Answers are grounded in this paper and cite their sources.
Predicting chemical reaction yields is a critical yet challenging task in organic chemistry. While integrating multi-modal information has shown promise, existing methods typically encode the entire reaction in different modalities and then align these embeddings for the same reactions. Such a coarse-grained modal fusion strategy may neglect atomic-level interactions crucial for accurate predictions. Recognizing the crucial role of modal fusion in multi-modal learning and the limitations of current methods in real-world scenarios, we propose YieldFCP, a reaction Yield ̲ prediction model based on F ̲ ine-grained C ̲ ross-modal P ̲ re-training. Its cross-modal projector links the molecular SMILES sequence with 3D geometric data, focusing on the atomic-level interactions to achieve fine-grained modal fusion and enhance yield prediction. YieldFCP is pre-trained on a large-scale dataset leveraging cross-modal self-supervised learning techniques. Experimental results on the high-throughput experiments, real-world electronic laboratory notebook, and real-world organic reaction publication datasets demonstrate the effectiveness of our approach. Particularly, YieldFCP outperforms the state-of-the-art methods in real − worldscenarios and successfully recognizes keycomponents that determine reaction yields with valuable interpretability.
No takes yet. Share an insight, caveat, or question.
Shi et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: