def plot_clusters(coords, clusters, s=1):
if coords.shape[0] != clusters.shape[0]:
sys.stderr.write(
'Mismatch: {} cells, {} labels\n'
.format(coords.shape[0], clusters.shape[0])
)
assert(coords.shape[0] == clusters.shape[0])
colors = np.array(
list(islice(cycle([
'#377eb8', '#ff7f00', '#4daf4a',
'#f781bf', '#a65628', '#984ea3',
'#999999', '#e41a1c', '#dede00',
'#ffe119', '#e6194b', '#ffbea3',
'#911eb4', '#46f0f0', '#f032e6',
'#d2f53c', '#008080', '#e6beff',
'#aa6e28', '#800000', '#aaffc3',
'#808000', '#ffd8b1', '#000080',
'#808080', '#fabebe', '#a3f4ff'
]), int(max(clusters) + 1)))
)
plt.figure()
plt.scatter(coords[:, 0], coords[:, 1],
c=colors[clusters], s=s)
def plot_batch(df, batch):
# Plot 50uM.
df_50uM = df[df.conc == -3]
if batch.startswith('Ala'):
df_dmso = df_50uM[df_50uM.comp == 'DMSO']
for comp in [ 'K252a', 'SU11652', 'TG101209', 'RIF', 'IKK16' ]:
df_comp = df_50uM[df_50uM.comp == comp]
t, p_2side = ss.ttest_ind(df_comp.fluo, df_dmso.fluo)
p_1side = p_2side / 2. if t < 0 else 1. - (p_2side / 2.)
print('{}, one-sided t-test P = {}, n = {}'
.format(comp, p_1side, len(df_comp)))
if batch == 'AlaA':
order = [ 'K252a', 'SU11652', 'TG101209', 'RIF', 'DMSO' ]
elif batch == 'AlaB':
order = [ 'IKK16', 'K252a', 'RIF', 'DMSO' ]
else:
return
plt.figure()
sns.barplot(x='comp', y='fluo', data=df_50uM, ci=95, dodge=False,
hue='control', palette=sns.color_palette("RdBu_r", 7),
order=order, capsize=0.2, errcolor='#888888',)
sns.swarmplot(x='comp', y='fluo', data=df_50uM, color='black',
order=order)
#plt.ylim([ 10, 300000 ])
if not batch.startswith('Ala'):
plt.yscale('log')
plt.savefig('figures/tb_culture_50uM_{}.svg'.format(batch))
plt.close()
# Plot dose-response.
comps = sorted(set(df.comp))
concentrations = sorted(set(df.conc))
plt.figure(figsize=(24, 6))
for cidx, comp in enumerate(order):
df_subset = df[df.comp == comp]
plt.subplot(1, 5, cidx + 1)
sns.lineplot(x='conc', y='fluo', data=df_subset, ci=95,)
sns.scatterplot(x='conc', y='fluo', data=df_subset,
color='black',)
plt.title(comp)
if batch.startswith('Ala'):
plt.ylim([ 0., 1.3 ])
else:
plt.ylim([ 10, 1000000 ])
plt.yscale('log')
plt.xticks(list(range(-3, -6, -1)),
[ '50', '25', '10', ])#'1', '0.1' ])
plt.savefig('figures/tb_culture_{}.svg'.format(batch))
plt.close()
def visualize_heatmap(chem_prot, suffix=''):
plt.figure()
cmap = sns.diverging_palette(220, 10, as_cmap=True)
sns.heatmap(chem_prot, cmap=cmap)
mkdir_p('figures/')
if suffix == '':
plt.savefig('figures/heatmap.png', dpi=300)
else:
plt.savefig('figures/heatmap_{}.png'.format(suffix), dpi=300)
plt.close()
def acquisition_scatter(y_unk_pred, var_unk_pred, acquisition, regress_type):
y_unk_pred = y_unk_pred[:]
y_unk_pred[y_unk_pred > 10000] = 10000
plt.figure()
plt.scatter(y_unk_pred, var_unk_pred, alpha=0.5, c=-acquisition,
cmap='hot')
plt.title(regress_type.title())
plt.xlabel('Predicted score')
plt.ylabel('Variance')
plt.savefig('figures/acquisition_unknown_{}.png'
.format(regress_type), dpi=200)
plt.close()
def score_scatter(y_pred, y, var_pred, regress_type, prefix=''):
y_pred = y_pred[:]
y_pred[y_pred < 0] = 0
y_pred[y_pred > 10000] = 10000
plt.figure()
plt.scatter(y_pred, var_pred, alpha=0.3,
c=(y - y.min()) / (y.max() - y.min()))
plt.viridis()
plt.xlabel('Predicted score')
plt.ylabel('Variance')
plt.savefig('figures/variance_vs_pred_{}regressors{}.png'
.format(prefix, regress_type), dpi=300)
plt.close()
def plot_values(df, score_fn):
models = ['mlper1', 'sparsehybrid', 'gp', 'real']
plt.figure(figsize=(10, 4))
for midx, model in enumerate(models):
if model == 'gp':
color = '#3e5c71'
elif model == 'sparsehybrid':
color = '#2d574e'
elif model == 'mlper1':
color = '#a12424'
elif model == 'real':
color = '#A9A9A9'
else:
raise ValueError('Invalid model'.format(model))
plt.subplot(1, len(models), midx + 1)
df_subset = df[df.model == model]
compounds = np.array(df_subset.compound_)
if model == 'real':
order = sorted(compounds)
else:
order = compounds[np.argsort(-df_subset.affinity)]
sns.barplot(data=df_subset,
x='compound_',
y='affinity',
color=color,
order=order)
if score_fn == 'rdock':
plt.ylim([0, -40])
else:
plt.ylim([0, -12])
plt.xticks(rotation=45)
plt.savefig('figures/design_docking_{}.svg'.format(score_fn))
plt.close()
print('Score function: {}'.format(score_fn))
print('GP vs MLP: {}'.format(
ttest_ind(
df[df.model == 'gp'].affinity,
df[df.model == 'mlper1'].affinity,
)))
print('Hybrid vs MLP: {}'.format(
ttest_ind(
df[df.model == 'sparsehybrid'].affinity,
df[df.model == 'mlper1'].affinity,
)))
print('')
def plot_mapping(curr_ds, curr_ref, ds_ind, ref_ind):
tsne = TSNE(n_iter=400, verbose=VERBOSE, random_state=69)
tsne.fit(curr_ds)
plt.figure()
coords_ds = tsne.embedding_[:, :]
coords_ds[:, 1] += 100
plt.scatter(coords_ds[:, 0], coords_ds[:, 1])
tsne.fit(curr_ref)
coords_ref = tsne.embedding_[:, :]
plt.scatter(coords_ref[:, 0], coords_ref[:, 1])
x_list, y_list = [], []
for r_i, c_i in zip(ds_ind, ref_ind):
x_list.append(coords_ds[r_i, 0])
x_list.append(coords_ref[c_i, 0])
x_list.append(None)
y_list.append(coords_ds[r_i, 1])
y_list.append(coords_ref[c_i, 1])
y_list.append(None)
plt.plot(x_list, y_list, 'b-', alpha=0.3)
plt.show()
continue
if t >= 1600000 + a:
break
d[line[:1]]['x'].append(t-a)
d[line[:1]]['y'].append(k)
s['x'].append(t-a)
s['y'].append(n)
for i in ['J']:
d[i] = sample(d[i],1000)
s = sample(s)
print "loaded data"
fig = plt.figure()
from matplotlib.ticker import EngFormatter
formatter = EngFormatter(places=1)
textsize = 11
mode = "all"
if mode == 'all':
fig.set_size_inches(20,4)
p = 211
i = 'J'
ax1 = fig.add_subplot(p)
ax1.set_ylabel('#Keys Moved')
formatter = EngFormatter(places=1)
'chem',
'prot',
'pred_Kd',
'Kd',
'Kdpoint',
])
models = sorted(set(df.model))
betas = sorted(set(df.beta))
for model in models:
if model == 'Sparse Hybrid':
palette = sns.color_palette('ch:2.5,-.2,dark=.3', len(betas))
else:
palette = list(reversed(sns.color_palette('Blues_d', len(betas))))
plt.figure()
for bidx, beta in enumerate(betas):
df_subset = df[(df.model == model) & (df.beta == beta)]
seen, order_list = set(), []
for zinc, order, Kd in zip(df_subset.zincid, df_subset.order,
df_subset.Kd):
if zinc in seen:
continue
seen.add(zinc)
order_list.append((order, Kd))
order_list = [
order for order, _ in sorted(order_list, key=lambda x: x[1])
]
#% Load model
model = load_model(filepath + 'unet_exp_' + str(exp) + '.h5', compile=False)
area = 11
# Prediction
ref_final, pre_final, prob_recontructed, ref_reconstructed, mask_no_considered_, mask_ts, time_ts = prediction(
model, image_array, image_ref, final_mask, mask_ts_, patch_size, area)
# Metrics
cm = confusion_matrix(ref_final, pre_final)
metrics = compute_metrics(ref_final, pre_final)
print('Confusion matrix \n', cm)
print('Accuracy: ', metrics[0])
print('F1score: ', metrics[1])
print('Recall: ', metrics[2])
print('Precision: ', metrics[3])
# Alarm area
total = (cm[1, 1] + cm[0, 1]) / len(ref_final) * 100
print('Area to be analyzed', total)
print('training time', end_training)
print('test time', time_ts)
#%% Show the results
# prediction of the whole image
fig1 = plt.figure('whole prediction')
plt.imshow(prob_recontructed)
# Show the test tiles
fig2 = plt.figure('prediction of test set')
plt.imshow(prob_recontructed * mask_ts)
for line in fileinput.input(f+"/control.queries"):
if "loadFreqs" in line:
loads.append(line)
if len(loads) < 2:
print "coudln't find loads for " + f
continue
loads_d = []
for i in loads:
loads_d.append(get_num_dict(i))
chord_loads.append(get_50_percent(loads_d[0]))
vserver_loads.append(get_50_percent(loads_d[1]))
x_values.append(next(get_numbers(f)))
plt.figure().set_size_inches(6.5,5)
plt.xlabel("#Nodes")
plt.ylabel("% of nodes storing 50% of data")
from matplotlib.ticker import EngFormatter
formatter = EngFormatter(places=0)
plt.gca().xaxis.set_major_formatter(formatter)
plt.ylim(0,0.5)
plt.xlim(0,1000000)
out_file = "intro_lb_chord.pdf"
d1 = prepare(x_values,chord_loads)
d2 = prepare(x_values,vserver_loads)
# ref_final, pre_final, prob_recontructed, ref_reconstructed, mask_no_considered_, mask_ts, time_ts = prediction(model, image_array, image_ref, final_mask, mask_ts_, patch_size, area)
# Metrics
true_labels = np.reshape(patches_test_ref, (patches_test_ref.shape[0]* patches_test_ref.shape[1]*patches_test_ref.shape[2]))
predicted_labels = np.reshape(patches_pred, (patches_pred.shape[0]* patches_pred.shape[1]*patches_pred.shape[2]))
cm = confusion_matrix(true_labels, predicted_labels)
metrics = compute_metrics(true_labels, predicted_labels)
print('Confusion matrix \n', cm)
print('Accuracy: ', metrics[0])
print('F1score: ', metrics[1])
print('Recall: ', metrics[2])
print('Precision: ', metrics[3])
# Alarm area
total = (cm[1,1]+cm[0,1])/len(true_label)*100
print('Area to be analyzed',total)
print('training time', end_training)
print('test time', time_ts)
#%% Show the results
# prediction of the whole image
fig1 = plt.figure('whole prediction')
plt.imshow(prob_recontructed)
# Show the test tiles
# fig2 = plt.figure('prediction of test set')
# plt.imshow(prob_recontructed*mask_ts)
y_true = masks.reshape(
masks.shape[0] * masks.shape[1] * masks.shape[2] * masks.shape[3], 1)
y_scores = np.where(y_scores > 0.5, 1, 0)
y_true = np.where(y_true > 0.5, 1, 0)
import os
os.mkdir('./output')
output_folder = 'output/'
#Area under the ROC curve
fpr, tpr, thresholds = roc_curve((y_true), y_scores)
AUC_ROC = roc_auc_score(y_true, y_scores)
print("\nArea under the ROC curve: " + str(AUC_ROC))
roc_curve = plt.figure()
plt.plot(fpr, tpr, '-', label='Area Under the Curve (AUC = %0.4f)' % AUC_ROC)
plt.title('ROC curve')
plt.xlabel("FPR (False Positive Rate)")
plt.ylabel("TPR (True Positive Rate)")
plt.legend(loc="lower right")
plt.savefig(output_folder + "ROC.png")
#Precision-recall curve
precision, recall, thresholds = precision_recall_curve(y_true, y_scores)
precision = np.fliplr([precision])[0]
recall = np.fliplr([recall])[0]
AUC_prec_rec = np.trapz(precision, recall)
print("\nArea under Precision-Recall curve: " + str(AUC_prec_rec))
prec_rec_curve = plt.figure()
plt.plot(recall,
def latent_scatter(var_unk_pred, y_unk_pred, acquisition, **kwargs):
chems = kwargs['chems']
chem2feature = kwargs['chem2feature']
idx_obs = kwargs['idx_obs']
idx_unk = kwargs['idx_unk']
regress_type = kwargs['regress_type']
prot_target = kwargs['prot_target']
chem_idx_obs = sorted(set([i for i, _ in idx_obs]))
chem_idx_unk = sorted(set([i for i, _ in idx_unk]))
feature_obs = np.array([chem2feature[chems[i]] for i in chem_idx_obs])
feature_unk = np.array([chem2feature[chems[i]] for i in chem_idx_unk])
from sklearn.neighbors import NearestNeighbors
nbrs = NearestNeighbors(n_neighbors=1).fit(feature_obs)
dist = np.ravel(nbrs.kneighbors(feature_unk)[0])
print('Distance Spearman r = {}, P = {}'.format(
*ss.spearmanr(dist, var_unk_pred)))
print('Distance Pearson rho = {}, P = {}'.format(
*ss.pearsonr(dist, var_unk_pred)))
X = np.vstack([feature_obs, feature_unk])
labels = np.concatenate(
[np.zeros(len(chem_idx_obs)),
np.ones(len(chem_idx_unk))])
sidx = np.argsort(-var_unk_pred)
from fbpca import pca
U, s, Vt = pca(
X,
k=3,
)
X_pca = U * s
from umap import UMAP
um = UMAP(
n_neighbors=15,
min_dist=0.5,
n_components=2,
metric='euclidean',
)
X_umap = um.fit_transform(X)
from MulticoreTSNE import MulticoreTSNE as TSNE
tsne = TSNE(
n_components=2,
n_jobs=20,
)
X_tsne = tsne.fit_transform(X)
if prot_target is None:
suffix = ''
else:
suffix = '_' + prot_target
for name, coords in zip(
['pca', 'umap', 'tsne'],
[X_pca, X_umap, X_tsne],
):
plt.figure()
sns.scatterplot(
x=coords[labels == 1, 0],
y=coords[labels == 1, 1],
color='blue',
alpha=0.1,
)
plt.scatter(
x=coords[labels == 0, 0],
y=coords[labels == 0, 1],
color='orange',
alpha=1.0,
marker='x',
linewidths=10,
)
plt.savefig('figures/latent_scatter_{}_ypred_{}{}.png'.format(
name, regress_type, suffix),
dpi=300)
plt.close()
plt.figure()
plt.scatter(x=coords[labels == 1, 0],
y=coords[labels == 1, 1],
c=ss.rankdata(var_unk_pred),
alpha=0.1,
cmap='coolwarm')
plt.savefig('figures/latent_scatter_{}_var_{}{}.png'.format(
name, regress_type, suffix),
dpi=300)
plt.close()
plt.figure()
plt.scatter(x=coords[labels == 1, 0],
y=coords[labels == 1, 1],
c=-acquisition,
alpha=0.1,
cmap='hot')
plt.savefig('figures/latent_scatter_{}_acq_{}{}.png'.format(
name, regress_type, suffix),
dpi=300)
plt.close()
def parse_log(regress_type, experiment, **kwargs):
log_fname = ('iterate_davis2011kinase_{}_{}.log'.format(
regress_type, experiment))
iteration = 0
iter_to_Kds = {}
iter_to_idxs = {}
with open(log_fname) as f:
while True:
line = f.readline()
if not line:
break
if not line.startswith('2019') and not line.startswith('2020'):
continue
if not ' | ' in line:
continue
line = line.split(' | ')[1]
if line.startswith('Iteration'):
iteration = int(line.strip().split()[-1])
if not iteration in iter_to_Kds:
iter_to_Kds[iteration] = []
if not iteration in iter_to_idxs:
iter_to_idxs[iteration] = []
continue
elif line.startswith('\tAcquire '):
fields = line.strip().split()
Kd = float(fields[-1])
iter_to_Kds[iteration].append(Kd)
chem_idx = int(fields[1].lstrip('(').rstrip(','))
prot_idx = int(fields[2].strip().rstrip(')'))
iter_to_idxs[iteration].append((chem_idx, prot_idx))
continue
assert (iter_to_Kds.keys() == iter_to_idxs.keys())
iterations = sorted(iter_to_Kds.keys())
# Plot Kd over iterations.
Kd_iter, Kd_iter_max, Kd_iter_min = [], [], []
all_Kds = []
for iteration in iterations:
Kd_iter.append(np.mean(iter_to_Kds[iteration]))
Kd_iter_max.append(max(iter_to_Kds[iteration]))
Kd_iter_min.append(min(iter_to_Kds[iteration]))
all_Kds += list(iter_to_Kds[iteration])
if iteration == 0:
print('First average Kd is {}'.format(Kd_iter[0]))
elif iteration > 4 and experiment == 'perprot':
break
print('Average Kd is {}'.format(np.mean(all_Kds)))
plt.figure()
plt.scatter(iterations, Kd_iter)
plt.plot(iterations, Kd_iter)
plt.fill_between(iterations, Kd_iter_min, Kd_iter_max, alpha=0.3)
plt.viridis()
plt.title(' '.join([regress_type, experiment]))
plt.savefig('figures/Kd_over_iterations_{}_{}.png'.format(
regress_type, experiment))
plt.close()
return
# Plot differential entropy of acquired samples over iterations.
chems = kwargs['chems']
prots = kwargs['prots']
chem2feature = kwargs['chem2feature']
prot2feature = kwargs['prot2feature']
d_entropies = []
X_acquired = []
for iteration in iterations:
for i, j in iter_to_idxs[iteration]:
chem = chems[i]
prot = prots[j]
X_acquired.append(chem2feature[chem] + prot2feature[prot])
if len(X_acquired) <= 1:
d_entropies.append(float('nan'))
else:
gaussian = GaussianMixture().fit(np.array(X_acquired))
gaussian = multivariate_normal(gaussian.means_[0],
gaussian.covariances_[0])
d_entropies.append(gaussian.entropy())
print('Final differential entropy is {}'.format(d_entropies[-1]))
plt.figure()
plt.scatter(iterations, d_entropies)
plt.plot(iterations, d_entropies)
plt.viridis()
plt.title(' '.join([regress_type, experiment]))
plt.savefig('figures/entropy_over_iterations_{}_{}.png'.format(
regress_type, experiment))
plt.close()
