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 expo(args):
def filename_fn(args):
rs = 'N({}, {})'.format(args.radius, args.sigma)
return rs
def fpath(fname):
_fpath = os.path.join(args.output_dir, fname)
return _fpath
length = 5 * args.radius
linspace, data = SyntheticDataset.grid_data(args.num_points, length=length)
# loader = dataset[args.dataset](args)
# trainData = loader.train
# for batch_idx, samples in enumerate(trainData):
# data,labels = samples[DatasetType.InD]
plt.xlim(-1 * length, length)
plt.ylim(-1 * length, length)
for scale in tqdm([1, 2, 3, 4]):
sigma = scale * args.sigma
scale_args = deepcopy(args)
scale_args.sigma = sigma
fname = filename_fn(scale_args)
checkpoint_dir = os.path.join(args.work_dir, 'checkpoints')
saver = Saver(checkpoint_dir) # makes directory if already not present
payload = saver.load(hash_args(
scale_args)) #hash_args(scale_args) generates the hex string
def run_and_save(scale_args):
export = main(scale_args) #Model creation??
payload = export['model']
saver.save(hash_args(scale_args), payload)
return payload
export = payload or run_and_save(scale_args)
with torch.no_grad():
scores = inference(export, data)
np_x = data.cpu().numpy()
for key in scores:
score = scores[key].cpu().numpy()
plot_pcolormesh(np_x, linspace, score)
score_fname = '{}_{}'.format(fname, key)
plt.title(score_fname)
flush_plot(plt, fpath(score_fname) + '.png')
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('')
continue
seen.add(zinc)
order_list.append((order, Kd))
order_list = [
order for order, _ in sorted(order_list, key=lambda x: x[1])
]
plt.subplot(1, 3, bidx + 1)
sns.barplot(
x='order',
y='Kdpoint',
data=df_subset,
color=palette[bidx],
order=order_list,
ci=95,
capsize=0.4,
errcolor='#888888',
)
sns.swarmplot(
x='order',
y='Kdpoint',
data=df_subset,
color='black',
order=order_list,
)
plt.ylim([-100, 10100])
plt.savefig('figures/prediction_barplot_{}.svg'.format(model))
plt.close()
fname = 'target/log/train_davis2011kinase_{}.log'.format(model)
data += parse_log(model, fname)
df = pd.DataFrame(data, columns=[
'model', 'metric', 'quadrant', 'value', 'uncertainty',
])
quadrants = sorted(set(df.quadrant))
metrics = sorted(set(df.metric))
for quadrant in quadrants:
for metric in metrics:
df_subset = df[(df.metric == metric) &
(df.quadrant == quadrant)]
plt.figure()
sns.barplot(x='model', y='value', data=df_subset, ci=None,
order=models, hue='uncertainty', dodge=False,
palette=sns.color_palette("RdBu", n_colors=8))
sns.swarmplot(x='model', y='value', data=df_subset, color='black',
order=models)
if (metric == 'Pearson rho' or metric == 'Spearman r') \
and quadrant != 'unknown_all':
plt.ylim([ -0.05, 0.7 ])
if metric == 'MSE' and quadrant != 'unknown_all':
plt.ylim([ -0.01e7, 3e7 ])
plt.savefig('figures/benchmark_cv_{}_{}.svg'
.format(metric, quadrant))
plt.close()
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)
d1['label'] = 'Neighbor Replication'
d1['linestyle'] = 'dashed'
d2['label'] = "Virtual Servers"
plot(out_file,d1,d2)