pydruglogics package
Subpackages
- pydruglogics.execution package
- pydruglogics.input package
- pydruglogics.model package
- Submodules
- pydruglogics.model.BooleanModel
BooleanModel.calculate_attractors()
BooleanModel.calculate_global_output()
BooleanModel.from_binary()
BooleanModel.to_binary()
BooleanModel.add_perturbations()
BooleanModel.print()
BooleanModel.clone()
BooleanModel.reset_attractors()
BooleanModel.has_attractors()
BooleanModel.has_stable_states()
BooleanModel.has_global_output()
BooleanModel.get_stable_states()
BooleanModel.model_name
BooleanModel.boolean_equations
BooleanModel.binary_boolean_equations
BooleanModel.mutation_type
BooleanModel.global_output
BooleanModel.attractors
BooleanModel.attractor_tool
BooleanModel.attractor_type
- pydruglogics.model.BooleanModelOptimizer
- pydruglogics.model.Evolution
- pydruglogics.model.InteractionModel
- pydruglogics.model.ModelPredictions
- pydruglogics.model.Statistics
- pydruglogics.model.BooleanModel
- Module contents
- Submodules
- pydruglogics.utils package
Module contents
- class pydruglogics.BooleanModel(model=None, file=None, attractor_tool='mpbn', attractor_type='stable_states', mutation_type='topology', model_name='', cloned_equations=None, cloned_binary_equations=None)
Bases:
object
- add_perturbations(perturbations)
- property attractor_tool
- property attractor_type
- property attractors
- property binary_boolean_equations
- property boolean_equations
- calculate_attractors(attractor_tool, attractor_type)
- calculate_global_output(model_outputs, normalized=True)
- clone()
- from_binary(binary_representation, mutation_type)
- get_stable_states()
- property global_output
- has_attractors()
- has_global_output()
- has_stable_states()
- property model_name
- property mutation_type
- print()
- reset_attractors()
- to_binary(mutation_type)
- class pydruglogics.Evolution(boolean_model=None, training_data=None, model_outputs=None, ga_args=None, ev_args=None)
Bases:
BooleanModelOptimizer
- property best_boolean_models
- calculate_fitness(ga_instance, solutions, solution_idx)
- create_initial_population(population_size, num_mutations, seed=None)
- run()
- save_to_file_models(base_folder='./results/models')
- class pydruglogics.InteractionModel(interactions_file=None, model_name='', remove_self_regulated_interactions=False, remove_inputs=False, remove_outputs=False)
Bases:
object
- property all_targets
- get_activating_regulators(index)
- get_inhibitory_regulators(index)
- get_interaction(index)
- get_target(index)
- property interactions
- property model_name
- print()
- size()
- class pydruglogics.ModelOutputs(input_file=None, input_dictionary=None)
Bases:
object
- get_model_output(node_name)
- property max_output
- property min_output
- property model_outputs
- property node_names
- print()
- size()
- class pydruglogics.ModelPredictions(boolean_models=None, perturbations=None, model_outputs=None, synergy_method='bliss', model_directory=None, attractor_tool=None, attractor_type=None)
Bases:
object
- get_prediction_matrix()
- property predicted_synergy_scores
- run_simulations(parallel=True, cores=4)
- save_to_file_predictions(base_folder='./results/predictions')
- class pydruglogics.Perturbation(drug_data=None, perturbation_data=None)
Bases:
object
- property drug_effects
- property drug_names
- property drug_targets
- property drugs
- property perturbations
- print()
- class pydruglogics.PlotUtil
Bases:
object
- static plot_pr_curve_with_ci(pr_df, auc_pr, boot_n, plot_discrete)
- static plot_roc_and_pr_curve(predicted_synergy_scores, observed_synergy_scores, synergy_method, labels=None)
- class pydruglogics.TrainingData(input_file=None, observations=None)
Bases:
object
- property observations
- print()
- property response
- property responses
- size()
- property weight_sum
- property weights
- pydruglogics.compare_two_simulations(boolean_models1, boolean_models2, observed_synergy_scores, model_outputs, perturbations, synergy_method='bliss', label1='Models 1', label2='Models 2', normalized=True, plot=True, save_result=True)
- pydruglogics.execute(train_params=None, predict_params=None)
- pydruglogics.sampling_with_ci(boolean_models, observed_synergy_scores, model_outputs, perturbations, synergy_method='bliss', repeat_time=10, sub_ratio=0.8, boot_n=1000, confidence_level=0.9, plot=True, plot_discrete=False, save_result=True, with_seeds=True, seeds=42)
- pydruglogics.train(*args, **kwargs)