def iterate(n_iters):
for i in tqdm(xrange(n_iters)):
sampler.sample()
likelihoods.append(sampler.tree.marg_log_likelihood())
plt.figure()
plt.xlabel("Iterations", fontsize=fontsize)
plt.ylabel("Data Log Likelihood", fontsize=fontsize)
plt.plot(likelihoods)
plt.legend(loc='best', fontsize=12)
plt.savefig('unconstrained-likelihoods.png', bbox_inches='tight')
final_tree = sampler.tree.copy()
plt.figure()
plot_tree_2d(final_tree, X, pca)
for node in final_tree.dfs():
if node.is_leaf():
node.point = y[node.point]
plt.figure()
newick = final_tree.to_newick()
tree = Phylo.read(StringIO(newick), 'newick')
Phylo.draw_graphviz(tree, prog='neato')
plt.savefig('unconstrained-tree.png', bbox_inches='tight')
graph = Phylo.to_networkx(tree)
with open('unconstrained-tree.nwk', 'w') as fp:
print >> fp, newick,
nx.write_dot(graph, 'unconstrained-tree.dot')
plt.show()
def iterate(n_iters):
for i in tqdm(xrange(n_iters)):
sampler.sample()
likelihoods.append(sampler.tree.marg_log_likelihood())
plt.figure()
plt.xlabel("Iterations", fontsize=fontsize)
plt.ylabel("Data Log Likelihood", fontsize=fontsize)
plt.plot(likelihoods)
plt.legend(loc='best', fontsize=12)
plt.savefig('unconstrained-likelihoods.png', bbox_inches='tight')
final_tree = sampler.tree.copy()
plt.figure()
plot_tree_2d(final_tree, X, pca)
for node in final_tree.dfs():
if node.is_leaf():
node.point = y[node.point]
plt.figure()
newick = final_tree.to_newick()
tree = Phylo.read(StringIO(newick), 'newick')
Phylo.draw_graphviz(tree, prog='neato')
plt.savefig('unconstrained-tree.png', bbox_inches='tight')
graph = Phylo.to_networkx(tree)
with open('unconstrained-tree.nwk', 'w') as fp:
print >>fp, newick,
nx.write_dot(graph, 'unconstrained-tree.dot')
plt.show()
def DrawSimple(self):
if self.chosenFileName == '':
self.showOpenFileWindow()
if self.tree != 0:
self.tree.root.color = '#808080'
Phylo.draw_graphviz(self.tree, node_size=2500)
pylab.show()
def plot_tree(tree, y):
final_tree = tree.copy()
for node in final_tree.dfs():
if node.is_leaf():
node.point = y[node.point]
newick = final_tree.to_newick()
tree = Phylo.read(StringIO(newick), 'newick')
Phylo.draw_graphviz(tree, prog='neato')
def plot_tree(tree, y):
final_tree = tree.copy()
for node in final_tree.dfs():
if node.is_leaf():
node.point = y[node.point]
newick = final_tree.to_newick()
tree = Phylo.read(StringIO(newick), 'newick')
Phylo.draw_graphviz(tree, prog='neato')
def showGraphvizRootedTreeWindow(self):
if self.chosenFileName == '':
self.showOpenFileDialog()
if self.tree != 0:
#self.tree.rooted = True
self.tree.root.color = '#808080'
Phylo.draw_graphviz(self.tree, node_size = 2500)
pylab.show()
def showPathWindow(self):
if self.cpath != '' and self.cpath2 != '':
self.start = self.tree.find_clades(self.cpath).next()
self.end = self.tree.find_clades(name=self.cpath2).next()
for clade in self.tree.trace(self.start, self.end):
clade.color = 'red'
for clade in self.tree.find_clades():
if not (clade in self.tree.trace(self.start, self.end)):
clade.color = 'grey'
self.start.color = 'blue'
# RYSOWANIE
Phylo.draw_graphviz(self.tree, node_size=2500)
pylab.plot(0, 0)
# DAJE CZYSTY OBRAZ BEZ OSI ** PEWNIE MOZNA PROSCIEJ
frame1 = pylab.gca()
for xlabel_i in frame1.axes.get_xticklabels():
xlabel_i.set_visible(False)
xlabel_i.set_fontsize(0.0)
for xlabel_i in frame1.axes.get_yticklabels():
xlabel_i.set_fontsize(0.0)
xlabel_i.set_visible(False)
for tick in frame1.axes.get_xticklines():
tick.set_visible(False)
for tick in frame1.axes.get_yticklines():
tick.set_visible(False)
pylab.show()
else:
print "Nie wybrano punktow"
# WYSWIETLA INFORMACJE
img = pylab.imread('img/wally.png', 'rb')
pylab.imshow(img)
pylab.plot(0, 0)
# DAJE CZYSTY OBRAZ BEZ OSI ** PEWNIE MOZNA PROSCIEJ
frame1 = pylab.gca()
for xlabel_i in frame1.axes.get_xticklabels():
xlabel_i.set_visible(False)
xlabel_i.set_fontsize(0.0)
for xlabel_i in frame1.axes.get_yticklabels():
xlabel_i.set_fontsize(0.0)
xlabel_i.set_visible(False)
for tick in frame1.axes.get_xticklines():
tick.set_visible(False)
for tick in frame1.axes.get_yticklines():
tick.set_visible(False)
# SHOWTIME
pylab.show()
def showPathWindow(self):
if self.cb1 != '' and self.cb2 != '':
self.start = self.tree.find_clades(self.cb1).next()
self.end = self.tree.find_clades(name = self.cb2).next()
for clade in self.tree.trace(self.start, self.end):
clade.color = 'red'
for clade in self.tree.find_clades():
if not(clade in self.tree.trace(self.start, self.end)):
clade.color = 'grey'
self.start.color = 'blue'
# RYSOWANIE
Phylo.draw_graphviz(self.tree, node_size = 2500)
pylab.plot(0,0)
# DAJE CZYSTY OBRAZ BEZ OSI ** PEWNIE MOZNA PROSCIEJ
frame1 = pylab.gca()
for xlabel_i in frame1.axes.get_xticklabels():
xlabel_i.set_visible(False)
xlabel_i.set_fontsize(0.0)
for xlabel_i in frame1.axes.get_yticklabels():
xlabel_i.set_fontsize(0.0)
xlabel_i.set_visible(False)
for tick in frame1.axes.get_xticklines():
tick.set_visible(False)
for tick in frame1.axes.get_yticklines():
tick.set_visible(False)
pylab.show()
else:
print "Nie wybrano punktow"
# WYSWIETLA INFORMACJE
img = pylab.imread('wally.png', 'rb')
pylab.imshow(img)
pylab.plot(0,0)
# DAJE CZYSTY OBRAZ BEZ OSI ** PEWNIE MOZNA PROSCIEJ
frame1 = pylab.gca()
for xlabel_i in frame1.axes.get_xticklabels():
xlabel_i.set_visible(False)
xlabel_i.set_fontsize(0.0)
for xlabel_i in frame1.axes.get_yticklabels():
xlabel_i.set_fontsize(0.0)
xlabel_i.set_visible(False)
for tick in frame1.axes.get_xticklines():
tick.set_visible(False)
for tick in frame1.axes.get_yticklines():
tick.set_visible(False)
# SHOWTIME
pylab.show()
def save_utree(tree_path):
logging.info("Saving unrooted tree.")
prefix_name = tree_path[:tree_path.rfind('.')]
unrooted_tree = Phylo.read(tree_path, 'newick')
unrooted_tree.ladderize()
Phylo.draw_graphviz(unrooted_tree)
try:
plt.savefig(common.UTREE_MASK % prefix_name)
except:
logging.error("Error while saving unrooted tree.")
raise
def main():
print >>sys.stderr, "Print the result to file"
if len(sys.argv) != 2:
print >>sys.stderr, "Using python %s file.tre[nexus]" % sys.argv[0]
sys.exit(0)
# -------------------------------------------------
file = sys.argv[1]
progN = "twopi"
# progN = 'neato'
tree = Phylo.read(file, "nexus")
Phylo.draw_graphviz(tree, prog=progN)
file2 = file.replace("tre", "png")
pylab.savefig(file2)
def main():
print >> sys.stderr, "Print the result to file"
if len(sys.argv) != 2:
print >> sys.stderr, 'Using python %s file.tre[nexus]' % sys.argv[0]
sys.exit(0)
#-------------------------------------------------
file = sys.argv[1]
progN = 'twopi'
#progN = 'neato'
tree = Phylo.read(file, 'nexus')
Phylo.draw_graphviz(tree, prog=progN)
file2 = file.replace('tre', 'png')
pylab.savefig(file2)
def plot_tree(final_tree, name):
final_tree = final_tree.copy()
for node in final_tree.dfs():
if node.is_leaf():
node.point = y[node.point]
final_tree = final_tree.induced_subtree(animal_list)
plt.figure()
newick = final_tree.to_newick()
tree = Phylo.read(StringIO(newick), 'newick')
Phylo.draw_graphviz(tree, prog='neato')
plt.savefig("%s.png" % name, dpi=200, bbox_inches='tight')
def plot_tree(final_tree, name):
final_tree = final_tree.copy()
for node in final_tree.dfs():
if node.is_leaf():
node.point = y[node.point]
final_tree = final_tree.induced_subtree(animal_list)
plt.figure()
newick = final_tree.to_newick()
tree = Phylo.read(StringIO(newick), 'newick')
Phylo.draw_graphviz(tree, prog='neato')
plt.savefig("%s.png" % name, dpi=200, bbox_inches='tight')
def display(self, isascii=False):
"""
Loads the tree from a file. And displays it.
"""
self.tree = Phylo.read('{}.dnd'.format(self.filename), 'newick')
if isascii:
Phylo.draw_ascii(self.tree)
try:
import pylab
Phylo.draw_graphviz(self.tree)
pylab.show()
except:
print('Warning: failed to display using graphviz')
Phylo.draw_ascii(self.tree)
def newick2img(newick, filepath, branch_length=True, radial=True, width=800):
'''
Create image file from given newick file. This method has it's own lock so
that many newick's cannot be drawn into same figure and thus corrupt resulting
image file.
newick absolute path to newick tree file
filepath absolute path to svg file to be created
branch_length boolean, if true shows branch lengths in numeric form
radial boolean, if true draws radial graph instead of "normal".
width width of the resulting svg file in pixels.
'''
prog = 'dot' if radial else 'neato'
nwk = Phylo.read(newick, 'newick')
Phylo.draw_graphviz(nwk, prog=prog, node_size=500)
#Phylo.draw(nwk, do_show = False)
plt.savefig(filepath)
def newick2img(newick, filepath, branch_length = True, radial = True, width = 800): ''' Create image file from given newick file. This method has it's own lock so that many newick's cannot be drawn into same figure and thus corrupt resulting image file. newick absolute path to newick tree file filepath absolute path to svg file to be created branch_length boolean, if true shows branch lengths in numeric form radial boolean, if true draws radial graph instead of "normal". width width of the resulting svg file in pixels. ''' prog = 'dot' if radial else 'neato' nwk = Phylo.read(newick, 'newick') Phylo.draw_graphviz(nwk, prog = prog, node_size = 500) #Phylo.draw(nwk, do_show = False) plt.savefig(filepath)
def test(n = 10, theta = 1.0, L = 10):
sim = fsmi.simulator_KingmanFiniteSites(n,theta,L)
myTree = sim_to_tree(sim)
# str_newick_test = '(A,(B,C)D);'
# dpTree_test = dp.Tree.get(data = str_newick_test, schema = 'newick')
# dpTree_test.print_plot()
str_newick_sim = myTree.str_newick(True)
print str_newick_sim
dpTree_sim = dp.Tree.get(data = str_newick_sim, schema = 'newick')
dpTree_sim.print_plot()
phyloTree = Phylo.read(StringIO(str_newick_sim),'newick')
print phyloTree
plt.figure()
Phylo.draw(phyloTree)
phyloTree.rooted = True
plt.figure()
Phylo.draw_graphviz(phyloTree, prog = 'dot')
plt.draw()
def main(args):
# Will need to make format an option here if we ever need to
tree = Phylo.read(args.tree, args.tree_format)
meta = csv.DictReader(args.metadata)
color_map = color_mapping(meta, args.color_by, args.palette)
legend = color_map['by_group']
sequence_mapping = color_map['by_sequence']
# Write out the tree
tree = apply_color_mapping(tree, sequence_mapping)
if args.image_out:
Phylo.draw_graphviz(tree)
pylab.show()
pylab.savefig(args.out)
else:
Phylo.write(tree, args.out, 'phyloxml')
# Write out our legend
leg_handle = open(args.out + '.legend', 'w')
write_color_legend(legend, leg_handle, args.color_by)
# close up shop
leg_handle.close()
args.metadata.close()
def main(args):
# Will need to make format an option here if we ever need to
tree = Phylo.read(args.tree, args.tree_format)
meta = csv.DictReader(args.metadata)
color_map = color_mapping(meta, args.color_by, args.palette)
legend = color_map['by_group']
sequence_mapping = color_map['by_sequence']
# Write out the tree
tree = apply_color_mapping(tree, sequence_mapping)
if args.image_out:
Phylo.draw_graphviz(tree)
pylab.show()
pylab.savefig(args.out)
else:
Phylo.write(tree, args.out, 'phyloxml')
# Write out our legend
leg_handle = open(args.out + '.legend', 'w')
write_color_legend(legend, leg_handle, args.color_by)
# close up shop
leg_handle.close()
args.metadata.close()
import matplotlib
matplotlib.use('GTKAgg')
from Bio import Phylo
import pylab
tree = Phylo.read('apaf.xml', 'phyloxml')
Phylo.draw_graphviz(tree)
pylab.show()
def out():
records = SeqIO.parse("%s" % e1.get(), "fasta")
lens = []
lens2 = []
file = open("phylo.phy", 'w')
for record in records:
ids = record.id
sequence = record.seq[0:100]
lens.append(record.id)
lens2.append(record.seq)
line = "%s %s" % (ids, sequence)
print(line)
lengthmax = len(max(lens, key=len))
lengthmin = len(min(lens, key=len))
file.write(" %s 100\n" % len(lens))
for i, item in enumerate(lens):
start = i - 1
end = i - 1
seq = lens2[end]
if len(item) == int(lengthmax):
if i < 10:
ids = "%s%s%s" % (i, "-", item + "-")
ids = ids
ids = ids.replace(".", "")
ids = ids.replace("_", "")
print("1")
else:
ids = "%s%s%s" % (i, "-", item)
ids = ids
ids = ids.replace(".", "")
ids = ids.replace("_", "")
print("1")
elif len(item) < int(lengthmax):
ids = "%s%s%s" % (i, "-", item)
add = int(lengthmax) - int(len(item))
ids = ids + (add * "-") + "-"
ids = ids
ids = ids.replace(".", "")
ids = ids.replace("_", "")
print("2")
line = "%s %s\n" % (ids.replace(".", ""), seq[0:100])
print(line)
file.write(line)
file.close()
# Read the sequences and align
aln = AlignIO.read('phylo.phy', 'phylip')
# Print the alignment
print(aln)
# Calculate the distance matrix
calculator = DistanceCalculator('identity')
dm = calculator.get_distance(aln)
# Print the distance Matrix
print('\nDistance Matrix\n===================')
print(dm)
# Construct the phylogenetic tree using UPGMA algorithm
constructor = DistanceTreeConstructor()
tree = constructor.upgma(dm)
Phylo.write(tree, 'apaf.xml', 'phyloxml')
tree = Phylo.read('apaf.xml', 'phyloxml')
Phylo.draw_graphviz(tree)
pylab.show()
win.destroy()
def proc():
tree = phylo.read('agi-tree.xml', 'phyloxml')
phylo.draw_graphviz(tree)
pylab.show()
def Arvore2():
tree = Phylo.read("backs\clustalw.dnd", "newick")
tree.rooted = True
tree = tree.as_phyloxml()
Phylo.draw_graphviz(tree, fontsize='6')
pylab.savefig(os.path.join(outpath,'%s.sequences.png'%model))
Clade(branch_length=0.102, name='A')
Clade(branch_length=0.23, name='B')
Clade(branch_length=0.4, name='C')
...
<img src="Phylo-draw-apaf1.png" title="fig:Rooted phylogram, via Phylo.draw" alt="Rooted phylogram, via Phylo.draw" width="500" />
tree = Phylo.read('apaf.xml', 'phyloxml')
tree.ladderize() # Flip branches so deeper clades are displayed at top
Phylo.draw(tree)
<img src="Phylo-apaf.png" title="Unrooted tree with colored nodes" alt="Unrooted tree with colored nodes" width="500" />
#for basic dendrogram
import pylab
tree = Phylo.read('apaf.xml', 'phyloxml')
Phylo.draw_graphviz(tree)
pylab.show()
#simple tree wiht defined branch lengths
tree = Phylo.parse('phyloxml_examples.xml', 'phyloxml').next()
Phylo.draw_ascii(tree)
apaf = Phylo.read('apaf.xml', 'phyloxml')
Phylo.draw_ascii(apaf)
#import networkx, pylab
#tree = Phylo.read('example.xml', 'phyloxml')
#net = Phylo.to_networkx(tree)
#networkx.draw(net)
#pylab.show()
def out():
records = SeqIO.parse(e1.get(), "fasta")
lens = []
for record in records:
print(record.seq)
ids = record.id
sequence = record.seq
op = lens.append(record.id)
# print(lens)
try:
lengthmax = len(max(lens, key=len))
lengthmin = len(min(lens, key=len))
except:
lengthmax = "0"
line = " %s %s\n" % (len(lens), "125")
file = open("phylo.phy", "w")
file.write(line)
for i, id in enumerate(lens):
if lengthmin < int(lengthmax):
add = int(lengthmax) - int(len(id))
# print(i)
id = id + (add * "-")
id = id.replace(".", "")
id = id.replace("_", "")
to_be_write = "%s%s%s %s" % (i, "-", id, sequence[0:100])
# file.write(" %s %s\n"%(num_rec,seqlen))
file.writelines(str("%s\n" % to_be_write))
print(id)
else:
add = int(lengthmax) - int(len(id))
id = id + (add * "-")
id = id.replace(".", "")
id = id.replace("_", "")
to_be_write = "%s %s" % (id, sequence[0:100])
# file.write(" %s %s\n"%(num_rec,seqlen))
file.writelines(str("%s\n" % (to_be_write)))
print(id)
# Read the sequences and align
aln = AlignIO.read('phylo.phy', 'phylip')
# Print the alignment
print(aln)
# Calculate the distance matrix
calculator = DistanceCalculator('identity')
dm = calculator.get_distance(aln)
# Print the distance Matrix
print('\nDistance Matrix\n===================')
print(dm)
# Construct the phylogenetic tree using UPGMA algorithm
constructor = DistanceTreeConstructor()
tree = constructor.upgma(dm)
Phylo.write(tree, 'apaf.xml', 'phyloxml')
tree = Phylo.read('apaf.xml', 'phyloxml')
Phylo.draw_graphviz(tree)
pylab.show()
win.destroy()
plt.figure()
plt.xlim([0, n_iters + constraint_add])
plt.xlabel("Iterations", fontsize=fontsize)
plt.ylabel("Data Log Likelihood", fontsize=fontsize)
plt.plot(likelihoods)
plt.legend(loc="best", fontsize=12)
plt.savefig("online-likelihoods.png", bbox_inches="tight")
final_tree = sampler.tree.copy()
plt.figure()
plot_tree_2d(final_tree, X, pca)
for node in final_tree.dfs():
if node.is_leaf():
node.point = y[node.point]
newick = final_tree.to_newick()
tree = Phylo.read(StringIO(newick), "newick")
plt.figure()
Phylo.draw_graphviz(tree, prog="neato")
plt.savefig("tree.png", bbox_inches="tight")
graph = Phylo.to_networkx(tree)
with open("tree.nwk", "w") as fp:
print >> fp, newick,
nx.write_dot(graph, "tree.dot")
plt.show()
plt.figure()
plt.xlim([0, n_iters + constraint_add])
plt.xlabel("Iterations", fontsize=fontsize)
plt.ylabel("Data Log Likelihood", fontsize=fontsize)
plt.plot(likelihoods)
plt.legend(loc='best', fontsize=12)
plt.savefig('online-likelihoods.png', bbox_inches='tight')
final_tree = sampler.tree.copy()
plt.figure()
plot_tree_2d(final_tree, X, pca)
for node in final_tree.dfs():
if node.is_leaf():
node.point = y[node.point]
newick = final_tree.to_newick()
tree = Phylo.read(StringIO(newick), 'newick')
plt.figure()
Phylo.draw_graphviz(tree, prog='neato')
plt.savefig('tree.png', bbox_inches='tight')
graph = Phylo.to_networkx(tree)
with open('tree.nwk', 'w') as fp:
print >> fp, newick,
nx.write_dot(graph, 'tree.dot')
plt.show()
def processing(raw_fasta_path, out_dir_path):
if not os.path.exists(out_dir_path):
logging.info("Making directory {0}".format(out_dir_path))
os.makedirs(out_dir_path)
deduplicated_fasta = remove_duplicates(SeqIO.parse(raw_fasta_path,
"fasta"))
base = os.path.basename(raw_fasta_path)
fasta_path = os.path.join(out_dir_path, base)
logging.info("Writing FASTA in {0}".format(fasta_path))
SeqIO.write(deduplicated_fasta, fasta_path, "fasta")
# Multiple sequence alignment
cline = ClustalwCommandline("clustalw2", infile=fasta_path)
stdout, stderr = cline()
logging.info(cline)
clustalw_result_path = fasta_path.replace(".fasta", ".aln")
alignment_dict = SeqIO.to_dict(
AlignIO.read(clustalw_result_path, "clustal"))
# writing alignment table in .txt
with open(os.path.join(out_dir_path, "alignment.txt"), "w") as fout:
fout.write("\n".join(
str(record.seq) for record in alignment_dict.itervalues()))
# alignment tree drawing
tree_path = fasta_path.replace(".fasta", ".dnd")
tree = Phylo.read(tree_path, "newick")
tree.ladderize()
# with labels
Phylo.draw_graphviz(tree, label_func=lambda x: x.name.replace("ID=", ""))
plt.savefig(os.path.join(
out_dir_path, "figure_with_labels.pdf")) # need pygraphviz, pylab
# Clustering
ids = dict(enumerate(alignment_dict.keys()))
distance_matrix = np.zeros([len(ids)] * 2)
for i, j in itertools.combinations(xrange(len(ids)), r=2):
distance_matrix[i][j] = distance_matrix[j][i] = \
distance(alignment_dict[ids[i]], alignment_dict[ids[j]])
# Compute and plot dendrogram
fig = plt.figure()
axdendro = fig.add_axes([0.09, 0.1, 0.2, 0.8])
Y = linkage(distance_matrix, method="centroid")
cutoff = 0.5 * max(Y[:, 2])
clusters = fcluster(Y, cutoff, "distance")
Z = dendrogram(Y, orientation="right", color_threshold=cutoff)
axdendro.set_yticks([])
# Plot distance matrix
axmatrix = fig.add_axes([0.3, 0.1, 0.6, 0.8])
index = Z["leaves"]
distance_matrix = distance_matrix[index, :]
distance_matrix = distance_matrix[:, index]
im = axmatrix.matshow(distance_matrix, aspect="auto", origin="lower")
axmatrix.set_xticks([])
axmatrix.set_yticks([])
# Plot colorbar
axcolor = fig.add_axes([0.91, 0.1, 0.02, 0.8])
plt.colorbar(im, cax=axcolor)
# Display and save figure
dendogram_path = os.path.join(out_dir_path, "dendogram.png")
fig.savefig(dendogram_path)
fasta_clusters = defaultdict(list)
for i, cluster in enumerate(clusters):
fasta_id = ids[i]
fasta_clusters[cluster].append(alignment_dict[fasta_id])
# Saving information about clusters
clusters_dir_path = os.path.join(out_dir_path, "clusters")
if not os.path.exists(clusters_dir_path):
os.makedirs(clusters_dir_path)
clusters_meta_path = os.path.join(clusters_dir_path, "clusters_meta.txt")
meta_file = open(clusters_meta_path, "w")
for cluster_id, cluster in fasta_clusters.iteritems():
cluster_path = os.path.join(clusters_dir_path,
"cluster_{0}.fasta".format(cluster_id))
SeqIO.write(cluster, cluster_path, "fasta")
summary_align = AlignInfo.SummaryInfo(MultipleSeqAlignment(cluster))
consensus = summary_align.dumb_consensus()
pssm = summary_align.pos_specific_score_matrix(consensus,
chars_to_ignore=['-'])
frequencies = dict.fromkeys(IUPAC.protein.letters, 0)
frequencies.update(
(key, len(list(group)))
for key, group in itertools.groupby(sorted(consensus)))
frequencies.pop("X")
meta_file.write("""Cluster ID: {0}
Cluster size: {1}
Consensus:
{2}
PSSM:
{3}
Frequencies in consensus:
{4}
""".format(cluster_id, len(cluster), textwrap.fill(str(consensus)), pssm,
pprint.pformat(frequencies)))
fig = plt.figure()
pos = np.arange(len(IUPAC.protein.letters))
width = .5 # gives histogram aspect to the bar diagram
ax = plt.axes()
ax.set_xticks(pos + (width / 2))
ax.set_xticklabels(IUPAC.protein.letters)
plt.bar(pos, [frequencies[letter] for letter in IUPAC.protein.letters],
width,
color='r')
frequencies_path = os.path.join(
clusters_dir_path, "frequencies_{0}.png".format(cluster_id))
fig.savefig(frequencies_path)
def compute_tree(options, mat, names):
""" make upgma hierarchical clustering and write it as png and
graphviz dot
"""
# oops, convert to biopython matrix
matrix = []
for i in xrange(len(names)):
row = []
for j in xrange(i + 1):
# tree constructor writes 0-distances as 1s for some reason
# so we hack around here
val = float(mat[names[i]][names[j]])
if val == 0.:
val = 1e-10
elif val == 1.:
val = 1.1
row.append(val)
matrix.append(row)
dm = _DistanceMatrix(names, matrix)
# upgma tree
constructor = DistanceTreeConstructor()
tree = constructor.upgma(dm)
robust_makedirs(os.path.dirname(tree_path(options)))
Phylo.write(tree, tree_path(options), "newick")
# png tree -- note : doesn't work in toil
def f(x):
if "Inner" in str(x):
return ""
else:
return x
Phylo.draw_graphviz(tree, label_func = f, node_size=1000, node_shape="s", font_size=10)
pylab.savefig(tree_path(options).replace("newick", "png"))
# graphviz
# get networkx graph
nxgraph = Phylo.to_networkx(tree)
# make undirected
nxgraph = nx.Graph(nxgraph)
# push names to name labels
nxgraph = nx.convert_node_labels_to_integers(nxgraph, label_attribute="label")
for node_id in nxgraph.nodes():
node = nxgraph.node[node_id]
if "Inner" in str(node["label"]):
node["label"] = "\"\""
node["width"] = 0.001
node["height"] = 0.001
else:
node["fontsize"] = 18
for edge_id in nxgraph.edges():
edge = nxgraph.edge[edge_id[0]][edge_id[1]]
# in graphviz, weight means something else, so make it a label
weight = float(edge["weight"])
# undo hack from above
if weight > 1:
weight = 1.
if weight <= 1e-10 or weight == 1.:
weight = 0.
edge["weight"] = None
edge["label"] = "{0:.3g}".format(float(weight) * 100.)
edge["fontsize"] = 14
edge["len"] = draw_len(weight)
nx.write_dot(nxgraph, tree_path(options).replace("newick", "dot"))
def save_tree(tree, filename):
Phylo.draw_graphviz(tree, prog='dot') # Draw the tree
plt.title(filename) # set Title for figure
plt.savefig('./Output/images/' + filename + '.png', dpi=100) # Save tree in an image
plt.close() # Close the figure
plt.legend(loc='best', fontsize=12)
plt.savefig('offline-scores.png', bbox_inches='tight')
plt.figure()
plt.xlim([0, n_iters])
# plt.ylim(ymin=-400)
plt.xlabel("Iterations", fontsize=fontsize)
plt.ylabel("Data Log Likelihood", fontsize=fontsize)
for name, likelihood in likelihoods.items():
plt.plot(likelihood, label=name)
plt.legend(loc='best', fontsize=12)
plt.savefig('offline-likelihoods.png', bbox_inches='tight')
for type, model in models.items():
final_tree = model.copy()
plt.figure()
plot_tree_2d(final_tree, X, pca)
for node in final_tree.dfs():
if node.is_leaf():
node.point = y[node.point]
newick = final_tree.to_newick()
tree = Phylo.read(StringIO(newick), 'newick')
Phylo.draw_graphviz(tree, prog='neato')
plt.savefig('tree-%s.png' % type, bbox_inches='tight')
plt.show()
def processing(raw_fasta_path, out_dir_path):
if not os.path.exists(out_dir_path):
logging.info("Making directory {0}".format(out_dir_path))
os.makedirs(out_dir_path)
deduplicated_fasta = remove_duplicates(
SeqIO.parse(raw_fasta_path, "fasta"))
base = os.path.basename(raw_fasta_path)
fasta_path = os.path.join(out_dir_path, base)
logging.info("Writing FASTA in {0}".format(fasta_path))
SeqIO.write(deduplicated_fasta, fasta_path, "fasta")
# Multiple sequence alignment
cline = ClustalwCommandline("clustalw2", infile=fasta_path)
stdout, stderr = cline()
logging.info(cline)
clustalw_result_path = fasta_path.replace(".fasta", ".aln")
alignment_dict = SeqIO.to_dict(
AlignIO.read(clustalw_result_path, "clustal"))
# writing alignment table in .txt
with open(os.path.join(out_dir_path, "alignment.txt"), "w") as fout:
fout.write(
"\n".join(
str(record.seq) for record in alignment_dict.itervalues()))
# alignment tree drawing
tree_path = fasta_path.replace(".fasta", ".dnd")
tree = Phylo.read(tree_path, "newick")
tree.ladderize()
# with labels
Phylo.draw_graphviz(tree, label_func=lambda x: x.name.replace("ID=", ""))
plt.savefig(os.path.join(out_dir_path,
"figure_with_labels.pdf")) # need pygraphviz, pylab
# Clustering
ids = dict(enumerate(alignment_dict.keys()))
distance_matrix = np.zeros([len(ids)] * 2)
for i, j in itertools.combinations(xrange(len(ids)), r=2):
distance_matrix[i][j] = distance_matrix[j][i] = \
distance(alignment_dict[ids[i]], alignment_dict[ids[j]])
# Compute and plot dendrogram
fig = plt.figure()
axdendro = fig.add_axes([0.09, 0.1, 0.2, 0.8])
Y = linkage(distance_matrix, method="centroid")
cutoff = 0.5 * max(Y[:, 2])
clusters = fcluster(Y, cutoff, "distance")
Z = dendrogram(Y, orientation="right", color_threshold=cutoff)
axdendro.set_yticks([])
# Plot distance matrix
axmatrix = fig.add_axes([0.3, 0.1, 0.6, 0.8])
index = Z["leaves"]
distance_matrix = distance_matrix[index, :]
distance_matrix = distance_matrix[:, index]
im = axmatrix.matshow(distance_matrix, aspect="auto", origin="lower")
axmatrix.set_xticks([])
axmatrix.set_yticks([])
# Plot colorbar
axcolor = fig.add_axes([0.91, 0.1, 0.02, 0.8])
plt.colorbar(im, cax=axcolor)
# Display and save figure
dendogram_path = os.path.join(out_dir_path, "dendogram.png")
fig.savefig(dendogram_path)
fasta_clusters = defaultdict(list)
for i, cluster in enumerate(clusters):
fasta_id = ids[i]
fasta_clusters[cluster].append(alignment_dict[fasta_id])
# Saving information about clusters
clusters_dir_path = os.path.join(out_dir_path, "clusters")
if not os.path.exists(clusters_dir_path):
os.makedirs(clusters_dir_path)
clusters_meta_path = os.path.join(clusters_dir_path, "clusters_meta.txt")
meta_file = open(clusters_meta_path, "w")
for cluster_id, cluster in fasta_clusters.iteritems():
cluster_path = os.path.join(clusters_dir_path,
"cluster_{0}.fasta".format(cluster_id))
SeqIO.write(cluster, cluster_path, "fasta")
summary_align = AlignInfo.SummaryInfo(MultipleSeqAlignment(cluster))
consensus = summary_align.dumb_consensus()
pssm = summary_align.pos_specific_score_matrix(consensus,
chars_to_ignore=['-'])
frequencies = dict.fromkeys(IUPAC.protein.letters, 0)
frequencies.update(
(key, len(list(group)))
for key, group in itertools.groupby(sorted(consensus)))
frequencies.pop("X")
meta_file.write("""Cluster ID: {0}
Cluster size: {1}
Consensus:
{2}
PSSM:
{3}
Frequencies in consensus:
{4}
""".format(cluster_id, len(cluster), textwrap.fill(str(consensus)), pssm,
pprint.pformat(frequencies)))
fig = plt.figure()
pos = np.arange(len(IUPAC.protein.letters))
width = .5 # gives histogram aspect to the bar diagram
ax = plt.axes()
ax.set_xticks(pos + (width / 2))
ax.set_xticklabels(IUPAC.protein.letters)
plt.bar(pos,
[frequencies[letter] for letter in IUPAC.protein.letters],
width, color='r')
frequencies_path = os.path.join(
clusters_dir_path, "frequencies_{0}.png".format(cluster_id))
fig.savefig(frequencies_path)
from Bio import Phylo
# from pygraphviz import *
# from networkx.drawing import nx_agraph
tree = Phylo.read("Plotly/small.newick", 'newick')
Phylo.draw_graphviz(tree, prog='dot')
