# Self-awareness of retrosynthesis via chemically inspired contrastive learning for reinforced molecule generation

## TL;DR

A new molecule generation model uses contrastive learning and reinforcement learning to create valid and biologically active compounds for cancer treatment.

## Contribution

A novel molecule generation model that integrates chemically inspired contrastive learning with reinforcement learning to optimize molecular properties.

## Key findings

- The model generates 100% valid and novel molecular structures.
- Generated molecules show fewer structural alerts compared to baselines.
- Molecules demonstrate potent biological activity against ATR and CDK9 targets in experiments.

## Abstract

The recent progress of deep generative models in modeling complex real-world data distributions has enabled the generation of novel compounds with potential therapeutic applications for various diseases. However, most studies fail to optimize the properties of generated molecules from the perspective of the intrinsic nature of chemical reactions. In this work, we propose a novel molecule generation model to overcome the limitation by deep reinforcement learning, in which an agent learns to optimize the properties of molecules initialized with a chemically inspired contrastive pretrained model. We finally assess the generation model by evaluating its ability to generate inhibitors against two prominent therapeutic targets in cancer treatment. Experimental results show that our model could generate 100% valid and novel structures and also exhibits superior performance in generating molecules with fewer structural alerts against several baselines. More importantly, the molecules generated by our proposed model show potent biological activities against ataxia telangiectasia and Rad3-related (ATR) and cyclin-dependent kinase 9 (CDK9) targets in wet-lab experiments.