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 = []