Adaptive Optimization of Chemical Reactions with Minimal Experimental Information

被引：57

作者：

Reker, Daniel ^{[1
,2
,3
,7
]}

Hoyt, Emily A. ^{[4
]}

Bernardes, Goncalo J. L. ^{[4
,5
]}

Rodrigues, Tiago ^{[5
,6
]}

机构：

[1] MIT, Koch Inst Integrat Canc Res, 77 Massachusetts Ave, Cambridge, MA 02139 USA

[2] Harvard Med Sch, Brigham & Womens Hosp, Div Gastroenterol, Boston, MA 02115 USA

[3] MIT, MIT IBM Watson AI Lab, 77 Massachusetts Ave, Cambridge, MA 02139 USA

[4] Univ Cambridge, Dept Chem, Lensfield Rd, Cambridge CB2 1EW, England

[5] Univ Lisbon, Inst Med Mol, Fac Med, Av Prof Egas Moniz 1649-028, Lisbon, Portugal

[6] Univ Lisbon, Fac Farm, Res Inst Med iMed ULisboa, Av Prof Gama Pinto 1649-003, Lisbon, Portugal

[7] Duke Univ, Dept Biomed Engn, Durham, NC 27708 USA

来源：

CELL REPORTS PHYSICAL SCIENCE | 2020年 / 1卷 / 11期

基金：

瑞士国家科学基金会; 欧盟地平线“2020”;

关键词：

SMALL MOLECULES; DISCOVERY; VARIABLES; REVEALS; SEARCH; SPACE;

D O I：

10.1016/j.xcrp.2020.100247

中图分类号：

O6 [化学];

学科分类号：

0703 ;

摘要：

Optimizing reaction conditions depends on expert chemistry knowledge and laborious exploration of reaction parameters. To automate this task and augment chemical intuition, we here report a computational tool to navigate search spaces. Our approach (LabMate.ML) integrates random sampling of 0.03%-0.04% of all search space as input data with an interpretable, adaptive machine-learning algorithm. LabMate.ML can optimize many real. valued and categorical reaction parameters simultaneously, with minimal computational resources and time. In nine prospective proof-of-concept studies pursuing distinctive objectives, we demonstrate how LabMate.ML can identify optimal goal-oriented conditions for several different chemistries and substrates. Double-blind competitions and the conducted expert surveys reveal that its performance is competitive with that of human experts. LabMate.ML does not require specialized hardware, affords quantitative and interpretable reactivity insights, and autonomously formalizes chemical intuition, thereby providing an innovative framework for informed, automated experiment selection toward the democratization of synthetic chemistry.

引用

页数：19

共 53 条

[1] Reductive amination of aldehydes and ketones with sodium triacetoxyborohydride. Studies on direct and indirect reductive amination procedures [J].