Files and links (1)
SubmittedCC BY-NC-ND V4.0, Open
Journal article
Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back
Science (American Association for the Advancement of Science), v 382(6677), pp 1374-1407
22 Dec 2023
PMID: 38127734
Abstract
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.
Metrics
Details
- Title
- Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back
- Creators
- Brent A. Koscher - Massachusetts Institute of TechnologyRichard B. Canty - Massachusetts Institute of TechnologyMatthew A. Mcdonald - Massachusetts Institute of TechnologyKevin P. Greenman - Massachusetts Institute of TechnologyCharles J. Mcgill - Massachusetts Institute of TechnologyCamille L. Bilodeau - Massachusetts Institute of TechnologyWengong Jin - Broad InstituteHaoyang Wu - Massachusetts Institute of TechnologyFlorence H. Vermeire - Massachusetts Institute of TechnologyBrooke Jin - Massachusetts Institute of TechnologyTravis Hart - Massachusetts Institute of TechnologyTimothy Kulesza - Massachusetts Institute of TechnologyShih-Cheng Li - MIT, Dept Chem Engn, Cambridge, MA 02139 USATommi S. Jaakkola - Massachusetts Institute of TechnologyRegina Barzilay - Massachusetts Institute of TechnologyRafael Gomez-Bombarelli - Massachusetts Institute of TechnologyWilliam H. Green - Massachusetts Institute of TechnologyKlavs F. Jensen - Massachusetts Institute of Technology
- Publication Details
- Science (American Association for the Advancement of Science), v 382(6677), pp 1374-1407
- Publisher
- Amer Assoc Advancement Science
- Number of pages
- 13
- Grant note
- HR00111920025 / DARPA Accelerated Molecular Discovery (AMD) program; United States Department of Defense Machine Learning for Pharmaceutical Discovery and Synthesis consortium (MLPDS) 1745302 / National Science Foundation Graduate Research Fellowship Program; National Science Foundation (NSF) MIT Consortium
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Chemical and Biological Engineering
- Web of Science ID
- WOS:001128567800029
- Scopus ID
- 2-s2.0-85180745837
- Other Identifier
- 991021958008904721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Chemistry, Multidisciplinary