RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning
Keywords: Retrosynthetic Planning, Route Evaluation, In-Context Learning, Large Language Model
TL;DR: Multimodal Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning
Abstract: Development of robust and effective strategies for retrosynthetic planning requires a deep understanding of the synthesis process. A critical step in achieving this goal is accurately identifying synthetic intermediates. Current machine learning-based methods often overlook the valuable context from the overall route, focusing only on predicting reactants from the product, requiring cost annotations for every reaction step, and ignoring the multi-faced nature of molecular, resulting in inaccurate synthetic route predictions. Therefore, we introduce RetroInText, an advanced end-to-end framework based on a multimodal Large Language Model (LLM), featuring in-context learning with TEXT descriptions of synthetic routes. First, RetroInText including ChatGPT presents detailed descriptions of the reaction procedure. It learns the distinct compound representations in parallel with corresponding molecule encoders to extract multi-modal representations including 3D features. Subsequently, we propose an attention-based mechanism that offers a fusion module to complement these multi-modal representations with in-context learning and a fine-tuned language model for a single-step model. As a result, RetroInText accurately represents and effectively captures the complex relationship between molecules and the synthetic route. In experiments on the USPTO pathways dataset RetroBench, RetroInText outperforms state-of-the-art methods, achieving up to a 5% improvement in Top-1 test accuracy, particularly for long synthetic routes. These results demonstrate the superiority of RetroInText by integrating with context information over routes. They also demonstrate its potential for advancing pathway design and facilitating the development of organic chemistry. Code is available at https://github.com/guofei-tju/RetroInText.
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 10375
Loading