用于分子逆向设计的多样本上下文学习
Many-Shot In-Context Learning for Molecular Inverse Design
AI总结:
针对分子逆向设计实验数据不足的问题,提出一种迭代纳入高预测性能分子的半监督学习方法,并集成至多模态LLM实现文本指令交互修改,大幅提升了分子设计性能且易于使用。
摘要:
大型语言模型(LLMs)在多种生成和判别化学设计任务的少样本上下文学习(ICL)中表现出色。LLMs新扩展的上下文窗口可进一步提升分子逆向设计和先导物优化的ICL能力。为充分利用这些能力,我们开发了一种新的半监督学习方法,以克服多样本ICL面临的实验数据缺乏问题。该方法迭代地纳入LLM生成的具有高预测性能的分子及实验数据。我们进一步将该方法集成到多模态LLM中,允许使用文本指令交互式地修改生成的分子结构。实验表明,新方法在分子设计上大幅改进了现有ICL方法,同时对科学家而言易于使用。
英文摘要:
Large Language Models (LLMs) have demonstrated great performance in few-shot In-Context Learning (ICL) for a variety of generative and discriminative chemical design tasks. The newly expanded context windows of LLMs can further improve ICL capabilities for molecular inverse design and lead optimization. To take full advantage of these capabilities we developed a new semi-supervised learning method that overcomes the lack of experimental data available for many-shot ICL. Our approach involves iterative inclusion of LLM generated molecules with high predicted performance, along with experimental data. We further integrated our method in a multi-modal LLM which allows for the interactive modification of generated molecular structures using text instructions. As we show, the new method greatly improves upon existing ICL methods for molecular design while being accessible and easy to use for scientists.
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。