def ilmat2imat(ilmat, rowlabels, collabels):
"""
Converts labeled matrix iterator (ilmat) to indexed matrix iterator (imat)
"""
rowlookup = util.list2lookup(rowlabels)
collookup = util.list2lookup(collabels)
for r, c, v in ilmat:
yield rowlookup[r], collookup[c], v
def renameTreeAlign(tree, align):
"""Rename the ancestral nodes of a tree"""
# rename leaves
for leaf in tree.leaves():
tree.rename(leaf.name, align.keys()[int(leaf.name) - 1])
names = align.keys()
name_lookup = util.list2lookup(names)
lookup = dict(align)
align.clear()
order = {}
# rename ancestral nodes by preorder
next = [1]
def walk(node):
oldname = node.name
if not node.is_leaf():
tree.rename(node.name, next[0])
next[0] += 1
align[str(node.name)] = lookup[str(oldname)]
order[str(node.name)] = name_lookup[str(oldname)]
else:
align[node.name] = lookup[node.name]
order[node.name] = name_lookup[node.name]
for child in node.children:
walk(child)
walk(tree.root)
align.names.sort(key=lambda x: order[x])
def map(self, func, headers=None):
"""Returns a new table with each row mapped by function 'func'"""
if len(self) == 0:
# handle case of zero length table
return self.new()
# determine what table will look like from first row
first_row = func(self[0])
# determine headers of new table
if headers is None:
# try order new headers the same way as old headers
headers = first_row.keys()
lookup = util.list2lookup(self.headers)
top = len(headers)
headers.sort(key=lambda x: (lookup.get(x, top), x))
tab = type(self)(itertools.chain([first_row],
(func(x) for x in self[1:])),
headers=headers)
tab.delim = self.delim
tab.nheaders = self.nheaders
return tab
def rename_tree_with_ids(tree, labels):
lookup = util.list2lookup(labels)
names = tree.nodes.keys()
for name in names:
if tree.nodes[name].is_leaf():
tree.rename(name, phylip_padding(str(lookup[name])))
def map(self, func, headers=None):
"""Returns a new table with each row mapped by function 'func'"""
if len(self) == 0:
# handle case of zero length table
return self.new()
# determine what table will look like from first row
first_row = func(self[0])
# determine headers of new table
if headers is None:
# try order new headers the same way as old headers
headers = first_row.keys()
lookup = util.list2lookup(self.headers)
top = len(headers)
headers.sort(key=lambda x:
(lookup.get(x, top), x))
tab = type(self)(
itertools.chain([first_row],
(func(x) for x in self[1:])),
headers=headers)
tab.delim = self.delim
tab.nheaders = self.nheaders
return tab
def renameTreeAlign(tree, align):
"""Rename the ancestral nodes of a tree"""
# rename leaves
for leaf in tree.leaves():
tree.rename(leaf.name, align.keys()[int(leaf.name)-1])
names = align.keys()
name_lookup = util.list2lookup(names)
lookup = dict(align)
align.clear()
order = {}
# rename ancestral nodes by preorder
next = [1]
def walk(node):
oldname = node.name
if not node.is_leaf():
tree.rename(node.name, next[0])
next[0] += 1
align[str(node.name)] = lookup[str(oldname)]
order[str(node.name)] = name_lookup[str(oldname)]
else:
align[node.name] = lookup[node.name]
order[node.name] = name_lookup[node.name]
for child in node.children:
walk(child)
walk(tree.root)
align.names.sort(key=lambda x: order[x])
def rename_tree_with_ids(tree, labels):
lookup = util.list2lookup(labels)
names = tree.nodes.keys()
for name in names:
if tree.nodes[name].is_leaf():
tree.rename(name, phylip_padding(str(lookup[name])))
def parts2partids(parts, labels):
lookup = util.list2lookup(labels)
partids = [0] * len(labels)
for i in xrange(len(parts)):
for item in parts[i]:
partids[lookup[item]] = i
return partids
def parts2partids(parts, labels):
lookup = util.list2lookup(labels)
partids = [0] * len(labels)
for i in xrange(len(parts)):
for item in parts[i]:
partids[lookup[item]] = i
return partids
def init_distmats(self):
"""Initialize distance matrices
Initialization should by done after trees and alignments
"""
if len(self.distmats) > 0:
self.matrices = []
# setup matrices
for i, distmat in enumerate(self.distmats):
# convert distmatrix to summon Matrix
if isinstance(distmat, matrix.Matrix):
mat = distmat
else:
mat = matrix.Matrix()
mat.from2DList(distmat)
# set default colormap
if mat.colormap == None:
mat.colormap = self.matrix_colormap
# determine labels
if self.dist_labels_from_align and self.align_order != None:
# determine row/col labels from alignment if it exists
mat.rowlabels = self.align_order
mat.collabels = self.align_order
elif self.distlabels != None:
mat.rowlabels = self.distlabels[i]
mat.collabels = self.distlabels[i]
else:
raise Exception("no labels given for matrix")
# reorder according to any given tree
if self.order != None:
lookup = util.list2lookup(mat.rowlabels)
mat.rperm = util.mget(lookup, self.order)
mat.cperm = util.mget(lookup, self.order)
mat.setup()
self.matrices.append(mat)
if self.seqs == None:
seqs = self.current_align
else:
seqs = self.seqs
# create matrix vis
self.current_matrix = self.matrices[0]
self.visdist = distmatrixvis.DistMatrixViewer(self.current_matrix,
seqs=seqs,
bgcolor=(1, 1, 1))
else:
self.visdist = None
def init_distmats(self):
"""Initialize distance matrices
Initialization should by done after trees and alignments
"""
if len(self.distmats) > 0:
self.matrices = []
# setup matrices
for i, distmat in enumerate(self.distmats):
# convert distmatrix to summon Matrix
if isinstance(distmat, matrix.Matrix):
mat = distmat
else:
mat = matrix.Matrix()
mat.from2DList(distmat)
# set default colormap
if mat.colormap == None:
mat.colormap = self.matrix_colormap
# determine labels
if self.dist_labels_from_align and self.align_order != None:
# determine row/col labels from alignment if it exists
mat.rowlabels = self.align_order
mat.collabels = self.align_order
elif self.distlabels != None:
mat.rowlabels = self.distlabels[i]
mat.collabels = self.distlabels[i]
else:
raise Exception("no labels given for matrix")
# reorder according to any given tree
if self.order != None:
lookup = util.list2lookup(mat.rowlabels)
mat.rperm = util.mget(lookup, self.order)
mat.cperm = util.mget(lookup, self.order)
mat.setup()
self.matrices.append(mat)
if self.seqs == None:
seqs = self.current_align
else:
seqs = self.seqs
# create matrix vis
self.current_matrix = self.matrices[0]
self.visdist = distmatrixvis.DistMatrixViewer(self.current_matrix,
seqs=seqs,
bgcolor=(1,1,1))
else:
self.visdist = None
def show_selection(self):
# sort genes by order in matrix
genes = list(self.selgenes)
lookup = util.list2lookup(self.mat.rowlabels)
genes.sort(key=lambda x: lookup[x])
print
print "selected genes:"
for i, gene in enumerate(genes):
print "%3d %s" % (i+1, gene)
def show_selection(self):
# sort genes by order in matrix
genes = list(self.selgenes)
lookup = util.list2lookup(self.mat.rowlabels)
genes.sort(key=lambda x: lookup[x])
print
print "selected genes:"
for i, gene in enumerate(genes):
print "%3d %s" % (i + 1, gene)
def splitString(split, leaves=None, leafDelim=" ", splitDelim="|"):
"""
Returns a string representing a split
If leaves are specified, leaf names will be displayed in that order.
"""
if leaves is not None:
lookup = util.list2lookup(leaves)
split = (sorted(split[0], key=lambda x: lookup[x]),
sorted(split[0], key=lambda x: lookup[x]))
return leafDelim.join(split[0]) + splitDelim + leafDelim.join(split[1])
def on_reorder_leaves(self):
leaves = self.current_tree.leaf_names()
# reorder matrix
for mat in self.matrices:
lookup = util.list2lookup(mat.rowlabels)
mat.rperm = util.mget(lookup, leaves)
mat.cperm = util.mget(lookup, leaves)
mat.setup()
if self.visdist:
self.visdist.redraw()
# reorder alignment
for aln in self.aligns:
aln.names = leaves
if self.visalign:
self.visalign.show()
def show_align(self):
if self.seqs == None:
print "cannot build alignment: no sequences are loaded"
return
if len(self.selgenes) == 0:
print "cannot build alignment: no sequences selected"
return
genes = list(self.selgenes)
lookup = util.list2lookup(self.mat.rowlabels)
self.aln = muscle.muscle(self.seqs.get(genes))
self.aln.names.sort(key=lambda x: lookup[x])
self.visaln = genomebrowser.show_align(self.aln)
self.visaln.win.set_name("alignment")
def show_align(self):
if self.seqs is None:
print "cannot build alignment: no sequences are loaded"
return
if len(self.selgenes) == 0:
print "cannot build alignment: no sequences selected"
return
genes = list(self.selgenes)
lookup = util.list2lookup(self.mat.rowlabels)
self.aln = muscle.muscle(self.seqs.get(genes))
self.aln.names.sort(key=lambda x: lookup[x])
self.visaln = genomebrowser.show_align(self.aln)
self.visaln.win.set_name("alignment")
def on_reorder_leaves(self):
leaves = self.current_tree.leaf_names()
# reorder matrix
for mat in self.matrices:
lookup = util.list2lookup(mat.rowlabels)
mat.rperm = util.mget(lookup, leaves)
mat.cperm = util.mget(lookup, leaves)
mat.setup()
if self.visdist:
self.visdist.redraw()
# reorder alignment
for aln in self.aligns:
aln.names = leaves
if self.visalign:
self.visalign.show()
def layout_arg(arg, leaves=None, yfunc=lambda x: x):
"""Layout the nodes of an ARG"""
layout = {}
# layout leaves
if leaves is None:
leafx = layout_arg_leaves(arg)
else:
leafx = util.list2lookup(leaves)
for node in arg.postorder():
if node.is_leaf():
layout[node] = [leafx[node], yfunc(node.age)]
else:
layout[node] = [
stats.mean(layout[child][0] for child in node.children),
yfunc(node.age)]
return layout
def layout_arg(arg, leaves=None, yfunc=lambda x: x):
"""Layout the nodes of an ARG"""
layout = {}
# layout leaves
if leaves is None:
leafx = layout_arg_leaves(arg)
else:
leafx = util.list2lookup(leaves)
for node in arg.postorder():
if node.is_leaf():
layout[node] = [leafx[node], yfunc(node.age)]
else:
layout[node] = [
stats.mean(layout[child][0] for child in node.children),
yfunc(node.age)]
return layout
def makePtree(tree):
"""Make parent tree array from tree"""
nodes = []
nodelookup = {}
ptree = []
def walk(node):
for child in node.children:
walk(child)
nodes.append(node)
walk(tree.root)
def leafsort(a, b):
if a.isLeaf():
if b.isLeaf():
return 0
else:
return -1
else:
if b.isLeaf():
return 1
else:
return 0
# bring leaves to front
nodes.sort(cmp=leafsort)
nodelookup = util.list2lookup(nodes)
for node in nodes:
if node == tree.root:
ptree.append(-1)
else:
ptree.append(nodelookup[node.parent])
assert nodes[-1] == tree.root
return ptree, nodes, nodelookup
def makeTopologyMatrix(tree, genes):
# find how edges split vertices
network = treelib.tree2graph(tree)
splits = find_all_branch_splits(network, set(genes))
edges = splits.keys()
# create topology matrix
n = len(genes)
ndists = n*(n-1) / 2
topmat = util.makeMatrix(ndists, len(edges))
vlookup = util.list2lookup(genes)
n = len(genes)
for e in xrange(len(edges)):
set1, set2 = splits[edges[e]]
for gene1 in set1:
for gene2 in set2:
i, j = util.sort([vlookup[gene1], vlookup[gene2]])
index = i*n-i*(i+1)/2+j-i-1
topmat[index][e] = 1.0
return topmat, edges
def order_names(self, aln):
"""Orders the names in the same order they appear in aln"""
lookup = util.list2lookup(aln.keys())
self.names.sort(key=lambda x: lookup[x])
def order_names(self, aln):
"""Orders the names in the same order they appear in aln"""
lookup = util.list2lookup(aln.keys())
self.names.sort(key=lambda x: lookup[x])
