def render(self, fname, layout=None, tree_style=None, palette=None):
"""
Renders the locus tree and writes the image to file.
:param fname: str
Output file path
:param layout:
:param tree_style:
:param palette:
:return: None
"""
if not palette:
palette = ['#1F77B4', '#AEC7E8', '#FF7F0E',
'#FFBB78', '#2CA02C', '#98DF8A',
'#D62728', '#FF9896', '#9467BD',
'#C5B0D5', '#8C564B', '#C49C94',
'#E377C2', '#F7B6D2', '#7F7F7F',
'#C7C7C7', '#BCBD22', '#DBDB8D',
'#17BECF', '#9EDAE5']
if not self.colorized:
self._colorize(palette)
self.colorized = True
if not tree_style:
from ete2 import TreeStyle
tree_style = TreeStyle() # imported during colorizing tree
# tstyle.show_leaf_name = False
tree_style.scale = 28
tree_style.branch_vertical_margin = 6
tree_style.show_branch_length = False
# tstyle.show_branch_support = True
tree_style.show_scale = False
self.L.convert_to_ultrametric()
self.L.render(file_name=fname, tree_style=tree_style)
def render_annotate(newick_path, output_path):
"""Render the annotated tree, showing internal node names.
The output_path should end in .PNG, .PDF or .SVG: this will determine the format.
To aid in testing, if output_path is None, the tree is shown rather than rendered.
"""
tree = Tree(newick_path, format=1)
ts = TreeStyle()
ts.show_leaf_name = True
ts.branch_vertical_margin = 15
ns = NodeStyle()
ns["size"] = 1
edge = 0
for node in tree.traverse():
node.name = node.name.replace("'", "")
node.name = node.name.replace("+", ",")
if not node.is_leaf() and node.name != "NoName":
f = TextFace(node.name)
f.margin_top = 5
f.margin_bottom = 5
f.margin_right = 10
f.margin_left = 10
edge += 1
node.add_face(f, column=0, position="branch-top")
if output_path is None:
tree.show(tree_style=ts)
else:
tree.render(output_path)
def make_tree(treefile, image_file, clone_info):
colour_list = ['MidnightBlue','RoyalBlue', 'LightSkyBlue', 'Aquamarine', 'SpringGreen', 'GreenYellow',\
'Gold','DarkOrange']
weeks = ['16', '30', '38', '48', '59', '119', '176', '206']
weeks = ['6', '14', '53', '92','144']
t = Tree(treefile,format = 1)
ts = TreeStyle()
for i in range(5):
ts.legend.add_face(CircleFace(20, colour_list[i]), column=0)
ts.legend.add_face(TextFace('week' + weeks[i]), column=1)
ts.legend_position = 2
ts.show_leaf_name = True
ts.branch_vertical_margin = 15
ts.rotation = 90
ns = NodeStyle()
ns["size"] = 1
ns.hz_line_width = 10
ns.vt_line_width = 10
edge = 0
for node in t.traverse():
node.name = node.name.replace("'", "")
node.name = node.name.replace(".", ",")
name = node.name.split(' ')[0]
print name
if name in clone_info.keys():
style_node(node, colour_list[int(clone_info[name][0])-1], int(int(clone_info[name][1])/10)+5)
if not node.is_leaf() and node.name != 'NoName':
f = TextFace(node.name)
f.margin_top = 2.5
f.margin_bottom = 2.5
f.margin_right = 2.5
f.margin_left = 2.5
node.add_face(f, column=0, position="branch-top")
t.render(image_file, tree_style = ts)
def render_annotate(newick_path, output_path):
"""Render the annotated tree, showing internal node names.
The output_path should end in .PNG, .PDF or .SVG: this will determine the format.
To aid in testing, if output_path is None, the tree is shown rather than rendered.
"""
tree = Tree(newick_path, format=1)
ts = TreeStyle()
ts.show_leaf_name = True
ts.branch_vertical_margin = 15
ns = NodeStyle()
ns["size"] = 1
edge = 0
for node in tree.traverse():
node.name = node.name.replace("'", "")
node.name = node.name.replace("+", ",")
if not node.is_leaf() and node.name != 'NoName':
f = TextFace(node.name)
f.margin_top = 5
f.margin_bottom = 5
f.margin_right = 10
f.margin_left = 10
edge += 1
node.add_face(f, column=0, position="branch-top")
if output_path is None:
tree.show(tree_style=ts)
else:
tree.render(output_path)
def draw_tree(tree, file):
root = tree.get_midpoint_outgroup()
try:
tree.set_outgroup(root)
except:
pass
root = tree.get_tree_root()
root.dist = 0
add_sig(tree)
ts = TreeStyle()
ts.branch_vertical_margin = 1
#ts.scale = 1500
ts.show_leaf_name = False
#ts.show_branch_support = True
leg_file = path.join(path.expanduser('~'), 'Perl', 'Modules', 'TreeLegend.png')
leg_face= ImgFace(img_file=leg_file)
leg_face.margin_left, leg_face.margin_top = 5, 5
ts.legend.add_face(leg_face, column=1)
ts.legend_position=1
title_face = TextFace(text=file.split('.')[0])
title_face.margin_left, title_face.margin_top = 10, 5
ts.title.add_face(title_face, column=1)
(ts.margin_left, ts.margin_right) = (5,5)
tree.render(file, tree_style=ts, w=6000, units='mm')
def show(self, tree_style=None, palette=None):
"""
Starts an interactive session to visualize the decomposition.
:return: None
"""
if not palette:
palette = ['#1F77B4', '#AEC7E8', '#FF7F0E',
'#FFBB78', '#2CA02C', '#98DF8A',
'#D62728', '#FF9896', '#9467BD',
'#C5B0D5', '#8C564B', '#C49C94',
'#E377C2', '#F7B6D2', '#7F7F7F',
'#C7C7C7', '#BCBD22', '#DBDB8D',
'#17BECF', '#9EDAE5']
if not self.colorized:
self._colorize(palette)
self.colorized = True
if not tree_style:
from ete2 import TreeStyle
tree_style = TreeStyle()
# tstyle.show_leaf_name = False
tree_style.scale = 28
tree_style.branch_vertical_margin = 6
tree_style.show_branch_length = False
# tstyle.show_branch_support = True
tree_style.show_scale = False
self.L.convert_to_ultrametric()
self.L.show(tree_style=tree_style)
def plotTree(self, tree, out_fn=None, rotation=270, show_leaf_name=False,
show_branch_length=False, circularTree=False, show_division_nodes=True,
distance_between_branches=4, show_border=False, width=None, height=None):
from ete2 import TreeStyle
from PyQt4 import QtSvg, QtCore, QtGui
from ete2.treeview import qt4_render, drawer, main
ts = TreeStyle()
ts.show_scale = False
ts.show_border = show_border
ts.orientation = 1 # 0, tree is drawn from left-to-right. 1, tree is drawn from right-to-left
ts.rotation = rotation
ts.show_leaf_name = show_leaf_name
ts.show_branch_length = show_branch_length
if circularTree:
ts.mode = 'c'
else:
ts.mode = 'r'
ts.branch_vertical_margin = distance_between_branches
def hideInternalNodesLayout(node):
if not node.is_leaf():
node.img_style["size"] = 0
if show_division_nodes is False:
ts.layout_fn = hideInternalNodesLayout
if out_fn is not None:
scene = qt4_render._TreeScene()
img = ts
tree_item, n2i, n2f = qt4_render.render(tree, img)
scene.init_data(tree, img, n2i, n2f)
tree_item.setParentItem(scene.master_item)
scene.master_item.setPos(0,0)
scene.addItem(scene.master_item)
main.save(scene, out_fn, w=width, h=height, dpi=600)
else:
scene, img = drawer.init_scene(tree, None, ts)
tree_item, n2i, n2f = qt4_render.render(tree, img)
scene.init_data(tree, img, n2i, n2f)
tree_item.setParentItem(scene.master_item)
scene.addItem(scene.master_item)
size = tree_item.rect()
w, h = size.width(), size.height()
svg = QtSvg.QSvgGenerator()
svg.setFileName("test.svg")
svg.setSize(QtCore.QSize(w, h))
svg.setViewBox(size)
pp = QtGui.QPainter()
pp.begin(svg)
scene.render(pp, tree_item.rect(), tree_item.rect(), QtCore.Qt.KeepAspectRatio)
def plotTree(self, tree, out_fn=None, rotation=270, show_leaf_name=False,
show_branch_length=False, circularTree=False, show_division_nodes=True,
distance_between_branches=4, show_border=False, width=None, height=None):
from ete2 import TreeStyle
from PyQt4 import QtSvg, QtCore, QtGui
from ete2.treeview import qt4_render, drawer, main
ts = TreeStyle()
ts.show_scale = False
ts.show_border = show_border
ts.orientation = 1 # 0, tree is drawn from left-to-right. 1, tree is drawn from right-to-left
ts.rotation = rotation
ts.show_leaf_name = show_leaf_name
ts.show_branch_length = show_branch_length
if circularTree:
ts.mode = 'c'
else:
ts.mode = 'r'
ts.branch_vertical_margin = distance_between_branches
def hideInternalNodesLayout(node):
if not node.is_leaf():
node.img_style["size"] = 0
if show_division_nodes is False:
ts.layout_fn = hideInternalNodesLayout
if out_fn is not None:
scene = qt4_render._TreeScene()
img = ts
tree_item, n2i, n2f = qt4_render.render(tree, img)
scene.init_data(tree, img, n2i, n2f)
tree_item.setParentItem(scene.master_item)
scene.master_item.setPos(0,0)
scene.addItem(scene.master_item)
main.save(scene, out_fn, w=width, h=height, dpi=600)
else:
scene, img = drawer.init_scene(tree, None, ts)
tree_item, n2i, n2f = qt4_render.render(tree, img)
scene.init_data(tree, img, n2i, n2f)
tree_item.setParentItem(scene.master_item)
scene.addItem(scene.master_item)
size = tree_item.rect()
w, h = size.width(), size.height()
svg = QtSvg.QSvgGenerator()
svg.setFileName("test.svg")
svg.setSize(QtCore.QSize(w, h))
svg.setViewBox(size)
pp = QtGui.QPainter()
pp.begin(svg)
scene.render(pp, tree_item.rect(), tree_item.rect(), QtCore.Qt.KeepAspectRatio)
def draw_ete_tree(self,
corpus,
fontsize=5,
color_leafs=False,
save_newick=True,
mode='c',
outputfile=None,
return_svg=True,
show=False,
save=False):
root = self.to_ete(labels=corpus.titles)
def layout(node):
if node.is_leaf():
N = AttrFace("name", fsize=7)
faces.add_face_to_node(faces.AttrFace("name", "Arial", 10,
None),
node,
0,
position='branch-right')
# problems: aligment of labels to branch, left padding of labels
ts = TreeStyle()
ts.mode = mode
ts.show_leaf_name = False
ts.scale = 120
ts.show_scale = False
ts.branch_vertical_margin = 10
nstyle = NodeStyle()
nstyle["fgcolor"] = "#0f0f0f"
nstyle["size"] = 0
nstyle["vt_line_color"] = "#0f0f0f"
nstyle["hz_line_color"] = "#0f0f0f"
nstyle["vt_line_width"] = 1
nstyle["hz_line_width"] = 1
nstyle["vt_line_type"] = 0
nstyle["hz_line_type"] = 0
for n in root.traverse():
n.set_style(nstyle)
ts.layout_fn = layout
if outputfile:
outputfile = os.path.expanduser(outputfile)
if save_newick: # save tree in newick format for later manipulation in e.g. FigTree:
root.write(outfile=os.path.splitext(outputfile)[0] + '.newick')
if save:
root.render(outputfile, tree_style=ts)
if show:
root.show(tree_style=ts)
if return_svg: # return the SVG as a string
return root.render("%%return")[0]
def draw_tree(tree, file):
ts = TreeStyle()
ts.branch_vertical_margin = 1
ts.show_leaf_name = False
if '.svg' in file:
ts.scale = 3000
tree.render(file, tree_style=ts, h=300, units='mm')
else:
ts.scale = 1500
tree.render(file, tree_style=ts, w=3000, units='mm')
def load_tree(f_tree, f_align):
# Tree style
ts = TreeStyle()
ts.show_leaf_name = True
ts.show_branch_length = True
ts.show_branch_support = True
ts.branch_vertical_margin = 10
# Load phylogenetic tree
tree = PhyloTree(f_tree.read())
if f_align is not None:
tree.link_to_alignment(f_align.read())
return tree, ts
def drawTree(nwfile, outfile):
from ete2 import Tree, TreeStyle, TextFace
ts = TreeStyle()
ts.show_leaf_name = False
ts.layout_fn = my_layout
ts.branch_vertical_margin = 12.75
ts.orientation = 1
titleFace = TextFace("Phylogenetic Tree", fsize=18, fgcolor="white")
titleFace.margin_top = 15
ts.title.add_face(titleFace, column=1)
t = Tree(nwfile)
t.render(outfile, tree_style=ts)
def drawTree(nwfile, outfile):
from ete2 import Tree, TreeStyle, TextFace
ts = TreeStyle()
ts.show_leaf_name = False
ts.layout_fn = my_layout
ts.branch_vertical_margin = 12.75
ts.orientation = 1
titleFace = TextFace("Phylogenetic Tree", fsize=18, fgcolor="white")
titleFace.margin_top = 15
ts.title.add_face(titleFace, column=1)
t = Tree(nwfile)
t.render(outfile, tree_style=ts)
def get_tree_style(tree_file, abund, rownames):
with open("matrix.txt", "w") as temp:
cols = len(abund[0])
header = "#Names"
for i in xrange(cols):
header += "\tOTU%d" % i
temp.write("%s\n" % header)
for i, row in enumerate(abund):
temp.write("%s\t%s\n" % (rownames[i], '\t'.join([str(i) for i in row])))
t = Tree(tree_file)
t.convert_to_ultrametric(10)
assert isinstance(abund, numpy.ndarray)
assert isinstance(rownames, numpy.ndarray)
ts = TreeStyle()
ts.mode = "r"
ts.show_leaf_name = False
ts.show_scale = False
ts.show_branch_length = False
ts.branch_vertical_margin = 20
ts.force_topology = True
ts.optimal_scale_level = "full"
ts.scale = 50
ts.draw_guiding_lines = True
ts.guiding_lines_type = 0
ts.guiding_lines_color = "black"
for n in t.traverse():
if not n.is_leaf():
nstyle = NodeStyle()
n.set_style(nstyle)
nstyle['size'] = 0
nstyle['hz_line_width'] = 3
nstyle['vt_line_width'] = 3
else:
nstyle = NodeStyle()
n.set_style(nstyle)
nstyle['size'] = 0
nstyle['hz_line_width'] = 3
nstyle['vt_line_width'] = 3
nstyle['fgcolor'] = "Black"
nstyle['shape'] = "square"
name_face = AttrFace("name", fsize=14, ftype="Arial", fgcolor="black", penwidth=10, text_prefix=" ", text_suffix=" ")
n.add_face(name_face, column=0, position="aligned")
row_index = rownames.tolist().index(n.name)
col = 1
for i in xrange(10):
col += 1
n.add_face(CircleFace(5, color=get_color(abund, row_index, i)), column=col, position="aligned")
return t, ts
def get_tree_style(scale=None, vertical_margin=None):
"""Setups the tree-style used when rendering the tree"""
style = TreeStyle()
style.show_leaf_name = False
if scale:
style.scale = scale
style.show_border = True
if vertical_margin:
style.branch_vertical_margin = vertical_margin
return style
def draw_ete_tree(self, corpus, fontsize=5,
color_leafs=False,
save_newick=True, mode='c',
outputfile=None,
return_svg=True, show=False,
save=False):
root = self.to_ete(labels=corpus.titles)
def layout(node):
if node.is_leaf():
N = AttrFace("name", fsize=7)
faces.add_face_to_node(faces.AttrFace("name","Arial",10, None), node, 0, position='branch-right')
# problems: aligment of labels to branch, left padding of labels
ts = TreeStyle()
ts.mode = mode
ts.show_leaf_name = False
ts.scale = 120
ts.show_scale = False
ts.branch_vertical_margin = 10
nstyle = NodeStyle()
nstyle["fgcolor"] = "#0f0f0f"
nstyle["size"] = 0
nstyle["vt_line_color"] = "#0f0f0f"
nstyle["hz_line_color"] = "#0f0f0f"
nstyle["vt_line_width"] = 1
nstyle["hz_line_width"] = 1
nstyle["vt_line_type"] = 0
nstyle["hz_line_type"] = 0
for n in root.traverse():
n.set_style(nstyle)
ts.layout_fn = layout
if outputfile:
outputfile = os.path.expanduser(outputfile)
if save_newick: # save tree in newick format for later manipulation in e.g. FigTree:
root.write(outfile=os.path.splitext(outputfile)[0]+'.newick')
if save:
root.render(outputfile, tree_style=ts)
if show:
root.show(tree_style=ts)
if return_svg: # return the SVG as a string
return root.render("%%return")[0]
def get_tree_style(scale=None, vertical_margin=None):
"""Setups the tree-style used when rendering the tree"""
style = TreeStyle()
style.show_leaf_name = False
if scale:
style.scale = scale
style.show_border = True
if vertical_margin:
style.branch_vertical_margin = vertical_margin
return style
def draw_significant_expansion_contraction(
self, outfile_prefix="significant_expansion_contraction_tree"):
tree = self.tree
for node in tree.traverse():
node.img_style["size"] = 0
def layout(node):
if node.up is not None:
attr = AttrFace("significant_expansion",
fsize=7,
fgcolor="green",
text_prefix="+")
faces.add_face_to_node(attr, node, 0, position="branch-top")
attr = AttrFace("significant_contraction",
fsize=7,
fgcolor="red",
text_prefix="-")
faces.add_face_to_node(attr, node, 0, position="branch-bottom")
if node.is_leaf():
attr = AttrFace("name",
fsize=10,
fgcolor="black",
text_prefix=" ",
fstyle="italic")
faces.add_face_to_node(attr, node, 0, position="aligned")
ts = TreeStyle()
ts.layout_fn = layout
ts.optimal_scale_level = "full"
ts.branch_vertical_margin = 10
ts.show_leaf_name = False
#ts.allow_face_overlap =True
tree.render("%s.png" % outfile_prefix,
w=200,
units='mm',
tree_style=ts,
dpi=1200)
tree.render("%s.svg" % outfile_prefix,
w=200,
units='mm',
tree_style=ts,
dpi=1200)
def drawete2PhylTree(treeFilePath):
tree = Tree(treeFilePath)
treeStyle = TreeStyle()
treeStyle.show_scale = False
#treeStyle.margin_left = 0
#treeStyle.margin_right = 0
#treeStyle.margin_top = 0
#treeStyle.margin_bottom = 0
#treeStyle.tree_width = treeWidth
no_of_nodes = countNodes(tree)
treeStyle.scale = 120#finalImageHeightinMM/no_of_nodes
treeStyle.branch_vertical_margin = 10#finalImageHeightinMM/no_of_nodes
#treeStyle.draw_aligned_faces_as_table = False
tree = changeNodeStyle(tree)
#tree.img_style["size"] = 30
#tree.img_style["fgcolor"] = "blue"
#tree.show(tree_style=treeStyle)
tree.render("tree.PNG",tree_style=treeStyle,units="mm")
def render_tree_image(self, filename):
def my_layout(node):
name_faces = AttrFace("name", fsize=10, fgcolor = "#0000FF")
faces.add_face_to_node(name_faces, node, column=0, position="branch-right")
t = Tree("%s;" % self.newick_string(), format = 1)
s = "0"
for n in t.iter_descendants():
text = TextFace(s)
if s == "0": s = "1"
else: s = "0"
text.fgcolor = "#FF0000";
nstyle = NodeStyle()
nstyle['size'] = 15
nstyle['fgcolor'] = "#333"
n.set_style(nstyle)
n.add_face(text, column = 0, position = "branch-top")
ts = TreeStyle()
ts.rotation = 90
ts.show_leaf_name = False
ts.layout_fn = my_layout
ts.margin_left = 0
ts.branch_vertical_margin = 50
ts.show_scale = False
t.render(filename, tree_style = ts, w = 2000)
def main():
args = parse_args()
if args.data:
print "\nReading tree from " + args.tree + " and data matrix from " + args.data
tree = ClusterTree(args.tree, text_array=args.data)
else:
print "\nReading tree from " + args.tree
tree = Tree(args.tree)
if args.midpoint:
R = tree.get_midpoint_outgroup()
tree.set_outgroup(R)
print "- Applying midpoint rooting"
elif args.outgroup:
tree.set_outgroup(tree & args.outgroup)
print "- Rooting using outgroup " + args.outgroup
if not args.no_ladderize:
tree.ladderize()
print "- Ladderizing tree"
table, column_list, column_values = readtable(args, tree.get_leaf_names())
labels = []
if args.labels:
print "\nThese labels will be printed next to each strain:"
for label in args.labels:
if label in column_list:
labels.append(label)
print " " + label
else:
print "WARNING: specified label " + label + " was not found in the columns of the info file provided, " + args.info
# set node styles
# start by setting all to no shapes, black labels
for n in tree.traverse():
nstyle = NodeStyle()
nstyle["fgcolor"] = "black"
nstyle["size"] = 0
n.set_style(nstyle)
# add colour tags next to nodes
if args.colour_tags:
colour_tags = []
print "\nThese columns will be used to generate colour tags:"
for label in args.colour_tags:
if label in column_list:
colour_tags.append(label)
print " " + label
else:
print "\tWARNING: specified label for colour tagging, " + label + ", was not found in the columns of the info file provided, " + args.info
print(colour_tags)
print("here")
for i in range(0, len(colour_tags)):
label = colour_tags[i]
print(label)
colour_dict = getColourPalette(column_values[label], args, label)
print "- Adding colour tag for " + label
for node in tree.get_leaves():
this_face = Face()
this_face.margin_left = args.padding
node.add_face(this_face, column=0, position="aligned")
if node.name in table:
this_label = table[node.name][label]
this_colour = colour_dict[this_label]
else:
this_colour = "white"
this_face = Face()
this_face.background.color = this_colour
this_face.margin_right = args.margin_right
this_face.margin_left = args.margin_left
this_face.margin_top = args.margin_top
this_face.margin_bottom = args.margin_bottom
this_face.border.width = args.border_width
this_face.border.color = "white"
node.add_face(this_face, column=i + 1, position="aligned")
print
else:
colour_tags = []
# add labels as columns
for i in range(0, len(labels)):
label = labels[i]
print "- Adding label " + label
if label == args.colour_nodes_by:
print " also colouring nodes by these values"
print(column_values)
print(args)
colour_dict = getColourPalette(column_values[label], args, label)
for node in tree.get_leaves():
if node.name in table:
this_label = table[node.name][label]
this_colour = colour_dict[this_label]
else:
this_label = ""
this_colour = "black"
this_face = TextFace(text=this_label, fsize=args.font_size)
if args.tags:
this_face.background.color = this_colour
elif label == args.colour_nodes_by:
this_face.fgcolor = this_colour
this_face.margin_right = args.padding
if i == 0:
this_face.margin_left = args.padding
node.add_face(this_face,
column=i + len(colour_tags) + 1,
position="aligned")
# set leaves to coloured circles
node.img_style["size"] = args.node_size
if label == args.colour_nodes_by:
node.img_style["fgcolor"] = this_colour
if args.colour_branches_by or args.colour_backgrounds_by or args.branch_support_colour:
if args.colour_branches_by:
print "- Colouring branches by label " + args.colour_branches_by
colour_dict_br = getColourPalette(
column_values[args.colour_branches_by], args,
args.colour_branches_by)
if args.colour_backgrounds_by:
print "- Colouring node backgrounds by label " + args.colour_backgrounds_by
colour_dict_bg = getColourPalette(
column_values[args.colour_backgrounds_by], args,
args.colour_backgrounds_by)
if args.branch_support_colour:
print "- Colouring branches by support values"
# colours extracted from R using rgb( colorRamp(c("white","red", "black"))(seq(0, 1, length = 100)), max = 255)
# support_colours = {0.0:"#FFFFFF",0.01:"#FFFFFF", 0.02:"#FFF9F9", 0.03:"#FFF4F4", 0.04:"#FFEFEF", 0.05:"#FFEAEA", 0.06:"#FFE5E5", 0.07:"#FFE0E0", 0.08:"#FFDADA", 0.09:"#FFD5D5", 0.1:"#FFD0D0", 0.11:"#FFCBCB", 0.12:"#FFC6C6", 0.13:"#FFC1C1", 0.14:"#FFBCBC", 0.15:"#FFB6B6", 0.16:"#FFB1B1", 0.17:"#FFACAC", 0.18:"#FFA7A7", 0.19:"#FFA2A2", 0.2:"#FF9D9D", 0.21:"#FF9797", 0.22:"#FF9292", 0.23:"#FF8D8D", 0.24:"#FF8888", 0.25:"#FF8383", 0.26:"#FF7E7E", 0.27:"#FF7979", 0.28:"#FF7373", 0.29:"#FF6E6E", 0.3:"#FF6969", 0.31:"#FF6464", 0.32:"#FF5F5F", 0.33:"#FF5A5A", 0.34:"#FF5454", 0.35:"#FF4F4F", 0.36:"#FF4A4A", 0.37:"#FF4545", 0.38:"#FF4040", 0.39:"#FF3B3B", 0.4:"#FF3636", 0.41:"#FF3030", 0.42:"#FF2B2B", 0.43:"#FF2626", 0.44:"#FF2121", 0.45:"#FF1C1C", 0.46:"#FF1717", 0.47:"#FF1212", 0.48:"#FF0C0C", 0.49:"#FF0707", 0.5:"#FF0202", 0.51:"#FC0000", 0.52:"#F70000", 0.53:"#F20000", 0.54:"#EC0000", 0.55:"#E70000", 0.56:"#E20000", 0.57:"#DD0000", 0.58:"#D80000", 0.59:"#D30000", 0.6:"#CE0000", 0.61:"#C80000", 0.62:"#C30000", 0.63:"#BE0000", 0.64:"#B90000", 0.65:"#B40000", 0.66:"#AF0000", 0.67:"#A90000", 0.68:"#A40000", 0.69:"#9F0000", 0.7:"#9A0000", 0.71:"#950000", 0.72:"#900000", 0.73:"#8B0000", 0.74:"#850000", 0.75:"#800000", 0.76:"#7B0000", 0.77:"#760000", 0.78:"#710000", 0.79:"#6C0000", 0.8:"#670000", 0.81:"#610000", 0.82:"#5C0000", 0.83:"#570000", 0.84:"#520000", 0.85:"#4D0000", 0.86:"#480000", 0.87:"#420000", 0.88:"#3D0000", 0.89:"#380000", 0.9:"#330000", 0.91:"#2E0000", 0.92:"#290000", 0.93:"#240000", 0.94:"#1E0000", 0.95:"#190000", 0.96:"#140000", 0.97:"#0F0000", 0.98:"#0A0000", 0.99:"#050000", 1:"#000000"}
# rgb( colorRamp(c("red", "black"))(seq(0, 1, length = 100)), max = 255))
support_colours = {}
if args.branch_support_cutoff:
for i in range(0, args.branch_support_cutoff):
support_colours[i] = "#FF0000"
for i in range(args.branch_support_cutoff, 101):
support_colours[i] = "#000000"
else:
if args.branch_support_percent:
support_colours = {
0: "#FF0000",
1: "#FF0000",
2: "#FC0000",
3: "#F90000",
4: "#F70000",
5: "#F40000",
6: "#F20000",
7: "#EF0000",
8: "#EC0000",
9: "#EA0000",
10: "#E70000",
11: "#E50000",
12: "#E20000",
13: "#E00000",
14: "#DD0000",
15: "#DA0000",
16: "#D80000",
17: "#D50000",
18: "#D30000",
19: "#D00000",
20: "#CE0000",
21: "#CB0000",
22: "#C80000",
23: "#C60000",
24: "#C30000",
25: "#C10000",
26: "#BE0000",
27: "#BC0000",
28: "#B90000",
29: "#B60000",
30: "#B40000",
31: "#B10000",
32: "#AF0000",
33: "#AC0000",
34: "#AA0000",
35: "#A70000",
36: "#A40000",
37: "#A20000",
38: "#9F0000",
39: "#9D0000",
40: "#9A0000",
41: "#970000",
42: "#950000",
43: "#920000",
44: "#900000",
45: "#8D0000",
46: "#8B0000",
47: "#880000",
48: "#850000",
49: "#830000",
50: "#800000",
51: "#7E0000",
52: "#7B0000",
53: "#790000",
54: "#760000",
55: "#730000",
56: "#710000",
57: "#6E0000",
58: "#6C0000",
59: "#690000",
60: "#670000",
61: "#640000",
62: "#610000",
63: "#5F0000",
64: "#5C0000",
65: "#5A0000",
66: "#570000",
67: "#540000",
68: "#520000",
69: "#4F0000",
70: "#4D0000",
71: "#4A0000",
72: "#480000",
73: "#450000",
74: "#420000",
75: "#400000",
76: "#3D0000",
77: "#3B0000",
78: "#380000",
79: "#360000",
80: "#330000",
81: "#300000",
82: "#2E0000",
83: "#2B0000",
84: "#290000",
85: "#260000",
86: "#240000",
87: "#210000",
88: "#1E0000",
89: "#1C0000",
90: "#190000",
91: "#170000",
92: "#140000",
93: "#120000",
94: "#0F0000",
95: "#0C0000",
96: "#0A0000",
97: "#070000",
98: "#050000",
99: "#020000",
100: "#000000"
}
else:
support_colours = {
0.0: "#FF0000",
0.01: "#FF0000",
0.02: "#FC0000",
0.03: "#F90000",
0.04: "#F70000",
0.05: "#F40000",
0.06: "#F20000",
0.07: "#EF0000",
0.08: "#EC0000",
0.09: "#EA0000",
0.1: "#E70000",
0.11: "#E50000",
0.12: "#E20000",
0.13: "#E00000",
0.14: "#DD0000",
0.15: "#DA0000",
0.16: "#D80000",
0.17: "#D50000",
0.18: "#D30000",
0.19: "#D00000",
0.2: "#CE0000",
0.21: "#CB0000",
0.22: "#C80000",
0.23: "#C60000",
0.24: "#C30000",
0.25: "#C10000",
0.26: "#BE0000",
0.27: "#BC0000",
0.28: "#B90000",
0.29: "#B60000",
0.3: "#B40000",
0.31: "#B10000",
0.32: "#AF0000",
0.33: "#AC0000",
0.34: "#AA0000",
0.35: "#A70000",
0.36: "#A40000",
0.37: "#A20000",
0.38: "#9F0000",
0.39: "#9D0000",
0.4: "#9A0000",
0.41: "#970000",
0.42: "#950000",
0.43: "#920000",
0.44: "#900000",
0.45: "#8D0000",
0.46: "#8B0000",
0.47: "#880000",
0.48: "#850000",
0.49: "#830000",
0.5: "#800000",
0.51: "#7E0000",
0.52: "#7B0000",
0.53: "#790000",
0.54: "#760000",
0.55: "#730000",
0.56: "#710000",
0.57: "#6E0000",
0.58: "#6C0000",
0.59: "#690000",
0.6: "#670000",
0.61: "#640000",
0.62: "#610000",
0.63: "#5F0000",
0.64: "#5C0000",
0.65: "#5A0000",
0.66: "#570000",
0.67: "#540000",
0.68: "#520000",
0.69: "#4F0000",
0.7: "#4D0000",
0.71: "#4A0000",
0.72: "#480000",
0.73: "#450000",
0.74: "#420000",
0.75: "#400000",
0.76: "#3D0000",
0.77: "#3B0000",
0.78: "#380000",
0.79: "#360000",
0.8: "#330000",
0.81: "#300000",
0.82: "#2E0000",
0.83: "#2B0000",
0.84: "#290000",
0.85: "#260000",
0.86: "#240000",
0.87: "#210000",
0.88: "#1E0000",
0.89: "#1C0000",
0.9: "#190000",
0.91: "#170000",
0.92: "#140000",
0.93: "#120000",
0.94: "#0F0000",
0.95: "#0C0000",
0.96: "#0A0000",
0.97: "#070000",
0.98: "#050000",
0.99: "#020000",
1.0: "#000000"
}
for node in tree.traverse():
nstyle = NodeStyle()
nstyle["size"] = 0
if node.name in table:
#print "Colouring individual " + node.name
if args.colour_branches_by:
nstyle["vt_line_color"] = colour_dict_br[table[node.name][
args.colour_branches_by]] # set branch colour
nstyle["hz_line_color"] = colour_dict_br[table[node.name][
args.colour_branches_by]]
if args.colour_backgrounds_by:
if args.colour_branches_by in table[node.name]:
if table[node.name][args.colour_branches_by] != "none":
if not args.colour_branches_by:
nstyle["hz_line_color"] = "black"
nstyle["vt_line_color"] = "black"
nstyle["bgcolor"] = colour_dict_bg[table[node.name][
args.
colour_backgrounds_by]] # set background colour
node.set_style(nstyle)
else:
# internal node
descendants = node.get_leaves()
descendant_labels_br = []
descendant_labels_bg = []
for d in descendants:
if args.colour_branches_by:
if d.name in table:
this_label_br = table[d.name][
args.colour_branches_by]
if this_label_br not in descendant_labels_br:
descendant_labels_br.append(this_label_br)
elif "none" not in descendant_labels_br:
descendant_labels_br.append("none")
if args.colour_backgrounds_by:
if d.name in table:
this_label_bg = table[d.name][
args.colour_backgrounds_by]
if this_label_bg not in descendant_labels_bg:
descendant_labels_bg.append(this_label_bg)
elif "none" not in descendant_labels_bg:
descendant_labels_bg.append("none")
# nstyle = NodeStyle()
# nstyle["size"] = 0
if len(descendant_labels_br
) == 1 and descendant_labels_br[0] != "none":
this_colour = colour_dict_br[descendant_labels_br[0]]
nstyle["vt_line_color"] = this_colour # set branch colour
nstyle["hz_line_color"] = this_colour
elif args.branch_support_colour and not node.is_leaf():
if int(node.support) in support_colours:
nstyle["vt_line_color"] = support_colours[int(
node.support)] # take colour from support value
nstyle["hz_line_color"] = support_colours[int(
node.support)]
else:
print " WARNING support values don't make sense. Note scale is assumed to be 0-1 unless using the --branch_support_percent flag."
if len(descendant_labels_bg
) == 1 and descendant_labels_bg[0] != "none":
this_colour = colour_dict_bg[descendant_labels_bg[0]]
nstyle["bgcolor"] = this_colour # set background colour
node.set_style(nstyle)
if args.colour_nodes_by:
if args.colour_nodes_by not in labels:
print "- Colouring nodes by label " + args.colour_nodes_by
colour_dict = getColourPalette(column_values[args.colour_nodes_by],
args, args.colour_nodes_by)
for node in tree.get_leaves():
if node.name in table:
this_label = table[node.name][args.colour_nodes_by]
this_colour = colour_dict[this_label]
if this_colour != "None":
node.img_style["fgcolor"] = this_colour
node.img_style["size"] = args.node_size
for node in tree.traverse():
node.img_style["hz_line_width"] = args.branch_thickness
node.img_style["vt_line_width"] = args.branch_thickness
# matches = search_by_size(tree, 75)
# print("matches")
# node = matches[0]
# node.swap_children()
########### COMENTADO PARA VER COMO QUEDA CON EL BARCODE. PORQUE ESE NO TIENE TODOS LOS NODOS
# rotate specific nodes
# matches = search_by_size(tree, 463)
# print("matches")
# node = matches[0]
# node.swap_children()
# matches = search_by_size(tree, 601)
# print("matches")
# node = matches[0]
# node.swap_children()
# matches = search_by_size(node, 7)
# print("matches")
# node = matches[1]
# node.swap_children()
# matches = search_by_size(node, 5)
# print("matches 5")
# node = matches[0]
# node.swap_children()
# matches = search_by_size(tree, 8)
# print("matches 8")
# node = matches[5]
# node.swap_children()
# matches = search_by_size(tree, 349)
# print("matches 349")
# node = matches[0]
# node.swap_children()
# matches = search_by_size(tree, 192)
# print("matches 192")
# node = matches[1]
# node.swap_children()
# matches = search_by_size(tree, 182)
# print("matches 182")
# node = matches[0]
# node.swap_children()
# matches = search_by_size(tree, 180)
# print("matches 180")
# node = matches[0]
# node.swap_children()
# matches = search_by_size(tree, 175)
# print("matches 175")
# node = matches[0]
# node.swap_children()
# matches = search_by_size(tree, 34)
# print("matches 34")
# node = matches[0]
# node.swap_children()
#### FIN ####
#for n in matches:
# print n
# set tree style
ts = TreeStyle()
ts.draw_guiding_lines = True
ts.guiding_lines_color = 'black'
if args.show_leaf_names:
ts.show_leaf_name = True
else:
ts.show_leaf_name = False
if args.length_scale:
ts.scale = args.length_scale
if args.branch_padding:
ts.branch_vertical_margin = args.branch_padding
if args.branch_support_print:
ts.show_branch_support = True
if args.fan:
ts.mode = "c"
print "\nPrinting circular tree (--fan)"
else:
print "\nPrinting rectangular tree, to switch to circular use --fan"
if args.title:
title = TextFace(args.title, fsize=20)
title.margin_left = 20
title.margin_top = 20
ts.title.add_face(title, column=1)
if args.no_guiding_lines:
ts.draw_guiding_lines = False
if args.data:
print "\nPrinting data matrix as " + args.data_type + " with range (" + str(
args.mindata) + "->" + str(args.maxdata) + ";" + str(
args.centervalue) + "), height " + str(
args.data_height) + ", width " + str(args.data_width)
profileFace = ProfileFace(min_v=args.mindata,
max_v=args.maxdata,
center_v=args.centervalue,
width=args.data_width,
height=args.data_height,
style=args.data_type)
def mylayout(node):
if node.is_leaf():
add_face_to_node(profileFace, node, 0, aligned=True)
ts.layout_fn = mylayout
# set root branch length to zero
tree.dist = 0
if args.delete_branches:
#print "Branches "+ args.delete_branches + " will not be shown"
for branch in args.delete_branches:
leaf = tree.get_leaves_by_name(branch)[0] #SRR1173284
leaf.delete()
# render tree
tree.render(args.output, w=args.width, dpi=400, units="mm", tree_style=ts)
print "\n FINISHED! Tree plot printed to file " + args.output
print
if args.print_colour_dict:
print colour_dict
if args.colour_branches_by:
print colour_dict_br
if args.colour_backgrounds_by:
print colour_dict_bg
if args.interactive:
print "\nEntering interactive mode..."
tree.show(tree_style=ts)
def main():
args = parse_args()
if args.data:
print "\nReading tree from " + args.tree + " and data matrix from " + args.data
tree = ClusterTree(args.tree, text_array=args.data)
else:
print "\nReading tree from " + args.tree
tree = Tree(args.tree)
if args.midpoint:
R = tree.get_midpoint_outgroup()
tree.set_outgroup(R)
print "- Applying midpoint rooting"
elif args.outgroup:
tree.set_outgroup( tree&args.outgroup )
print "- Rooting using outgroup " + args.outgroup
if not args.no_ladderize:
tree.ladderize()
print "- Ladderizing tree"
table, column_list, column_values = readtable(args, tree.get_leaf_names())
labels = []
if args.labels:
print "\nThese labels will be printed next to each strain:"
for label in args.labels:
if label in column_list:
labels.append(label)
print " " + label
else:
print "WARNING: specified label " + label + " was not found in the columns of the info file provided, " + args.info
# set node styles
# start by setting all to no shapes, black labels
for n in tree.traverse():
nstyle = NodeStyle()
nstyle["fgcolor"] = "black"
nstyle["size"] = 0
n.set_style(nstyle)
# add colour tags next to nodes
if args.colour_tags:
colour_tags = []
print "\nThese columns will be used to generate colour tags:"
for label in args.colour_tags:
if label in column_list:
colour_tags.append(label)
print " " + label
else:
print "\tWARNING: specified label for colour tagging, " + label + ", was not found in the columns of the info file provided, " + args.info
for i in range(0,len(colour_tags)):
label = colour_tags[i]
colour_dict = getColourPalette(column_values[label],args,label)
print "- Adding colour tag for " + label
for node in tree.get_leaves():
this_face = Face()
this_face.margin_left = args.padding
node.add_face(this_face, column=0, position = "aligned")
if node.name in table:
this_label = table[node.name][label]
this_colour = colour_dict[this_label]
else:
this_colour = "white"
this_face = Face()
this_face.background.color = this_colour
this_face.margin_right = args.margin_right
this_face.margin_left = args.margin_left
this_face.margin_top = args.margin_top
this_face.margin_bottom = args.margin_bottom
this_face.border.width = args.border_width
this_face.border.color="white"
node.add_face(this_face, column=i+1, position = "aligned")
print
else:
colour_tags = []
# add labels as columns
for i in range(0,len(labels)):
label = labels[i]
print "- Adding label " + label
if label == args.colour_nodes_by:
print " also colouring nodes by these values"
colour_dict = getColourPalette(column_values[label],args,label)
for node in tree.get_leaves():
if node.name in table:
this_label = table[node.name][label]
this_colour = colour_dict[this_label]
else:
this_label = ""
this_colour = "black"
this_face = TextFace(text=this_label, fsize = args.font_size)
if args.tags:
this_face.background.color = this_colour
elif label == args.colour_nodes_by:
this_face.fgcolor = this_colour
this_face.margin_right = args.padding
if i == 0:
this_face.margin_left = args.padding
node.add_face(this_face, column=i+len(colour_tags)+1, position = "aligned")
# set leaves to coloured circles
node.img_style["size"] = args.node_size
if label == args.colour_nodes_by:
node.img_style["fgcolor"] = this_colour
if args.colour_branches_by or args.colour_backgrounds_by or args.branch_support_colour:
if args.colour_branches_by:
print "- Colouring branches by label " + args.colour_branches_by
colour_dict_br = getColourPalette(column_values[args.colour_branches_by],args,args.colour_branches_by)
if args.colour_backgrounds_by:
print "- Colouring node backgrounds by label " + args.colour_backgrounds_by
colour_dict_bg = getColourPalette(column_values[args.colour_backgrounds_by],args,args.colour_backgrounds_by)
if args.branch_support_colour:
print "- Colouring branches by support values"
# colours extracted from R using rgb( colorRamp(c("white","red", "black"))(seq(0, 1, length = 100)), max = 255)
# support_colours = {0.0:"#FFFFFF",0.01:"#FFFFFF", 0.02:"#FFF9F9", 0.03:"#FFF4F4", 0.04:"#FFEFEF", 0.05:"#FFEAEA", 0.06:"#FFE5E5", 0.07:"#FFE0E0", 0.08:"#FFDADA", 0.09:"#FFD5D5", 0.1:"#FFD0D0", 0.11:"#FFCBCB", 0.12:"#FFC6C6", 0.13:"#FFC1C1", 0.14:"#FFBCBC", 0.15:"#FFB6B6", 0.16:"#FFB1B1", 0.17:"#FFACAC", 0.18:"#FFA7A7", 0.19:"#FFA2A2", 0.2:"#FF9D9D", 0.21:"#FF9797", 0.22:"#FF9292", 0.23:"#FF8D8D", 0.24:"#FF8888", 0.25:"#FF8383", 0.26:"#FF7E7E", 0.27:"#FF7979", 0.28:"#FF7373", 0.29:"#FF6E6E", 0.3:"#FF6969", 0.31:"#FF6464", 0.32:"#FF5F5F", 0.33:"#FF5A5A", 0.34:"#FF5454", 0.35:"#FF4F4F", 0.36:"#FF4A4A", 0.37:"#FF4545", 0.38:"#FF4040", 0.39:"#FF3B3B", 0.4:"#FF3636", 0.41:"#FF3030", 0.42:"#FF2B2B", 0.43:"#FF2626", 0.44:"#FF2121", 0.45:"#FF1C1C", 0.46:"#FF1717", 0.47:"#FF1212", 0.48:"#FF0C0C", 0.49:"#FF0707", 0.5:"#FF0202", 0.51:"#FC0000", 0.52:"#F70000", 0.53:"#F20000", 0.54:"#EC0000", 0.55:"#E70000", 0.56:"#E20000", 0.57:"#DD0000", 0.58:"#D80000", 0.59:"#D30000", 0.6:"#CE0000", 0.61:"#C80000", 0.62:"#C30000", 0.63:"#BE0000", 0.64:"#B90000", 0.65:"#B40000", 0.66:"#AF0000", 0.67:"#A90000", 0.68:"#A40000", 0.69:"#9F0000", 0.7:"#9A0000", 0.71:"#950000", 0.72:"#900000", 0.73:"#8B0000", 0.74:"#850000", 0.75:"#800000", 0.76:"#7B0000", 0.77:"#760000", 0.78:"#710000", 0.79:"#6C0000", 0.8:"#670000", 0.81:"#610000", 0.82:"#5C0000", 0.83:"#570000", 0.84:"#520000", 0.85:"#4D0000", 0.86:"#480000", 0.87:"#420000", 0.88:"#3D0000", 0.89:"#380000", 0.9:"#330000", 0.91:"#2E0000", 0.92:"#290000", 0.93:"#240000", 0.94:"#1E0000", 0.95:"#190000", 0.96:"#140000", 0.97:"#0F0000", 0.98:"#0A0000", 0.99:"#050000", 1:"#000000"}
# rgb( colorRamp(c("red", "black"))(seq(0, 1, length = 100)), max = 255))
support_colours = {}
if args.branch_support_cutoff:
for i in range(0,args.branch_support_cutoff):
support_colours[i] = "#FF0000"
for i in range(args.branch_support_cutoff,101):
support_colours[i] = "#000000"
else:
if args.branch_support_percent:
support_colours = {0:"#FF0000",1:"#FF0000",2:"#FC0000",3:"#F90000",4:"#F70000",5:"#F40000",6:"#F20000",7:"#EF0000",8:"#EC0000",9:"#EA0000",10:"#E70000",11:"#E50000",12:"#E20000",13:"#E00000",14:"#DD0000",15:"#DA0000",16:"#D80000",17:"#D50000",18:"#D30000",19:"#D00000",20:"#CE0000",21:"#CB0000",22:"#C80000",23:"#C60000",24:"#C30000",25:"#C10000",26:"#BE0000",27:"#BC0000",28:"#B90000",29:"#B60000",30:"#B40000",31:"#B10000",32:"#AF0000",33:"#AC0000",34:"#AA0000",35:"#A70000",36:"#A40000",37:"#A20000",38:"#9F0000",39:"#9D0000",40:"#9A0000",41:"#970000",42:"#950000",43:"#920000",44:"#900000",45:"#8D0000",46:"#8B0000",47:"#880000",48:"#850000",49:"#830000",50:"#800000",51:"#7E0000",52:"#7B0000",53:"#790000",54:"#760000",55:"#730000",56:"#710000",57:"#6E0000",58:"#6C0000",59:"#690000",60:"#670000",61:"#640000",62:"#610000",63:"#5F0000",64:"#5C0000",65:"#5A0000",66:"#570000",67:"#540000",68:"#520000",69:"#4F0000",70:"#4D0000",71:"#4A0000",72:"#480000",73:"#450000",74:"#420000",75:"#400000",76:"#3D0000",77:"#3B0000",78:"#380000",79:"#360000",80:"#330000",81:"#300000",82:"#2E0000",83:"#2B0000",84:"#290000",85:"#260000",86:"#240000",87:"#210000",88:"#1E0000",89:"#1C0000",90:"#190000",91:"#170000",92:"#140000",93:"#120000",94:"#0F0000",95:"#0C0000",96:"#0A0000",97:"#070000",98:"#050000",99:"#020000",100:"#000000"}
else:
support_colours = {0.0:"#FF0000", 0.01:"#FF0000", 0.02:"#FC0000", 0.03:"#F90000", 0.04:"#F70000", 0.05:"#F40000", 0.06:"#F20000", 0.07:"#EF0000", 0.08:"#EC0000", 0.09:"#EA0000", 0.1:"#E70000", 0.11:"#E50000", 0.12:"#E20000", 0.13:"#E00000", 0.14:"#DD0000", 0.15:"#DA0000", 0.16:"#D80000", 0.17:"#D50000", 0.18:"#D30000", 0.19:"#D00000", 0.2:"#CE0000", 0.21:"#CB0000", 0.22:"#C80000", 0.23:"#C60000", 0.24:"#C30000", 0.25:"#C10000", 0.26:"#BE0000", 0.27:"#BC0000", 0.28:"#B90000", 0.29:"#B60000", 0.3:"#B40000", 0.31:"#B10000", 0.32:"#AF0000", 0.33:"#AC0000", 0.34:"#AA0000", 0.35:"#A70000", 0.36:"#A40000", 0.37:"#A20000", 0.38:"#9F0000", 0.39:"#9D0000", 0.4:"#9A0000", 0.41:"#970000", 0.42:"#950000", 0.43:"#920000", 0.44:"#900000", 0.45:"#8D0000", 0.46:"#8B0000", 0.47:"#880000", 0.48:"#850000", 0.49:"#830000", 0.5:"#800000", 0.51:"#7E0000", 0.52:"#7B0000", 0.53:"#790000", 0.54:"#760000", 0.55:"#730000", 0.56:"#710000", 0.57:"#6E0000", 0.58:"#6C0000", 0.59:"#690000", 0.6:"#670000", 0.61:"#640000", 0.62:"#610000", 0.63:"#5F0000", 0.64:"#5C0000", 0.65:"#5A0000", 0.66:"#570000", 0.67:"#540000", 0.68:"#520000", 0.69:"#4F0000", 0.7:"#4D0000", 0.71:"#4A0000", 0.72:"#480000", 0.73:"#450000", 0.74:"#420000", 0.75:"#400000", 0.76:"#3D0000", 0.77:"#3B0000", 0.78:"#380000", 0.79:"#360000", 0.8:"#330000", 0.81:"#300000", 0.82:"#2E0000", 0.83:"#2B0000", 0.84:"#290000", 0.85:"#260000", 0.86:"#240000", 0.87:"#210000", 0.88:"#1E0000", 0.89:"#1C0000", 0.9:"#190000", 0.91:"#170000", 0.92:"#140000", 0.93:"#120000", 0.94:"#0F0000", 0.95:"#0C0000", 0.96:"#0A0000", 0.97:"#070000", 0.98:"#050000", 0.99:"#020000", 1.0:"#000000"}
for node in tree.traverse():
nstyle = NodeStyle()
nstyle["size"] = 0
if node.name in table:
#print "Colouring individual " + node.name
if args.colour_branches_by:
nstyle["vt_line_color"] = colour_dict_br[table[node.name][args.colour_branches_by]] # set branch colour
nstyle["hz_line_color"] = colour_dict_br[table[node.name][args.colour_branches_by]]
if args.colour_backgrounds_by:
if args.colour_branches_by in table[node.name]:
if table[node.name][args.colour_branches_by] != "none":
nstyle["bgcolor"] = colour_dict_bg[table[node.name][args.colour_backgrounds_by]] # set background colour
node.set_style(nstyle)
else:
# internal node
descendants = node.get_leaves()
descendant_labels_br = []
descendant_labels_bg = []
for d in descendants:
if args.colour_branches_by:
if d.name in table:
this_label_br = table[d.name][args.colour_branches_by]
if this_label_br not in descendant_labels_br:
descendant_labels_br.append(this_label_br)
elif "none" not in descendant_labels_br:
descendant_labels_br.append("none")
if args.colour_backgrounds_by:
if d.name in table:
this_label_bg = table[d.name][args.colour_backgrounds_by]
if this_label_bg not in descendant_labels_bg:
descendant_labels_bg.append(this_label_bg)
elif "none" not in descendant_labels_bg:
descendant_labels_bg.append("none")
# nstyle = NodeStyle()
# nstyle["size"] = 0
if len(descendant_labels_br) == 1 and descendant_labels_br[0] != "none":
this_colour = colour_dict_br[descendant_labels_br[0]]
nstyle["vt_line_color"] = this_colour # set branch colour
nstyle["hz_line_color"] = this_colour
elif args.branch_support_colour and not node.is_leaf():
if int(node.support) in support_colours:
nstyle["vt_line_color"] = support_colours[int(node.support)] # take colour from support value
nstyle["hz_line_color"] = support_colours[int(node.support)]
else:
print " WARNING support values don't make sense. Note scale is assumed to be 0-1 unless using the --branch_support_percent flag."
if len(descendant_labels_bg) == 1 and descendant_labels_bg[0] != "none":
this_colour = colour_dict_bg[descendant_labels_bg[0]]
nstyle["bgcolor"] = this_colour # set background colour
node.set_style(nstyle)
if args.colour_nodes_by:
if args.colour_nodes_by not in labels:
print "- Colouring nodes by label " + args.colour_nodes_by
colour_dict = getColourPalette(column_values[args.colour_nodes_by],args,args.colour_nodes_by)
for node in tree.get_leaves():
if node.name in table:
this_label = table[node.name][args.colour_nodes_by]
this_colour = colour_dict[this_label]
if this_colour != "None":
node.img_style["fgcolor"] = this_colour
node.img_style["size"] = args.node_size
for node in tree.traverse():
node.img_style["hz_line_width"] = args.branch_thickness
node.img_style["vt_line_width"] = args.branch_thickness
# set tree style
ts = TreeStyle()
if args.show_leaf_names:
ts.show_leaf_name = True
else:
ts.show_leaf_name = False
if args.length_scale:
ts.scale = args.length_scale
if args.branch_padding:
ts.branch_vertical_margin = args.branch_padding
if args.branch_support_print:
ts.show_branch_support = True
if args.fan:
ts.mode = "c"
print "\nPrinting circular tree (--fan)"
else:
print "\nPrinting rectangular tree, to switch to circular use --fan"
if args.title:
title = TextFace(args.title, fsize=20)
title.margin_left = 20
title.margin_top = 20
ts.title.add_face(title, column=1)
if args.no_guiding_lines:
ts.draw_guiding_lines = False
if args.data:
print "\nPrinting data matrix as " + args.data_type + " with range (" + str(args.mindata) + "->" + str(args.maxdata) + ";" + str(args.centervalue) + "), height " + str(args.data_height) + ", width " + str(args.data_width)
profileFace = ProfileFace(min_v=args.mindata, max_v=args.maxdata, center_v=args.centervalue, width=args.data_width, height=args.data_height, style=args.data_type)
def mylayout(node):
if node.is_leaf():
add_face_to_node(profileFace, node, 0, aligned=True)
ts.layout_fn = mylayout
# set root branch length to zero
tree.dist=0
# render tree
tree.render(args.output, w=args.width, dpi=300, units="mm", tree_style=ts)
print "\n FINISHED! Tree plot printed to file " + args.output
print
if args.print_colour_dict:
print colour_dict
if args.colour_branches_by:
print colour_dict_br
if args.colour_backgrounds_by:
print colour_dict_bg
if args.interactive:
print "\nEntering interactive mode..."
tree.show(tree_style=ts)
fgcolor="green",
text_prefix="")
faces.add_face_to_node(attr, node, 0, position="branch-top")
#ts.show_branch_support = True
tree_index = 1
with open(args.input_tree_file, "r") as in_fd:
for line in in_fd:
tree_line = line.strip()
tree = Tree(tree_line, format=args.input_tree_format)
for node in tree.traverse():
node.img_style["size"] = 0
ts = TreeStyle()
ts.layout_fn = layout
ts.optimal_scale_level = "full"
ts.branch_vertical_margin = 10
ts.show_leaf_name = False
#print(tree.write(format=args.input_tree_format, features=[args.feature_name]))
if args.draw_mode == "render":
tree.render("%s_%i.png" %
(args.output_tree_file_prefix, tree_index),
tree_style=ts,
w=args.width,
units=args.width_units)
else:
tree.show()
tree_index += 1
# configuration # We extend the minimum WebTreeApplication with our own WSGI # application application.set_external_app_handler(example_app) # Lets now apply our custom tree loader function to the main # application application.set_tree_loader(my_tree_loader) # And our layout as the default one to render trees ts = TreeStyle() ts.show_leaf_name = False ts.layout_fn.append(main_layout) ts.mode = "r" ts.branch_vertical_margin = 5 #ts.scale = 20 application.set_tree_style(ts) #application.set_default_layout_fn(main_layout) application.set_tree_size(None, None) # I want to make up how tree image in shown using a custrom tree # renderer that adds much more HTML code application.set_external_tree_renderer(tree_renderer) # ============================================================================== # ADD CUSTOM ACTIONS TO THE APPLICATION # # The function "register_action" allows to attach functionality to # nodes in the image. All registered accions will be shown in the # popup menu bound to the nodes and faces in the web image.
def bct_dendrogram(corpus,
tree,
outputfile=None,
fontsize=5,
save_newick=True,
mode='c',
show=False,
color_leafs=False,
save=False,
return_svg=True):
"""
Draw a dendrogram of the texts in the corpus using ETE.
Parameters
----------
corpus : `Corpus` instance
The corpus to be plotted.
tree : `(VN)Clusterer` object
The clusterer object which was
applied to the corpus.
outputfile : str
The path where the plot should be saved.
color_leafs: boolean, default=True,
If true, will color the text labels
according to their category.
fontsize : int, default=5
The fontsize of the labels on the axes.
save_newick : boolean, default=True
Whether to dump a representation of the
tree in newick-format, which can later
be modified using software like FigTree:
http://tree.bio.ed.ac.uk/software/figtree/
mode : str, default='c'
The type of tree to be drawn. Supports:
- 'c': circular dendrogram
- 'r': traditional, rectangular dendrogram
save : boolean, default=False
Whether to save the plot to `outputfile`.
return_svg : boolean, default=True
Whether to return the plot in SVG-format.
Useful for the GUI.
"""
for leaf in tree.get_leaves():
leaf.name = leaf.name.replace("'", '')
def layout(node):
if node.is_leaf():
N = AttrFace("name", fsize=7)
faces.add_face_to_node(faces.AttrFace("name", "Arial", 10, None),
node,
0,
position='branch-right')
# problems: aligment of labels to branch, left padding of labels
ts = TreeStyle()
ts.mode = mode
ts.show_leaf_name = False
ts.scale = 120
ts.show_scale = False
ts.branch_vertical_margin = 10
nstyle = NodeStyle()
nstyle["fgcolor"] = "#0f0f0f"
nstyle["size"] = 0
nstyle["vt_line_color"] = "#0f0f0f"
nstyle["hz_line_color"] = "#0f0f0f"
nstyle["vt_line_width"] = 1
nstyle["hz_line_width"] = 1
nstyle["vt_line_type"] = 0
nstyle["hz_line_type"] = 0
for n in tree.traverse():
n.set_style(nstyle)
ts.layout_fn = layout
if outputfile:
outputfile = os.path.expanduser(outputfile)
if save_newick: # save tree in newick format for later manipulation in e.g. FigTree:
tree.write(outfile=os.path.splitext(outputfile)[0] + '.newick')
if save:
tree.render(outputfile, tree_style=ts)
if show:
tree.show(tree_style=ts)
if return_svg: # return the SVG as a string
return tree.render("%%return")[0]
def cluster():
fileManager = managers.utility.loadFileManager()
leq = '≤'.decode('utf-8')
if request.method == "GET":
# "GET" request occurs when the page is first loaded.
if 'analyoption' not in session:
session['analyoption'] = constants.DEFAULT_ANALIZE_OPTIONS
if 'hierarchyoption' not in session:
session['hierarchyoption'] = constants.DEFAULT_HIERARCHICAL_OPTIONS
labels = fileManager.getActiveLabels()
thresholdOps = {}
return render_template('cluster.html', labels=labels, thresholdOps=thresholdOps)
if 'getdendro' in request.form:
labelDict = fileManager.getActiveLabels()
labels = []
for ind, label in labelDict.items():
labels.append(label)
# Apply re-tokenisation and filters to DTM
#countMatrix = fileManager.getMatrix(ARGUMENTS OMITTED)
# Get options from request.form
orientation = str(request.form['orientation'])
title = request.form['title']
pruning = request.form['pruning']
pruning = int(request.form['pruning']) if pruning else 0
linkage = str(request.form['linkage'])
metric = str(request.form['metric'])
# Get active files
allContents = [] # list of strings-of-text for each segment
tempLabels = [] # list of labels for each segment
for lFile in fileManager.files.values():
if lFile.active:
contentElement = lFile.loadContents()
allContents.append(contentElement)
if request.form["file_" + str(lFile.id)] == lFile.label:
tempLabels.append(lFile.label.encode("utf-8"))
else:
newLabel = request.form["file_" + str(lFile.id)].encode("utf-8")
tempLabels.append(newLabel)
# More options
ngramSize = int(request.form['tokenSize'])
useWordTokens = request.form['tokenType'] == 'word'
try:
useFreq = request.form['normalizeType'] == 'freq'
useTfidf = request.form['normalizeType'] == 'tfidf' # if use TF/IDF
normOption = "N/A" # only applicable when using "TF/IDF", set default value to N/A
if useTfidf:
if request.form['norm'] == 'l1':
normOption = u'l1'
elif request.form['norm'] == 'l2':
normOption = u'l2'
else:
normOption = None
except:
useFreq = useTfidf = False
normOption = None
onlyCharGramsWithinWords = False
if not useWordTokens: # if using character-grams
# this option is disabled on the GUI, because countVectorizer count front and end markers as ' ' if this is true
onlyCharGramsWithinWords = 'inWordsOnly' in request.form
greyWord = 'greyword' in request.form
MostFrequenWord = 'mfwcheckbox' in request.form
Culling = 'cullcheckbox' in request.form
showDeletedWord = False
if 'greyword' or 'mfwcheckbox' or 'cullcheckbox' in request.form:
if 'onlygreyword' in request.form:
showDeletedWord = True
if useWordTokens:
tokenType = u'word'
else:
tokenType = u'char'
if onlyCharGramsWithinWords:
tokenType = u'char_wb'
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
vectorizer = CountVectorizer(input=u'content', encoding=u'utf-8', min_df=1,
analyzer=tokenType, token_pattern=ur'(?u)\b[\w\']+\b',
ngram_range=(ngramSize, ngramSize),
stop_words=[], dtype=float, max_df=1.0)
# make a (sparse) Document-Term-Matrix (DTM) to hold all counts
DocTermSparseMatrix = vectorizer.fit_transform(allContents)
dtm = DocTermSparseMatrix.toarray()
from sklearn.metrics.pairwise import euclidean_distances
from scipy.cluster.hierarchy import ward
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import average, weighted, ward, single, complete, dendrogram
from scipy.cluster import hierarchy
from scipy.spatial.distance import pdist
if orientation == "left":
orientation = "right"
if orientation == "top":
LEAF_ROTATION_DEGREE = 90
else:
LEAF_ROTATION_DEGREE = 0
if linkage == "ward":
dist = euclidean_distances(dtm)
np.round(dist, 1)
linkage_matrix = ward(dist)
dendrogram(linkage_matrix, orientation=orientation, leaf_rotation=LEAF_ROTATION_DEGREE, labels=labels)
Z = linkage_matrix
else:
Y = pdist(dtm, metric)
Z = hierarchy.linkage(Y, method=linkage)
dendrogram(Z, orientation=orientation, leaf_rotation=LEAF_ROTATION_DEGREE, labels=labels)
plt.tight_layout() # fixes margins
## Conversion to Newick/ETE
# Stuff we need
from scipy.cluster.hierarchy import average, linkage, to_tree
#from hcluster import linkage, to_tree
from ete2 import Tree, TreeStyle, NodeStyle
# Change it to a distance matrix
T = to_tree(Z)
# ete2 section
root = Tree()
root.dist = 0
root.name = "root"
item2node = {T: root}
to_visit = [T]
while to_visit:
node = to_visit.pop()
cl_dist = node.dist /2.0
for ch_node in [node.left, node.right]:
if ch_node:
ch = Tree()
ch.dist = cl_dist
ch.name = str(ch_node.id)
item2node[node].add_child(ch)
item2node[ch_node] = ch
to_visit.append(ch_node)
# This is the ETE tree structure
tree = root
ts = TreeStyle()
ts.show_leaf_name = True
ts.show_branch_length = True
ts.show_scale = False
ts.scale = None
if orientation == "top":
ts.rotation = 90
ts.branch_vertical_margin = 10 # 10 pixels between adjacent branches
# Draws nodes as small red spheres of diameter equal to 10 pixels
nstyle = NodeStyle()
nstyle["size"] = 0
# Replace the node labels
for leaf in tree:
k = leaf.name
k = int(k)
leaf.name = labels[k]
# Apply node styles to nodes
for n in tree.traverse():
n.set_style(nstyle)
# Convert the ETE tree to Newick
newick = tree.write()
f = open('C:\\Users\\Scott\\Documents\\GitHub\\d3-dendro\\newickStr.txt', 'w')
f.write(newick)
f.close()
# Save the image as .png...
from os import path, makedirs
# Using ETE
folder = pathjoin(session_manager.session_folder(), constants.RESULTS_FOLDER)
if (not os.path.isdir(folder)):
makedirs(folder)
# saves dendrogram as a .png with pyplot
plt.savefig(path.join(folder, constants.DENDROGRAM_PNG_FILENAME))
plt.close()
# if orientation == "top":
# plt.figure(figsize=(20,80))
# else:
# plt.figure(figsize=(80,20))
pdfPageNumber, score, inconsistentMax, maxclustMax, distanceMax, distanceMin, monocritMax, monocritMin, threshold = utility.generateDendrogram(
fileManager)
session['dengenerated'] = True
labels = fileManager.getActiveLabels()
inconsistentOp = "0 " + leq + " t " + leq + " " + str(inconsistentMax)
maxclustOp = "2 " + leq + " t " + leq + " " + str(maxclustMax)
distanceOp = str(distanceMin) + " " + leq + " t " + leq + " " + str(distanceMax)
monocritOp = str(monocritMin) + " " + leq + " t " + leq + " " + str(monocritMax)
thresholdOps = {"inconsistent": inconsistentOp, "maxclust": maxclustOp, "distance": distanceOp,
"monocrit": monocritOp}
managers.utility.saveFileManager(fileManager)
session_manager.cacheAnalysisOption()
session_manager.cacheHierarchyOption()
import random
ver = random.random() * 100
return render_template('cluster.html', labels=labels, pdfPageNumber=pdfPageNumber, score=score,
inconsistentMax=inconsistentMax, maxclustMax=maxclustMax, distanceMax=distanceMax,
distanceMin=distanceMin, monocritMax=monocritMax, monocritMin=monocritMin,
threshold=threshold, thresholdOps=thresholdOps, ver=ver)
def bct_dendrogram(corpus, tree, outputfile=None,
fontsize=5, save_newick=True, mode='c', show=False,
color_leafs=False, save=False, return_svg=True):
"""
Draw a dendrogram of the texts in the corpus using ETE.
Parameters
----------
corpus : `Corpus` instance
The corpus to be plotted.
tree : `(VN)Clusterer` object
The clusterer object which was
applied to the corpus.
outputfile : str
The path where the plot should be saved.
color_leafs: boolean, default=True,
If true, will color the text labels
according to their category.
fontsize : int, default=5
The fontsize of the labels on the axes.
save_newick : boolean, default=True
Whether to dump a representation of the
tree in newick-format, which can later
be modified using software like FigTree:
http://tree.bio.ed.ac.uk/software/figtree/
mode : str, default='c'
The type of tree to be drawn. Supports:
- 'c': circular dendrogram
- 'r': traditional, rectangular dendrogram
save : boolean, default=False
Whether to save the plot to `outputfile`.
return_svg : boolean, default=True
Whether to return the plot in SVG-format.
Useful for the GUI.
"""
for leaf in tree.get_leaves():
leaf.name = leaf.name.replace("'", '')
def layout(node):
if node.is_leaf():
N = AttrFace("name", fsize=7)
faces.add_face_to_node(faces.AttrFace("name","Arial",10, None), node, 0, position='branch-right')
# problems: aligment of labels to branch, left padding of labels
ts = TreeStyle()
ts.mode = mode
ts.show_leaf_name = False
ts.scale = 120
ts.show_scale = False
ts.branch_vertical_margin = 10
nstyle = NodeStyle()
nstyle["fgcolor"] = "#0f0f0f"
nstyle["size"] = 0
nstyle["vt_line_color"] = "#0f0f0f"
nstyle["hz_line_color"] = "#0f0f0f"
nstyle["vt_line_width"] = 1
nstyle["hz_line_width"] = 1
nstyle["vt_line_type"] = 0
nstyle["hz_line_type"] = 0
for n in tree.traverse():
n.set_style(nstyle)
ts.layout_fn = layout
if outputfile:
outputfile = os.path.expanduser(outputfile)
if save_newick: # save tree in newick format for later manipulation in e.g. FigTree:
tree.write(outfile=os.path.splitext(outputfile)[0]+'.newick')
if save:
tree.render(outputfile, tree_style=ts)
if show:
tree.show(tree_style=ts)
if return_svg: # return the SVG as a string
return tree.render("%%return")[0]
def showTree(delimitation, scale = 500, render = False, fout = "", form = "svg", show_support = False):
"""delimitation: species_setting class"""
tree = delimitation.root
style0 = NodeStyle()
style0["fgcolor"] = "#000000"
style0["vt_line_color"] = "#0000aa"
style0["hz_line_color"] = "#0000aa"
style0["vt_line_width"] = 2
style0["hz_line_width"] = 2
style0["vt_line_type"] = 0
style0["hz_line_type"] = 0
style0["size"] = 0
tree.clear_face()
for node in tree.get_descendants():
node.set_style(style0)
node.img_style["size"] = 0
node.clear_face()
tree.set_style(style0)
tree.img_style["size"] = 0
style1 = NodeStyle()
style1["fgcolor"] = "#000000"
style1["vt_line_color"] = "#ff0000"
style1["hz_line_color"] = "#0000aa"
style1["vt_line_width"] = 2
style1["hz_line_width"] = 2
style1["vt_line_type"] = 0
style1["hz_line_type"] = 0
style1["size"] = 0
style2 = NodeStyle()
style2["fgcolor"] = "#0f0f0f"
style2["vt_line_color"] = "#ff0000"
style2["hz_line_color"] = "#ff0000"
style2["vt_line_width"] = 2
style2["hz_line_width"] = 2
style2["vt_line_type"] = 0
style2["hz_line_type"] = 0
style2["size"] = 0
for node in delimitation.active_nodes:
node.set_style(style1)
node.img_style["size"] = 0
for des in node.get_descendants():
des.set_style(style2)
des.img_style["size"] = 0
for node in delimitation.root.traverse(strategy='preorder'):
if show_support and hasattr(node, "bs"):
if node.bs == 0.0:
node.add_face(TextFace("0", fsize = 8), column=0, position = "branch-top")
else:
node.add_face(TextFace("{0:.2f}".format(node.bs), fsize = 8), column=0, position = "branch-top")
ts = TreeStyle()
"""scale pixels per branch length unit"""
ts.scale = scale
ts.branch_vertical_margin = 7
if render:
tree.render(fout+"."+form, tree_style=ts)
else:
tree.show(tree_style=ts)
def run(args):
if args.text_mode:
from ete2 import Tree
for tindex, tfile in enumerate(args.src_tree_iterator):
#print tfile
if args.raxml:
nw = re.sub(":(\d+\.\d+)\[(\d+)\]", ":\\1[&&NHX:support=\\2]", open(tfile).read())
t = Tree(nw)
else:
t = Tree(tfile)
print t.get_ascii(show_internal=args.show_internal_names,
attributes=args.show_attributes)
return
import random
import re
import colorsys
from collections import defaultdict
from ete2 import (Tree, PhyloTree, TextFace, RectFace, faces, TreeStyle,
add_face_to_node, random_color)
global FACES
if args.face:
FACES = parse_faces(args.face)
else:
FACES = []
# VISUALIZATION
ts = TreeStyle()
ts.mode = args.mode
ts.show_leaf_name = True
ts.tree_width = args.tree_width
for f in FACES:
if f["value"] == "@name":
ts.show_leaf_name = False
break
if args.as_ncbi:
ts.show_leaf_name = False
FACES.extend(parse_faces(
['value:@sci_name, size:10, fstyle:italic',
'value:@taxid, color:grey, size:6, format:" - %s"',
'value:@sci_name, color:steelblue, size:7, pos:b-top, nodetype:internal',
'value:@rank, color:indianred, size:6, pos:b-bottom, nodetype:internal',
]))
if args.alg:
FACES.extend(parse_faces(
['value:@sequence, size:10, pos:aligned, ftype:%s' %args.alg_type]
))
if args.heatmap:
FACES.extend(parse_faces(
['value:@name, size:10, pos:aligned, ftype:heatmap']
))
if args.bubbles:
for bubble in args.bubbles:
FACES.extend(parse_faces(
['value:@%s, pos:float, ftype:bubble, opacity:0.4' %bubble,
]))
ts.branch_vertical_margin = args.branch_separation
if args.show_support:
ts.show_branch_support = True
if args.show_branch_length:
ts.show_branch_length = True
if args.force_topology:
ts.force_topology = True
ts.layout_fn = lambda x: None
for tindex, tfile in enumerate(args.src_tree_iterator):
#print tfile
if args.raxml:
nw = re.sub(":(\d+\.\d+)\[(\d+)\]", ":\\1[&&NHX:support=\\2]", open(tfile).read())
t = PhyloTree(nw)
else:
t = PhyloTree(tfile)
if args.alg:
t.link_to_alignment(args.alg, alg_format=args.alg_format)
if args.heatmap:
DEFAULT_COLOR_SATURATION = 0.3
BASE_LIGHTNESS = 0.7
def gradient_color(value, max_value, saturation=0.5, hue=0.1):
def rgb2hex(rgb):
return '#%02x%02x%02x' % rgb
def hls2hex(h, l, s):
return rgb2hex( tuple(map(lambda x: int(x*255), colorsys.hls_to_rgb(h, l, s))))
lightness = 1 - (value * BASE_LIGHTNESS) / max_value
return hls2hex(hue, lightness, DEFAULT_COLOR_SATURATION)
heatmap_data = {}
max_value, min_value = None, None
for line in open(args.heatmap):
if line.startswith('#COLNAMES'):
pass
elif line.startswith('#') or not line.strip():
pass
else:
fields = line.split('\t')
name = fields[0].strip()
values = map(lambda x: float(x) if x else None, fields[1:])
maxv = max(values)
minv = min(values)
if max_value is None or maxv > max_value:
max_value = maxv
if min_value is None or minv < min_value:
min_value = minv
heatmap_data[name] = values
heatmap_center_value = 0
heatmap_color_center = "white"
heatmap_color_up = 0.3
heatmap_color_down = 0.7
heatmap_color_missing = "black"
heatmap_max_value = abs(heatmap_center_value - max_value)
heatmap_min_value = abs(heatmap_center_value - min_value)
if heatmap_center_value <= min_value:
heatmap_max_value = heatmap_min_value + heatmap_max_value
else:
heatmap_max_value = max(heatmap_min_value, heatmap_max_value)
# scale the tree
if not args.height:
args.height = None
if not args.width:
args.width = None
f2color = {}
f2last_seed = {}
for node in t.traverse():
node.img_style['size'] = 0
if len(node.children) == 1:
node.img_style['size'] = 2
node.img_style['shape'] = "square"
node.img_style['fgcolor'] = "steelblue"
ftype_pos = defaultdict(int)
for findex, f in enumerate(FACES):
if (f['nodetype'] == 'any' or
(f['nodetype'] == 'leaf' and node.is_leaf()) or
(f['nodetype'] == 'internal' and not node.is_leaf())):
# if node passes face filters
if node_matcher(node, f["filters"]):
if f["value"].startswith("@"):
fvalue = getattr(node, f["value"][1:], None)
else:
fvalue = f["value"]
# if node's attribute has content, generate face
if fvalue is not None:
fsize = f["size"]
fbgcolor = f["bgcolor"]
fcolor = f['color']
if fcolor:
# Parse color options
auto_m = re.search("auto\(([^)]*)\)", fcolor)
if auto_m:
target_attr = auto_m.groups()[0].strip()
if not target_attr :
color_keyattr = f["value"]
else:
color_keyattr = target_attr
color_keyattr = color_keyattr.lstrip('@')
color_bin = getattr(node, color_keyattr, None)
last_seed = f2last_seed.setdefault(color_keyattr, random.random())
seed = last_seed + 0.10 + random.uniform(0.1, 0.2)
f2last_seed[color_keyattr] = seed
fcolor = f2color.setdefault(color_bin, random_color(h=seed))
if fbgcolor:
# Parse color options
auto_m = re.search("auto\(([^)]*)\)", fbgcolor)
if auto_m:
target_attr = auto_m.groups()[0].strip()
if not target_attr :
color_keyattr = f["value"]
else:
color_keyattr = target_attr
color_keyattr = color_keyattr.lstrip('@')
color_bin = getattr(node, color_keyattr, None)
last_seed = f2last_seed.setdefault(color_keyattr, random.random())
seed = last_seed + 0.10 + random.uniform(0.1, 0.2)
f2last_seed[color_keyattr] = seed
fbgcolor = f2color.setdefault(color_bin, random_color(h=seed))
if f["ftype"] == "text":
if f.get("format", None):
fvalue = f["format"] % fvalue
F = TextFace(fvalue,
fsize = fsize,
fgcolor = fcolor or "black",
fstyle = f.get('fstyle', None))
elif f["ftype"] == "fullseq":
F = faces.SeqMotifFace(seq=fvalue, seq_format="seq",
seqtail_format="seq",
height=fsize)
elif f["ftype"] == "compactseq":
F = faces.SeqMotifFace(seq=fvalue, seq_format="compactseq",
seqtail_format="compactseq",
height=fsize)
elif f["ftype"] == "blockseq":
F = faces.SeqMotifFace(seq=fvalue, seq_format="blockseq",
seqtail_format="blockseq",
height=fsize,
fgcolor=fcolor or "slategrey",
bgcolor=fbgcolor or "slategrey",
scale_factor = 1.0)
fbgcolor = None
elif f["ftype"] == "bubble":
try:
v = float(fvalue)
except ValueError:
rad = fsize
else:
rad = fsize * v
F = faces.CircleFace(radius=rad, style="sphere",
color=fcolor or "steelblue")
elif f["ftype"] == "heatmap":
if not f['column']:
col = ftype_pos[f["pos"]]
else:
col = f["column"]
for i, value in enumerate(heatmap_data.get(node.name, [])):
ftype_pos[f["pos"]] += 1
if value is None:
color = heatmap_color_missing
elif value > heatmap_center_value:
color = gradient_color(abs(heatmap_center_value - value), heatmap_max_value, hue=heatmap_color_up)
elif value < heatmap_center_value:
color = gradient_color(abs(heatmap_center_value - value), heatmap_max_value, hue=heatmap_color_down)
else:
color = heatmap_color_center
node.add_face(RectFace(20, 20, color, color), position="aligned", column=col + i)
# Add header
# for i, name in enumerate(header):
# nameF = TextFace(name, fsize=7)
# nameF.rotation = -90
# tree_style.aligned_header.add_face(nameF, column=i)
F = None
elif f["ftype"] == "profile":
# internal profiles?
F = None
elif f["ftype"] == "barchart":
F = None
elif f["ftype"] == "piechart":
F = None
# Add the Face
if F:
F.opacity = f['opacity'] or 1.0
# Set face general attributes
if fbgcolor:
F.background.color = fbgcolor
if not f['column']:
col = ftype_pos[f["pos"]]
ftype_pos[f["pos"]] += 1
else:
col = f["column"]
node.add_face(F, column=col, position=f["pos"])
if args.image:
t.render("t%d.%s" %(tindex, args.image),
tree_style=ts, w=args.width, h=args.height, units=args.size_units)
else:
t.show(None, tree_style=ts)
def cluster():
fileManager = managers.utility.loadFileManager()
leq = '≤'.decode('utf-8')
if request.method == "GET":
# "GET" request occurs when the page is first loaded.
if 'analyoption' not in session:
session['analyoption'] = constants.DEFAULT_ANALIZE_OPTIONS
if 'hierarchyoption' not in session:
session['hierarchyoption'] = constants.DEFAULT_HIERARCHICAL_OPTIONS
labels = fileManager.getActiveLabels()
thresholdOps = {}
return render_template('cluster.html',
labels=labels,
thresholdOps=thresholdOps)
if 'getdendro' in request.form:
labelDict = fileManager.getActiveLabels()
labels = []
for ind, label in labelDict.items():
labels.append(label)
# Apply re-tokenisation and filters to DTM
#countMatrix = fileManager.getMatrix(ARGUMENTS OMITTED)
# Get options from request.form
orientation = str(request.form['orientation'])
title = request.form['title']
pruning = request.form['pruning']
pruning = int(request.form['pruning']) if pruning else 0
linkage = str(request.form['linkage'])
metric = str(request.form['metric'])
# Get active files
allContents = [] # list of strings-of-text for each segment
tempLabels = [] # list of labels for each segment
for lFile in fileManager.files.values():
if lFile.active:
contentElement = lFile.loadContents()
allContents.append(contentElement)
if request.form["file_" + str(lFile.id)] == lFile.label:
tempLabels.append(lFile.label.encode("utf-8"))
else:
newLabel = request.form["file_" +
str(lFile.id)].encode("utf-8")
tempLabels.append(newLabel)
# More options
ngramSize = int(request.form['tokenSize'])
useWordTokens = request.form['tokenType'] == 'word'
try:
useFreq = request.form['normalizeType'] == 'freq'
useTfidf = request.form['normalizeType'] == 'tfidf' # if use TF/IDF
normOption = "N/A" # only applicable when using "TF/IDF", set default value to N/A
if useTfidf:
if request.form['norm'] == 'l1':
normOption = u'l1'
elif request.form['norm'] == 'l2':
normOption = u'l2'
else:
normOption = None
except:
useFreq = useTfidf = False
normOption = None
onlyCharGramsWithinWords = False
if not useWordTokens: # if using character-grams
# this option is disabled on the GUI, because countVectorizer count front and end markers as ' ' if this is true
onlyCharGramsWithinWords = 'inWordsOnly' in request.form
greyWord = 'greyword' in request.form
MostFrequenWord = 'mfwcheckbox' in request.form
Culling = 'cullcheckbox' in request.form
showDeletedWord = False
if 'greyword' or 'mfwcheckbox' or 'cullcheckbox' in request.form:
if 'onlygreyword' in request.form:
showDeletedWord = True
if useWordTokens:
tokenType = u'word'
else:
tokenType = u'char'
if onlyCharGramsWithinWords:
tokenType = u'char_wb'
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
vectorizer = CountVectorizer(input=u'content',
encoding=u'utf-8',
min_df=1,
analyzer=tokenType,
token_pattern=ur'(?u)\b[\w\']+\b',
ngram_range=(ngramSize, ngramSize),
stop_words=[],
dtype=float,
max_df=1.0)
# make a (sparse) Document-Term-Matrix (DTM) to hold all counts
DocTermSparseMatrix = vectorizer.fit_transform(allContents)
dtm = DocTermSparseMatrix.toarray()
from sklearn.metrics.pairwise import euclidean_distances
from scipy.cluster.hierarchy import ward
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import average, weighted, ward, single, complete, dendrogram
from scipy.cluster import hierarchy
from scipy.spatial.distance import pdist
if orientation == "left":
orientation = "right"
if orientation == "top":
LEAF_ROTATION_DEGREE = 90
else:
LEAF_ROTATION_DEGREE = 0
if linkage == "ward":
dist = euclidean_distances(dtm)
np.round(dist, 1)
linkage_matrix = ward(dist)
dendrogram(linkage_matrix,
orientation=orientation,
leaf_rotation=LEAF_ROTATION_DEGREE,
labels=labels)
Z = linkage_matrix
else:
Y = pdist(dtm, metric)
Z = hierarchy.linkage(Y, method=linkage)
dendrogram(Z,
orientation=orientation,
leaf_rotation=LEAF_ROTATION_DEGREE,
labels=labels)
plt.tight_layout() # fixes margins
## Conversion to Newick/ETE
# Stuff we need
from scipy.cluster.hierarchy import average, linkage, to_tree
#from hcluster import linkage, to_tree
from ete2 import Tree, TreeStyle, NodeStyle
# Change it to a distance matrix
T = to_tree(Z)
# ete2 section
root = Tree()
root.dist = 0
root.name = "root"
item2node = {T: root}
to_visit = [T]
while to_visit:
node = to_visit.pop()
cl_dist = node.dist / 2.0
for ch_node in [node.left, node.right]:
if ch_node:
ch = Tree()
ch.dist = cl_dist
ch.name = str(ch_node.id)
item2node[node].add_child(ch)
item2node[ch_node] = ch
to_visit.append(ch_node)
# This is the ETE tree structure
tree = root
ts = TreeStyle()
ts.show_leaf_name = True
ts.show_branch_length = True
ts.show_scale = False
ts.scale = None
if orientation == "top":
ts.rotation = 90
ts.branch_vertical_margin = 10 # 10 pixels between adjacent branches
# Draws nodes as small red spheres of diameter equal to 10 pixels
nstyle = NodeStyle()
nstyle["size"] = 0
# Replace the node labels
for leaf in tree:
k = leaf.name
k = int(k)
leaf.name = labels[k]
# Apply node styles to nodes
for n in tree.traverse():
n.set_style(nstyle)
# Convert the ETE tree to Newick
newick = tree.write()
f = open(
'C:\\Users\\Scott\\Documents\\GitHub\\d3-dendro\\newickStr.txt',
'w')
f.write(newick)
f.close()
# Save the image as .png...
from os import path, makedirs
# Using ETE
folder = pathjoin(session_manager.session_folder(),
constants.RESULTS_FOLDER)
if (not os.path.isdir(folder)):
makedirs(folder)
# saves dendrogram as a .png with pyplot
plt.savefig(path.join(folder, constants.DENDROGRAM_PNG_FILENAME))
plt.close()
# if orientation == "top":
# plt.figure(figsize=(20,80))
# else:
# plt.figure(figsize=(80,20))
pdfPageNumber, score, inconsistentMax, maxclustMax, distanceMax, distanceMin, monocritMax, monocritMin, threshold = utility.generateDendrogram(
fileManager)
session['dengenerated'] = True
labels = fileManager.getActiveLabels()
inconsistentOp = "0 " + leq + " t " + leq + " " + str(inconsistentMax)
maxclustOp = "2 " + leq + " t " + leq + " " + str(maxclustMax)
distanceOp = str(distanceMin) + " " + leq + " t " + leq + " " + str(
distanceMax)
monocritOp = str(monocritMin) + " " + leq + " t " + leq + " " + str(
monocritMax)
thresholdOps = {
"inconsistent": inconsistentOp,
"maxclust": maxclustOp,
"distance": distanceOp,
"monocrit": monocritOp
}
managers.utility.saveFileManager(fileManager)
session_manager.cacheAnalysisOption()
session_manager.cacheHierarchyOption()
import random
ver = random.random() * 100
return render_template('cluster.html',
labels=labels,
pdfPageNumber=pdfPageNumber,
score=score,
inconsistentMax=inconsistentMax,
maxclustMax=maxclustMax,
distanceMax=distanceMax,
distanceMin=distanceMin,
monocritMax=monocritMax,
monocritMin=monocritMin,
threshold=threshold,
thresholdOps=thresholdOps,
ver=ver)
width = 600 # For other output args, see http://etetoolkit.org/docs/latest/tutorial/tutorial_drawing.html#rendering-trees-as-images
# Configure tree styles
ts = TreeStyle()
ts.show_leaf_name = True
ts.show_branch_length = True
ts.show_scale = False
ts.scale = None
ts.mode = "c" # draw tree in circular style
ts.arc_start = 0
ts.arc_span = 360
if orientation == "top":
ts.rotation = 90
ts.branch_vertical_margin = 10 # 10 pixels between adjacent branches
# Remove the default small red spheres for each node
nstyle = NodeStyle()
nstyle["size"] = 0
for leaf in tree:
k = leaf.name
k = int(k)
leaf.name = labels[k]
# Apply node styles to nodes
for n in tree.traverse():
n.set_style(nstyle)
# Plot the tree
tree.show(tree_style=ts)
width = 600 # For other output args, see http://etetoolkit.org/docs/latest/tutorial/tutorial_drawing.html#rendering-trees-as-images
# Configure tree styles
ts = TreeStyle()
ts.show_leaf_name = True
ts.show_branch_length = True
ts.show_scale = False
ts.scale = None
ts.mode = "c" # draw tree in circular style
ts.arc_start = 0
ts.arc_span = 360
if orientation == "top":
ts.rotation = 90
ts.branch_vertical_margin = 10 # 10 pixels between adjacent branches
# Remove the default small red spheres for each node
nstyle = NodeStyle()
nstyle["size"] = 0
for leaf in tree:
k = leaf.name
k = int(k)
leaf.name = labels[k]
# Apply node styles to nodes
for n in tree.traverse():
n.set_style(nstyle)
# Plot the tree
tree.show(tree_style=ts)
common_tree_file = args.tree_with_general_data
general_tree_file = "%s.png" % args.output_prefix
general_significant_tree_file = "%s_significant.png" % args.output_prefix
general_tree_file_no_labels = "%s_no_labels.png" % args.output_prefix
with open(common_tree_file, "r") as tree_fd:
tree = Tree(tree_fd.readline().strip(), format=1)
for node in tree.traverse():
node.img_style["size"] = 0
ts = TreeStyle()
ts.layout_fn = layout
ts.optimal_scale_level = "full"
ts.branch_vertical_margin = 10
ts.show_leaf_name = False
#ts.allow_face_overlap =True
tree.render(general_tree_file, w=200, units='mm', tree_style=ts, dpi=300)
ts_significant = TreeStyle()
ts_significant.layout_fn = layout_significant
ts_significant.optimal_scale_level = "full"
ts_significant.branch_vertical_margin = 10
ts_significant.show_leaf_name = False
#ts.allow_face_overlap =True
tree.render(general_significant_tree_file,
w=200,
units='mm',