def layout(node):
#print(node)
if node.is_leaf():
if node.name in x_file_names:
#make reconstructed bubble
size = x[x_file_names.index(node.name)]
F = CircleFace(radius=500*math.sqrt(size), color="RoyalBlue", style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F,node, 0, position="branch-right")
if taxonomic_names_on_leaves:
nameFace = AttrFace("name", fsize=25, fgcolor='black',text_suffix="_"+taxonomy[x_file_names.index(node.name)])
faces.add_face_to_node(nameFace, node, 0, position="branch-right")
else:
nameFace = AttrFace("name", fsize=25, fgcolor='black')
faces.add_face_to_node(nameFace, node, 0, position="branch-right")
elif node.name in hyp_node_names: #Otherwise it's a hypothetical node, just use recon x
node_base_name = hyp_node_names[node.name][0]
percent = hyp_node_names[node.name][1]
if node_base_name in x_file_names:
idx = hyp_node_names[node.name][2]
size = x[x_file_names.index(node_base_name)+(idx+1)*len(x_file_names)]
F = CircleFace(radius=500*math.sqrt(size), color="RoyalBlue", style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F,node, 0, position="branch-right")
#print node
#print size
else:
size=0
else:
size=0
def layout(node):
node_style = NodeStyle()
node_style["hz_line_width"] = 10
node_style["vt_line_width"] = 10
node.set_style(node_style)
#print(node)
if node.is_leaf():
if node.name in org_names:
#make reconstructed bubble
size = x[org_names.index(node.name)]
F = CircleFace(radius=size_factor*math.sqrt(size), color="RoyalBlue", style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F,node, 0, position="branch-right")
#Denote that this was a training organism
nameFace = AttrFace("name", fsize=font_size, fgcolor='black')
faces.add_face_to_node(nameFace, node, 0, position="branch-right")
elif node.name in hyp_node_names: #Otherwise it's a hypothetical node, just use recon x
node_base_name = hyp_node_names[node.name][0]
percent = hyp_node_names[node.name][1]
if node_base_name in org_names:
idx = hyp_node_names[node.name][2]
size = x[org_names.index(node_base_name)+(idx+1)*len(org_names)]
F = CircleFace(radius=size_factor*math.sqrt(size), color="RoyalBlue", style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F,node, 0, position="branch-right")
#This is if I want the names of the hypothetical nodes to be printed as well
#nameFace = AttrFace("name", fsize=font_size, fgcolor='black')
#faces.add_face_to_node(nameFace, node, 0, position="branch-right")
else:
size=0
else:
size=0
def layout(node):
#print(node)
if node.is_leaf():
if node.name in x_file_names:
#make reconstructed bubble
size = x[x_file_names.index(node.name)]
F = CircleFace(radius=500 * math.sqrt(size),
color="RoyalBlue",
style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F, node, 0, position="branch-right")
if taxonomic_names_on_leaves:
nameFace = AttrFace(
"name",
fsize=25,
fgcolor='black',
text_suffix="_" +
taxonomy[x_file_names.index(node.name)])
faces.add_face_to_node(nameFace,
node,
0,
position="branch-right")
else:
nameFace = AttrFace("name", fsize=25, fgcolor='black')
faces.add_face_to_node(nameFace,
node,
0,
position="branch-right")
elif node.name in hyp_node_names: #Otherwise it's a hypothetical node, just use recon x
node_base_name = hyp_node_names[node.name][0]
percent = hyp_node_names[node.name][1]
if node_base_name in x_file_names:
idx = hyp_node_names[node.name][2]
size = x[x_file_names.index(node_base_name) +
(idx + 1) * len(x_file_names)]
F = CircleFace(radius=500 * math.sqrt(size),
color="RoyalBlue",
style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F, node, 0, position="branch-right")
#print node
#print size
else:
size = 0
else:
size = 0
def makeSupportSymbols(node, secondary_support):
#function to make circle with size scaled to base support value and color of circle scaled to the level of the second support value
opacity = 0.01
# Let's make the sphere transparent
if secondary_support == None:
circle_color = "Grey"
opacity = 1.0
factor = 6
elif secondary_support >=95.0:
circle_color = "Black"
opacity = 1.0
factor = 10
elif secondary_support >=70.0:
circle_color = "Black"
opacity = 1.0
factor = 8
elif secondary_support <70.0:
circle_color = "Black"
opacity = 1.0
factor = 6
else:
print "secondary value unexpected: {}".format(secondary_support())
circle_color = "Red"
opacity = 1.0
#circle_color = "#33343E" #a black from the pomacanthus drawing
#print "color is {}, bootstrap is {}, opacity is {}".format(color, secondary_support, opacity)
support_face = CircleFace(radius=node.support * factor, color=circle_color, style="circle")
support_face.opacity = opacity
faces.add_face_to_node(support_face, node, 0, position="float-behind")
def layout(node):
if node.is_leaf():
#######################################################
#~ Taxon Label Size and Margin Adjustment
N = AttrFace("name", fsize=1200, fgcolor="#000000")
N.margin_top = 250
N.margin_right = 100 #outside
N.margin_left = 1000 #inside
N.margin_bottom = 250
#######################################################
#######################################################
#~ Taxon Label Background Color Setting
tmp = "<myTaxaonLabel>"
#~ if not(node.name.find(tmp)) : N.background.color="#FF9999"
#######################################################
faces.add_face_to_node(N, node, 0, position="aligned")
if (not node.is_leaf()):
S = faces.AttrFace("support", fsize=200, fgcolor="#000000")
S.margin_top = 20
S.margin_right = 10
S.margin_left = 20
S.margin_bottom = 20
faces.add_face_to_node(S, node, column=0, position="float")
if "support" in node.features:
# Creates a sphere face whose size is proportional to node's
# feature "weight"
C = CircleFace(radius=node.support * 20,
color="RoyalBlue",
style="sphere")
# Let's make the sphere transparent
C.opacity = 0.3
# And place as a float face over the tree
faces.add_face_to_node(C, node, position="float", column=1)
style = NodeStyle()
style["size"] = 0
style["vt_line_width"] = 150
style["hz_line_width"] = 150
style["vt_line_type"] = 0 # 0 solid, 1 dashed, 2 dotted
style["hz_line_type"] = 0
node.set_style(style)
bgcol1 = "#FFCCCC"
bgcol2 = "#FFE5CC"
bgcol3 = "#FFFFCC"
bgcol4 = "#E5FFCC"
bgcol5 = "#CCFFCC"
bgcol6 = "#CCFFE5"
bgcol7 = "#FFCCE5"
bgcol8 = "#CCFFFF"
bgcol9 = "#CCE5FF"
bgcol10 = "#CCCCFF"
bgcol11 = "#E5CCFF"
def layout(node):
node_style = NodeStyle()
node_style["hz_line_width"] = 10
node_style["vt_line_width"] = 10
node.set_style(node_style)
#print(node)
if node.is_leaf():
if node.name in org_names:
#make reconstructed bubble
size = x[org_names.index(node.name)]
F = CircleFace(radius=size_factor * math.sqrt(size),
color="RoyalBlue",
style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F, node, 0, position="branch-right")
#Denote that this was a training organism
nameFace = AttrFace("name", fsize=font_size, fgcolor='black')
faces.add_face_to_node(nameFace,
node,
0,
position="branch-right")
elif node.name in hyp_node_names: #Otherwise it's a hypothetical node, just use recon x
node_base_name = hyp_node_names[node.name][0]
percent = hyp_node_names[node.name][1]
if node_base_name in org_names:
idx = hyp_node_names[node.name][2]
size = x[org_names.index(node_base_name) +
(idx + 1) * len(org_names)]
F = CircleFace(radius=size_factor * math.sqrt(size),
color="RoyalBlue",
style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F, node, 0, position="branch-right")
#This is if I want the names of the hypothetical nodes to be printed as well
#nameFace = AttrFace("name", fsize=font_size, fgcolor='black')
#faces.add_face_to_node(nameFace, node, 0, position="branch-right")
else:
size = 0
else:
size = 0
def layout(node): if node.name in ckm_name_to_perc: ckm_perc = float(ckm_name_to_perc[node.name]) else: ckm_perc = 0 F = CircleFace(radius=3.14*math.sqrt(ckm_perc), color="RoyalBlue", style="sphere") F.border.width = None F.opacity = 0.6 faces.add_face_to_node(F,node, 0, position="branch-right") if label_internal_nodes: faces.add_face_to_node(TextFace(node.name, fsize=7),node, 0, position="branch-top")
def layout(node):
if node.is_leaf():
#######################################################
#~ Taxon Label Size and Margin Adjustment
N = AttrFace("name", fsize=1200,fgcolor="#000000")
N.margin_top = 250
N.margin_right = 100 #outside
N.margin_left = 1000 #inside
N.margin_bottom = 250
#######################################################
#######################################################
#~ Taxon Label Background Color Setting
tmp = "<myTaxaonLabel>"
#~ if not(node.name.find(tmp)) : N.background.color="#FF9999"
#######################################################
faces.add_face_to_node(N, node, 0, position="aligned")
if (not node.is_leaf()) :
S=faces.AttrFace("support", fsize=200, fgcolor="#000000")
S.margin_top = 20
S.margin_right = 10
S.margin_left = 20
S.margin_bottom = 20
faces.add_face_to_node( S, node, column=0 , position = "float")
if "support" in node.features:
# Creates a sphere face whose size is proportional to node's
# feature "weight"
C = CircleFace(radius=node.support*20, color="RoyalBlue", style="sphere")
# Let's make the sphere transparent
C.opacity = 0.3
# And place as a float face over the tree
faces.add_face_to_node(C, node, position="float",column=1)
style = NodeStyle()
style["size"] = 0
style["vt_line_width"] = 150
style["hz_line_width"] = 150
style["vt_line_type"] = 0 # 0 solid, 1 dashed, 2 dotted
style["hz_line_type"] = 0
node.set_style(style)
bgcol1="#FFCCCC"
bgcol2="#FFE5CC"
bgcol3="#FFFFCC"
bgcol4="#E5FFCC"
bgcol5="#CCFFCC"
bgcol6="#CCFFE5"
bgcol7="#FFCCE5"
bgcol8="#CCFFFF"
bgcol9="#CCE5FF"
bgcol10="#CCCCFF"
bgcol11="#E5CCFF"
def layout(node):
if node.is_leaf():
# Add node name to laef nodes
N = AttrFace("name", fsize=14, fgcolor="black")
faces.add_face_to_node(N, node, 0)
if "weight" in node.features:
# Creates a sphere face whose size is proportional to node's
# feature "weight"
C = CircleFace(radius=node.weight, color="RoyalBlue", style="sphere")
# Let's make the sphere transparent
C.opacity = 0.3
# And place as a float face over the tree
faces.add_face_to_node(C, node, 0, position="float")
def layout(node): if not node.is_root(): # give node name to all but the root faces.add_face_to_node(TextFace(node.name), node, 0) # and increase them with the wight if "weight" in node.features: # Creates a sphere face whose size is proportional to node's # feature "weight" C = CircleFace(radius=node.weight, color="RoyalBlue", style="sphere") # Let's make the sphere transparent C.opacity = 0.34 # And place as a float face over the tree faces.add_face_to_node(C, node, 0, position="float")
def layout(node): if not node.is_root(): # give node name to all but the root faces.add_face_to_node(TextFace(node.name), node, 0) # and increase them with the wight if "weight" in node.features: # Creates a sphere face whose size is proportional to node's # feature "weight" C = CircleFace(radius=node.weight, color="RoyalBlue", style="sphere") # Let's make the sphere transparent C.opacity = 0.34 # And place as a float face over the tree faces.add_face_to_node(C, node, 0, position="float")
def layout(node):
def color(node):
if type(node.item) is Value:
return "Red"
elif type(node.item) is Parameter:
return "Yellow"
elif node.item.leaf:
return "Green"
else:
return "RoyalBlue"
N = AttrFace("name", fsize=14, fgcolor="black")
faces.add_face_to_node(N, node, 0)
C = CircleFace(radius=node.weight, color=color(node), style="sphere")
C.opacity = 0.3
faces.add_face_to_node(C, node, 0, position="float")
def layout(node):
if not node.is_root():
# Add node name to laef nodes
#N = AttrFace("name", fsize=14, fgcolor="black")
#faces.add_face_to_node(N, node, 0)
#pass
faces.add_face_to_node(TextFace(node.name), node, 0)
if "weight" in node.features:
# Creates a sphere face whose size is proportional to node's
# feature "weight"
C = CircleFace(radius=node.weight, color="RoyalBlue", style="sphere")
# Let's make the sphere transparent
C.opacity = 0.3
# And place as a float face over the tree
faces.add_face_to_node(C, node, 0, position="float")
def __layout__(self, node):
if node.is_leaf():
# Add node name to laef nodes
N = AttrFace("name", fsize=14, fgcolor="black")
faces.add_face_to_node(N, node, 0)
nstyle = NodeStyle()
nstyle["size"] = 0
node.set_style(nstyle)
if "internalCount" in node.features:
print node.name
# Creates a sphere face whose size is proportional to node's
# feature "weight"
C = CircleFace(radius=int(node.internalCount)/10, color="RoyalBlue", style="sphere")
T = TextFace("10")
# Let's make the sphere transparent
C.opacity = 0.3
# And place as a float face over the tree
faces.add_face_to_node(C, node, 0, position="float")
faces.add_face_to_node(T, node, 1)
def __layout__(self, node):
if node.is_leaf():
# Add node name to laef nodes
N = AttrFace("name", fsize=14, fgcolor="black")
faces.add_face_to_node(N, node, 0)
nstyle = NodeStyle()
nstyle["size"] = 0
node.set_style(nstyle)
if "internalCount" in node.features:
print node.name
# Creates a sphere face whose size is proportional to node's
# feature "weight"
C = CircleFace(radius=int(node.internalCount) / 10,
color="RoyalBlue",
style="sphere")
T = TextFace("10")
# Let's make the sphere transparent
C.opacity = 0.3
# And place as a float face over the tree
faces.add_face_to_node(C, node, 0, position="float")
faces.add_face_to_node(T, node, 1)
def MakePlot(x, org_names, ckm30, ckm50, outgroup, outfile, outfilexml, sum_x):
#Make sure names are unique
names = org_names
for name in names:
if names.count(name)>1:
temp_name = name
i=1
for dummy in range(0,names.count(name)-1): #Don't change the last one, just to make sure we don't conflict with the outgroup
names[names.index(temp_name)] = temp_name + "_" + str(i)
i = i +1
#Normalize the x vector
x = map(lambda y: y/sum(x),x)
ckm30_norm = np.multiply(ckm30,1/np.diag(ckm30))
ckm50_norm = np.multiply(ckm50,1/np.diag(ckm50))
num_rows = ckm30_norm.shape[0]
num_cols = ckm30_norm.shape[1]
matrix=list()
for i in range(num_rows):
matrix.append([.5*(1-.5*ckm30_norm[i,j]-.5*ckm30_norm[j,i])+.5*(1-.5*ckm50_norm[i,j]-.5*ckm50_norm[j,i]) for j in range(i+1)])
#Make the list of distances (ave of the two ckm matrices)
ckm_ave_train = .5*ckm30_norm+.5*ckm50_norm
ckm_ave_train_dist = dict()
for i in range(len(org_names)):
ckm_ave_train_dist[org_names[i]] = [.5*ckm_ave_train[i,j]+.5*ckm_ave_train[j,i] for j in range(len(org_names))]
#Construct the tree. Note I could use RapidNJ here, but a few tests have shown that the trees that RapidNJ creates are rubbish.
dm = _DistanceMatrix(names, matrix)
constructor = DistanceTreeConstructor()
tree = constructor.nj(dm)
t=Tree(tree.format('newick'),format=1)
#tree.format('newick')
#Phylo.draw_ascii(tree)
#Now I will put internal nodes in a certain phylogenetic distance between the root and a given node.
#Function to insert a node at a given distance
def insert_node(t, name_to_insert, insert_above, dist_along):
insert_at_node = t.search_nodes(name=insert_above)[0]
parent = (t&insert_above).up
orig_branch_length = t.get_distance(insert_at_node,parent)
if orig_branch_length < dist_along:
raise ValueError("error: dist_along larger than orig_branch_length in PlotPackage.py")
removed_node = insert_at_node.detach()
removed_node.dist = orig_branch_length - dist_along
added_node = parent.add_child(name=name_to_insert, dist=dist_along)
added_node.add_child(removed_node)
#Function to insert a node some % along a branch, taking into account the ckm distances and nodes already created in the NJ tree (and what distance their descendants are from everyone else)
def insert_hyp_node(t, leaf_name, percent, ckm_ave_train_dist, org_names):
dists = map(lambda y: abs(y-percent), ckm_ave_train_dist[leaf_name])
nearby_indicies = list()
#Add all the organisms that are within 0.05 of the given percent
# for i in range(len(dists)):
# if dists[i]<=.05:
# nearby_indicies.append(i)
nearby_names = list()
#If there are no nearby indicies, add the closest organism to the given percent
if nearby_indicies==[]:
nearby_names.append(org_names[dists.index(min(dists))])
else:
for i in range(len(nearby_indicies)):
nearby_names.append(org_names[i])
mean_dist = np.mean(map(lambda y: ckm_ave_train_dist[leaf_name][org_names.index(y)],nearby_names))
nearby_names.append(leaf_name)
LCA = t.get_common_ancestor(nearby_names)
LCA_to_leaf_dist = t.get_distance(LCA,leaf_name)
#divide the dist to the right/left of the LCA node by the number of percentage points in there
if LCA.name==t.name:
percent_dist = percent*LCA_to_leaf_dist
if mean_dist <= percent:
child_node = (t&leaf_name)
else:
child_node = (t&nearby_names[0])#This means "go up from root" in the direction of the nearest guy
ancestor_node = (t&child_node.name).up
elif mean_dist <= percent:
percent_dist = t.get_distance(LCA) + abs(percent-mean_dist)*(LCA_to_leaf_dist)/(1-mean_dist)
child_node = (t&leaf_name)
ancestor_node = (t&child_node.name).up
else:
percent_dist = t.get_distance(LCA) - abs(percent-mean_dist)*(t.get_distance(LCA))/(mean_dist)
child_node = (t&leaf_name)
ancestor_node = (t&child_node.name).up
while t.get_distance(t.name, ancestor_node) > percent_dist:
child_node = ancestor_node
ancestor_node = (t&child_node.name).up
insert_node(t, leaf_name+"_"+str(percent), child_node.name, percent_dist-t.get_distance(t.name, ancestor_node))
#Set outgroup
if outgroup in names:
t.set_outgroup(t&outgroup) #I will need to check that this outgroup is actually one of the names...
else:
print("WARNING: the chosen outgroup " + outgroup + " is not in the given taxonomy: ")
print(names)
print("Proceeding without setting an outgroup. This may cause results to be uninterpretable.")
#Insert hypothetical nodes
hyp_node_names = dict()
cutoffs = [.9,.8,.7,.6,.5,.4,.3,.2,.1]
cutoffs = [-.5141*(val**3)+1.0932*(val**2)+0.3824*val for val in cutoffs]
for i in range(len(org_names)):
xi = x[i:len(x):len(org_names)]
for j in range(1,len(cutoffs)+1):
if xi[j]>0:
insert_hyp_node(t, org_names[i], cutoffs[j-1],ckm_ave_train_dist, org_names)
hyp_node_names[org_names[i]+"_"+str(cutoffs[j-1])] = [org_names[i], cutoffs[j-1], j-1] #in case there are "_" in the file names
size_factor=250
font_size=55
#Now put the bubbles on the nodes
def layout(node):
node_style = NodeStyle()
node_style["hz_line_width"] = 10
node_style["vt_line_width"] = 10
node.set_style(node_style)
#print(node)
if node.is_leaf():
if node.name in org_names:
#make reconstructed bubble
size = x[org_names.index(node.name)]
F = CircleFace(radius=size_factor*math.sqrt(size), color="RoyalBlue", style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F,node, 0, position="branch-right")
#Denote that this was a training organism
nameFace = AttrFace("name", fsize=font_size, fgcolor='black')
faces.add_face_to_node(nameFace, node, 0, position="branch-right")
elif node.name in hyp_node_names: #Otherwise it's a hypothetical node, just use recon x
node_base_name = hyp_node_names[node.name][0]
percent = hyp_node_names[node.name][1]
if node_base_name in org_names:
idx = hyp_node_names[node.name][2]
size = x[org_names.index(node_base_name)+(idx+1)*len(org_names)]
F = CircleFace(radius=size_factor*math.sqrt(size), color="RoyalBlue", style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F,node, 0, position="branch-right")
#This is if I want the names of the hypothetical nodes to be printed as well
#nameFace = AttrFace("name", fsize=font_size, fgcolor='black')
#faces.add_face_to_node(nameFace, node, 0, position="branch-right")
else:
size=0
else:
size=0
ts = TreeStyle()
ts.layout_fn = layout
ts.mode = "r"
#ts.mode = "c"
ts.scale = 2*1000
ts.show_leaf_name = False
ts.min_leaf_separation = 50
F = CircleFace(radius=.87*size_factor, color="RoyalBlue", style="sphere")
F.border.width = None
F.opacity = 0.6
ts.legend.add_face(F,0)
ts.legend.add_face(TextFace(" Inferred relative abundance",fsize=1.5*font_size,fgcolor="Blue"),1)
ts.legend.add_face(TextFace(" Total absolute abundance depicted " + str(sum_x)[0:8], fsize=1.5*font_size,fgcolor="Black"),1)
ts.legend_position=4
#t.show(tree_style=ts)
t.render(outfile, w=550, units="mm", tree_style=ts)
#Redner the XML file
project = Phyloxml()
phylo = phyloxml.PhyloxmlTree(newick=t.write(format=0, features=[]))
project.add_phylogeny(phylo)
project.export(open(outfilexml,'w'))
def style_node2(node, colour, size):
C = CircleFace(radius = size, color = colour, style="sphere")
C.opacity = 0.8
node.add_face(C, 0, position="float")
def MakePlot(x, org_names, ckm30, ckm50, outgroup, outfile, outfilexml, sum_x):
#Make sure names are unique
names = org_names
for name in names:
if names.count(name) > 1:
temp_name = name
i = 1
for dummy in range(
0,
names.count(name) - 1
): #Don't change the last one, just to make sure we don't conflict with the outgroup
names[names.index(temp_name)] = temp_name + "_" + str(i)
i = i + 1
#Normalize the x vector
x = map(lambda y: y / sum(x), x)
ckm30_norm = np.multiply(ckm30, 1 / np.diag(ckm30))
ckm50_norm = np.multiply(ckm50, 1 / np.diag(ckm50))
num_rows = ckm30_norm.shape[0]
num_cols = ckm30_norm.shape[1]
matrix = list()
for i in range(num_rows):
matrix.append([
.5 * (1 - .5 * ckm30_norm[i, j] - .5 * ckm30_norm[j, i]) + .5 *
(1 - .5 * ckm50_norm[i, j] - .5 * ckm50_norm[j, i])
for j in range(i + 1)
])
#Make the list of distances (ave of the two ckm matrices)
ckm_ave_train = .5 * ckm30_norm + .5 * ckm50_norm
ckm_ave_train_dist = dict()
for i in range(len(org_names)):
ckm_ave_train_dist[org_names[i]] = [
.5 * ckm_ave_train[i, j] + .5 * ckm_ave_train[j, i]
for j in range(len(org_names))
]
#Construct the tree. Note I could use RapidNJ here, but a few tests have shown that the trees that RapidNJ creates are rubbish.
dm = _DistanceMatrix(names, matrix)
constructor = DistanceTreeConstructor()
tree = constructor.nj(dm)
t = Tree(tree.format('newick'), format=1)
#tree.format('newick')
#Phylo.draw_ascii(tree)
#Now I will put internal nodes in a certain phylogenetic distance between the root and a given node.
#Function to insert a node at a given distance
def insert_node(t, name_to_insert, insert_above, dist_along):
insert_at_node = t.search_nodes(name=insert_above)[0]
parent = (t & insert_above).up
orig_branch_length = t.get_distance(insert_at_node, parent)
if orig_branch_length < dist_along:
raise ValueError(
"error: dist_along larger than orig_branch_length in PlotPackage.py"
)
removed_node = insert_at_node.detach()
removed_node.dist = orig_branch_length - dist_along
added_node = parent.add_child(name=name_to_insert, dist=dist_along)
added_node.add_child(removed_node)
#Function to insert a node some % along a branch, taking into account the ckm distances and nodes already created in the NJ tree (and what distance their descendants are from everyone else)
def insert_hyp_node(t, leaf_name, percent, ckm_ave_train_dist, org_names):
dists = map(lambda y: abs(y - percent), ckm_ave_train_dist[leaf_name])
nearby_indicies = list()
#Add all the organisms that are within 0.05 of the given percent
# for i in range(len(dists)):
# if dists[i]<=.05:
# nearby_indicies.append(i)
nearby_names = list()
#If there are no nearby indicies, add the closest organism to the given percent
if nearby_indicies == []:
nearby_names.append(org_names[dists.index(min(dists))])
else:
for i in range(len(nearby_indicies)):
nearby_names.append(org_names[i])
mean_dist = np.mean(
map(lambda y: ckm_ave_train_dist[leaf_name][org_names.index(y)],
nearby_names))
nearby_names.append(leaf_name)
LCA = t.get_common_ancestor(nearby_names)
LCA_to_leaf_dist = t.get_distance(LCA, leaf_name)
#divide the dist to the right/left of the LCA node by the number of percentage points in there
if LCA.name == t.name:
percent_dist = percent * LCA_to_leaf_dist
if mean_dist <= percent:
child_node = (t & leaf_name)
else:
child_node = (
t & nearby_names[0]
) #This means "go up from root" in the direction of the nearest guy
ancestor_node = (t & child_node.name).up
elif mean_dist <= percent:
percent_dist = t.get_distance(LCA) + abs(percent - mean_dist) * (
LCA_to_leaf_dist) / (1 - mean_dist)
child_node = (t & leaf_name)
ancestor_node = (t & child_node.name).up
else:
percent_dist = t.get_distance(LCA) - abs(percent - mean_dist) * (
t.get_distance(LCA)) / (mean_dist)
child_node = (t & leaf_name)
ancestor_node = (t & child_node.name).up
while t.get_distance(t.name, ancestor_node) > percent_dist:
child_node = ancestor_node
ancestor_node = (t & child_node.name).up
insert_node(t, leaf_name + "_" + str(percent), child_node.name,
percent_dist - t.get_distance(t.name, ancestor_node))
#Set outgroup
if outgroup in names:
t.set_outgroup(
t & outgroup
) #I will need to check that this outgroup is actually one of the names...
else:
print("WARNING: the chosen outgroup " + outgroup +
" is not in the given taxonomy: ")
print(names)
print(
"Proceeding without setting an outgroup. This may cause results to be uninterpretable."
)
#Insert hypothetical nodes
hyp_node_names = dict()
cutoffs = [.9, .8, .7, .6, .5, .4, .3, .2, .1]
cutoffs = [
-.5141 * (val**3) + 1.0932 * (val**2) + 0.3824 * val for val in cutoffs
]
for i in range(len(org_names)):
xi = x[i:len(x):len(org_names)]
for j in range(1, len(cutoffs) + 1):
if xi[j] > 0:
insert_hyp_node(t, org_names[i], cutoffs[j - 1],
ckm_ave_train_dist, org_names)
hyp_node_names[org_names[i] + "_" + str(cutoffs[j - 1])] = [
org_names[i], cutoffs[j - 1], j - 1
] #in case there are "_" in the file names
size_factor = 250
font_size = 55
#Now put the bubbles on the nodes
def layout(node):
node_style = NodeStyle()
node_style["hz_line_width"] = 10
node_style["vt_line_width"] = 10
node.set_style(node_style)
#print(node)
if node.is_leaf():
if node.name in org_names:
#make reconstructed bubble
size = x[org_names.index(node.name)]
F = CircleFace(radius=size_factor * math.sqrt(size),
color="RoyalBlue",
style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F, node, 0, position="branch-right")
#Denote that this was a training organism
nameFace = AttrFace("name", fsize=font_size, fgcolor='black')
faces.add_face_to_node(nameFace,
node,
0,
position="branch-right")
elif node.name in hyp_node_names: #Otherwise it's a hypothetical node, just use recon x
node_base_name = hyp_node_names[node.name][0]
percent = hyp_node_names[node.name][1]
if node_base_name in org_names:
idx = hyp_node_names[node.name][2]
size = x[org_names.index(node_base_name) +
(idx + 1) * len(org_names)]
F = CircleFace(radius=size_factor * math.sqrt(size),
color="RoyalBlue",
style="sphere")
F.border.width = None
F.opacity = 0.6
faces.add_face_to_node(F, node, 0, position="branch-right")
#This is if I want the names of the hypothetical nodes to be printed as well
#nameFace = AttrFace("name", fsize=font_size, fgcolor='black')
#faces.add_face_to_node(nameFace, node, 0, position="branch-right")
else:
size = 0
else:
size = 0
ts = TreeStyle()
ts.layout_fn = layout
ts.mode = "r"
#ts.mode = "c"
ts.scale = 2 * 1000
ts.show_leaf_name = False
ts.min_leaf_separation = 50
F = CircleFace(radius=.87 * size_factor, color="RoyalBlue", style="sphere")
F.border.width = None
F.opacity = 0.6
ts.legend.add_face(F, 0)
ts.legend.add_face(
TextFace(" Inferred relative abundance",
fsize=1.5 * font_size,
fgcolor="Blue"), 1)
ts.legend.add_face(
TextFace(" Total absolute abundance depicted " + str(sum_x)[0:8],
fsize=1.5 * font_size,
fgcolor="Black"), 1)
ts.legend_position = 4
#t.show(tree_style=ts)
t.render(outfile, w=550, units="mm", tree_style=ts)
#Redner the XML file
project = Phyloxml()
phylo = phyloxml.PhyloxmlTree(newick=t.write(format=0, features=[]))
project.add_phylogeny(phylo)
project.export(open(outfilexml, 'w'))