def get_example_tree():
# Performs a tree reconciliation analysis
gene_tree_nw = '((Dme_001,Dme_002),(((Cfa_001,Mms_001),((Hsa_001,Ptr_001),Mmu_001)),(Ptr_002,(Hsa_002,Mmu_002))));'
t = PhyloTree(gene_tree_nw)
ts = TreeStyle()
# disable default PhyloTree Layout
ts.layout_fn = lambda x: True
t.link_to_alignment(alg)
node2content = t.get_cached_content()
for node in t.traverse():
node.img_style["size"] = 0
if not node.is_leaf():
leaves = node2content[node]
# get columns with different aa
subseqs, relevant_columns = mutation_columns([lf.sequence for lf in leaves])
for seq in subseqs:
f = SeqMotifFace(seq, seq_format="seq", width=10, height=8)
f.margin_top = 2
f.margin_right = 6
node.add_face(f, column=0, position="branch-bottom")
for j, col in enumerate(relevant_columns):
col_f = RectFace(10, 10, fgcolor=None, bgcolor=None,
label={"text":str(col), "fonttype":"Courier", "color":"black", "fontsize":6})
node.add_face(col_f, column=j, position="branch-top")
col_f.margin_bottom = 2
else:
f = SeqMotifFace(node.sequence, seq_format="seq", width=6)
node.add_face(f, column=0, position="aligned")
alg_length = len(lf.sequence)
ts.draw_aligned_faces_as_table = False
for colnum in xrange(alg_length):
col_f = RectFace(10, 10, fgcolor=None, bgcolor=None,
label={"text":str(colnum), "fonttype":"Courier", "color":"black", "fontsize":6})
ts.aligned_header.add_face(col_f, column=colnum)
return t, ts
def get_tree_style(**kwargs):
style = TreeStyle()
style.layout_fn = layout
style.allow_face_overlap = True
style.branch_vertical_margin = 5
style.complete_branch_lines_when_necessary = False
style.draw_aligned_faces_as_table = False
style.scale = 1500
style.scale_length = 0.05
style.show_branch_support = False
style.show_leaf_name = False
for key, value in kwargs.items():
if value == "True":
value = True
else:
try:
value = float(value)
except ValueError:
pass
setattr(style, key, value)
return style
def draw_tree(tree, conf, outfile):
try:
from ete3 import (add_face_to_node, AttrFace, TextFace, TreeStyle, RectFace, CircleFace,
SequenceFace, random_color, SeqMotifFace)
except ImportError as e:
print(e)
return
def ly_basic(node):
if node.is_leaf():
node.img_style['size'] = 0
else:
node.img_style['size'] = 0
node.img_style['shape'] = 'square'
if len(MIXED_RES) > 1 and hasattr(node, "tree_seqtype"):
if node.tree_seqtype == "nt":
node.img_style["bgcolor"] = "#CFE6CA"
ntF = TextFace("nt", fsize=6, fgcolor='#444', ftype='Helvetica')
add_face_to_node(ntF, node, 10, position="branch-bottom")
if len(NPR_TREES) > 1 and hasattr(node, "tree_type"):
node.img_style['size'] = 4
node.img_style['fgcolor'] = "steelblue"
node.img_style['hz_line_width'] = 1
node.img_style['vt_line_width'] = 1
def ly_leaf_names(node):
if node.is_leaf():
spF = TextFace(node.species, fsize=10, fgcolor='#444444', fstyle='italic', ftype='Helvetica')
add_face_to_node(spF, node, column=0, position='branch-right')
if hasattr(node, 'genename'):
geneF = TextFace(" (%s)" %node.genename, fsize=8, fgcolor='#777777', ftype='Helvetica')
add_face_to_node(geneF, node, column=1, position='branch-right')
def ly_supports(node):
if not node.is_leaf() and node.up:
supFace = TextFace("%0.2g" %(node.support), fsize=7, fgcolor='indianred')
add_face_to_node(supFace, node, column=0, position='branch-top')
def ly_tax_labels(node):
if node.is_leaf():
c = LABEL_START_COL
largest = 0
for tname in TRACKED_CLADES:
if hasattr(node, "named_lineage") and tname in node.named_lineage:
linF = TextFace(tname, fsize=10, fgcolor='white')
linF.margin_left = 3
linF.margin_right = 2
linF.background.color = lin2color[tname]
add_face_to_node(linF, node, c, position='aligned')
c += 1
for n in range(c, len(TRACKED_CLADES)):
add_face_to_node(TextFace('', fsize=10, fgcolor='slategrey'), node, c, position='aligned')
c+=1
def ly_full_alg(node):
pass
def ly_block_alg(node):
if node.is_leaf():
if 'sequence' in node.features:
seqFace = SeqMotifFace(node.sequence, [])
# [10, 100, "[]", None, 10, "black", "rgradient:blue", "arial|8|white|domain Name"],
motifs = []
last_lt = None
for c, lt in enumerate(node.sequence):
if lt != '-':
if last_lt is None:
last_lt = c
if c+1 == len(node.sequence):
start, end = last_lt, c
motifs.append([start, end, "()", 0, 12, "slategrey", "slategrey", None])
last_lt = None
elif lt == '-':
if last_lt is not None:
start, end = last_lt, c-1
motifs.append([start, end, "()", 0, 12, "grey", "slategrey", None])
last_lt = None
seqFace = SeqMotifFace(node.sequence, motifs,
intermotif_format="line",
seqtail_format="line", scale_factor=ALG_SCALE)
add_face_to_node(seqFace, node, ALG_START_COL, aligned=True)
TRACKED_CLADES = ["Eukaryota", "Viridiplantae", "Fungi",
"Alveolata", "Metazoa", "Stramenopiles", "Rhodophyta",
"Amoebozoa", "Crypthophyta", "Bacteria",
"Alphaproteobacteria", "Betaproteobacteria", "Cyanobacteria",
"Gammaproteobacteria",]
# ["Opisthokonta", "Apicomplexa"]
colors = random_color(num=len(TRACKED_CLADES), s=0.45)
lin2color = dict([(ln, colors[i]) for i, ln in enumerate(TRACKED_CLADES)])
NAME_FACE = AttrFace('name', fsize=10, fgcolor='#444444')
LABEL_START_COL = 10
ALG_START_COL = 40
ts = TreeStyle()
ts.draw_aligned_faces_as_table = False
ts.draw_guiding_lines = False
ts.show_leaf_name = False
ts.show_branch_support = False
ts.scale = 160
ts.layout_fn = [ly_basic, ly_leaf_names, ly_supports, ly_tax_labels]
MIXED_RES = set()
MAX_SEQ_LEN = 0
NPR_TREES = []
for n in tree.traverse():
if hasattr(n, "tree_seqtype"):
MIXED_RES.add(n.tree_seqtype)
if hasattr(n, "tree_type"):
NPR_TREES.append(n.tree_type)
seq = getattr(n, "sequence", "")
MAX_SEQ_LEN = max(len(seq), MAX_SEQ_LEN)
if MAX_SEQ_LEN:
ALG_SCALE = min(1, 1000./MAX_SEQ_LEN)
ts.layout_fn.append(ly_block_alg)
if len(NPR_TREES) > 1:
rF = RectFace(4, 4, "steelblue", "steelblue")
rF.margin_right = 10
rF.margin_left = 10
ts.legend.add_face(rF, 0)
ts.legend.add_face(TextFace(" NPR node"), 1)
ts.legend_position = 3
if len(MIXED_RES) > 1:
rF = RectFace(20, 20, "#CFE6CA", "#CFE6CA")
rF.margin_right = 10
rF.margin_left = 10
ts.legend.add_face(rF, 0)
ts.legend.add_face(TextFace(" Nucleotide based alignment"), 1)
ts.legend_position = 3
try:
tree.set_species_naming_function(spname)
annotate_tree_with_ncbi(tree)
a = tree.search_nodes(species='Dictyostelium discoideum')[0]
b = tree.search_nodes(species='Chondrus crispus')[0]
#out = tree.get_common_ancestor([a, b])
#out = tree.search_nodes(species='Haemophilus parahaemolyticus')[0].up
tree.set_outgroup(out)
tree.swap_children()
except Exception:
pass
tree.render(outfile, tree_style=ts, w=170, units='mm', dpi=150)
tree.render(outfile+'.svg', tree_style=ts, w=170, units='mm', dpi=150)
tree.render(outfile+'.pdf', tree_style=ts, w=170, units='mm', dpi=150)
def draw_tree(tree, conf, outfile):
try:
from ete3 import (add_face_to_node, AttrFace, TextFace, TreeStyle,
RectFace, CircleFace, SequenceFace, random_color,
SeqMotifFace)
except ImportError as e:
print(e)
return
def ly_basic(node):
if node.is_leaf():
node.img_style['size'] = 0
else:
node.img_style['size'] = 0
node.img_style['shape'] = 'square'
if len(MIXED_RES) > 1 and hasattr(node, "tree_seqtype"):
if node.tree_seqtype == "nt":
node.img_style["bgcolor"] = "#CFE6CA"
ntF = TextFace("nt",
fsize=6,
fgcolor='#444',
ftype='Helvetica')
add_face_to_node(ntF, node, 10, position="branch-bottom")
if len(NPR_TREES) > 1 and hasattr(node, "tree_type"):
node.img_style['size'] = 4
node.img_style['fgcolor'] = "steelblue"
node.img_style['hz_line_width'] = 1
node.img_style['vt_line_width'] = 1
def ly_leaf_names(node):
if node.is_leaf():
spF = TextFace(node.species,
fsize=10,
fgcolor='#444444',
fstyle='italic',
ftype='Helvetica')
add_face_to_node(spF, node, column=0, position='branch-right')
if hasattr(node, 'genename'):
geneF = TextFace(" (%s)" % node.genename,
fsize=8,
fgcolor='#777777',
ftype='Helvetica')
add_face_to_node(geneF,
node,
column=1,
position='branch-right')
def ly_supports(node):
if not node.is_leaf() and node.up:
supFace = TextFace("%0.2g" % (node.support),
fsize=7,
fgcolor='indianred')
add_face_to_node(supFace, node, column=0, position='branch-top')
def ly_tax_labels(node):
if node.is_leaf():
c = LABEL_START_COL
largest = 0
for tname in TRACKED_CLADES:
if hasattr(node,
"named_lineage") and tname in node.named_lineage:
linF = TextFace(tname, fsize=10, fgcolor='white')
linF.margin_left = 3
linF.margin_right = 2
linF.background.color = lin2color[tname]
add_face_to_node(linF, node, c, position='aligned')
c += 1
for n in range(c, len(TRACKED_CLADES)):
add_face_to_node(TextFace('', fsize=10, fgcolor='slategrey'),
node,
c,
position='aligned')
c += 1
def ly_full_alg(node):
pass
def ly_block_alg(node):
if node.is_leaf():
if 'sequence' in node.features:
seqFace = SeqMotifFace(node.sequence, [])
# [10, 100, "[]", None, 10, "black", "rgradient:blue", "arial|8|white|domain Name"],
motifs = []
last_lt = None
for c, lt in enumerate(node.sequence):
if lt != '-':
if last_lt is None:
last_lt = c
if c + 1 == len(node.sequence):
start, end = last_lt, c
motifs.append([
start, end, "()", 0, 12, "slategrey",
"slategrey", None
])
last_lt = None
elif lt == '-':
if last_lt is not None:
start, end = last_lt, c - 1
motifs.append([
start, end, "()", 0, 12, "grey", "slategrey",
None
])
last_lt = None
seqFace = SeqMotifFace(node.sequence,
motifs,
intermotif_format="line",
seqtail_format="line",
scale_factor=ALG_SCALE)
add_face_to_node(seqFace, node, ALG_START_COL, aligned=True)
TRACKED_CLADES = [
"Eukaryota",
"Viridiplantae",
"Fungi",
"Alveolata",
"Metazoa",
"Stramenopiles",
"Rhodophyta",
"Amoebozoa",
"Crypthophyta",
"Bacteria",
"Alphaproteobacteria",
"Betaproteobacteria",
"Cyanobacteria",
"Gammaproteobacteria",
]
# ["Opisthokonta", "Apicomplexa"]
colors = random_color(num=len(TRACKED_CLADES), s=0.45)
lin2color = dict([(ln, colors[i]) for i, ln in enumerate(TRACKED_CLADES)])
NAME_FACE = AttrFace('name', fsize=10, fgcolor='#444444')
LABEL_START_COL = 10
ALG_START_COL = 40
ts = TreeStyle()
ts.draw_aligned_faces_as_table = False
ts.draw_guiding_lines = False
ts.show_leaf_name = False
ts.show_branch_support = False
ts.scale = 160
ts.layout_fn = [ly_basic, ly_leaf_names, ly_supports, ly_tax_labels]
MIXED_RES = set()
MAX_SEQ_LEN = 0
NPR_TREES = []
for n in tree.traverse():
if hasattr(n, "tree_seqtype"):
MIXED_RES.add(n.tree_seqtype)
if hasattr(n, "tree_type"):
NPR_TREES.append(n.tree_type)
seq = getattr(n, "sequence", "")
MAX_SEQ_LEN = max(len(seq), MAX_SEQ_LEN)
if MAX_SEQ_LEN:
ALG_SCALE = min(1, 1000. / MAX_SEQ_LEN)
ts.layout_fn.append(ly_block_alg)
if len(NPR_TREES) > 1:
rF = RectFace(4, 4, "steelblue", "steelblue")
rF.margin_right = 10
rF.margin_left = 10
ts.legend.add_face(rF, 0)
ts.legend.add_face(TextFace(" NPR node"), 1)
ts.legend_position = 3
if len(MIXED_RES) > 1:
rF = RectFace(20, 20, "#CFE6CA", "#CFE6CA")
rF.margin_right = 10
rF.margin_left = 10
ts.legend.add_face(rF, 0)
ts.legend.add_face(TextFace(" Nucleotide based alignment"), 1)
ts.legend_position = 3
try:
tree.set_species_naming_function(spname)
annotate_tree_with_ncbi(tree)
a = tree.search_nodes(species='Dictyostelium discoideum')[0]
b = tree.search_nodes(species='Chondrus crispus')[0]
#out = tree.get_common_ancestor([a, b])
#out = tree.search_nodes(species='Haemophilus parahaemolyticus')[0].up
tree.set_outgroup(out)
tree.swap_children()
except Exception:
pass
tree.render(outfile, tree_style=ts, w=170, units='mm', dpi=150)
tree.render(outfile + '.svg', tree_style=ts, w=170, units='mm', dpi=150)
tree.render(outfile + '.pdf', tree_style=ts, w=170, units='mm', dpi=150)
>0
AAATGGCTGTGCACGTC
>1
GACTGGATCTGCACGTC
>2
CTCTGGATGTGCACGTG
>3
AAATGGCGGTGCGCCTA
"""
t = PhyloTree(nw, alignment=fa, alg_format='fasta', format=1)
ts = TreeStyle()
ts.show_branch_length = False
ts.show_leaf_name = False
ts.draw_guiding_lines = True
ts.draw_aligned_faces_as_table = True
ts.show_scale = False
def my_layout(node):
#
# add names to all nodes (not just to leaf nodes)
# ete3/test/test_treeview/face_rotation.py
F = TextFace(node.name, tight_text=True)
add_face_to_node(F, node, column=0, position="branch-right")
#
# add branch lengths
# ete3/treeview/qt4_render.py
if not node.is_root():
bl_face = AttrFace("dist",
fsize=8,
from ete3 import add_face_to_node, TextFace, AttrFace, SequenceFace
nw = '(0:0, 1:20);'
fa = """
>0
AA..
>1
CAA.
"""
t = PhyloTree(nw, alignment=fa, alg_format='fasta', format=1)
ts = TreeStyle()
ts.show_branch_length = False
ts.show_leaf_name = False
ts.draw_guiding_lines = True
ts.draw_aligned_faces_as_table = True
ts.show_scale = False
def my_layout(node):
#
# add names to all nodes (not just to leaf nodes)
# ete3/test/test_treeview/face_rotation.py
F = TextFace(node.name, tight_text=True)
add_face_to_node(F, node, column=0, position="branch-right")
#
# add branch lengths
# ete3/treeview/qt4_render.py
if not node.is_root():
bl_face = AttrFace("dist", fsize=8, ftype="Arial",
fgcolor="black", formatter="%0.3g")
#
def render(self,
outfile,
idlabel=False,
isolabel=False,
colormap=None,
chain_split=None):
'''Render to image file, filetype inferred from suffix, svg for color images'''
def my_layout(node):
circle_color = 'lightgray' if colormap is None or node.name not in colormap else colormap[
node.name]
text_color = 'black'
if isinstance(circle_color, str):
if isolabel and hasattr(node, 'isotype'):
nl = ''.join(
sorted(set([ISO_SHORT[iss] for iss in node.isotype]),
key=lambda x: ISO_TYPE_charORDER[x]))
else:
nl = str(node.frequency)
C = CircleFace(radius=max(3, 10 * scipy.sqrt(node.frequency)),
color=circle_color,
label={
'text': nl,
'color': text_color
} if node.frequency > 0 else None)
C.rotation = -90
C.hz_align = 1
faces.add_face_to_node(C, node, 0)
else:
P = PieChartFace(
[100 * x / node.frequency for x in circle_color.values()],
2 * 10 * scipy.sqrt(node.frequency),
2 * 10 * scipy.sqrt(node.frequency),
colors=[(color if color != 'None' else 'lightgray')
for color in list(circle_color.keys())],
line_color=None)
T = TextFace(' '.join(
[str(x) for x in list(circle_color.values())]),
tight_text=True)
T.hz_align = 1
T.rotation = -90
faces.add_face_to_node(P, node, 0, position='branch-right')
faces.add_face_to_node(T, node, 1, position='branch-right')
if idlabel:
T = TextFace(node.name, tight_text=True, fsize=6)
T.rotation = -90
T.hz_align = 1
faces.add_face_to_node(
T,
node,
1 if isinstance(circle_color, str) else 2,
position='branch-right')
elif isolabel and hasattr(node, 'isotype') and False:
iso_name = ''.join(
sorted(set([ISO_SHORT[iss] for iss in node.isotype]),
key=lambda x: ISO_TYPE_charORDER[x]))
#T = TextFace(iso_name, tight_text=True, fsize=6)
#T.rotation = -90
#T.hz_align = 1
#faces.add_face_to_node(T, node, 1 if isinstance(circle_color, str) else 2, position='branch-right')
C = CircleFace(radius=max(3, 10 * scipy.sqrt(node.frequency)),
color=circle_color,
label={
'text': iso_name,
'color': text_color
} if node.frequency > 0 else None)
C.rotation = -90
C.hz_align = 1
faces.add_face_to_node(C, node, 0)
for node in self.tree.traverse():
nstyle = NodeStyle()
nstyle['size'] = 0
if node.up is not None:
if set(node.sequence.upper()) == set(
'ACGT'): # Don't know what this do, try and delete
aa = translate(node.sequence)
aa_parent = translate(node.up.sequence)
nonsyn = hamming_distance(aa, aa_parent)
if '*' in aa:
nstyle['bgcolor'] = 'red'
if nonsyn > 0:
nstyle['hz_line_color'] = 'black'
nstyle['hz_line_width'] = nonsyn
else:
nstyle['hz_line_type'] = 1
node.set_style(nstyle)
ts = TreeStyle()
ts.show_leaf_name = False
ts.rotation = 90
ts.draw_aligned_faces_as_table = False
ts.allow_face_overlap = True
ts.layout_fn = my_layout
ts.show_scale = False
self.tree.render(outfile, tree_style=ts)
# If we labelled seqs, let's also write the alignment out so we have the sequences (including of internal nodes):
if idlabel:
aln = MultipleSeqAlignment([])
for node in self.tree.traverse():
aln.append(
SeqRecord(Seq(str(node.sequence), generic_dna),
id=node.name,
description='abundance={}'.format(
node.frequency)))
AlignIO.write(aln,
open(os.path.splitext(outfile)[0] + '.fasta', 'w'),
'fasta')
def render(self,
outfile,
idlabel=False,
colormap=None,
show_support=False,
chain_split=None):
'''render to image file, filetype inferred from suffix, svg for color images'''
def my_layout(node):
circle_color = 'lightgray' if colormap is None or node.name not in colormap else colormap[
node.name]
text_color = 'black'
if isinstance(circle_color, str):
C = CircleFace(radius=max(3, 10 * scipy.sqrt(node.frequency)),
color=circle_color,
label={
'text': str(node.frequency),
'color': text_color
} if node.frequency > 0 else None)
C.rotation = -90
C.hz_align = 1
faces.add_face_to_node(C, node, 0)
else:
P = PieChartFace(
[100 * x / node.frequency for x in circle_color.values()],
2 * 10 * scipy.sqrt(node.frequency),
2 * 10 * scipy.sqrt(node.frequency),
colors=[(color if color != 'None' else 'lightgray')
for color in list(circle_color.keys())],
line_color=None)
T = TextFace(' '.join(
[str(x) for x in list(circle_color.values())]),
tight_text=True)
T.hz_align = 1
T.rotation = -90
faces.add_face_to_node(P, node, 0, position='branch-right')
faces.add_face_to_node(T, node, 1, position='branch-right')
if idlabel:
T = TextFace(node.name, tight_text=True, fsize=6)
T.rotation = -90
T.hz_align = 1
faces.add_face_to_node(
T,
node,
1 if isinstance(circle_color, str) else 2,
position='branch-right')
for node in self.tree.traverse():
nstyle = NodeStyle()
nstyle['size'] = 0
if node.up is not None:
if set(node.sequence.upper()) == set('ACGT'):
if chain_split is not None:
if self.frame is not None:
raise NotImplementedError(
'frame not implemented with chain_split')
leftseq_mutated = hamming_distance(
node.sequence[:chain_split],
node.up.sequence[:chain_split]) > 0
rightseq_mutated = hamming_distance(
node.sequence[chain_split:],
node.up.sequence[chain_split:]) > 0
if leftseq_mutated and rightseq_mutated:
nstyle['hz_line_color'] = 'purple'
nstyle['hz_line_width'] = 3
elif leftseq_mutated:
nstyle['hz_line_color'] = 'red'
nstyle['hz_line_width'] = 2
elif rightseq_mutated:
nstyle['hz_line_color'] = 'blue'
nstyle['hz_line_width'] = 2
if self.frame is not None:
aa = Seq(
node.sequence[(self.frame -
1):(self.frame - 1 +
(3 *
(((len(node.sequence) -
(self.frame - 1)) // 3))))],
generic_dna).translate()
aa_parent = Seq(
node.up.sequence[(self.frame -
1):(self.frame - 1 + (3 * ((
(len(node.sequence) -
(self.frame - 1)) // 3))))],
generic_dna).translate()
nonsyn = hamming_distance(aa, aa_parent)
if '*' in aa:
nstyle['bgcolor'] = 'red'
if nonsyn > 0:
nstyle['hz_line_color'] = 'black'
nstyle['hz_line_width'] = nonsyn
else:
nstyle['hz_line_type'] = 1
node.set_style(nstyle)
ts = TreeStyle()
ts.show_leaf_name = False
ts.rotation = 90
ts.draw_aligned_faces_as_table = False
ts.allow_face_overlap = True
ts.layout_fn = my_layout
ts.show_scale = False
ts.show_branch_support = show_support
self.tree.render(outfile, tree_style=ts)
# if we labelled seqs, let's also write the alignment out so we have the sequences (including of internal nodes)
if idlabel:
aln = MultipleSeqAlignment([])
for node in self.tree.traverse():
aln.append(
SeqRecord(Seq(str(node.sequence), generic_dna),
id=str(node.name),
description='abundance={}'.format(
node.frequency)))
AlignIO.write(aln,
open(os.path.splitext(outfile)[0] + '.fasta', 'w'),
'fasta')
