by , , , , , ,
Discovering new reactions, optimizing their performance, and extending the syn-thetically accessible chemical space are critical drivers for major technologicaladvances and more sustainable processes. The current wave of machine intelligenceis revolutionizing all data-rich disciplines. Machine intelligence has emerged as apotential game-changer for chemical reaction space exploration and the synthesisof novel molecules and materials. Herein, we will address the recent developmentof data-driven technologies for chemical reaction tasks, including forward reactionprediction, retrosynthesis, reaction optimization, catalysts design, inference ofexperimental procedures, and reaction classification. Accurate predictions of chemi-cal reactivity are changing the R&D processes and, at the same time, promoting anaccelerated discovery scheme both in academia and across chemical and pharma-ceutical industries. This work will help to clarify the key contributions in the fieldsand the open challenges that remain to be addressed.
Machine intelligence for chemical reaction space P. Schwaller, A. C. Vaucher, R. Laplaza, C. Bunne, A. Krause, C. Corminboeuf, T. LainoIn WIREs Computational Molecular Science Advanced Reviews, 2022
Bibtex Entry:
	author = {Philippe Schwaller and Alain C. Vaucher and Ruben Laplaza and Charlotte Bunne and Andreas Krause and Clemence Corminboeuf and Teodoro Laino},
	doi = {10.1002/wcms.1604},
	journal = {WIREs Computational Molecular Science Advanced Reviews},
	month = {March},
	title = {Machine intelligence for chemical reaction space},
	year = {2022}}