def main(self, name, opts):
logging.basicConfig(filename=opts.log_file,
format='%(levelname)s (%(asctime)s): %(message)s')
log = logging.getLogger(name)
if opts.verbose:
log.setLevel(logging.DEBUG)
else:
log.setLevel(logging.INFO)
if not opts.model_files:
raise ValueError('No model files provided!')
log.info('Loading model ...')
model = mod.load_model(opts.model_files)
log.info('Loading data ...')
nb_sample = dat.get_nb_sample(opts.data_files, opts.nb_sample)
replicate_names = dat.get_replicate_names(opts.data_files[0],
regex=opts.replicate_names,
nb_key=opts.nb_replicate)
data_reader = mod.data_reader_from_model(
model, replicate_names, replicate_names=replicate_names)
# Seed used since unobserved input CpG states are randomly sampled
if opts.seed is not None:
np.random.seed(opts.seed)
random.seed(opts.seed)
data_reader = data_reader(opts.data_files,
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False,
shuffle=False)
meta_reader = hdf.reader(opts.data_files, ['chromo', 'pos'],
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False,
shuffle=False)
writer = None
if opts.out_data:
writer = H5Writer(opts.out_data, nb_sample)
log.info('Predicting ...')
nb_tot = 0
nb_eval = 0
data_eval = dict()
perf_eval = []
progbar = ProgressBar(nb_sample, log.info)
for inputs, outputs, weights in data_reader:
batch_size = len(list(inputs.values())[0])
nb_tot += batch_size
progbar.update(batch_size)
preds = to_list(model.predict(inputs))
data_batch = dict()
data_batch['preds'] = dict()
data_batch['outputs'] = dict()
for i, name in enumerate(model.output_names):
data_batch['preds'][name] = preds[i].squeeze()
data_batch['outputs'][name] = outputs[name].squeeze()
for name, value in six.iteritems(next(meta_reader)):
data_batch[name] = value
if writer:
writer.write_dict(data_batch)
nb_eval += batch_size
dat.add_to_dict(data_batch, data_eval)
if nb_tot >= nb_sample or \
(opts.eval_size and nb_eval >= opts.eval_size):
data_eval = dat.stack_dict(data_eval)
perf_eval.append(
ev.evaluate_outputs(data_eval['outputs'],
data_eval['preds']))
data_eval = dict()
nb_eval = 0
progbar.close()
if writer:
writer.close()
report = pd.concat(perf_eval)
report = report.groupby(['metric', 'output']).mean().reset_index()
if opts.out_report:
report.to_csv(opts.out_report, sep='\t', index=False)
report = ev.unstack_report(report)
print(report.to_string())
log.info('Done!')
return 0
def main(self, name, opts):
logging.basicConfig(filename=opts.log_file,
format='%(levelname)s (%(asctime)s): %(message)s')
log = logging.getLogger(name)
if opts.verbose:
log.setLevel(logging.DEBUG)
else:
log.setLevel(logging.INFO)
if opts.seed is not None:
np.random.seed(opts.seed)
random.seed(opts.seed)
self.log = log
self.opts = opts
make_dir(opts.out_dir)
log.info('Building model ...')
model = self.build_model()
model.summary()
self.set_trainability(model)
if opts.filter_weights:
conv_layer = mod.get_first_conv_layer(model.layers)
log.info('Initializing filters of %s ...' % conv_layer.name)
self.init_filter_weights(opts.filter_weights, conv_layer)
mod.save_model(model, os.path.join(opts.out_dir, 'model.json'))
log.info('Computing output statistics ...')
output_names = []
for output_layer in model.output_layers:
output_names.append(output_layer.name)
output_stats = OrderedDict()
if opts.no_class_weights:
class_weights = None
else:
class_weights = OrderedDict()
for name in output_names:
output = hdf.read(opts.train_files,
'outputs/%s' % name,
nb_sample=opts.nb_train_sample)
output = list(output.values())[0]
output_stats[name] = get_output_stats(output)
if class_weights is not None:
class_weights[name] = get_output_class_weights(name, output)
self.print_output_stats(output_stats)
if class_weights:
self.print_class_weights(class_weights)
output_weights = None
if opts.output_weights:
log.info('Initializing output weights ...')
output_weights = get_output_weights(output_names,
opts.output_weights)
print('Output weights:')
for output_name in output_names:
if output_name in output_weights:
print('%s: %.2f' %
(output_name, output_weights[output_name]))
print()
self.metrics = dict()
for output_name in output_names:
self.metrics[output_name] = get_metrics(output_name)
optimizer = Adam(lr=opts.learning_rate)
model.compile(optimizer=optimizer,
loss=mod.get_objectives(output_names),
loss_weights=output_weights,
metrics=self.metrics)
log.info('Loading data ...')
replicate_names = dat.get_replicate_names(opts.train_files[0],
regex=opts.replicate_names,
nb_key=opts.nb_replicate)
data_reader = mod.data_reader_from_model(
model, replicate_names=replicate_names)
nb_train_sample = dat.get_nb_sample(opts.train_files,
opts.nb_train_sample)
train_data = data_reader(opts.train_files,
class_weights=class_weights,
batch_size=opts.batch_size,
nb_sample=nb_train_sample,
shuffle=True,
loop=True)
if opts.val_files:
nb_val_sample = dat.get_nb_sample(opts.val_files,
opts.nb_val_sample)
val_data = data_reader(opts.val_files,
batch_size=opts.batch_size,
nb_sample=nb_val_sample,
shuffle=False,
loop=True)
else:
val_data = None
nb_val_sample = None
log.info('Initializing callbacks ...')
callbacks = self.get_callbacks()
log.info('Training model ...')
print()
print('Training samples: %d' % nb_train_sample)
if nb_val_sample:
print('Validation samples: %d' % nb_val_sample)
model.fit_generator(train_data,
nb_train_sample,
opts.nb_epoch,
callbacks=callbacks,
validation_data=val_data,
nb_val_samples=nb_val_sample,
max_q_size=opts.data_q_size,
nb_worker=opts.data_nb_worker,
verbose=0)
print('\nTraining set performance:')
print(
format_table(self.perf_logger.epoch_logs, precision=LOG_PRECISION))
if self.perf_logger.val_epoch_logs:
print('\nValidation set performance:')
print(
format_table(self.perf_logger.val_epoch_logs,
precision=LOG_PRECISION))
# Restore model with highest validation performance
filename = os.path.join(opts.out_dir, 'model_weights_val.h5')
if os.path.isfile(filename):
model.load_weights(filename)
# Delete metrics since they cause problems when loading the model
# from HDF5 file. Metrics can be loaded from json + weights file.
model.metrics = None
model.metrics_names = None
model.metrics_tensors = None
model.save(os.path.join(opts.out_dir, 'model.h5'))
log.info('Done!')
return 0
def main(self, name, opts):
logging.basicConfig(filename=opts.log_file,
format='%(levelname)s (%(asctime)s): %(message)s')
log = logging.getLogger(name)
if opts.verbose:
log.setLevel(logging.DEBUG)
else:
log.setLevel(logging.INFO)
log.debug(opts)
if opts.seed is not None:
np.random.seed(opts.seed)
if not opts.model_files:
raise ValueError('No model files provided!')
log.info('Loading model ...')
K.set_learning_phase(0)
model = mod.load_model(opts.model_files)
# Get DNA layer.
dna_layer = None
for layer in model.layers:
if layer.name == 'dna':
dna_layer = layer
break
if not dna_layer:
raise ValueError('The provided model is not a DNA model!')
# Create output vector.
outputs = []
for output in model.outputs:
outputs.append(K.reshape(output, (-1, 1)))
outputs = K.concatenate(outputs, axis=1)
# Compute gradient of outputs wrt. DNA layer.
grads = []
for name in opts.targets:
if name == 'mean':
target = K.mean(outputs, axis=1)
elif name == 'var':
target = K.var(outputs, axis=1)
else:
raise ValueError('Invalid effect size "%s"!' % name)
grad = K.gradients(target, dna_layer.output)
grads.extend(grad)
grad_fun = K.function(model.inputs, grads)
log.info('Reading data ...')
nb_sample = dat.get_nb_sample(opts.data_files, opts.nb_sample)
replicate_names = dat.get_replicate_names(opts.data_files[0],
regex=opts.replicate_names,
nb_key=opts.nb_replicate)
data_reader = mod.data_reader_from_model(
model, outputs=False, replicate_names=replicate_names)
data_reader = data_reader(opts.data_files,
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False,
shuffle=False)
meta_reader = hdf.reader(opts.data_files, ['chromo', 'pos'],
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False,
shuffle=False)
out_file = h5.File(opts.out_file, 'w')
out_group = out_file
def h5_dump(path, data, idx, dtype=None, compression='gzip'):
if path not in out_group:
if dtype is None:
dtype = data.dtype
out_group.create_dataset(name=path,
shape=[nb_sample] +
list(data.shape[1:]),
dtype=dtype,
compression=compression)
out_group[path][idx:idx + len(data)] = data
log.info('Computing effects ...')
progbar = ProgressBar(nb_sample, log.info)
idx = 0
for inputs in data_reader:
if isinstance(inputs, dict):
inputs = list(inputs.values())
batch_size = len(inputs[0])
progbar.update(batch_size)
# Compute gradients.
grads = grad_fun(inputs)
# Slice window at center.
if opts.dna_wlen:
for i, grad in enumerate(grads):
delta = opts.dna_wlen // 2
ctr = grad.shape[1] // 2
grads[i] = grad[:, (ctr - delta):(ctr + delta + 1)]
# Aggregate effects in window
if opts.agg_effects:
for i, grad in enumerate(grads):
if opts.agg_effects == 'mean':
grad = grad.mean(axis=1)
elif opts.agg_effects == 'wmean':
weights = linear_weights(grad.shape[1])
grad = np.average(grad, axis=1, weights=weights)
elif opts.agg_effects == 'max':
grad = grad.max(axis=1)
else:
tmp = 'Invalid function "%s"!' % (opts.agg_effects)
raise ValueError(tmp)
grads[i] = grad
# Write computed effects
for name, grad in zip(opts.targets, grads):
h5_dump(name, grad, idx)
# Store inputs
if opts.store_inputs:
for name, value in zip(model.input_names, inputs):
h5_dump(name, value, idx)
# Store positions
for name, value in next(meta_reader).items():
h5_dump(name, value, idx)
idx += batch_size
progbar.close()
out_file.close()
log.info('Done!')
return 0
def main(self, name, opts):
logging.basicConfig(filename=opts.log_file,
format='%(levelname)s (%(asctime)s): %(message)s')
log = logging.getLogger(name)
if opts.verbose:
log.setLevel(logging.DEBUG)
else:
log.setLevel(logging.INFO)
log.debug(opts)
if opts.seed is not None:
np.random.seed(opts.seed)
if not opts.model_files:
raise ValueError('No model files provided!')
log.info('Loading model ...')
K.set_learning_phase(0)
model = mod.load_model(opts.model_files)
# Get DNA layer.
dna_layer = None
for layer in model.layers:
if layer.name == 'dna':
dna_layer = layer
break
if not dna_layer:
raise ValueError('The provided model is not a DNA model!')
# Create output vector.
outputs = []
for output in model.outputs:
outputs.append(K.reshape(output, (-1, 1)))
outputs = K.concatenate(outputs, axis=1)
# Compute gradient of outputs wrt. DNA layer.
grads = []
for name in opts.targets:
if name == 'mean':
target = K.mean(outputs, axis=1)
elif name == 'var':
target = K.var(outputs, axis=1)
else:
raise ValueError('Invalid effect size "%s"!' % name)
grad = K.gradients(target, dna_layer.output)
grads.extend(grad)
grad_fun = K.function(model.inputs, grads)
log.info('Reading data ...')
nb_sample = dat.get_nb_sample(opts.data_files, opts.nb_sample)
replicate_names = dat.get_replicate_names(
opts.data_files[0],
regex=opts.replicate_names,
nb_key=opts.nb_replicate)
data_reader = mod.data_reader_from_model(
model, outputs=False, replicate_names=replicate_names)
data_reader = data_reader(opts.data_files,
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False,
shuffle=False)
meta_reader = hdf.reader(opts.data_files, ['chromo', 'pos'],
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False,
shuffle=False)
out_file = h5.File(opts.out_file, 'w')
out_group = out_file
def h5_dump(path, data, idx, dtype=None, compression='gzip'):
if path not in out_group:
if dtype is None:
dtype = data.dtype
out_group.create_dataset(
name=path,
shape=[nb_sample] + list(data.shape[1:]),
dtype=dtype,
compression=compression
)
out_group[path][idx:idx+len(data)] = data
log.info('Computing effects ...')
progbar = ProgressBar(nb_sample, log.info)
idx = 0
for inputs in data_reader:
if isinstance(inputs, dict):
inputs = list(inputs.values())
batch_size = len(inputs[0])
progbar.update(batch_size)
# Compute gradients.
grads = grad_fun(inputs)
# Slice window at center.
if opts.dna_wlen:
for i, grad in enumerate(grads):
delta = opts.dna_wlen // 2
ctr = grad.shape[1] // 2
grads[i] = grad[:, (ctr-delta):(ctr+delta+1)]
# Aggregate effects in window
if opts.agg_effects:
for i, grad in enumerate(grads):
if opts.agg_effects == 'mean':
grad = grad.mean(axis=1)
elif opts.agg_effects == 'wmean':
weights = linear_weights(grad.shape[1])
grad = np.average(grad, axis=1, weights=weights)
elif opts.agg_effects == 'max':
grad = grad.max(axis=1)
else:
tmp = 'Invalid function "%s"!' % (opts.agg_effects)
raise ValueError(tmp)
grads[i] = grad
# Write computed effects
for name, grad in zip(opts.targets, grads):
h5_dump(name, grad, idx)
# Store inputs
if opts.store_inputs:
for name, value in zip(model.input_names, inputs):
h5_dump(name, value, idx)
# Store positions
for name, value in next(meta_reader).items():
h5_dump(name, value, idx)
idx += batch_size
progbar.close()
out_file.close()
log.info('Done!')
return 0
def main(self, name, opts):
logging.basicConfig(filename=opts.log_file,
format='%(levelname)s (%(asctime)s): %(message)s')
log = logging.getLogger(name)
if opts.verbose:
log.setLevel(logging.DEBUG)
else:
log.setLevel(logging.INFO)
if opts.seed is not None:
np.random.seed(opts.seed)
random.seed(opts.seed)
self.log = log
self.opts = opts
make_dir(opts.out_dir)
log.info('Building model ...')
model = self.build_model()
model.summary()
self.set_trainability(model)
if opts.filter_weights:
conv_layer = mod.get_first_conv_layer(model.layers)
log.info('Initializing filters of %s ...' % conv_layer.name)
self.init_filter_weights(opts.filter_weights, conv_layer)
mod.save_model(model, os.path.join(opts.out_dir, 'model.json'))
log.info('Computing output statistics ...')
output_names = model.output_names
output_stats = OrderedDict()
if opts.no_class_weights:
class_weights = None
else:
class_weights = OrderedDict()
for name in output_names:
output = hdf.read(opts.train_files, 'outputs/%s' % name,
nb_sample=opts.nb_train_sample)
output = list(output.values())[0]
output_stats[name] = get_output_stats(output)
if class_weights is not None:
class_weights[name] = get_output_class_weights(name, output)
self.print_output_stats(output_stats)
if class_weights:
self.print_class_weights(class_weights)
output_weights = None
if opts.output_weights:
log.info('Initializing output weights ...')
output_weights = get_output_weights(output_names,
opts.output_weights)
print('Output weights:')
for output_name in output_names:
if output_name in output_weights:
print('%s: %.2f' % (output_name,
output_weights[output_name]))
print()
self.metrics = dict()
for output_name in output_names:
self.metrics[output_name] = get_metrics(output_name)
optimizer = Adam(lr=opts.learning_rate)
model.compile(optimizer=optimizer,
loss=mod.get_objectives(output_names),
loss_weights=output_weights,
metrics=self.metrics)
log.info('Loading data ...')
replicate_names = dat.get_replicate_names(
opts.train_files[0],
regex=opts.replicate_names,
nb_key=opts.nb_replicate)
data_reader = mod.data_reader_from_model(
model, replicate_names=replicate_names)
nb_train_sample = dat.get_nb_sample(opts.train_files,
opts.nb_train_sample)
train_data = data_reader(opts.train_files,
class_weights=class_weights,
batch_size=opts.batch_size,
nb_sample=nb_train_sample,
shuffle=True,
loop=True)
if opts.val_files:
nb_val_sample = dat.get_nb_sample(opts.val_files,
opts.nb_val_sample)
val_data = data_reader(opts.val_files,
batch_size=opts.batch_size,
nb_sample=nb_val_sample,
shuffle=False,
loop=True)
else:
val_data = None
nb_val_sample = None
log.info('Initializing callbacks ...')
callbacks = self.get_callbacks()
log.info('Training model ...')
print()
print('Training samples: %d' % nb_train_sample)
if nb_val_sample:
print('Validation samples: %d' % nb_val_sample)
model.fit_generator(
train_data,
steps_per_epoch=nb_train_sample // opts.batch_size,
epochs=opts.nb_epoch,
callbacks=callbacks,
validation_data=val_data,
validation_steps=nb_val_sample // opts.batch_size,
max_queue_size=opts.data_q_size,
workers=opts.data_nb_worker,
verbose=0)
print('\nTraining set performance:')
print(format_table(self.perf_logger.epoch_logs,
precision=LOG_PRECISION))
if self.perf_logger.val_epoch_logs:
print('\nValidation set performance:')
print(format_table(self.perf_logger.val_epoch_logs,
precision=LOG_PRECISION))
# Restore model with highest validation performance
filename = os.path.join(opts.out_dir, 'model_weights_val.h5')
if os.path.isfile(filename):
model.load_weights(filename)
# Delete metrics since they cause problems when loading the model
# from HDF5 file. Metrics can be loaded from json + weights file.
model.metrics = None
model.metrics_names = None
model.metrics_tensors = None
model.save(os.path.join(opts.out_dir, 'model.h5'))
log.info('Done!')
return 0
def main(self, name, opts):
logging.basicConfig(filename=opts.log_file,
format='%(levelname)s (%(asctime)s): %(message)s')
log = logging.getLogger(name)
if opts.verbose:
log.setLevel(logging.DEBUG)
else:
log.setLevel(logging.INFO)
if not opts.model_files:
raise ValueError('No model files provided!')
log.info('Loading model ...')
model = mod.load_model(opts.model_files)
log.info('Loading data ...')
nb_sample = dat.get_nb_sample(opts.data_files, opts.nb_sample)
replicate_names = dat.get_replicate_names(
opts.data_files[0],
regex=opts.replicate_names,
nb_key=opts.nb_replicate)
data_reader = mod.data_reader_from_model(
model, replicate_names, replicate_names=replicate_names)
data_reader = data_reader(opts.data_files,
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False, shuffle=False)
meta_reader = hdf.reader(opts.data_files, ['chromo', 'pos'],
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False, shuffle=False)
log.info('Predicting ...')
data = dict()
progbar = ProgressBar(nb_sample, log.info)
for inputs, outputs, weights in data_reader:
batch_size = len(list(inputs.values())[0])
progbar.update(batch_size)
preds = to_list(model.predict(inputs))
data_batch = dict()
data_batch['preds'] = dict()
data_batch['outputs'] = dict()
for i, name in enumerate(model.output_names):
data_batch['preds'][name] = preds[i].squeeze()
data_batch['outputs'][name] = outputs[name].squeeze()
for name, value in next(meta_reader).items():
data_batch[name] = value
dat.add_to_dict(data_batch, data)
progbar.close()
data = dat.stack_dict(data)
report = ev.evaluate_outputs(data['outputs'], data['preds'])
if opts.out_report:
report.to_csv(opts.out_report, sep='\t', index=False)
report = ev.unstack_report(report)
print(report.to_string())
if opts.out_data:
hdf.write_data(data, opts.out_data)
log.info('Done!')
return 0
def main(self, name, opts):
logging.basicConfig(filename=opts.log_file,
format='%(levelname)s (%(asctime)s): %(message)s')
log = logging.getLogger(name)
if opts.verbose:
log.setLevel(logging.DEBUG)
else:
log.setLevel(logging.INFO)
if not opts.model_files:
raise ValueError('No model files provided!')
log.info('Loading model ...')
model = mod.load_model(opts.model_files)
log.info('Loading data ...')
nb_sample = dat.get_nb_sample(opts.data_files, opts.nb_sample)
replicate_names = dat.get_replicate_names(
opts.data_files[0],
regex=opts.replicate_names,
nb_key=opts.nb_replicate)
data_reader = mod.data_reader_from_model(
model, replicate_names, replicate_names=replicate_names)
# Seed used since unobserved input CpG states are randomly sampled
if opts.seed is not None:
np.random.seed(opts.seed)
random.seed(opts.seed)
data_reader = data_reader(opts.data_files,
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False, shuffle=False)
meta_reader = hdf.reader(opts.data_files, ['chromo', 'pos'],
nb_sample=nb_sample,
batch_size=opts.batch_size,
loop=False, shuffle=False)
writer = None
if opts.out_data:
writer = H5Writer(opts.out_data, nb_sample)
log.info('Predicting ...')
nb_tot = 0
nb_eval = 0
data_eval = dict()
perf_eval = []
progbar = ProgressBar(nb_sample, log.info)
for inputs, outputs, weights in data_reader:
batch_size = len(list(inputs.values())[0])
nb_tot += batch_size
progbar.update(batch_size)
preds = to_list(model.predict(inputs))
data_batch = dict()
data_batch['preds'] = dict()
data_batch['outputs'] = dict()
for i, name in enumerate(model.output_names):
data_batch['preds'][name] = preds[i].squeeze()
data_batch['outputs'][name] = outputs[name].squeeze()
for name, value in six.iteritems(next(meta_reader)):
data_batch[name] = value
if writer:
writer.write_dict(data_batch)
nb_eval += batch_size
dat.add_to_dict(data_batch, data_eval)
if nb_tot >= nb_sample or \
(opts.eval_size and nb_eval >= opts.eval_size):
data_eval = dat.stack_dict(data_eval)
perf_eval.append(ev.evaluate_outputs(data_eval['outputs'],
data_eval['preds']))
data_eval = dict()
nb_eval = 0
progbar.close()
if writer:
writer.close()
report = pd.concat(perf_eval)
report = report.groupby(['metric', 'output']).mean().reset_index()
if opts.out_report:
report.to_csv(opts.out_report, sep='\t', index=False)
report = ev.unstack_report(report)
print(report.to_string())
log.info('Done!')
return 0
