In Oct, HOU Tingjun's lab from College of Pharamceutical Sciences Zhejiang University, CHEN Xi's lab from Wuhan University, CAO Dongsheng's lab from Central South Universiy, together with Tencent Quantum Lab, published a research article entitled Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning in Nature Machine Intelligence.

Machine learning-based generative models can generate novel molecules with desirable physiochemical and pharmacological properties from scratch. Many excellent generative models have been proposed, but multi-objective optimizations in molecular generative tasks are still quite challenging for most existing models. Here we proposed the multi-constraint molecular generation (MCMG) approach that can satisfy multiple constraints by combining conditional transformer and reinforcement learning algorithms through knowledge distillation. A conditional transformer was used to train a molecular generative model by efficiently learning and incorporating the structure–property relations into a biased generative process. A knowledge distillation model was then employed to reduce the model’s complexity so that it can be efficiently fine-tuned by reinforcement learning and enhance the structural diversity of the generated molecules. As demonstrated by a set of comprehensive benchmarks, MCMG is a highly effective approach to traverse large and complex chemical space in search of novel compounds that satisfy multiple property constraints.

Zhejiang University Institute of Intelligent Innovative Drugs & Pharmacy is the first signatory unit of this paper. Ph.D. student WANG Jike from College of Pharamceutical Sciences Zhejiang University and Wuhan University School of Computer Science, Ph.D. XIE Changyu from Tencent Quantum Lab are co-first authour of this work, under the supervision of Professor HOU Tingjun from Zhejiang University, Professor CHEN Xi from Wuhan University, Professor CAO Dongsheng from Central South Universiy.

https://www.nature.com/articles/s42256-021-00403-1