arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.11259cs.LGcs.AIcs.CEcs.CL
收藏

具有化学反馈的领域无关分子生成

Domain-Agnostic Molecular Generation with Chemical Feedback

College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);ZJU-Ant Group Joint Research Center for Knowledge Graphs, Zhejiang University(浙江大学蚂蚁集团知识图谱联合研究中心);Hangzhou Innovation Center, Zhejiang University(浙江大学杭州创新中心)

Yin Fang, Ningyu Zhang, Zhuo Chen, Lingbing Guo, Xiaohui Fan, Huajun Chen

AI总结:

本文提出预训练分子语言模型 MolGen,通过亿级 SELFIES 重构、领域无关前缀调优与化学反馈,提升跨领域分子生成的有效性、多样性及化学合理性。

摘要:

生成具有所需性质的分子已变得越来越受欢迎,它彻底改变了科学家设计分子结构的方式,并为化学和药物设计提供了宝贵支持。然而,尽管语言模型在分子生成方面具有潜力,它们仍面临诸多挑战,例如生成在句法或化学上存在缺陷的分子、领域关注范围狭窄,以及由于标注数据或外部分子数据库有限而难以创造多样化且可行的分子。为应对这些挑战,我们提出了 MolGen,这是一个专门为分子生成定制的预训练分子语言模型。通过重构超过1亿个分子 SELFIES,MolGen 内化了结构和语法方面的洞见。这一能力进一步通过领域无关的分子前缀调优得到增强,从而促进跨不同领域的稳健知识迁移。重要的是,我们的化学反馈范式引导模型远离分子幻觉,确保模型估计概率与现实世界化学偏好之间保持一致。在知名基准上进行的大量实验突显了 MolGen 在 penalized logP、QED 和分子对接等性质上的优化能力。额外分析证实,它擅长准确捕捉分子分布、识别复杂结构模式并高效探索化学空间。代码可在 https://github.com/zjunlp/MolGen 获取。

英文摘要:

The generation of molecules with desired properties has become increasingly popular, 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 challenges such as generating syntactically or chemically flawed molecules, having narrow domain focus, and struggling to create diverse and feasible molecules due to limited annotated data or external molecular databases. To tackle these challenges, we introduce MolGen, a pre-trained molecular language model tailored specifically for molecule generation. Through the reconstruction of over 100 million molecular SELFIES, MolGen internalizes structural and grammatical insights. This is further enhanced by domain-agnostic molecular prefix tuning, fostering robust knowledge transfer across diverse domains. Importantly, our chemical feedback paradigm steers the model away from molecular hallucinations, ensuring alignment between the model's estimated probabilities and real-world chemical preferences. Extensive experiments on well-known benchmarks underscore MolGen's optimization capabilities in properties such as penalized logP, QED, and molecular docking. Additional analyses confirm its proficiency in accurately capturing molecule distributions, discerning intricate structural patterns, and efficiently exploring the chemical space. Code is available at https://github.com/zjunlp/MolGen.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑