Data-driven Chemical Reaction Prediction and Retrosynthesis
Problem
Predicting organic chemical reactions and designing synthesis routes, which traditionally requires chemists with years of knowledge and experience.
Why it matters
Chemical synthesis is central to drug discovery, material synthesis and biomolecular chemistry.
What the AI did
The review covers data-driven (AI/ML) approaches that learn from data to predict forward reactions and retrosynthetic routes, aiming to support expert chemists.
Results
not stated in source
Impact
Authors say AI is profoundly changing computer-aided reaction prediction, but data-driven methods still need to demonstrate their full potential versus expert rule-based systems.
Record
| Venue | CHIMIA International Journal for Chemistry |
|---|---|
| Published | 2019 |
| Work type | article |
| Authors | Vishnu H Nair, Philippe Schwaller, Teodoro Laino |
| Citations | 32 (OpenAlex, at import time) |
| References | 34 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.2533/chimia.2019.997 |
| Open access | diamond |
| Keywords | retrosynthesis, reaction prediction, machine learning, chemical synthesis, drug discovery |
Importance rating
significant — thousands to millions affected
Abstract states organic synthesis is central to drug discovery, material synthesis and biomolecular chemistry, and that route-design support is a half-century-old challenge now being transformed by AI. No quantified scale given.