Combining Force Fields and Neural Networks for an Accurate Representation of Bonded Interactions
We present a formalism of a neural network encoding bonded interactions in molecules. This intramolecular encoding is consistent with the models of intermolecular interactions previously designed by this group. Variants of the encoding fed into a corresponding neural network may be used to economically improve the representation of torsional degrees of freedom in any force field. We test the accuracy of the reproduction of the ab initio potential energy surface on a set of conformations of two dipeptides, methyl-capped ALA and ASP, in several scenarios. The encoding, either alone or in conjunction with an analytical potential, improves agreement with ab initio energies that are on par with those of other neural network-based potentials. Using the encoding and neural nets in tandem with an analytical model places the agreements firmly within "chemical accuracy" of ±0.5 kcal/mol.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:128 |
|---|---|
| Enthalten in: |
The journal of physical chemistry. A - 128(2024), 4 vom: 01. Feb., Seite 807-812 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Kamath, Ganesh [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 02.02.2024 Date Revised 12.04.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1021/acs.jpca.3c07598 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM36723274X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM36723274X | ||
| 003 | DE-627 | ||
| 005 | 20240412232724.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240118s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1021/acs.jpca.3c07598 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1373.xml |
| 035 | |a (DE-627)NLM36723274X | ||
| 035 | |a (NLM)38232765 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Kamath, Ganesh |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Combining Force Fields and Neural Networks for an Accurate Representation of Bonded Interactions |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 02.02.2024 | ||
| 500 | |a Date Revised 12.04.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a We present a formalism of a neural network encoding bonded interactions in molecules. This intramolecular encoding is consistent with the models of intermolecular interactions previously designed by this group. Variants of the encoding fed into a corresponding neural network may be used to economically improve the representation of torsional degrees of freedom in any force field. We test the accuracy of the reproduction of the ab initio potential energy surface on a set of conformations of two dipeptides, methyl-capped ALA and ASP, in several scenarios. The encoding, either alone or in conjunction with an analytical potential, improves agreement with ab initio energies that are on par with those of other neural network-based potentials. Using the encoding and neural nets in tandem with an analytical model places the agreements firmly within "chemical accuracy" of ±0.5 kcal/mol | ||
| 650 | 4 | |a Journal Article | |
| 650 | 7 | |a Dipeptides |2 NLM | |
| 700 | 1 | |a Illarionov, Alexey |e verfasserin |4 aut | |
| 700 | 1 | |a Sakipov, Serzhan |e verfasserin |4 aut | |
| 700 | 1 | |a Pereyaslavets, Leonid |e verfasserin |4 aut | |
| 700 | 1 | |a Kurnikov, Igor V |e verfasserin |4 aut | |
| 700 | 1 | |a Butin, Oleg |e verfasserin |4 aut | |
| 700 | 1 | |a Voronina, Ekaterina |e verfasserin |4 aut | |
| 700 | 1 | |a Ivahnenko, Ilya |e verfasserin |4 aut | |
| 700 | 1 | |a Leontyev, Igor |e verfasserin |4 aut | |
| 700 | 1 | |a Nawrocki, Grzegorz |e verfasserin |4 aut | |
| 700 | 1 | |a Darkhovskiy, Mikhail |e verfasserin |4 aut | |
| 700 | 1 | |a Olevanov, Michael |e verfasserin |4 aut | |
| 700 | 1 | |a Cherniavskyi, Yevhen K |e verfasserin |4 aut | |
| 700 | 1 | |a Lock, Christopher |e verfasserin |4 aut | |
| 700 | 1 | |a Greenslade, Sean |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, YuChun |e verfasserin |4 aut | |
| 700 | 1 | |a Kornberg, Roger D |e verfasserin |4 aut | |
| 700 | 1 | |a Levitt, Michael |e verfasserin |4 aut | |
| 700 | 1 | |a Fain, Boris |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The journal of physical chemistry. A |d 1997 |g 128(2024), 4 vom: 01. Feb., Seite 807-812 |w (DE-627)NLM098261479 |x 1520-5215 |7 nnns |
| 773 | 1 | 8 | |g volume:128 |g year:2024 |g number:4 |g day:01 |g month:02 |g pages:807-812 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1021/acs.jpca.3c07598 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 128 |j 2024 |e 4 |b 01 |c 02 |h 807-812 | ||