def sink_tree(filen, outfn):
t = tree_reader.read_tree_file_iter(filen).__next__()
cutoffa = 80
cutoffb = 95
nds = set()
for i in t.iternodes():
if len(t.children) < 2:
continue
l = i.label
if "/" in l:
s = l.split("/")
a = float(s[0])
b = float(s[1])
if a < cutoffa or b < cutoffb:
nds.add(i)
i.label = ""
for j in nds:
chs = j.children
par = j.parent
par.remove_child(j)
for k in chs:
k.parent = par
par.add_child(k)
outf = open(outfn, "w")
outf.write(t.get_newick_repr(False) + ";")
outf.close()
import sys
import tree_reader
import os
from utils import newick_name
if __name__ == "__main__":
if len(sys.argv) != 4:
print("python " + sys.argv[0] + " all_names.txt infile outfile")
sys.exit(0)
tab = open(sys.argv[1], "r")
idn = {}
for i in tab:
spls = i.strip().split("\t")
idn[spls[0]] = spls[3]
tab.close()
outf = open(sys.argv[3], "w")
for i in tree_reader.read_tree_file_iter(sys.argv[2]):
for j in i.iternodes():
if j.label in idn:
j.label = newick_name(idn[j.label])
outf.write(i.get_newick_repr(True) + ";")
outf.close()
for i in tre.iternodes():
if len(i.children) > 0:
if i.label in nms:
toremove.append(i)
for i in toremove:
sys.stderr.write("remove internal: "+i.get_newick_repr(False)+"\n")
par = i.parent
par.remove_child(i)
if __name__ == "__main__":
if len(sys.argv) != 3:
print "python "+sys.argv[0]+ " addtree bigtre"
sys.exit(0)
tree1 = tree_reader.read_tree_file_iter(sys.argv[1]).next()
bigtree = tree_reader.read_tree_file_iter(sys.argv[2]).next()
if EDITLEN:
tree_utils.set_heights(tree1)
tree_utils.set_heights(bigtree)
rootnms = set(tree1.lvsnms())
remove_int_ext_nodes(rootnms,bigtree)
othernms = set(bigtree.lvsnms())
if VERBOSE:
ddifs = rootnms.difference(othernms)
for i in ddifs:
sys.stderr.write(i+"\n")
diffnms = []
import os
import seq
import networkx as nx
import tree_reader
from networkx.drawing.nx_agraph import write_dot
"""
This will make a graph of the connectivity of the genes and taxa
given some tree (probably taxonomy) and a set of genes
"""
if __name__ == "__main__":
if len(sys.argv) < 3:
print("python " + sys.argv[0] + " tree files...")
sys.exit(0)
tree = next(tree_reader.read_tree_file_iter(sys.argv[1]))
genes = {}
seqfiles = []
badseqs = []
goodseqs = []
for i in sys.argv[2:]:
if i[0] != "_":
seqfiles.append(i)
else:
goodseqs.append(i[1:])
for i in seqfiles:
genes[i] = []
for j in seq.read_fasta_file_iter(i):
genes[i].append(j.name)
print(seqfiles)
def run_bp_window(infn, tsegfiles, mltr, segc, outf):
write_r()
mlto = tree_reader.read_tree_file_iter(mltr).__next__()
mlbps = get_biparts(mlto)
segs = {}
segslong = {}
segstree = {}
plotsegs = [] # each row is a seg, each column is a node
conflictsegscount = []
count = 0
for i in range(len(tsegfiles)):
conflictcount = 0
segs[count] = []
segslong[count] = set()
plotsegs.append([0] * len(mlbps))
cmd = "bp -c " + mltr + " -t " + tsegfiles[i] + " -tv"
segstree[count] = open(tsegfiles[i], "r").readline()
o = subprocess.check_output(cmd.split(" "), stderr=subprocess.STDOUT)
keepo = str(o).split("\\n")
cf = keepo[-8]
cc = keepo[-7]
cft = tree_reader.read_tree_string(cf)
cct = tree_reader.read_tree_string(cc)
for j, k in zip(cft.iternodes(), cct.iternodes()):
if len(j.children) > 1:
sbp = None
inde = None
if j.label != "" or k.label != "":
sbp = get_bipart(j, cft)
inde = get_bp_ind(mlbps, sbp)
# conflict one
if j.label != "":
if int(j.label) > 0:
conflictcount += 1
segs[count].append(sbp)
plotsegs[i][inde] = -1
# process the bp out from above to record the actual split that conflicts
start = False
for l in keepo:
if start:
if " (" == l[0:3]:
tttt = tree_reader.read_tree_string(
l.strip().split(" ")[-1])
segslong[count] = add_bp(
segslong[count],
get_biparts(tttt)[0])
if "read " == l[0:5]:
start = True
if "TREES " == l[0:6]:
break
# concordant one
if k.label != "":
if int(k.label) > 0:
plotsegs[i][inde] = 1
if remove_intermediate_files:
otf = tsegfiles[i]
if os.path.exists(otf):
os.remove(otf)
conflictsegscount.append(
conflictcount) #just a running tally of the conflicts per segment
count += 1
# print the number of conflicts per segment
print(infn + " " + " ".join([str(k) for k in conflictsegscount]))
# print the verbose stuff to the gzip
detfile = gzip.open(outf + ".details.gz", "wt")
for i, sc, sl, t in zip(segs, segc, segslong, segstree):
detfile.write(
str(i) + " " + "-".join([str(k) for k in list(sc)]) + "\n")
for j in segs[i]:
detfile.write(" conflicts with:" + str(j) + "\n")
for j in segslong[i]:
detfile.write(" prefers:" + str(j) + "\n")
detfile.write(" tree:" + segstree[t] + "\n")
detfile.close()
# write the plotting information
ouf = open(outf, "w")
first = True
for sc in segc:
if first == True:
first = False
else:
ouf.write(" ")
ouf.write("\"" + "-".join([str(k) for k in list(sc)]) + "\"")
ouf.write("\n")
for i in range(len(mlbps)):
s = []
for j in range(len(plotsegs)):
s.append(str(plotsegs[j][i]))
ouf.write(" ".join(s) + "\n")
ouf.close()
cmd = "Rscript rplot.r " + outf + " " + outf + ".png " + infn[
0:min(15, len(infn))] + " > rlog 2>&1"
os.system(cmd)
import tree_reader
import sys
import os
"""
right now this just chooses the longest
BEWARE, this writes over the file
"""
if __name__ == "__main__":
if len(sys.argv) != 3:
print "python " + sys.argv[0] + " table treefile"
sys.exit(0)
tab = open(sys.argv[1], "r")
idn = {}
for i in tab:
spls = i.strip().split("\t")
idn[spls[3]] = spls[4]
tab.close()
tf = tree_reader.read_tree_file_iter(sys.argv[2]).next()
for i in tf.iternodes():
if i.label in idn:
i.label = idn[i.label].replace(" ", "_")
print tf.get_newick_repr() + ";"
# This will be used to limit the taxa
taxalistf = None
if len(sys.argv) == 7:
taxalistf = sys.argv[6]
print(colored.yellow("LIMITING TO TAXA IN"), sys.argv[6])
# Log file
logfile = sys.argv[5]
if logfile[-len(".md.gz"):] != ".md.gz":
logfile += ".md.gz"
tname = dirl + "/" + taxon + ".tre"
cmd = py + " " + DI + "get_ncbi_tax_tree_no_species.py " + taxon + " " + db + " > " + tname
print(colored.yellow("MAKING TREE"), taxon)
os.system(cmd)
trn = tree_reader.read_tree_file_iter(tname).__next__().label
cmd = py + " " + DI + "make_dirs.py " + tname + " " + dirl
print(colored.yellow("MAKING DIRS IN"), dirl)
os.system(cmd)
cmd = py + " " + DI + "populate_dirs_first.py " + tname + " " + dirl + " " + db
if taxalistf != None:
cmd += " " + taxalistf
print(colored.yellow("POPULATING DIRS"), dirl)
os.system(cmd)
if os.path.isfile("log.md.gz"):
os.remove("log.md.gz")
cmd = py + " " + DI + "bait_tree.py " + dirl + "/" + trn + "/ " + baitdir + " " + logfile
os.system(cmd)
print(colored.blue("PYPHLAWD DONE " + emoticons.get_ran_emot("excited")))
nd.data["names"] = set()
tf = open(root + "/" + root.split("/")[-1] + ".table", "r")
for i in tf:
spls = i.strip().split("\t")
nd.data["names"].add(spls[4].replace(" ", "_"))
tf.close()
for j in dirs:
if "clusters" not in j:
cnd = node.Node()
cnd.label = j
cnd.parent = nd
nd.add_child(cnd)
nodes[j] = cnd
count += 1
intree = tree_reader.read_tree_file_iter(sys.argv[3]).next()
for i in intree.iternodes(order="POSTORDER"):
lvsnms = set(i.lvsnms())
for j in tree.iternodes(order="POSTORDER"):
if lvsnms.issubset(j.data["names"]):
j.set_dist_root()
i.data["h"] = j.droot
if len(i.children) > 0:
i.label = str(j.droot)
break
for i in intree.iternodes(order="POSTORDER"):
if len(i.children) > 0:
try:
if max(i.children[0].data["h"], i.children[1].data["h"]) - min(
i.children[0].data["h"], i.children[1].data["h"]) > 1:
tr = open(sys.argv[1],"r")
for i in tr:
spls = i.strip().split(":")
if "taxon" in spls[0]:
removetaxa.add(spls[1])
elif "constraint" in spls[0]:
remove_mrca.append(spls[1].split(","))
tr.close()
tr = open(sys.argv[3]+".postrem","w")
for i in seq.read_fasta_file_iter(sys.argv[3]):
if i.name not in removetaxa:
tr.write(i.get_fasta())
tr.close()
tree = next(tree_reader.read_tree_file_iter(sys.argv[2]))
nodes = {}
mrca_pars = [] #vector of the parents of each remove constraint
child_constraints = [] #vector of child_constraints for each remove constraint
for i in tree.leaves():
nodes[i.label] = i
for i in remove_mrca:
tnods = []
for j in i:
tnods.append(nodes[j])
mr = tree_utils.get_mrca(tnods,tree)
par = mr.parent
tchild_constraints = []
for j in mr.children:
if len(j.children) > 0:
tchild_constraints.append(j)
import argparse as ap
def generate_argparser():
parser = ap.ArgumentParser(prog="change_wcid_to_name_tre.py",
formatter_class=ap.ArgumentDefaultsHelpFormatter)
parser = ap.ArgumentParser()
parser.add_argument("-t", "--table", type=str, help="WCID translation table", required=True)
parser.add_argument("-i", "--infile", type=str, help="Input tree", required=True)
parser.add_argument("-o", "--outfile", type=str, help="Output tree", required=True)
return parser
if __name__ == "__main__":
parser = generate_argparser()
if len(sys.argv[1:]) == 0:
sys.argv.append("-h")
args = parser.parse_args(sys.argv[1:])
tab = open(args.table,"r")
idn = {}
for i in tab:
spls = i.strip().split("\t")
idn[spls[-3]] = spls[-1]
tab.close()
outf = open(args.outfile,"w")
for i in tree_reader.read_tree_file_iter(args.infile):
for j in i.iternodes():
if j.label in idn:
j.label = newick_name(idn[j.label])
outf.write(i.get_newick_repr(True)+";")
outf.close()
count += 1
spls = i.split("\t|\t")
try:
idn["ott"+spls[0]] = spls[2].replace(" ","_")
except:
continue
tab.close()
return idn
if __name__ == "__main__":
if len(sys.argv) != 5:
print("python "+sys.argv[0]+" ott_taxonomy.tsv db infile outfile")
sys.exit(0)
ottids = []
ncbis = []
for i in tree_reader.read_tree_file_iter(sys.argv[3]):
for j in i.iternodes():
if len(j.label) > 0:
if "ott" in j.label:
ottids.append(j.label.replace("ott",""))
else:
ncbis.append(j.label)
# first do ott
oidn = get_ott_names(sys.argv[1], ottids)
# now do ncbi
nidn = get_ncbi_names(sys.argv[2],ncbis)
names_done = set()
import argparse
import tree_reader
if __name__ == "__main__":
if len(sys.argv[1:]) == 0:
sys.argv.append("-h")
parser = argparse.ArgumentParser()
parser.add_argument("speciesTree", help="species tree in newick")
parser.add_argument("geneTree",
help="gene tree in newick format, \
with taxon names formatted species@sequence, \
where species matches species tree.")
args = parser.parse_args()
sTree = [x for x in tree_reader.read_tree_file_iter(args.speciesTree)][0]
gTree = [x for x in tree_reader.read_tree_file_iter(args.geneTree)][0]
species = sTree.lvsnms()
genes = []
for i in gTree.lvsnms():
if "@" in i:
i = i.split("@")
genes.append((i[0], "@" + i[1]))
else:
genes.append((i, ""))
mapping = {}
for s in species:
mapping[s] = []
for g in genes:
import sys
import os
import tree_reader
import tree_utils
"""
assuming that the datedtre just has ott ids as the tip names
assuming the labelled_supertree has ott in front of the ott ids
"""
if __name__ == "__main__":
if len(sys.argv) != 3:
print "python " + sys.argv[0] + " datedtree labelled_superrtree"
sys.exit(0)
dated = tree_reader.read_tree_file_iter(sys.argv[1]).next()
ott = tree_reader.read_tree_file_iter(sys.argv[2]).next()
tree_utils.set_heights(dated)
ottlvsd = {} #key is name and value is node
for i in ott.iternodes():
ottlvsd[i.label] = i
for i in dated.leaves():
try:
i.data["node"] = ottlvsd[i.label] #ottlvsd["ott"+i.label]
except:
print >> sys.stderr, "not matched", i.label
continue
done = set()
dates = {} # key is node, value is date
dates_names = {} #key is node, value is mrca string
db = sys.argv[2]
# This will be used to limit the taxa
taxalistf = None
if len(sys.argv) == 5:
taxalistf = sys.argv[4]
print colored.yellow("LIMITING TO TAXA IN"), sys.argv[4]
tname = dirl + "/" + taxon + ".tre"
if taxalistf != None:
cmd = "python " + DI + "get_ncbi_tax_tree_no_species.py " + taxon + " " + db + " " + taxalistf + " > " + tname
else:
cmd = "python " + DI + "get_ncbi_tax_tree_no_species.py " + taxon + " " + db + " > " + tname
print colored.yellow("MAKING TREE"), taxon, colored.yellow(
emoticons.get_ran_emot("excited"))
os.system(cmd)
trn = tree_reader.read_tree_file_iter(tname).next().label
cmd = "python " + DI + "make_dirs.py " + tname + " " + dirl
print colored.yellow("MAKING DIRS IN"), dirl, colored.yellow(
emoticons.get_ran_emot("excited"))
os.system(cmd)
cmd = "python " + DI + "populate_dirs_first.py " + tname + " " + dirl + " " + db
if taxalistf != None:
cmd += " " + taxalistf
print colored.yellow("POPULATING DIRS"), dirl, colored.yellow(
emoticons.get_ran_emot("excited"))
os.system(cmd)
if os.path.isfile("log.md.gz"):
os.remove("log.md.gz")
cmd = "python " + DI + "cluster_tree.py " + dirl + "/" + trn + "/ log.md.gz"
os.system(cmd)
#! /usr/bin/python3
import sys
import argparse
import tree_reader
if __name__ == "__main__":
if len(sys.argv[1:]) == 0:
sys.argv.append("-h")
parser = argparse.ArgumentParser()
parser.add_argument("tree",
help="gophy-formatted output tree, with model \
label per node")
args = parser.parse_args()
t = [x for x in tree_reader.read_tree_file_iter(args.tree)][0]
print("tip,model")
for n in t.iternodes():
if n.istip:
model = n.parent.label
print(n.label + "," + str(model))
