One class classification as a practical approach for accelerating π–π co-crystal discovery-Reference-Cited by-同舟云学术

One class classification as a practical approach for accelerating π–π co-crystal discovery

Published:2021 Issue:5 Volume:12 Page:1702-1719
ISSN:2041-6520
Container-title:Chemical Science
language:en
Short-container-title:Chem. Sci.

Author:

Vriza Aikaterini¹²³⁴⁵^ORCID,Canaj Angelos B.¹²³⁴^ORCID,Vismara Rebecca¹²³⁴^ORCID,Kershaw Cook Laurence J.¹²³⁴^ORCID,Manning Troy D.¹²³⁴^ORCID,Gaultois Michael W.¹²³⁴⁵^ORCID,Wood Peter A.⁶⁷⁴^ORCID,Kurlin Vitaliy⁸⁹²¹⁰⁴^ORCID,Berry Neil¹²³⁴^ORCID,Dyer Matthew S.¹²³⁴⁵^ORCID,Rosseinsky Matthew J.¹²³⁴⁵^ORCID

Affiliation:

1. Department of Chemistry and Materials Innovation Factory

2. University of Liverpool

3. Liverpool L7 3NY

4. UK

5. Leverhulme Research Centre for Functional Materials Design

6. Cambridge Crystallographic Data Centre

7. Cambridge CB2 1EZ

8. Materials Innovation Factory

9. Computer Science Department

10. Liverpool

Abstract

Machine learning using one class classification on a database of existing co-crystals enables the identification of co-formers which are likely to form stable co-crystals, resulting in the synthesis of two co-crystals of polyaromatic hydrocarbons.

Funder

Engineering and Physical Sciences Research Council

Leverhulme Trust

Royal Society

Publisher

Royal Society of Chemistry (RSC)

Subject

General Chemistry

Link

http://pubs.rsc.org/en/content/articlepdf/2021/SC/D0SC04263C

Reference83 articles.

1. Machine-learning-assisted materials discovery using failed experiments