Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back
Science · 22.12.2023 · 382 (6677)
DOI: 10.1126/science.adi1407 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science, erschienen am 22.12.2023. Verfasst von Brent A Koscher und 17 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. Die Arbeit wurde bisher 170-mal zitiert (Crossref) und nennt 76 Literaturangaben.
Abstract (Originalsprache)
A closed-loop, autonomous molecular discovery platform driven by integrated machine learning tools was developed to accelerate the design of molecules with desired properties. We demonstrated two case studies on dye-like molecules, targeting absorption wavelength, lipophilicity, and photooxidative stability. In the first study, the platform experimentally realized 294 unreported molecules across three automatic iterations of molecular design-make-test-analyze cycles while exploring the structure-function space of four rarely reported scaffolds. In each iteration, the property prediction models that guided exploration learned the structure-property space of diverse scaffold derivatives, which were realized with multistep syntheses and a variety of reactions. The second study exploited property models trained on the explored chemical space and previously reported molecules to discover nine top-performing molecules within a lightly explored structure-property space.
Autor:innen und Institutionen
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA.
- Broad Institute of MIT and Harvard, Cambridge, MA, USA.
- Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA.
- Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA.
ORCID-Profile: Brent A Koscher, Richard B Canty, Matthew A McDonald, Kevin P Greenman, Camille L Bilodeau, Haoyang Wu, Florence H Vermeire, Brooke Jin, Travis Hart, Shih-Cheng Li, Tommi S Jaakkola, Regina Barzilay, Rafael Gómez-Bombarelli, William H Green, Klavs F Jensen
Zitieren
APA
Koscher, B. A., Canty, R. B., McDonald, M. A., Greenman, K. P., McGill, C. J., Bilodeau, C. L., Jin, W., Wu, H., Vermeire, F. H., Jin, B., Hart, T., Kulesza, T., Li, S. C., Jaakkola, T. S., Barzilay, R., Gómez-Bombarelli, R., Green, W. H., & Jensen, K. F. (2023). Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back. Science, 382(6677). https://doi.org/10.1126/science.adi1407
Vancouver
Koscher BA, Canty RB, McDonald MA, Greenman KP, McGill CJ, Bilodeau CL, et al. Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back. Science. 2023;382(6677). doi:10.1126/science.adi1407
BibTeX
@article{Koscher2023,
author = {Koscher, Brent A and Canty, Richard B and McDonald, Matthew A and Greenman, Kevin P and McGill, Charles J and Bilodeau, Camille L and Jin, Wengong and Wu, Haoyang and Vermeire, Florence H and Jin, Brooke and Hart, Travis and Kulesza, Timothy and Li, Shih-Cheng and Jaakkola, Tommi S and Barzilay, Regina and Gómez-Bombarelli, Rafael and Green, William H and Jensen, Klavs F},
title = {Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back},
journal = {Science},
year = {2023},
volume = {382},
number = {6677},
doi = {10.1126/science.adi1407}
}
EUVIMED