A graph-based genetic algorithm and generative model/Monte Carlo tree search for the exploration of chemical space
Jan H. Jensen
Abstract
, 972-976) using a recurrent neural network (RNN) generative model, and the GB-GM-based method is several orders of magnitude faster. The MCTS results seem more dependent on the composition of the training set than the GA approach for this particular property. Our results suggest that the performance of new ML-based generative models should be compared to that of more traditional, and often simpler, approaches such a GA.
Topics & Concepts
Parameterized complexityAlgorithmGenerative modelComputer scienceMonte Carlo tree searchTraverseMonte Carlo methodGraphTree (set theory)Genetic algorithmGenerative grammarChemical spaceSet (abstract data type)Artificial intelligenceTheoretical computer scienceMachine learningMathematicsCombinatoricsBioinformaticsGeographyStatisticsDrug discoveryProgramming languageGeodesyBiologyComputational Drug Discovery MethodsMachine Learning in Materials ScienceAnalytical Chemistry and Chromatography