Abstract

Automatic molecule design with machine learning and simulations has shown a remarkable ability to generate new and promising drug candidates. We propose a new population-based approach using a grammatical evolution named ChemGE, that can update a large population of molecules concurrently and evaluate with multiple simulators in parallel. In computational experiments, ChemGE succeeded in finding hundreds of candidate molecules whose affinity for thymidine kinase is better than that of known binding molecules in a database (DUD-E).

We propose a new population-based approach using grammatical evolution named ChemGE, that can update a large population of molecules concurrently and evaluate with multiple simulators in parallel. In computational experiments, ChemGE succeeded in finding hundreds of candidate molecules whose affinities for thymidine kinase are better than those of known binding molecules in a database (DUD-E).