GuacaMol: Benchmarking Models for de Novo Molecular Design

• Published in: Journal of chemical information and modeling Vol. 59; no. 3; pp. 1096 - 1108
• Main Authors: Brown, Nathan, Fiscato, Marco, Segler, Marwin H.S, Vaucher, Alain C
• Format: Journal Article
• Language: English
• Published: United States American Chemical Society 25.03.2019
• Subjects: Algorithms; Benchmarking - methods; Benchmarks; Comparative studies; Deep Learning; Drug Design; Isomerism; Machine learning; Models, Molecular; Molecular Structure; Monte Carlo Method; Multiple objective analysis; Neural networks; Optimization; Organic chemistry; Pharmaceutical Preparations - chemistry; Quantitative Structure-Activity Relationship
• ISSN: 1549-9596; 1549-960X; 1549-960X
• DOI: 10.1021/acs.jcim.8b00839

De novo design seeks to generate molecules with required property profiles by virtual design-make-test cycles. With the emergence of deep learning and neural generative models in many application areas, models for molecular design based on neural networks appeared recently and show promising results. However, the new models have not been profiled on consistent tasks, and comparative studies to well-established algorithms have only seldom been performed. To standardize the assessment of both classical and neural models for de novo molecular design, we propose an evaluation framework, GuacaMol, based on a suite of standardized benchmarks. The benchmark tasks encompass measuring the fidelity of the models to reproduce the property distribution of the training sets, the ability to generate novel molecules, the exploration and exploitation of chemical space, and a variety of single and multiobjective optimization tasks. The benchmarking open-source Python code and a leaderboard can be found on https://benevolent.ai/guacamol.