ChemBART: A Pre-trained BART Model Assisting Organic Chemistry Analysis

2026-01-06

arXiv.org

AI Summary

This work addresses the limitation of existing chemical language models, which are typically confined to single tasks and thus ill-suited for the multi-task coordination required in organic synthesis planning. The authors propose a unified pretraining paradigm for chemical reactions based on the BART architecture, employing masked SMILES sequence reconstruction to enable a versatile framework capable of precursor/reagent generation, temperature–yield regression, molecular property classification, and multi-step retrosynthetic pathway planning. By integrating Monte Carlo tree search with reinforcement learning, the model generates concise, high-yielding synthetic routes that were successfully validated in wet-lab experiments, achieving approximately 30% higher yields than literature benchmarks. This study represents the first demonstration of a “pretrain once, apply to many tasks” approach that directly guides experimental synthesis.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recent advances in large language models (LLMs) have demonstrated transformative potential across diverse fields. While LLMs have been applied to molecular simplified molecular input line entry system (SMILES) in computer-aided synthesis planning (CASP), existing methodologies typically address single tasks, such as precursor prediction. We introduce ChemBART, a SMILES-based LLM pre-trained on chemical reactions, which enables a unified model for multiple downstream chemical tasks--achieving the paradigm of"one model, one pre-training, multiple tasks."By leveraging outputs from a mask-filling pre-training task on reaction expressions, ChemBART effectively solves a variety of chemical problems, including precursor/reagent generation, temperature-yield regression, molecular property classification, and optimizing the policy and value functions within a reinforcement learning framework, integrated with Monte Carlo tree search for multi-step synthesis route design. Unlike single-molecule pre-trained LLMs constrained to specific applications, ChemBART addresses broader chemical challenges and integrates them for comprehensive synthesis planning. Crucially, ChemBART-designed multi-step synthesis routes and reaction conditions directly inspired wet-lab validation, which confirmed shorter pathways with ~30% yield improvement over literature benchmarks. Our work validates the power of reaction-focused pre-training and showcases the broad utility of ChemBART in advancing the complete synthesis planning cycle.

Problem

• large language models
• organic chemistry analysis
• computer-aided synthesis planning
• multi-task learning
• chemical reaction prediction

Innovation

• ChemBART
• reaction-based pre-training
• multi-task chemical modeling
• SMILES-based LLM
• synthesis planning