def read_phyloxml(input_file):
"""
Parses a pyhlogenetic tree in phyloxml-format.
:param str input_file: path to file
:return: ete2.Tree object
"""
from ete2 import Phyloxml
project = Phyloxml()
project.build_from_file(input_file)
return project.get_phylogeny()
def getRelevantEdges( adjGraph, t1, t2 ):
pxml = Phyloxml()
pxml.build_from_file(t1)
pxml.build_from_file(t2)
la = filter( lambda x : x.find('LOST') == -1, pxml.phylogeny[0].get_leaf_names() )
lb = filter( lambda x : x.find('LOST') == -1, pxml.phylogeny[1].get_leaf_names() )
#lb = filter( lambda x : x.find('LOST') == -1, map( getName, cogent.LoadTree(t2).tips() ) )
crossValidationEdges = filter( lambda (x,y) : ((x in la) and (y in lb)) or ((y in la) and (x in lb)) , adjGraph.edges() )
relevantEdges = filter( lambda (x,y) : ((x in la) or (x in lb)) and ((y in la) or (y in lb)) , adjGraph.edges() )
newGraph = nx.Graph()
newGraph.add_nodes_from( la + lb )
newGraph.add_edges_from( relevantEdges )
return newGraph, crossValidationEdges
def getTreeFromPhyloxml(xml, saveToFile="default.xml", delFile=True): """ Read a phylogeny tree from a phyloxml string and return a TreeClass object or a list of TreeClass object """ project = Phyloxml() fo=open(saveToFile, "w+") fo.write(xml) fo.close() project.build_from_file(saveToFile) treeList=[] for tree in project.get_phylogeny(): treeList.append(TreeClass.import_from_PhyloxmlTree(tree)) if(delFile): os.remove(saveToFile) if len(treeList)==1: return treeList[0] return treeList
def readScoreFile(fname, noself, randomize=False):
# The strings naming the proteins whose interaction was removed in
# this input
tstring = fname.split('@')[-2].split("#")
# Convert to upper case and make into an edge name
tedge = (tstring[0].upper(), tstring[1].upper())
# Read in the phylogenies for the orthology groups
treeDir = "../../Parana2Data/HerpesPPIs/trees/rearranged"#"dataOut_June17/rearranged"
baseFile = fname.split('/')[-1]
orthoGroup1 = baseFile.split('@')[0]
orthoGroup2 = baseFile.split('@')[1]
t1 = "{0}/{1}.xml.rooting.0.ntg.reconciled.0.ntg.rearrange.0.ntg".format(treeDir,orthoGroup1)
t2 = "{0}/{1}.xml.rooting.0.ntg.reconciled.0.ntg.rearrange.0.ntg".format(treeDir,orthoGroup2)
if ( not (os.path.exists(t1) and os.path.exists(t2)) ):
return None, None
# The extant (non ancestral, non lost) nodes from the two homology groups
getName = lambda x : x.Name.upper()
pxml = Phyloxml()
pxml.build_from_file(t1)
pxml.build_from_file(t2)
la = filter( lambda x : x.find('LOST') == -1, map( lambda x: x.upper(), pxml.phylogeny[0].get_leaf_names() ) )
lb = filter( lambda x : x.find('LOST') == -1, map( lambda x: x.upper(), pxml.phylogeny[1].get_leaf_names() ) )
# The set of all possible interactions among the two homology groups
#pe = list(itertools.product(la,la)) + list(itertools.product(la,lb)) + list(itertools.product(lb,lb))
possibleEndpoints = combinationsWithSelf(la) + list(itertools.product(la,lb)) + combinationsWithSelf(lb) \
if not (orthoGroup1 == orthoGroup2 ) else combinationsWithSelf(la)
# From among all possible endpoints, only those protein pairs that reside in the
# same species represent a potential edge
allPossibleEdges = filter( lambda (x,y): x.split('_')[-1] == y.split('_')[-1], possibleEndpoints )
# an edge has both endpoints in the set of extant nodes
inCurrentGroups = lambda e, x, y: (e[0] in x or e[0] in y) and (e[1] in x or e[1] in y)
# an edge is relevant if it's constrained to the current groups
relevantExtantEdges = [ e for e in ExtantNetwork.edges_iter() if inCurrentGroups(e,la,lb) ]
# the set of potential edges that don't appear in the input network
nonPresentEdgesMinusTarget = list(set([ x for x in allPossibleEdges if not ExtantNetwork.has_edge(x[0],x[1])]))
# the same as above but including our target edge
nonPresentEdges = nonPresentEdgesMinusTarget + [tedge]
import random
# Ancestral edges start with an N or R
ancestral = ['R','N']
# The node is valid if it is neither lost nor ancestral
isValidNode = lambda x : (x[0] not in ancestral) and (x.find('LOST') == -1)
# Is the edge u,v the target edge?
isCurrentEdge = lambda u,v : (u == tedge[0] and v == tedge[1]) or (u == tedge[1] and v == tedge[0])
isRealEdge = lambda u,v : (not isCurrentEdge(u,v)) and ExtantNetwork.has_edge(u,v)
isValidEdge = lambda u,v : ((isValidNode(u) and isValidNode(v)) and (not isRealEdge(u,v)))
# Is u,v one of the edges we wish to consider?
def inPotentialEdges(u,v) :
contains = (u,v) in nonPresentEdges or (v,u) in nonPresentEdges
if noself:
return u != v and contains
else:
return contains
def isEdge( se, p1, p2 ):
r = ((se.p1 == p1 and se.p2 == p2) or (se.p1 == p2 and se.p2 == p1))
return r
scoredEdges = []
nonEdgesWithProb = set( nonPresentEdges )
with open(fname,'rb') as ifile:
for l in ifile:
toks = l.rstrip().split()
p1 = toks[0].upper()
p2 = toks[1].upper()
s = float(toks[3])
if inPotentialEdges(p1,p2):
if randomize: s = random.uniform(0.0,1.0)
#if p1 == p2: s = 0.0
se = ScoredEdge(p1,p2,s)
scoredEdges.append( se )
nonEdgesWithProb.discard((p1,p2))
nonEdgesWithProb.discard((p2,p1))
rev = True
for u,v in (nonEdgesWithProb - set(nonPresentEdges)):
s = random.uniform(0.0,1.0) if randomize else 0.0
scoredEdges.append(ScoredEdge(u, v, s))
# cost = 0.0
# for u,v in nonPresentEdges:
# se = ScoredEdge(u,v,cost)
# fe = [ e for e in scoredEdges if isEdge(e, u, v) ]
# if len(fe) == 0:
# scoredEdges.append(se)
random.shuffle(scoredEdges)
scoredEdges = list(enumerate(sorted( scoredEdges, key=lambda x: x.score, reverse=rev )))
# print(len(scoredEdges))
# print(t1,t2)
# print("Target Edge = {0}".format(tedge))
# print("Extant Edges = {0}".format(relevantExtantEdges))
# print("Potential Edges = {0}".format(nonPresentEdges))
# print("Scored Edges = {0}".format(scoredEdges))
res = [ x for x in scoredEdges if isEdge(x[1], tedge[0], tedge[1]) ]
if len(res) > 0:
print(res)
# Prev (ISMB)
#print(res[0][0],float(len(nonPresentEdges)-1))
#return (res[0][0], float(len(nonPresentEdges)-1))
# New
#print(res[0][0],float(len(scoredEdges)-1))
return (res[0][0], float(len(scoredEdges)-1))
else:
raise 'Hell'
def main ():
global options, args
if options.verbose: print time.asctime(),
if options.verbose: print "load and parse newick file"
# TODO: read newick file
tree = Phylo.read(args[0],'newick')
# TODO: convert newick to phyloxml
treeXML = StringIO()
Phylo.write(tree,treeXML,'phyloxml')
# TODO: read phyloxml as ete object
hPhylotree = Phyloxml()
with tempinput(treeXML.getvalue()) as tempfilename:
hPhylotree.build_from_file(tempfilename)
# TODO: get the tree
tree2 = hPhylotree.get_phylogeny()[0]
if options.verbose: print time.asctime(),
if options.verbose: print "load and parse taxonomy file"
# TODO: read taxonomy file
tax = get_taxonomy(args[1])
# TODO: refine taxonomy annotation of internal node
tree2 = add_taxonomy_for_internal_branch(tree2,tax)
# TODO: refine tree node label
#tree2 = add_node_label(tree2,tax)
for node in tree2.traverse():
if not node.is_leaf():
label = "null"
for t in ['kingdom','phylum','class','order','family','genus','species']:
if len(tax[node.id][t])>3:
label = tax[node.id][t]
node.add_feature("mylabel",label)
# TODO: add node depth
depth={}
if options.depth:
with open(options.depth) as f:
for line in f:
(id,dep) = line.split()
depth[id] = float(dep)
# TODO: add color attribute
if options.depth:
for node in tree2.iter_leaves():
if depth[node.id] >= 10 and depth[node.id] < 100:
node.add_feature("color","#D8BFD8")
elif depth[node.id] >= 100 and depth[node.id] < 1000:
node.add_feature("color","#DDA0DD")
elif depth[node.id] >= 1000 and depth[node.id] < 5000:
node.add_feature("color","#EE82EE")
elif depth[node.id] >= 5000:
node.add_feature("color","#DA70D6")
else:
node.add_feature("color","#E6E6FA")
# TODO: set tree style
ts = TreeStyle()
ts.show_leaf_name = False
ts.layout_fn = tree_layout
# TODO: show tree2
#tree2.show(tree_style=ts)
tree2.render(args[0]+".png",dpi=2048,tree_style=ts)
def readScoreFile(fname, noself, randomize=False):
# The strings naming the proteins whose interaction was removed in
# this input
tstring = fname.split('@')[-2].split("#")
# Convert to upper case and make into an edge name
tedge = (tstring[0].upper(), tstring[1].upper())
# Read in the phylogenies for the orthology groups
treeDir = "../../Parana2Data/HerpesPPIs/trees/rearranged" #"dataOut_June17/rearranged"
baseFile = fname.split('/')[-1]
orthoGroup1 = baseFile.split('@')[0]
orthoGroup2 = baseFile.split('@')[1]
t1 = "{0}/{1}.xml.rooting.0.ntg.reconciled.0.ntg.rearrange.0.ntg".format(
treeDir, orthoGroup1)
t2 = "{0}/{1}.xml.rooting.0.ntg.reconciled.0.ntg.rearrange.0.ntg".format(
treeDir, orthoGroup2)
if (not (os.path.exists(t1) and os.path.exists(t2))):
return None, None
# The extant (non ancestral, non lost) nodes from the two homology groups
getName = lambda x: x.Name.upper()
pxml = Phyloxml()
pxml.build_from_file(t1)
pxml.build_from_file(t2)
la = filter(lambda x: x.find('LOST') == -1,
map(lambda x: x.upper(), pxml.phylogeny[0].get_leaf_names()))
lb = filter(lambda x: x.find('LOST') == -1,
map(lambda x: x.upper(), pxml.phylogeny[1].get_leaf_names()))
# The set of all possible interactions among the two homology groups
#pe = list(itertools.product(la,la)) + list(itertools.product(la,lb)) + list(itertools.product(lb,lb))
possibleEndpoints = combinationsWithSelf(la) + list(itertools.product(la,lb)) + combinationsWithSelf(lb) \
if not (orthoGroup1 == orthoGroup2 ) else combinationsWithSelf(la)
# From among all possible endpoints, only those protein pairs that reside in the
# same species represent a potential edge
allPossibleEdges = filter(
lambda (x, y): x.split('_')[-1] == y.split('_')[-1], possibleEndpoints)
# an edge has both endpoints in the set of extant nodes
inCurrentGroups = lambda e, x, y: (e[0] in x or e[0] in y) and (e[
1] in x or e[1] in y)
# an edge is relevant if it's constrained to the current groups
relevantExtantEdges = [
e for e in ExtantNetwork.edges_iter() if inCurrentGroups(e, la, lb)
]
# the set of potential edges that don't appear in the input network
nonPresentEdgesMinusTarget = list(
set([
x for x in allPossibleEdges
if not ExtantNetwork.has_edge(x[0], x[1])
]))
# the same as above but including our target edge
nonPresentEdges = nonPresentEdgesMinusTarget + [tedge]
import random
# Ancestral edges start with an N or R
ancestral = ['R', 'N']
# The node is valid if it is neither lost nor ancestral
isValidNode = lambda x: (x[0] not in ancestral) and (x.find('LOST') == -1)
# Is the edge u,v the target edge?
isCurrentEdge = lambda u, v: (u == tedge[0] and v == tedge[1]) or (
u == tedge[1] and v == tedge[0])
isRealEdge = lambda u, v: (not isCurrentEdge(u, v)
) and ExtantNetwork.has_edge(u, v)
isValidEdge = lambda u, v: (
(isValidNode(u) and isValidNode(v)) and (not isRealEdge(u, v)))
# Is u,v one of the edges we wish to consider?
def inPotentialEdges(u, v):
contains = (u, v) in nonPresentEdges or (v, u) in nonPresentEdges
if noself:
return u != v and contains
else:
return contains
def isEdge(se, p1, p2):
r = ((se.p1 == p1 and se.p2 == p2) or (se.p1 == p2 and se.p2 == p1))
return r
scoredEdges = []
nonEdgesWithProb = set(nonPresentEdges)
with open(fname, 'rb') as ifile:
for l in ifile:
toks = l.rstrip().split()
p1 = toks[0].upper()
p2 = toks[1].upper()
s = float(toks[3])
if inPotentialEdges(p1, p2):
if randomize: s = random.uniform(0.0, 1.0)
#if p1 == p2: s = 0.0
se = ScoredEdge(p1, p2, s)
scoredEdges.append(se)
nonEdgesWithProb.discard((p1, p2))
nonEdgesWithProb.discard((p2, p1))
rev = True
for u, v in (nonEdgesWithProb - set(nonPresentEdges)):
s = random.uniform(0.0, 1.0) if randomize else 0.0
scoredEdges.append(ScoredEdge(u, v, s))
# cost = 0.0
# for u,v in nonPresentEdges:
# se = ScoredEdge(u,v,cost)
# fe = [ e for e in scoredEdges if isEdge(e, u, v) ]
# if len(fe) == 0:
# scoredEdges.append(se)
random.shuffle(scoredEdges)
scoredEdges = list(
enumerate(sorted(scoredEdges, key=lambda x: x.score, reverse=rev)))
# print(len(scoredEdges))
# print(t1,t2)
# print("Target Edge = {0}".format(tedge))
# print("Extant Edges = {0}".format(relevantExtantEdges))
# print("Potential Edges = {0}".format(nonPresentEdges))
# print("Scored Edges = {0}".format(scoredEdges))
res = [x for x in scoredEdges if isEdge(x[1], tedge[0], tedge[1])]
if len(res) > 0:
print(res)
# Prev (ISMB)
#print(res[0][0],float(len(nonPresentEdges)-1))
#return (res[0][0], float(len(nonPresentEdges)-1))
# New
#print(res[0][0],float(len(scoredEdges)-1))
return (res[0][0], float(len(scoredEdges) - 1))
else:
raise 'Hell'
from ete2 import Phyloxml
project = Phyloxml()
project.build_from_file("apaf.xml")
# Each tree contains the same methods as a PhyloTree object
for tree in project.get_phylogeny():
print tree
# you can even use rendering options
tree.show()
# PhyloXML features are stored in the phyloxml_clade attribute
for node in tree:
print "Node name:", node.name
for seq in node.phyloxml_clade.get_sequence():
for domain in seq.domain_architecture.get_domain():
domain_data = [domain.valueOf_, domain.get_from(), domain.get_to()]
print " Domain:", '\t'.join(map(str, domain_data))
from ete2 import Phyloxml
project = Phyloxml()
project.build_from_file("testTree.xml")
# Each tree contains the same methods as a PhyloTree object
for tree in project.get_phylogeny():
print tree
# you can even use rendering options
tree.show()
# PhyloXML features are stored in the phyloxml_clade attribute
for node in tree:
print "Node name:", node.name
for seq in node.phyloxml_clade.get_sequence():
for domain in seq.domain_architecture.get_domain():
domain_data = [domain.valueOf_, domain.get_from(), domain.get_to()]
print " Domain:", '\t'.join(map(str, domain_data))
