Choosing the right molecular machine learning potential.
Journal
Chemical science
ISSN: 2041-6520
Titre abrégé: Chem Sci
Pays: England
ID NLM: 101545951
Informations de publication
Date de publication:
10 Nov 2021
10 Nov 2021
Historique:
received:
29
06
2021
accepted:
14
09
2021
entrez:
9
12
2021
pubmed:
10
12
2021
medline:
10
12
2021
Statut:
epublish
Résumé
Quantum-chemistry simulations based on potential energy surfaces of molecules provide invaluable insight into the physicochemical processes at the atomistic level and yield such important observables as reaction rates and spectra. Machine learning potentials promise to significantly reduce the computational cost and hence enable otherwise unfeasible simulations. However, the surging number of such potentials begs the question of which one to choose or whether we still need to develop yet another one. Here, we address this question by evaluating the performance of popular machine learning potentials in terms of accuracy and computational cost. In addition, we deliver structured information for non-specialists in machine learning to guide them through the maze of acronyms, recognize each potential's main features, and judge what they could expect from each one.
Identifiants
pubmed: 34880991
doi: 10.1039/d1sc03564a
pii: d1sc03564a
pmc: PMC8580106
doi:
Types de publication
Journal Article
Langues
eng
Pagination
14396-14413Informations de copyright
This journal is © The Royal Society of Chemistry.
Déclaration de conflit d'intérêts
The authors declare no competing interests.
Références
Nat Commun. 2020 Oct 30;11(1):5505
pubmed: 33127879
J Chem Phys. 2019 Jun 28;150(24):244113
pubmed: 31255074
Phys Rev Lett. 2020 Oct 16;125(16):166001
pubmed: 33124874
J Chem Phys. 2018 Jun 28;148(24):241709
pubmed: 29960372
J Chem Theory Comput. 2020 Oct 13;16(10):6195-6206
pubmed: 32786896
J Chem Theory Comput. 2020 Jun 9;16(6):3989-4001
pubmed: 32374164
Acc Chem Res. 2021 Apr 6;54(7):1575-1585
pubmed: 33715355
J Chem Theory Comput. 2020 Sep 8;16(9):5474-5484
pubmed: 32787180
Nat Chem. 2020 Oct;12(10):945-951
pubmed: 32929248
Chem Rev. 2021 Aug 25;121(16):10187-10217
pubmed: 33021368
Phys Rev Lett. 2012 Feb 3;108(5):058301
pubmed: 22400967
J Chem Phys. 2019 Apr 7;150(13):131102
pubmed: 30954036
J Chem Theory Comput. 2020 Aug 11;16(8):5410-5421
pubmed: 32672968
Chem Rev. 2021 Aug 25;121(16):10142-10186
pubmed: 33705118
Chem Sci. 2017 Apr 1;8(4):3192-3203
pubmed: 28507695
J Chem Phys. 2020 Oct 21;153(15):154112
pubmed: 33092371
Chem Sci. 2018 Jan 18;9(8):2261-2269
pubmed: 29719699
J Comput Chem. 2020 Mar 30;41(8):790-799
pubmed: 31845368
J Chem Theory Comput. 2013 Aug 13;9(8):3404-19
pubmed: 26584096
Chem Sci. 2017 Oct 1;8(10):6924-6935
pubmed: 29147518
Annu Rev Phys Chem. 2020 Apr 20;71:361-390
pubmed: 32092281
J Phys Chem A. 2020 Sep 3;124(35):7199-7210
pubmed: 32786977
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
J Comput Chem. 2019 Oct 5;40(26):2339-2347
pubmed: 31219626
J Chem Inf Model. 2020 Mar 23;60(3):1184-1193
pubmed: 31935100
J Chem Theory Comput. 2019 Jun 11;15(6):3678-3693
pubmed: 31042390
J Chem Phys. 2019 Feb 14;150(6):064105
pubmed: 30769998
J Phys Chem Lett. 2020 Oct 15;11(20):8710-8720
pubmed: 32955889
Nat Methods. 2014 Feb;11(2):119-20
pubmed: 24645192
Sci Rep. 2017 Aug 18;7(1):8737
pubmed: 28821842
J Chem Theory Comput. 2018 Nov 13;14(11):5777-5786
pubmed: 30351931
Nature. 2021 Jan;589(7840):59-64
pubmed: 33408379
Phys Rev Lett. 2007 Apr 6;98(14):146401
pubmed: 17501293
J Chem Phys. 2018 Jun 28;148(24):241718
pubmed: 29960361
J Chem Phys. 2013 Aug 7;139(5):054112
pubmed: 23927248
J Phys Chem Lett. 2018 Jun 7;9(11):2725-2732
pubmed: 29732893
J Chem Theory Comput. 2020 Jul 14;16(7):4192-4202
pubmed: 32543858
J Chem Phys. 2019 Nov 21;151(19):194111
pubmed: 31757150
J Chem Phys. 2018 Jun 28;148(24):241704
pubmed: 29960317
J Chem Phys. 2018 Jun 28;148(24):241710
pubmed: 29960377
Adv Sci (Weinh). 2019 Jan 29;6(9):1801367
pubmed: 31065514
J Chem Phys. 2017 Jun 28;146(24):244108
pubmed: 28668062
J Chem Phys. 2016 Oct 28;145(16):161102
pubmed: 27802646
J Chem Phys. 2016 Nov 7;145(17):170901
pubmed: 27825224
Nat Commun. 2017 Jan 09;8:13890
pubmed: 28067221
Sci Adv. 2017 May 05;3(5):e1603015
pubmed: 28508076
J Chem Phys. 2019 Apr 21;150(15):154102
pubmed: 31005106
J Chem Theory Comput. 2021 Jan 12;17(1):571-582
pubmed: 33382621
J Chem Phys. 2019 Jun 28;150(24):244110
pubmed: 31255049
Chem Sci. 2019 Aug 5;10(35):8100-8107
pubmed: 31857878
J Chem Phys. 2018 Jun 28;148(24):241722
pubmed: 29960322
J Phys Chem Lett. 2020 Mar 19;11(6):2336-2347
pubmed: 32125858
J Chem Phys. 2016 Aug 21;145(7):071101
pubmed: 27544080
Top Curr Chem (Cham). 2021 Jun 8;379(4):27
pubmed: 34101036
J Chem Phys. 2021 Mar 28;154(12):124102
pubmed: 33810678
J Chem Phys. 2011 Feb 21;134(7):074106
pubmed: 21341827
Phys Rev Lett. 2009 Feb 20;102(7):073005
pubmed: 19257665
J Chem Phys. 2012 May 7;136(17):174101
pubmed: 22583204
J Chem Phys. 2017 May 28;146(20):204301
pubmed: 28571343
Nat Commun. 2018 Sep 24;9(1):3887
pubmed: 30250077
Nat Commun. 2020 Nov 11;11(1):5713
pubmed: 33177517
J Chem Theory Comput. 2019 Aug 13;15(8):4386-4398
pubmed: 31283237
J Chem Phys. 2019 Mar 21;150(11):114102
pubmed: 30901990
Phys Rev Lett. 1996 Oct 28;77(18):3865-3868
pubmed: 10062328
J Chem Phys. 2020 Aug 7;153(5):054111
pubmed: 32770921
Sci Rep. 2017 Oct 9;7(1):12817
pubmed: 28993674
Phys Rev Lett. 2018 Apr 6;120(14):143001
pubmed: 29694129
Phys Rev Lett. 2010 Apr 2;104(13):136403
pubmed: 20481899
J Chem Phys. 2020 Jan 31;152(4):044107
pubmed: 32007071
J Chem Inf Model. 2020 Jul 27;60(7):3408-3415
pubmed: 32568524
Neural Comput. 1996 Jul 1;8(5):1085-106
pubmed: 8697228
J Phys Chem Lett. 2015 Jun 18;6(12):2326-31
pubmed: 26113956
Phys Chem Chem Phys. 2016 May 18;18(20):13754-69
pubmed: 27101873