首个可交替生成文本与分子图的多模态大模型，实现逆向分子设计与逆合成规划。
Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning
- 将文本与分子图交替生成，融合LLM与图神经网络实现可控分子设计
- 在12项指标上超越14个适配模型，显著提升逆合成规划效率
- 适合药物发现与材料设计研究者使用，支持复杂分子结构生成
尽管大语言模型（LLMs）已能处理图像，但将其应用于图结构仍具挑战性，限制了其在材料与药物设计中的应用。这一难题源于文本与图结构间连贯的自回归生成需求。为此，我们提出Llamole，首个支持文本与图交错生成的多模态大语言模型，实现了结合逆合成规划的分子逆向设计。Llamole通过基础LLM与图扩散变换器、图神经网络融合，实现文本中多条件分子生成与反应推理；同时，增强的分子理解能力使LLM灵活控制不同图模块的激活。此外，集成基于LLM的代价函数与A*搜索，实现高效逆合成规划。我们构建基准数据集并进行大量实验，评估其在上下文学习与监督微调下的表现。在12项指标上，Llamole显著优于14个适配的LLM，展现出卓越的可控分子设计与逆合成规划能力。
原文摘要 · Abstract (English)
While large language models (LLMs) have integrated images, adapting them to graphs remains challenging, limiting their applications in materials and drug design. This difficulty stems from the need for coherent autoregressive generation across texts and graphs. To address this, we introduce Llamole, the first multimodal LLM capable of interleaved text and graph generation, enabling molecular inverse design with retrosynthetic planning. Llamole integrates a base LLM with the Graph Diffusion Transformer and Graph Neural Networks for multi-conditional molecular generation and reaction inference within texts, while the LLM, with enhanced molecular understanding, flexibly controls activation among the different graph modules. Additionally, Llamole integrates A* search with LLM-based cost functions for efficient retrosynthetic planning. We create benchmarking datasets and conduct extensive experiments to evaluate Llamole against in-context learning and supervised fine-tuning. Llamole significantly outperforms 14 adapted LLMs across 12 metrics for controllable molecular design and retrosynthetic planning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。