Neural‐Symbolic Machine Learning for Retrosynthesis and Reaction Prediction

2017/01/30 by Marwin Segler, Marwin H. S. Segler, Mark P. Waller · 10 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Chemical Synthesis and Analysis #Computational Drug Discovery Methods #Machine Learning in Materials Science

paper · doi:10.1002/chem.201605499

openalex publication_date 2017/01/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30

Abstract

Reaction prediction and retrosynthesis are the cornerstones of organic chemistry. Rule-based expert systems have been the most widespread approach to computationally solve these two related challenges to date. However, reaction rules often fail because they ignore the molecular context, which leads to reactivity conflicts. Herein, we report that deep neural networks can learn to resolve reactivity conflicts and to prioritize the most suitable transformation rules. We show that by training our model on 3.5 million reactions taken from the collective published knowledge of the entire discipline of chemistry, our model exhibits a top10-accuracy of 95 % in retrosynthesis and 97 % for reaction prediction on a validation set of almost 1 million reactions.

Cited by

• Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers
• AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search
• The consolidation of open-source computer-assisted chemical synthesis data into a comprehensive database
• FragmentRetro: A Quadratic Retrosynthetic Method Based on Fragmentation Algorithms
• Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis
• CarAT: Carbon Atom Tracing across Industrial Chemical Value Chains via Chemistry Language Models
• Uni-Mol3: A Multi-Molecular Foundation Model for Advancing Organic Reaction Modeling
• A Large Language Model for Chemistry and Retrosynthesis Predictions
• Cross-disciplinary perspectives on the potential for artificial intelligence across chemistry
• DiffER: Categorical Diffusion for Chemical Retrosynthesis

Related

• A Unified View of Deep Learning for Reaction and Retrosynthesis Prediction: Current Status and Future Challenges
• Retrosynthetic reaction prediction using neural sequence-to-sequence models
• Predicting Retrosynthetic Reaction using Self-Corrected Transformer Neural Networks
• Retrosynthesis Prediction with Conditional Graph Logic Network
• Self-Improved Retrosynthetic Planning