Bridging Chemical Knowledge and Machine Learning for Performance Prediction of Organic Synthesis

• Published in: Chemistry : a European journal Vol. 29; no. 6; pp. e202202834 - n/a
• Main Authors: Zhang, Shuo‐Qing, Xu, Li‐Cheng, Li, Shu‐Wen, Oliveira, João C. A., Li, Xin, Ackermann, Lutz, Hong, Xin
• Format: Journal Article
• Language: English
• Published: Germany Wiley Subscription Services, Inc 27.01.2023; John Wiley and Sons Inc
• Subjects: Chemical synthesis; Chemistry; Chemists; Computer applications; Digitization; Embedding; Human performance; Informatics; Learning algorithms; Machine learning; molecular embedding; Organic chemistry; organic synthesis; Performance prediction; Predictions; Review; Reviews; Selectivity; synthetic dataset; Tactics; performance prediction; machine learning; molecular embedding; organic synthesis; synthetic dataset
• ISSN: 0947-6539; 1521-3765; 1521-3765
• DOI: 10.1002/chem.202202834

Recent years have witnessed a boom of machine learning (ML) applications in chemistry, which reveals the potential of data‐driven prediction of synthesis performance. Digitalization and ML modelling are the key strategies to fully exploit the unique potential within the synergistic interplay between experimental data and the robust prediction of performance and selectivity. A series of exciting studies have demonstrated the importance of chemical knowledge implementation in ML, which improves the model's capability for making predictions that are challenging and often go beyond the abilities of human beings. This Minireview summarizes the cutting‐edge embedding techniques and model designs in synthetic performance prediction, elaborating how chemical knowledge can be incorporated into machine learning until June 2022. By merging organic synthesis tactics and chemical informatics, we hope this Review can provide a guide map and intrigue chemists to revisit the digitalization and computerization of organic chemistry principles. Predicting organic transformations is one of the most critical challenges in molecular syntheses. The synergy between machine learning and chemical knowledge provides a distinctive and powerful strategy for syntheses predictions. This Minireview summarizes the state‐of‐the‐art embedding approaches and model designs for developing synthesis‐sensitive machine learning models to allow for robust yield and selectivity predictions in molecular syntheses.