用於逆向分子設計的多模式大型語言模型與回溯合成計劃

Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning

October 5, 2024

作者: Gang Liu, Michael Sun, Wojciech Matusik, Meng Jiang, Jie Chen

cs.AI

摘要

儘管大型語言模型（LLMs）已整合圖像，但將其適應圖形仍然具有挑戰性，限制了其在材料和藥物設計中的應用。這一困難源於需要在文本和圖形之間實現連貫的自回歸生成。為了應對這一問題，我們引入了Llamole，這是第一個多模態LLM，能夠交錯生成文本和圖形，實現具有逆合成規劃的分子設計。Llamole將基礎LLM與圖擴散Transformer和圖神經網絡相結合，用於在文本中進行多條件分子生成和反應推斷，同時，具有增強的分子理解能力的LLM靈活地控制不同圖形模塊之間的激活。此外，Llamole將A*搜索與基於LLM的成本函數相結合，用於高效的逆合成規劃。我們創建了基準測試數據集，並進行了廣泛的實驗，以評估Llamole與上下文學習和監督微調的效果。Llamole在可控分子設計和逆合成規劃的12個指標中，明顯優於14個適應LLMs。

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.