Domain-Agnostic Molecular Generation with Self-feedback

The generation of molecules with desired properties has gained tremendous popularity, revolutionizing the way scientists design molecular structures and providing valuable support for chemical and drug design. However, despite the potential of language models in molecule generation, they face numerous challenges such as the generation of syntactically or chemically flawed molecules, narrow domain focus, and limitations in creating diverse and directionally feasible molecules due to a dearth of annotated data or external molecular databases. To this end, we introduce MolGen, a pre-trained molecular language model tailored specifically for molecule generation. MolGen acquires intrinsic structural and grammatical insights by reconstructing over 100 million molecular SELFIES, while facilitating knowledge transfer between different domains through domain-agnostic molecular prefix tuning. Moreover, we present a self-feedback paradigm that inspires the pre-trained model to align with the ultimate goal of producing molecules with desirable properties. Extensive experiments on well-known benchmarks confirm MolGen's optimization capabilities, encompassing penalized logP, QED, and molecular docking properties. Further analysis shows that MolGen can accurately capture molecule distributions, implicitly learn their structural characteristics, and efficiently explore chemical space. The pre-trained model, codes, and datasets are publicly available for future research at https://github.com/zjunlp/MolGen.Comment: Work in progress. Add results of binding affinit