TY - JOUR
T1 - Exploring chemical compound space with quantum-based machine learning
AU - von Lilienfeld, O. Anatole
AU - Müller, Klaus Robert
AU - Tkatchenko, Alexandre
N1 - Funding Information:
All authors thank F. A. Faber and J. Wagner for preparing the graphics in Fig. 1 and the cover image related to this article, respectively. O.A.v.L. acknowledges funding from the Swiss National Science foundation (nos. PP00P2_138932 and 407540_167186 NFP 75 Big Data) and from the European Research Council (ERC-CoG grant QML). This work was partly supported by the NCCR MARVEL, funded by the Swiss National Science Foundation. A.T. acknowledges financial support from the European Research Council (ERC-CoG grant BeStMo). K.-R.M. acknowledges partial financial support by the German Federal Ministry of Education and Research (BMBF) under grants 01IS14013A-E, 01GQ1115 and 01GQ0850; Deutsche Forschungsgesellschaft (DFG) under grant Math+, EXC 2046/1, project ID 390685689 and by the Institute for Information & Communication Technology Promotion (IITP) grant funded by the Korea government (nos. 2017-0-00451 and 2017-0-01779). Correspondence to O.A.v.L., K.-R.M. and A.T.
Publisher Copyright:
© 2020, Springer Nature Limited.
PY - 2020/7/1
Y1 - 2020/7/1
N2 - Rational design of compounds with specific properties requires understanding and fast evaluation of molecular properties throughout chemical compound space — the huge set of all potentially stable molecules. Recent advances in combining quantum-mechanical calculations with machine learning provide powerful tools for exploring wide swathes of chemical compound space. We present our perspective on this exciting and quickly developing field by discussing key advances in the development and applications of quantum-mechanics-based machine-learning methods to diverse compounds and properties, and outlining the challenges ahead. We argue that significant progress in the exploration and understanding of chemical compound space can be made through a systematic combination of rigorous physical theories, comprehensive synthetic data sets of microscopic and macroscopic properties, and modern machine-learning methods that account for physical and chemical knowledge. [Figure not available: see fulltext.].
AB - Rational design of compounds with specific properties requires understanding and fast evaluation of molecular properties throughout chemical compound space — the huge set of all potentially stable molecules. Recent advances in combining quantum-mechanical calculations with machine learning provide powerful tools for exploring wide swathes of chemical compound space. We present our perspective on this exciting and quickly developing field by discussing key advances in the development and applications of quantum-mechanics-based machine-learning methods to diverse compounds and properties, and outlining the challenges ahead. We argue that significant progress in the exploration and understanding of chemical compound space can be made through a systematic combination of rigorous physical theories, comprehensive synthetic data sets of microscopic and macroscopic properties, and modern machine-learning methods that account for physical and chemical knowledge. [Figure not available: see fulltext.].
UR - http://www.scopus.com/inward/record.url?scp=85086405344&partnerID=8YFLogxK
U2 - 10.1038/s41570-020-0189-9
DO - 10.1038/s41570-020-0189-9
M3 - Article
AN - SCOPUS:85086405344
SN - 2397-3358
VL - 4
SP - 347
EP - 358
JO - Nature Reviews Chemistry
JF - Nature Reviews Chemistry
IS - 7
ER -