Intuition-enabled machine learning beats the competition when joint human-robot teams perform inorganic chemical experiments

Duros, V., Grizou, J., Sharma, A., Mehr, S. H. M., Bubliauskas, A., Frei, P., Miras, H. N. and Cronin, L. (2019) Intuition-enabled machine learning beats the competition when joint human-robot teams perform inorganic chemical experiments. Journal of Chemical Information and Modeling, 59(6), pp. 2664-2671. (doi:10.1021/acs.jcim.9b00304) (PMID:31025861)

[img]
Preview
Text
185445.pdf - Published Version
Available under License Creative Commons Attribution.

2MB

Abstract

Traditionally, chemists have relied on years of training and accumulated experience in order to discov-er new molecules. But the space of possible molecules so vast, only a limited exploration with the tra-ditional methods can be ever possible. This means that many opportunities for the discovery of inter-esting phenomena have been missed, and in addition, the inherent variability of these phenomena can make them difficult to control and understand. The current state-of-the-art is moving towards the de-velopment of automated and eventually fully autonomous systems coupled with in-line analytics and decision-making algorithms. Yet even these, despite the substantial progress achieved recently, still cannot easily tackle large combinatorial spaces as they are limited by the lack of high-quality data. Herein, we explore the utility of active learning methods for exploring the chemical space by compar-ing collaboration between human experimenters with an algorithm-based search, against their perfor-mance individually to probe the self-assembly and crystallization of the polyoxometalate cluster Na6[Mo120Ce6O366H12(H2O)78]·200H2O (1). We show that the robot-human teams are able to increase the prediction accuracy to 75.6±1.8%, from 71.8±0.3% with the algorithm alone and 66.3±1.8% from only the human experimenters demonstrating that human-robot teams beat robots or humans working alone.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Sharma, Mr Abhishek and Moiras, Dr Haralampos and Grizou, Dr Jonathan and Bubliauskas, Mr Andrius and Duros, Mr Wasilios and Frei, Mr Przemyslaw and Cronin, Professor Lee
Authors: Duros, V., Grizou, J., Sharma, A., Mehr, S. H. M., Bubliauskas, A., Frei, P., Miras, H. N., and Cronin, L.
College/School:College of Science and Engineering > School of Chemistry
Journal Name:Journal of Chemical Information and Modeling
Publisher:American Chemical Society
ISSN:1549-9596
ISSN (Online):1549-960X
Published Online:26 April 2019
Copyright Holders:Copyright © 2019 American Chemical Society
First Published:First published in Journal of Chemical Information and Modeling 59(6): 2664-2671
Publisher Policy:Reproduced under a Creative Commons License

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
723171Advanced Mass Spectrometry Kit for Controlling Chemical Robots and Exploring Complex Chemical SystemsLeroy CroninEngineering and Physical Sciences Research Council (EPSRC)EP/P00153X/1CHEM - CHEMISTRY
577391Programmable Molecular Metal Oxides (PMMOs) - From Fundamentals to ApplicationLeroy CroninEngineering and Physical Sciences Research Council (EPSRC)EP/J015156/1CHEM - CHEMISTRY
605821The Multi-Corder: Poly-Sensor TechnologyDavid CummingEngineering and Physical Sciences Research Council (EPSRC)EP/K021966/1ENG - ENGINEERING ELECTRONICS & NANO ENG
621351Synthetic Biology applications to Water Supply and RemediationSteven BeaumontEngineering and Physical Sciences Research Council (EPSRC)EP/K038885/1VPO VICE PRINCIPAL RESEARCH & ENTERPRISE
633821A Digital DNA Nano Writer (DNA NanoFab)Leroy CroninEngineering and Physical Sciences Research Council (EPSRC)EP/L015668/1CHEM - CHEMISTRY
646611Programmable 'Digital' Synthesis for Discovery and Scale-up of Molecules, Clusters and NanomaterialsLeroy CroninEngineering and Physical Sciences Research Council (EPSRC)EP/L023652/1CHEM - CHEMISTRY
685741SMARTPOM: Artificial-Intelligence Driven Discovery and Synthesis of Polyoxometalate ClustersLeroy CroninEuropean Research Council (ERC)670467CHEM - CHEMISTRY

Downloads per month over past year

View more statistics