PMID- 38441881
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240326
IS  - 1549-9626 (Electronic)
IS  - 1549-9618 (Linking)
VI  - 20
IP  - 6
DP  - 2024 Mar 26
TI  - Fragment-Based Deep Learning for Simultaneous Prediction of Polarizabilities and 
      NMR Shieldings of Macromolecules and Their Aggregates.
PG  - 2655-2665
LID - 10.1021/acs.jctc.3c01415 [doi]
AB  - Simultaneous prediction of the molecular response properties, such as 
      polarizability and the NMR shielding constant, at a low computational cost is an 
      unresolved issue. We propose to combine a linear-scaling generalized energy-based 
      fragmentation (GEBF) method and deep learning (DL) with both molecular and atomic 
      information-theoretic approach (ITA) quantities as effective descriptors. In 
      GEBF, the total molecular polarizability can be assembled as a linear combination 
      of the corresponding quantities calculated from a set of small embedded 
      subsystems in GEBF. In the new GEBF-DL(ITA) protocol, one can predict subsystem 
      polarizabilities based on the corresponding molecular wave function (thus 
      electron density and ITA quantities) and DL model rather than calculate them from 
      the computationally intensive coupled-perturbed Hartree-Fock or Kohn-Sham 
      equations and finally obtain the total molecular polarizability via a linear 
      combination equation. As a proof-of-concept application, we predict the molecular 
      polarizabilities of large proteins and protein aggregates. GEBF-DL(ITA) is shown 
      to be as accurate enough as GEBF, with mean absolute percentage error <1%. For 
      the largest protein aggregate (>4000 atoms), GEBF-DL(ITA) gains a speedup ratio 
      of 3 compared with GEBF. It is anticipated that when more advanced electronic 
      structure methods are used, this advantage will be more appealing. Moreover, one 
      can also predict the NMR chemical shieldings of proteins with reasonably good 
      accuracy. Overall, the cost-efficient GEBF-DL(ITA) protocol should be a robust 
      theoretical tool for simultaneously predicting polarizabilities and NMR 
      shieldings of large systems.
FAU - Zhao, Dongbo
AU  - Zhao D
AUID- ORCID: 0000-0002-0927-4361
AD  - Institute of Biomedical Research, Yunnan University, Kunming, Yunnan 650500, P. 
      R. China.
FAU - Zhao, Yilin
AU  - Zhao Y
AD  - Department of Chemistry and Chemical Biology, McMaster University, Hamilton 
      ONL8S4M1, Canada.
FAU - Xu, Enhua
AU  - Xu E
AD  - Graduate School of System Informatics, Kobe University, Nada-ku, Kobe, Hyogo 
      657-8501, Japan.
FAU - Liu, Wenqi
AU  - Liu W
AD  - Institute of Biomedical Research, Yunnan University, Kunming, Yunnan 650500, P. 
      R. China.
FAU - Ayers, Paul W
AU  - Ayers PW
AUID- ORCID: 0000-0003-2605-3883
AD  - Department of Chemistry and Chemical Biology, McMaster University, Hamilton 
      ONL8S4M1, Canada.
FAU - Liu, Shubin
AU  - Liu S
AUID- ORCID: 0000-0001-9331-0427
AD  - Research Computing Center, University of North Carolina, Chapel Hill, North 
      Carolina 27599-3420, United States.
AD  - Department of Chemistry, University of North Carolina, Chapel Hill, North 
      Carolina 27599-3290, United States.
FAU - Chen, Dahua
AU  - Chen D
AD  - Institute of Biomedical Research, Yunnan University, Kunming, Yunnan 650500, P. 
      R. China.
LA  - eng
PT  - Journal Article
DEP - 20240305
PL  - United States
TA  - J Chem Theory Comput
JT  - Journal of chemical theory and computation
JID - 101232704
SB  - IM
EDAT- 2024/03/05 12:47
MHDA- 2024/03/05 12:48
CRDT- 2024/03/05 11:29
PHST- 2024/03/05 12:48 [medline]
PHST- 2024/03/05 12:47 [pubmed]
PHST- 2024/03/05 11:29 [entrez]
AID - 10.1021/acs.jctc.3c01415 [doi]
PST - ppublish
SO  - J Chem Theory Comput. 2024 Mar 26;20(6):2655-2665. doi: 10.1021/acs.jctc.3c01415. 
      Epub 2024 Mar 5.