from neuralbinder.deepomics import utils, fit
#---------------------------------------------------------------------------------------
num_epochs = 200
batch_size = 100
# different deep learning models to try out
models = [
'affinity_conv_net', 'affinity_residualbind', 'affinity_all_conv_net'
]
normalize_method = 'log_norm' # 'clip_norm' 'log_norm'
ss_types = ['seq', 'pu', 'struct']
data_path = neuralbinder.get_datasets('rnacompete2013.h5')
results_path = helper.make_directory('../../results', 'RNAcompete_2013')
#---------------------------------------------------------------------------------------
# get list of rnacompete experiments
experiments = helper.get_experiments_hdf5(data_path)
# loop over different secondary structure contexts
for ss_type in ss_types:
print('input data: ' + ss_type)
sstype_path = helper.make_directory(results_path,
normalize_method + '_' + ss_type)
# loop over different models
for model in models:
print('model: ' + model)
}
return model_layers, optimization
#---------------------------------------------------------------------------------------
# get list of rnacompete experiments
rbp_names = ['Fusip','HuR', 'PTB', 'RBM4', 'SF2', 'SLM2', 'U1A', 'VTS1', 'YB1'] #
# loop over different secondary structure contexts
for ss_type in ss_types:
print('input data: ' + ss_type)
sstype_path = os.path.join(trained_path, normalize_method+'_'+ss_type)
# directory to save parameters of saliency
classifier_path = helper.make_directory(results_path, normalize_method+'_'+ss_type)
classifier_path = helper.make_directory(classifier_path, 'ensemble')
# path to pre-trained model parameters
best_path = os.path.join(trained_path, 'mixed_'+normalize_method+'_'+ss_type)
# loop over different RNA binding proteins
for rbp_name in rbp_names:
print('Analyzing: '+ rbp_name)
tf.reset_default_graph() # reset any tensorflow graphs
np.random.seed(247) # for reproducibilitjy
tf.set_random_seed(247) # for reproducibility
# load rbp dataset
train, valid, test = helper.load_dataset_hdf5(data_path, dataset_name=rbp_name, ss_type=ss_type)
#rbp_names = ['TIA1', 'RBFOX2', 'PTBP1', 'HNRNPC', 'TIA1', 'RBFOX2', 'PTBP1', 'PUM2']
#cell_names = ['HepG2', 'HepG2', 'HepG2', 'HepG2', 'K562', 'K562', 'K562', 'K562']
rbp_name = 'PPIG'
cell_name = 'HepG2'
model_name = 'clip_residualbind' #'clip_conv_net'
ss_type = 'seq'
window = 200
# dataset path
dataset_path = '/media/peter/storage/encode_eclip/eclip_datasets'
dataset_file_path = os.path.join(dataset_path,
experiment_name + '_' + str(window) + '.h5')
# set results path
results_path = helper.make_directory('../../results', 'encode_eclip')
# model results path
model_path = helper.make_directory(results_path, model_name)
# path to save model
experiment_name = rbp_name + '_' + cell_name
model_save_path = os.path.join(model_path, experiment_name)
#-----------------------------------------------------------------------------------------
# load dataset
train, valid, test = helper.load_dataset_hdf5(dataset_file_path,
ss_type=ss_type)
# get shapes of data
input_shape = list(train['inputs'].shape)
}
return model_layers, optimization
#---------------------------------------------------------------------------------------
# get list of rnacompete experiments
rbp_names = ['Fusip', 'HuR', 'PTB', 'RBM4', 'SF2', 'SLM2', 'U1A', 'VTS1', 'YB1']
# loop over different secondary structure contexts
for ss_type in ss_types:
print('input data: ' + ss_type)
sstype_path = os.path.join(trained_path, normalize_method+'_'+ss_type)
# path to save parameters of saliency classifier
classifier_sstype_path = helper.make_directory(results_path, normalize_method+'_'+ss_type)
# loop over different models
for model in models:
print('model: ' + model)
model_path = os.path.join(sstype_path, model)
classifier_model_path = helper.make_directory(classifier_sstype_path, model)
# loop over different RNA binding proteins
for rbp_name in rbp_names:
print('Analyzing: '+ rbp_name)
tf.reset_default_graph() # reset any tensorflow graphs
np.random.seed(247) # for reproducibilitjy
tf.set_random_seed(247) # for reproducibility
data_path = neuralbinder.get_datasets('rnacompete2013.h5')
trained_path = '../../results/RNAcompete_2013'
results_path = utils.make_directory(trained_path, 'saliency')
#---------------------------------------------------------------------------------------
# get list of rnacompete experiments
experiments = helper.get_experiments_hdf5(data_path)
# loop over different secondary structure contexts
for ss_type in ss_types:
print('input data: ' + ss_type)
sstype_path = os.path.join(trained_path, normalize_method+'_'+ss_type)
# directory to save parameters of saliency
saliency_sstype_path = helper.make_directory(results_path, normalize_method+'_'+ss_type)
saliency_sstype_path = helper.make_directory(saliency_sstype_path, 'ensemble')
# path to pre-trained model parameters
best_path = os.path.join(trained_path, normalize_method+'_'+ss_type)
# loop over different RNA binding proteins
for rbp_index, experiment in enumerate(experiments):
print('Analyzing: '+ experiment)
tf.reset_default_graph() # reset any tensorflow graphs
np.random.seed(247) # for reproducibilitjy
tf.set_random_seed(247) # for reproducibility
# path to save saliency plots for each rbp experiment
rbp_path = helper.make_directory(saliency_sstype_path, experiment)
print(rbp_path)
from neuralbinder.neuralbindhelpers import helper
from neuralbinder.deepomics import neuralnetwork as nn
from neuralbinder.deepomics import utils, fit
#---------------------------------------------------------------------------------------------------
models = ['clip_conv_net', 'clip_residualbind', 'clip_all_conv_net']
ss_types = ['seq', 'pu']
window = 200
# dataset path
dataset_path = '/media/peter/storage/encode_eclip/eclip_datasets'
# set results path
results_path = helper.make_directory('../../results', 'encode_eclip')
# get list of .h5 files in dataset path
file_names = helper.get_file_names(dataset_path)
# loop through models
for model in models:
# model results path
model_path = helper.make_directory(results_path, model)
# loop through secondary structure types
for ss_type in ss_types:
# model results path
sstype_path = helper.make_directory(model_path, ss_type)
ss_types = ['seq', 'pu']
data_path = neuralbinder.get_datasets('rnacompete2009.h5')
trained_path = '../../results/RNAcompete_2009'
results_path = utils.make_directory(trained_path, 'mixed_saliency')
#---------------------------------------------------------------------------------------
# get list of rnacompete experiments
rbp_names = ['Fusip', 'HuR', 'PTB', 'RBM4', 'SF2', 'SLM2', 'U1A', 'VTS1', 'YB1']
# loop over different secondary structure contexts
for ss_type in ss_types:
print('input data: ' + ss_type)
sstype_path = helper.make_directory(trained_path, 'mixed_'+normalize_method+'_'+ss_type)
# directory to save parameters of saliency
saliency_sstype_path = helper.make_directory(results_path, 'mixed_'+normalize_method+'_'+ss_type)
# loop over different models
for model in models:
print('model: ' + model)
model_path = helper.make_directory(sstype_path, model)
# sub-directory to save parameters of saliency
saliency_model_path = helper.make_directory(saliency_sstype_path, model)
# loop over different RNA binding proteins
for rbp_name in rbp_names:
print('Analyzing: '+ rbp_name)
data_path = neuralbinder.get_datasets('rnacompete2013.h5')
trained_path = '../../results/RNAcompete_2013'
results_path = utils.make_directory(trained_path, 'saliency')
#---------------------------------------------------------------------------------------
# get list of rnacompete experiments
experiments = helper.get_experiments_hdf5(data_path)
# loop over different secondary structure contexts
for ss_type in ss_types:
print('input data: ' + ss_type)
sstype_path = os.path.join(trained_path, normalize_method + '_' + ss_type)
# directory to save parameters of saliency
saliency_sstype_path = helper.make_directory(
results_path, normalize_method + '_' + ss_type)
# loop over different models
for model in models:
print('model: ' + model)
model_path = helper.make_directory(sstype_path, model)
# sub-directory to save parameters of saliency
saliency_model_path = helper.make_directory(saliency_sstype_path,
model)
# loop over different RNA binding proteins
for rbp_index, experiment in enumerate(experiments):
print('Analyzing: ' + experiment)
tf.reset_default_graph() # reset any tensorflow graphs
np.random.seed(247) # for reproducibilitjy
from neuralbinder.neuralbindhelpers import helper, plot_helper
from neuralbinder.deepomics import neuralnetwork as nn
from neuralbinder.deepomics import utils, fit
#---------------------------------------------------------------------------------------
models = ['clip_conv_net', 'clip_residualbind']
ss_types = ['seq', 'pu']
window = 200
# dataset path
dataset_path = '/media/peter/storage/encode_eclip/eclip_datasets'
# set results path
results_path = helper.make_directory('../../results', 'encode_eclip')
saliency_results_path = utils.make_directory(results_path, 'saliency_ensemble')
# get list of .h5 files in dataset path
file_names = helper.get_file_names(dataset_path)
# loop through secondary structure types
for ss_type in ss_types:
# model results path
sstype_path = os.path.join(results_path, ss_type)
saliency_sstype_path = helper.make_directory(saliency_results_path,
ss_type)
# loop through each eclip dataset
results = []
