--target_attr", dest="target_attr",
type=str,
help=("attribute in target tree used as leaf name"))
args = parser.parse_args(argv)
print __DESCRIPTION__
reftree = args.reftree
if args.targets_file and args.target_trees:
print >>sys.stderr, 'The use of targets_file and targets at the same time is not supported.'
sys.exit(1)
if args.targets_file:
target_trees = tree_iterator(args.targets_file)
else:
target_trees = args.target_trees
t = Tree(reftree)
if args.ref_attr:
for lf in t.iter_leaves():
lf._origname = lf.name
if args.ref_attr not in lf.features:
print lf
lf.name = getattr(lf, args.ref_attr)
if args.outgroup:
if len(args.outgroup) > 1:
out = t.get_common_ancestor(args.outgroup)
else:
out = t.search_nodes(name=args.outgroup[0])[0]
t.set_outgroup(out)
ref_names = set(t.get_leaf_names())
reftree_len = len(t)
reftree_edges = (reftree_len*2)-2
ncollapsed_branches = len([n for n in t.traverse() if n.children and n.support < args.min_support])
#reftree_edges -= ncollapsed_branches
#if ncollapsed_branches:
# print '%d branches collapsed in reference tree' %ncollapsed_branches
HEADER = ("target tree", 'dups', 'subtrees', 'used trees', 'treeko', "RF", "maxRF", 'normRF', "%reftree", "%genetree", "avgSize", "minSize", "common tips", "refSize", "targetSize")
if args.output:
OUT = open(args.output, "w")
print >>OUT, '# ' + ctime()
print >>OUT, '# ' + ' '.join(sys.argv)
print >>OUT, '#'+'\t'.join(HEADER)
else:
print '# ' + ctime()
print '# ' + ' '.join(sys.argv)
COL_WIDTHS = [20, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7]
print_table([HEADER], fix_col_width=COL_WIDTHS, wrap_style='wrap')
prev_tree = None
for counter, tfile in enumerate(target_trees):
if args.targets_file:
seedid, tfile = tfile
else:
seedid = None
if args.extract_species:
tt = PhyloTree(tfile, sp_naming_function = lambda name: name.split(args.spname_delimiter)[args.spname_field])
else:
tt = Tree(tfile)
if args.target_attr:
for lf in tt.iter_leaves():
lf._origname = lf.name
lf.name = getattr(lf, args.target_attr)
if args.outgroup:
if len(args.outgroup) > 1:
out = tt.get_common_ancestor(args.outgroup)
else:
out = tt.search_nodes(name=args.outgroup[0])[0]
tt.set_outgroup(out)
if args.target_trees:
fname = os.path.basename(tfile)
else:
fname = '%05d' %counter
max_size, min_size, avg_size, common = -1, -1, -1, -1
total_rf, max_rf, norm_rf = -1, -1, -1
treeko_d = -1
ref_branches_in_target, target_branches_in_ref = -1, -1
target_tree_len = -1
used_subtrees = -1
if args.extract_species:
orig_target_size = len(tt)
ntrees, ndups, sp_trees = tt.get_speciation_trees(autodetect_duplications=True, newick_only=True)
if ntrees < 1000:
all_rf = []
ref_found = []
target_found = []
tree_sizes = []
all_max_rf = []
common_names = 0
for subtree_nw in sp_trees:
if seedid and not args.collateral and (seedid not in subtree_nw):
continue
subtree = PhyloTree(subtree_nw, sp_naming_function = lambda name: name.split(args.spname_delimiter)[args.spname_field])
# only necessary if rf function is going to filter by support value. It slows downs the analysis, obviously
if args.min_support:
subtree_content = subtree.get_cached_content(store_attr='name')
for n in subtree.traverse():
if n.children:
n.support = tt.get_common_ancestor(subtree_content[n]).support
rf, maxr, common, p1, p2, d1, d2 = t.robinson_foulds(subtree, expand_polytomies=args.polytomies, unrooted_trees=args.unrooted,
attr_t2='species', min_support_t2=args.min_support)
if maxr > 0 and p1 and p2:
all_rf.append(rf)
tree_sizes.append(len(common))
all_max_rf.append(maxr)
common_names = max(common_names, len(common))
ref_found.append(float(len(p2 & p1)) / reftree_edges)
p2bis = set([p for p in (p2-d2) if len(p[0])>1 and len(p[1])>1]) # valid edges in target not leaves
if p2bis:
incompatible_target_branches = float(len((p2-d2) - p1))
target_found.append(1 - (incompatible_target_branches / (len(p2-d2))))
# valid_target = p2-d2
# valid_ref = p1-d1
# ref_found.append(float(len(valid_target & valid_ref)) / reftree_edges)
# p2bis = set([p for p in (p2-d2) if len(p[0])>1 and len(p[1])>1])
# if p2bis-d2:
# incompatible_target_branches = float(len((p2-d2) - p1))
# target_found.append(1 - (incompatible_target_branches / (len(p2-d2))))
if all_rf:
# Treeko speciation distance
alld = [(all_rf[i]/float(all_max_rf[i])) for i in xrange(len(all_rf))]
a = numpy.sum([alld[i] * tree_sizes[i] for i in xrange(len(all_rf))])
b = float(numpy.sum(tree_sizes))
treeko_d = a/b
total_rf = numpy.mean(all_rf)
norm_rf = numpy.mean([(all_rf[i]/float(all_max_rf[i])) for i in xrange(len(all_rf))])
max_rf = numpy.max(all_max_rf)
ref_branches_in_target = numpy.mean(ref_found)
target_branches_in_ref = numpy.mean(target_found) if target_found else -1
target_tree_len = numpy.mean(tree_sizes)
used_subtrees = len(all_rf)
else:
target_tree_len = len(tt)
ndups, ntrees, used_subtrees = 0, 1, 1
treeko_d = -1
total_rf, max_rf, common, p1, p2, d1, d2 = tt.robinson_foulds(t, expand_polytomies=args.polytomies, unrooted_trees=args.unrooted)
common_names = len(common)
if max_rf:
norm_rf = total_rf / float(max_rf)
if p1 and p2:
sizes = [len(p) for p in p2 ^ p1]
if sizes:
avg_size = sum(sizes) / float(len(sizes))
max_size, min_size = max(sizes), min(sizes)
else:
max_size, min_size, avg_size = 0, 0, 0
ref_branches_in_target = float(len(p2 & p1)) / reftree_edges
#if p2-d2:
# incompatible_target_branches = float(len((p2-d2) - p1))
# target_found.append(1 - (incompatible_target_branches / (len(p2-d2))))
else:
ref_branches_in_target = 0.0
target_branches_in_ref = 0.0
max_size, min_size, avg_size = -1, -1, -1
if args.output:
print >>OUT, '\t'.join(map(str, (fname, ndups, ntrees, used_subtrees, treeko_d, total_rf, max_rf, norm_rf, ref_branches_in_target, target_branches_in_ref,
avg_size, min_size, common_names, reftree_len, target_tree_len)))
else:
print_table([map(istr, (fname[-30:], ndups, ntrees, used_subtrees, treeko_d, total_rf, max_rf, norm_rf, '%0.4f' %ref_branches_in_target, '%0.4f' %target_branches_in_ref,
avg_size, min_size, common_names, reftree_len, target_tree_len))], fix_col_width = COL_WIDTHS, wrap_style='cut')
if args.output:
OUT.close()
def main(argv):
global args
parser = argparse.ArgumentParser(description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("-r", dest="reftree",
type=str, required=True,
help="""Reference tree""")
parser.add_argument("--source_trees", dest="source_trees",
type=str, required = True,
help=("A list of *rooted* genetrees, one per line, in the format: TreeID/SeedID [TAB] newick "))
parser.add_argument("--plot_newick", dest="plot_newick",
type=str,
help=(""))
parser.add_argument("--spname_delimiter", dest="spname_delimiter",
type=str, default="_",
help=("species code delimiter in node names"))
parser.add_argument("--spname_field", dest="spname_field",
type=int, default=-1,
help=("position of the species code extracted from node names. -1 = last field"))
parser.add_argument("--collateral", dest="use_collateral",
action="store_true",
help=("If enabled, collateral information will be used as"
" equally qualified data. Otherwise, such data will"
" be reported separatedly. Use this if your set of"
" trees are not overlaping. "))
parser.add_argument("--skip_dup_detection", dest="skip_dup_detection",
action="store_true",
help=('If used, duplications will be expected to be annotated'
' in the source gene trees with the evoltype="D" tag.'
' Otherwise they will be inferred on the fly using'
' the species overlap algorithm.'))
parser.add_argument("--spoverlap", dest="species_overlap",
type=float, default=0.0,
help=("Species overlap cutoff. A number between 0 and 1 "
"representing the percentage of species that should be "
"shared between two sister partitions to be considered a"
" duplication. 0 = any overlap represents a duplication. "))
parser.add_argument("--debug", dest="debug",
action="store_true",
help=("generate an image of every input gene tree tree, so the result can be inspected"))
parser.add_argument("--snapshot_step", dest="snapshot_step",
type=int, default=1000,
help=("How many trees should be processed between snapshots dumps?"))
parser.add_argument("--reftree_constraint", dest="reftree_constraint",
type=str,
help=("A python module from from which a function called "
"*is_valid_treeid(treeid, refbranch)* should be importable. "
"The function will be used to decide if the info of a given "
"source tree is informative or not for each reftree branch. "))
parser.add_argument("-o", dest="output",
type=str, required=True,
help=("output tag name (extensions will be added)"))
parser.add_argument("--cpu", dest="cpu",
type=int, default=1,
help=("enable parallel computation"))
parser.add_argument("--img_report", dest="img_report",
action="store_true",
help=("If true, it generates a summary image results with all the computed data"))
parser.add_argument("--report_supports", dest="report_supports",
action="store_true",
help=("If used, supported ref tree branches are individually reported for each gene tree "))
args = parser.parse_args(argv)
if args.plot_newick:
t = Tree(args.plot_newick)
ts = TreeStyle()
ts.layout_fn = info_layout
t.render("tree_analysis.png", tree_style=ts)
sys.exit(0)
SPNAME_FIELD, SPNAME_DELIMITER = args.spname_field, args.spname_delimiter
USE_COLLATERAL = args.use_collateral
DETECT_DUPLICATIONS = True if not args.skip_dup_detection else False
REPORT_PER_TREE_SUPPORTS = True if args.report_supports else False
SP_OVERLAP = args.species_overlap
DEBUG = args.debug
IMG_REPORT = args.img_report
reftree = PhyloTree(args.reftree, sp_naming_function=None)
for nid, n in enumerate(reftree.traverse()):
n.add_features(nid = nid)
REFTREE_SPECIES = set(reftree.get_leaf_names())
print __DESCRIPTION__
if REPORT_PER_TREE_SUPPORTS:
REPORT_SUPPORT_FILE = open("%s.gentree_supports" %args.output, "w")
print >>REPORT_SUPPORT_FILE, '#'+'\t'.join(map(str, ["treeId", "spCoverage", "mean_support", "mean_coll_support", "tested_branches", 'tested_coll_branches']))
TOTAL_TREES = int(commands.getoutput("wc -l %s" %args.source_trees).split()[0]) + 1
print >>sys.stderr, "Processing %d source trees" %TOTAL_TREES
if args.reftree_constraint:
import imp
constraint = imp.load_source('constraint', args.reftree_constraint)
IS_VALID_TREEID = constraint.is_valid_treeid
else:
IS_VALID_TREEID = None
if args.cpu > 1:
MONITOR_STEP = 0
#return (informed_branches, dup_per_branch, losses_per_branch, losses_per_dup_branch, refbranch_supports,
# coll_dup_per_branch, coll_losses_per_branch, coll_losses_per_dup_branch, coll_refbranch_supports)
# The output of the process_trees function are 9 dictionaries in which keys are refbranches
target_dicts = [{} for x in range(9)]
def merge_dict_results(target, source):
def merge_dict(target, source):
for k, v in source.iteritems():
if k not in target:
target[k] = v
elif isinstance(v, list):
target[k].extend(v)
elif isinstance(v, set):
target[k].update(v)
elif isinstance(v, int):
target[k] += v
else:
raise ValueError("Impossible to merge str results")
for index in xrange(len(target)):
merge_dict(target[index], out[index])
from multiprocessing import Process, Queue
from Queue import Empty as QueueEmpty
outputs_queue = Queue()
if TOTAL_TREES > args.cpu:
trees_per_cpu = TOTAL_TREES / args.cpu
trees_per_cpu += 1 if TOTAL_TREES % args.cpu else 0
else:
trees_per_cpu = 1
args.cpu = TOTAL_TREES
all_workers = set()
for cpu_num in xrange(args.cpu):
sline = (cpu_num*trees_per_cpu)
eline = (cpu_num*trees_per_cpu) + trees_per_cpu
data_iter = tree_iterator(args.source_trees,
restrict_species=REFTREE_SPECIES,
start_line=sline,
end_line=eline)
print >>sys.stderr, "Launching worker %d from %d to %d" %(cpu_num, sline, eline)
worker = Process(target=run_parallel,
args=(cpu_num, outputs_queue, process_trees, data_iter, reftree, trees_per_cpu))
worker.name = "Worker_%d" %cpu_num
all_workers.add(worker)
worker.start()
while all_workers:
# clear done threads
for w in list(all_workers):
if not w.is_alive():
print >>sys.stderr, "%s thread is done!" %w.name
all_workers.discard(w)
# get and merge results
while 1:
try:
out = outputs_queue.get(False)
except QueueEmpty:
break
else:
# This merge depends on process_trees return output!!!!!
merge_dict_results(target_dicts, out)
# Dump a snapshot
dump_results(reftree, *target_dicts)
time.sleep(0.1)
if all_workers:
time.sleep(1)
# collected data
(informed_branches, dup_per_branch, losses_per_branch, losses_per_dup_branch, refbranch_supports,
coll_dup_per_branch, coll_losses_per_branch, coll_losses_per_dup_branch,
coll_refbranch_supports) = target_dicts
else:
MONITOR_STEP = args.snapshot_step
data_iter = tree_iterator(args.source_trees, restrict_species=REFTREE_SPECIES)
(informed_branches, dup_per_branch, losses_per_branch, losses_per_dup_branch, refbranch_supports,
coll_dup_per_branch, coll_losses_per_branch, coll_losses_per_dup_branch,
coll_refbranch_supports) = process_trees(data_iter, reftree, TOTAL_TREES)
if REPORT_PER_TREE_SUPPORTS:
REPORT_SUPPORT_FILE.close()
dump_results(reftree, informed_branches, dup_per_branch, losses_per_branch, losses_per_dup_branch, refbranch_supports,
coll_dup_per_branch, coll_losses_per_branch, coll_losses_per_dup_branch, coll_refbranch_supports)
print >>sys.stderr, "Dumping full analysis..."
# Full dump, including duplication details
cPickle.dump(reftree, open("%s.pkl"%args.output, "w"))
def main(argv):
parser = argparse.ArgumentParser(description=__DESCRIPTION__, formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("--tf", dest="target_trees_file", type=str, help="target_trees")
parser.add_argument("-t", dest="target_trees", type=str, nargs="+", help="target_trees")
parser.add_argument(
"--unique",
dest="unique",
type=str,
help="When used, all the provided trees are compared and unique topologies are dumped in the specified file.",
)
parser.add_argument("--stats", dest="stats", type=str, help="Show general stats for the provided trees")
parser.add_argument(
"--distmatrix",
dest="distmatrix",
type=str,
help="Dump a distance matrix (robinson foulds) among all topologies",
)
args = parser.parse_args(argv)
print __DESCRIPTION__
unique_topo = {}
stats_table = []
for tfile in itertrees(args.target_trees, args.target_trees_file):
t = Tree(tfile)
if args.unique:
tid = t.get_topology_id()
if tid not in unique_topo:
unique_topo[tid] = t
if args.stats:
most_distance_node, tree_length = t.get_farthest_leaf()
supports = []
names = []
distances = []
leaves = 0
for n in t.traverse():
names.append(n.name)
if n.up:
supports.append(n.support)
distances.append(n.dist)
if n.is_leaf():
leaves += 1
min_support, max_support = min(supports), max(supports)
mean_support, std_support = mean_std_dev(supports)
min_dist, max_dist = min(distances), max(distances)
mean_dist, std_dist = mean_std_dev(distances)
stats_table.append(
[
str(t.children <= 2),
leaves,
tree_length,
most_distance_node.name,
min_support,
max_support,
mean_support,
std_support,
min_dist,
max_dist,
mean_dist,
std_dist,
]
)
if stats_table:
header = [
"rooted",
"#tips",
"tree length",
"most distant tip",
"min support",
"max support",
"min support",
"std support",
"max dist",
"min dist",
"mean dist",
"std dist",
]
print_table(stats_table, header=header, max_col_width=12)
if unique_topo:
print "%d unique topologies found" % len(unique_topo)
topos = unique_topo.values()
open(args.unique + ".trees", "w").write("\n".join([topo.write(format=9) for topo in topos]) + "\n")
import itertools
for a, b in itertools.product(topos, topos):
print a.diff(b, output="diffs_tab")
