def main():
""" Main function """
# Use 128 permutations to create the MinHash
enc = tm.Minhash(128)
lf = tm.LSHForest(128)
d = 10000
n = 1000
data = []
# Generating some random data
start = timer()
for i in range(n):
data.append(tm.VectorUchar(np.random.randint(0, high=2, size=d)))
print(f"Generating the data took {(timer() - start) * 1000}ms.")
# Use batch_add to parallelize the insertion of the arrays
start = timer()
lf.batch_add(enc.batch_from_binary_array(data))
print(f"Adding the data took {(timer() - start) * 1000}ms.")
# Index the added data
start = timer()
lf.index()
print(f"Indexing took {(timer() - start) * 1000}ms.")
# The configuration for the MST plot
# Distribute the tree more evenly
cfg = tm.LayoutConfiguration()
cfg.sl_scaling_min = 1
cfg.sl_scaling_max = 1
cfg.node_size = 1 / 50
# Construct the k-nearest neighbour graph
start = timer()
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, config=cfg)
print(f"layout_from_lsh_forest took {(timer() - start) * 1000}ms.")
# Plot spanning tree layout
start = timer()
for i in range(len(s)):
plt.plot(
[x[s[i]], x[t[i]]],
[y[s[i]], y[t[i]]],
"r-",
linewidth=1.0,
alpha=0.5,
zorder=1,
)
plt.scatter(x, y, s=0.1, zorder=2)
plt.tight_layout()
plt.savefig("lsh_forest_knng_mpl.png")
print(f"Plotting using matplotlib took {(timer() - start) * 1000}ms.")
def tree_coords(lf, node_size=1 / 20, k=20, mmm_rps=2):
print('Converting to tmap coordinates')
# Create a LayoutConfiguration instance
cfg = tm.LayoutConfiguration()
cfg.node_size = node_size
cfg.mmm_repeats = mmm_rps
cfg.sl_extra_scaling_steps = 5
cfg.k = k
cfg.sl_scaling_type = tm.RelativeToAvgLength
#Create minimum spanning tree from the LSHForest and LayoutConfiguration instance
#The x and y coordinates of the vertices, the ids of the vertices spanning the edges
#information on the graph is ignored
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, cfg)
return list(x), list(y), list(s), list(t)
def main():
""" Main function """
n = 1000
edge_list = []
weights = {}
# Create a random graph
for i in range(n):
for j in np.random.randint(0, high=n, size=2):
# Do not add parallel edges here, to be sure
# to have the right weight later
if i in weights and j in weights[i] or j in weights and i in weights[j]:
continue
weight = np.random.rand(1)
edge_list.append([i, j, weight])
# Store the weights in 2d map for easy access
if i not in weights:
weights[i] = {}
if j not in weights:
weights[j] = {}
# Invert weights to make lower ones more visible in the plot
weights[i][j] = 1.0 - weight
weights[j][i] = 1.0 - weight
# Set the initial randomized positioning to True
# Otherwise, OGDF tends to segfault
cfg = tm.LayoutConfiguration()
cfg.fme_randomize = True
# The configuration for the MST plot
# Distribute the tree more evenly
cfg_mst = tm.LayoutConfiguration()
cfg_mst.sl_scaling_min = 1
cfg_mst.sl_scaling_max = 1
# Compute the layout
x, y, s, t, _ = tm.layout_from_edge_list(n, edge_list, config=cfg, create_mst=False)
x_mst, y_mst, s_mst, t_mst, _ = tm.layout_from_edge_list(
n, edge_list, config=cfg_mst, create_mst=True
)
_, (ax1, ax2) = plt.subplots(ncols=2, sharey=True)
# Plot graph layout with spanning tree superimposed in red
for i in range(len(s)):
ax1.plot(
[x[s[i]], x[t[i]]],
[y[s[i]], y[t[i]]],
"k-",
linewidth=weights[s[i]][t[i]],
alpha=0.5,
zorder=1,
)
for i in range(len(s_mst)):
ax1.plot(
[x[s_mst[i]], x[t_mst[i]]],
[y[s_mst[i]], y[t_mst[i]]],
"r-",
linewidth=weights[s_mst[i]][t_mst[i]],
alpha=0.5,
zorder=2,
)
ax1.scatter(x, y, s=0.1, zorder=3)
# Plot spanning tree layout
for i in range(len(s_mst)):
ax2.plot(
[x_mst[s_mst[i]], x_mst[t_mst[i]]],
[y_mst[s_mst[i]], y_mst[t_mst[i]]],
"r-",
linewidth=weights[s_mst[i]][t_mst[i]],
alpha=0.5,
zorder=1,
)
ax2.scatter(x_mst, y_mst, s=0.1, zorder=2)
plt.tight_layout()
plt.savefig("spanning_tree_big.png")
from tqdm import tqdm
import os
import tmap as tm
# Load the data
MN = MNIST("./data/mnist-data")
IMAGES_TRAIN, LABELS_TRAIN = MN.load_training()
IMAGES_TEST, LABELS_TEST = MN.load_testing()
IMAGES = np.concatenate((IMAGES_TRAIN, IMAGES_TEST))
LABELS = np.concatenate((LABELS_TRAIN, LABELS_TEST))
IMAGE_LABELS = []
# Coniguration for the tmap layout
CFG = tm.LayoutConfiguration()
CFG.node_size = 1 / 50
def main():
""" Main function """
# Initialize and configure tmap
dims = 1024
enc = tm.Minhash(dims)
lf = tm.LSHForest(dims, 128)
print("Converting images ...")
for image in tqdm(IMAGES):
img = Image.fromarray(np.uint8(np.split(np.array(image), 28)))
buffered = BytesIO()
def main():
""" The main function """
df = pd.read_csv("papers.tar.xz")
df.drop(df.tail(1).index, inplace=True)
df["title"] = df["title"].apply(lambda t: t.replace("'", '"'))
enc = tm.Minhash()
lf = tm.LSHForest()
ctr = Counter()
texts = []
for _, row in df.iterrows():
text = re.sub(r"[^a-zA-Z-]+", " ", row["paper_text"])
text = [t.lower() for t in text.split(" ") if len(t) > 2]
ctr.update(text)
texts.append(text)
# Remove the top n words
n = 6000
ctr = ctr.most_common()[: -(len(ctr) - n) - 1 : -1]
# Make it fast using a lookup map
all_words = {}
for i, (key, _) in enumerate(ctr):
all_words[key] = i
# Create the fingerprints and also check whether the word
# "deep" is found in the document
fingerprints = []
has_word = []
for text in texts:
if "deep" in text:
has_word.append(1)
else:
has_word.append(0)
fingerprint = []
for t in text:
if t in all_words:
fingerprint.append(all_words[t])
fingerprints.append(tm.VectorUint(fingerprint))
# Index the article fingerprints
lf.batch_add(enc.batch_from_sparse_binary_array(fingerprints))
lf.index()
# Create the tmap
config = tm.LayoutConfiguration()
config.k = 100
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, config=config)
faerun = Faerun(
view="front", coords=False, legend_title="", legend_number_format="{:.0f}"
)
# Add a scatter that is bigger than the one above, to add colored
# circles.
faerun.add_scatter(
"NIPS_word",
{"x": x, "y": y, "c": has_word, "labels": df["title"]},
colormap="Set1",
point_scale=7.5,
max_point_size=25,
shader="smoothCircle",
has_legend=True,
categorical=True,
legend_title="Contains word<br/>'deep'",
legend_labels=[(0, "No"), (1, "Yes")],
interactive=False,
)
# Add a scatter that is colored by year on top
faerun.add_scatter(
"NIPS",
{"x": x, "y": y, "c": df["year"], "labels": df["title"]},
colormap="gray",
point_scale=5.0,
max_point_size=20,
shader="smoothCircle",
has_legend=True,
legend_title="Year of<br/>Publication",
)
faerun.add_tree(
"NIPS_tree", {"from": s, "to": t}, point_helper="NIPS", color="#666666"
)
faerun.plot("nips_papers")
def main():
""" Main function """
dims = 512
lf = tm.LSHForest(dims, 128, store=True)
# Due to the large data size (> 1GB) the following files are not provided directly
smiles, target_class, activity, chembl_id = pickle.load(
open("chembl.pickle", "rb"))
labels = []
for i, s in enumerate(smiles):
labels.append(
s + "__" + chembl_id[i] + "__" +
f'<a target="_blank" href="https://www.ebi.ac.uk/chembl/compound_report_card/{chembl_id[i]}">{chembl_id[i]}</a>'
)
lf.restore("chembl.dat")
target_class_map = dict([(y, x + 1)
for x, y in enumerate(sorted(set(target_class)))])
classes = [
"enzyme",
"kinase",
"protease",
"cytochrome p450",
"ion channel",
"transporter",
"transcription factor",
"membrane receptor",
"epigenetic regulator",
]
i = 0
for key, value in target_class_map.items():
if key not in classes:
target_class_map[key] = 7
else:
target_class_map[key] = i
i += 1
if i == 7:
i = 8
cfg = tm.LayoutConfiguration()
cfg.node_size = 1 / 70
cfg.mmm_repeats = 2
cfg.sl_repeats = 2
start = timer()
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, cfg)
end = timer()
print(end - start)
activity = np.array(activity)
activity = np.maximum(0.0, activity)
activity = np.minimum(100.0, activity)
activity = 10.0 - activity
legend_labels = [
(0, "Cytochrome p450"),
(1, "Other Enzyme"),
(2, "Epigenetic Regulator"),
(3, "Ion Channel"),
(4, "Kinase"),
(5, "Membrane Receptor"),
(6, "Protease"),
(8, "Transcription Factor"),
(9, "Transporter"),
(7, "Other"),
]
vals = [int(target_class_map[x]) for x in target_class]
faerun = Faerun(view="front", coords=False)
faerun.add_scatter(
"chembl",
{
"x": x,
"y": y,
"c": vals,
"labels": labels
},
colormap="tab10",
point_scale=1.0,
max_point_size=10,
has_legend=True,
categorical=True,
shader="smoothCircle",
legend_labels=legend_labels,
title_index=1,
)
faerun.add_tree("chembl_tree", {
"from": s,
"to": t
},
point_helper="chembl",
color="#222222")
faerun.plot("chembl", template="smiles")
"""
Visualizing RNA sequencing data using tmap.
Data Source:
https://gdc.cancer.gov/about-data/publications/pancanatlas
"""
import numpy as np
import pandas as pd
from faerun import Faerun
import tmap as tm
# Coniguration for the tmap layout
CFG_TMAP = tm.LayoutConfiguration()
CFG_TMAP.k = 50
CFG_TMAP.kc = 50
CFG_TMAP.node_size = 1 / 20
DATA = pd.read_csv("data.csv.xz", index_col=0, sep=",")
LABELS = pd.read_csv("labels.csv", index_col=0, sep=",")
LABELMAP = {"PRAD": 1, "LUAD": 2, "BRCA": 3, "KIRC": 4, "COAD": 5}
LABELS = np.array([int(LABELMAP[v]) for v in LABELS["Class"]], dtype=np.int)
def main():
""" Main function """
# Initialize and configure tmap
dims = 256
enc = tm.Minhash(len(DATA.columns), 42, dims)
def main():
""" The main function """
df = pd.read_csv("drugbank.csv").dropna(subset=["SMILES"]).reset_index(
drop=True)
enc = MHFPEncoder()
lf = tm.LSHForest(2048, 128)
fps = []
labels = []
groups = []
tpsa = []
logp = []
mw = []
h_acceptors = []
h_donors = []
ring_count = []
is_lipinski = []
has_coc = []
has_sa = []
has_tz = []
substruct_coc = AllChem.MolFromSmiles("COC")
substruct_sa = AllChem.MolFromSmiles("NS(=O)=O")
substruct_tz = AllChem.MolFromSmiles("N1N=NN=C1")
total = len(df)
for i, row in df.iterrows():
if i % 1000 == 0 and i > 0:
print(f"{round(100 * (i / total))}% done ...")
smiles = row[6]
mol = AllChem.MolFromSmiles(smiles)
if mol and mol.GetNumAtoms() > 5 and smiles.count(".") < 2:
fps.append(tm.VectorUint(enc.encode_mol(mol, min_radius=0)))
labels.append(
f'{smiles}__<a href="https://www.drugbank.ca/drugs/{row[0]}" target="_blank">{row[0]}</a>__{row[1]}'
.replace("'", ""))
groups.append(row[3].split(";")[0])
tpsa.append(Descriptors.TPSA(mol))
logp.append(Descriptors.MolLogP(mol))
mw.append(Descriptors.MolWt(mol))
h_acceptors.append(Descriptors.NumHAcceptors(mol))
h_donors.append(Descriptors.NumHDonors(mol))
ring_count.append(Descriptors.RingCount(mol))
is_lipinski.append(lipinski_pass(mol))
has_coc.append(mol.HasSubstructMatch(substruct_coc))
has_sa.append(mol.HasSubstructMatch(substruct_sa))
has_tz.append(mol.HasSubstructMatch(substruct_tz))
# Create the labels and the integer encoded array for the groups,
# as they're categorical
labels_groups, groups = Faerun.create_categories(groups)
tpsa_ranked = ss.rankdata(np.array(tpsa) / max(tpsa)) / len(tpsa)
logp_ranked = ss.rankdata(np.array(logp) / max(logp)) / len(logp)
mw_ranked = ss.rankdata(np.array(mw) / max(mw)) / len(mw)
h_acceptors_ranked = ss.rankdata(
np.array(h_acceptors) / max(h_acceptors)) / len(h_acceptors)
h_donors_ranked = ss.rankdata(
np.array(h_donors) / max(h_donors)) / len(h_donors)
ring_count_ranked = ss.rankdata(
np.array(ring_count) / max(ring_count)) / len(ring_count)
lf.batch_add(fps)
lf.index()
cfg = tm.LayoutConfiguration()
cfg.k = 100
# cfg.sl_extra_scaling_steps = 1
cfg.sl_repeats = 2
cfg.mmm_repeats = 2
cfg.node_size = 2
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, config=cfg)
# Define a colormap highlighting approved vs non-approved
custom_cmap = ListedColormap(
[
"#2ecc71", "#9b59b6", "#ecf0f1", "#e74c3c", "#e67e22", "#f1c40f",
"#95a5a6"
],
name="custom",
)
bin_cmap = ListedColormap(["#e74c3c", "#2ecc71"], name="bin_cmap")
f = Faerun(
clear_color="#222222",
coords=False,
view="front",
impress=
'made with <a href="http://tmap.gdb.tools" target="_blank">tmap</a><br />and <a href="https://github.com/reymond-group/faerun-python" target="_blank">faerun</a><br /><a href="https://gist.github.com/daenuprobst/5cddd0159c0cf4758fb16b4b4acbef89">source</a>',
)
f.add_scatter(
"Drugbank",
{
"x":
x,
"y":
y,
"c": [
groups,
is_lipinski,
has_coc,
has_sa,
has_tz,
tpsa_ranked,
logp_ranked,
mw_ranked,
h_acceptors_ranked,
h_donors_ranked,
ring_count_ranked,
],
"labels":
labels,
},
shader="smoothCircle",
colormap=[
custom_cmap,
bin_cmap,
bin_cmap,
bin_cmap,
bin_cmap,
"viridis",
"viridis",
"viridis",
"viridis",
"viridis",
"viridis",
],
point_scale=2.5,
categorical=[
True, True, True, True, True, False, False, False, False, False
],
has_legend=True,
legend_labels=[
labels_groups,
[(0, "No"), (1, "Yes")],
[(0, "No"), (1, "Yes")],
[(0, "No"), (1, "Yes")],
[(0, "No"), (1, "Yes")],
],
selected_labels=["SMILES", "Drugbank ID", "Name"],
series_title=[
"Group",
"Lipinski",
"Ethers",
"Sulfonamides",
"Tetrazoles",
"TPSA",
"logP",
"Mol Weight",
"H Acceptors",
"H Donors",
"Ring Count",
],
max_legend_label=[
None,
None,
None,
None,
None,
str(round(max(tpsa))),
str(round(max(logp))),
str(round(max(mw))),
str(round(max(h_acceptors))),
str(round(max(h_donors))),
str(round(max(ring_count))),
],
min_legend_label=[
None,
None,
None,
None,
None,
str(round(min(tpsa))),
str(round(min(logp))),
str(round(min(mw))),
str(round(min(h_acceptors))),
str(round(min(h_donors))),
str(round(min(ring_count))),
],
title_index=2,
legend_title="",
)
f.add_tree("drugbanktree", {"from": s, "to": t}, point_helper="Drugbank")
f.plot("drugbank", template="smiles")
