A Large Language Model for Chemistry and Retrosynthesis Predictions

TL;DR

This paper introduces ECNU-ChemGPT, a specialized large language model for chemistry and retrosynthesis, utilizing domain-specific data, prompt engineering, and multi-model scheduling to outperform existing models in chemical reasoning tasks.

Contribution

The paper presents a novel chemistry-specific LLM, ECNU-ChemGPT, with advanced training strategies and dynamic multi-model integration for improved chemical knowledge understanding and retrosynthesis prediction.

Findings

Achieves 68.3% Top-1 accuracy on USPTO_50K retrosynthesis benchmark.

Reconstructs 13 complete experimental pathways for drug molecules.

Outperforms GPT-4 and other general models in chemistry tasks.

Abstract

Large language models (LLM) have achieved impressive progress across a broad range of general-purpose tasks, but their effectiveness in chemistry remains limited due to scarce domain-specific datasets and the demand for precise symbolic and structural reasoning. Here we introduce ECNU-ChemGPT(name after East China Normal University), a chemistry-specialized LLM engineered for deep chemical knowledge understanding and accurate retrosynthetic route planning. Our approach is distinguished by four key strategies: structured prompt-based knowledge distillation from authoritative chemistry textbooks to construct a high-quality question-answering dataset; domain-specific prompt engineering using curated chemical keywords, combined with LLMs APIs for data derivation and knowledge distillation; large-scale fine-tuning on a meticulously cleaned and enriched Pistachio reaction dataset to enhance retrosynthesis prediction accuracy; and integration of BrainGPT, a dynamic multi-model scheduling framework that enables task-specific invocation of multiple specialized models trained for diverse chemistry-related tasks. ECNU-ChemGPT exhibits superior performance on chemistry question-answering and retrosynthetic planning benchmarks, outperforming leading general-purpose models-including Deepseek-R1, Qwen-2.5, and GPT-4o. In retrosynthesis, it achieves a Top-1 accuracy of 68.3% on the USPTO_50K dataset and successfully reconstructed 13 complete experimental pathways for real-world drug molecules from medicinal chemistry journals. These results underscore the effectiveness of domain-adapted fine-tuning combined with dynamic multi-model task scheduling, providing a scalable and robust solution for chemical knowledge question answering and retrosynthetic planning.