Building an ab initio solvated DNA model using Euclidean neural networks.
Accurately modeling large biomolecules such as DNA from first principles is fundamentally challenging due to the steep computational scaling of ab initio quantum chemistry methods. This limitation becomes even more prominent when modeling biomolecules in solution due to the need to include large num...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2024-01-01
|
Series: | PLoS ONE |
Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0297502&type=printable |
_version_ | 1797301370254000128 |
---|---|
author | Alex J Lee Joshua A Rackers Shivesh Pathak William P Bricker |
author_facet | Alex J Lee Joshua A Rackers Shivesh Pathak William P Bricker |
author_sort | Alex J Lee |
collection | DOAJ |
description | Accurately modeling large biomolecules such as DNA from first principles is fundamentally challenging due to the steep computational scaling of ab initio quantum chemistry methods. This limitation becomes even more prominent when modeling biomolecules in solution due to the need to include large numbers of solvent molecules. We present a machine-learned electron density model based on a Euclidean neural network framework that includes a built-in understanding of equivariance to model explicitly solvated double-stranded DNA. By training the machine learning model using molecular fragments that sample the key DNA and solvent interactions, we show that the model predicts electron densities of arbitrary systems of solvated DNA accurately, resolves polarization effects that are neglected by classical force fields, and captures the physics of the DNA-solvent interaction at the ab initio level. |
first_indexed | 2024-03-07T23:20:38Z |
format | Article |
id | doaj.art-20ad7dcfe06c4f7b9f57f2e4ea479561 |
institution | Directory Open Access Journal |
issn | 1932-6203 |
language | English |
last_indexed | 2024-03-07T23:20:38Z |
publishDate | 2024-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS ONE |
spelling | doaj.art-20ad7dcfe06c4f7b9f57f2e4ea4795612024-02-21T05:31:51ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-01192e029750210.1371/journal.pone.0297502Building an ab initio solvated DNA model using Euclidean neural networks.Alex J LeeJoshua A RackersShivesh PathakWilliam P BrickerAccurately modeling large biomolecules such as DNA from first principles is fundamentally challenging due to the steep computational scaling of ab initio quantum chemistry methods. This limitation becomes even more prominent when modeling biomolecules in solution due to the need to include large numbers of solvent molecules. We present a machine-learned electron density model based on a Euclidean neural network framework that includes a built-in understanding of equivariance to model explicitly solvated double-stranded DNA. By training the machine learning model using molecular fragments that sample the key DNA and solvent interactions, we show that the model predicts electron densities of arbitrary systems of solvated DNA accurately, resolves polarization effects that are neglected by classical force fields, and captures the physics of the DNA-solvent interaction at the ab initio level.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0297502&type=printable |
spellingShingle | Alex J Lee Joshua A Rackers Shivesh Pathak William P Bricker Building an ab initio solvated DNA model using Euclidean neural networks. PLoS ONE |
title | Building an ab initio solvated DNA model using Euclidean neural networks. |
title_full | Building an ab initio solvated DNA model using Euclidean neural networks. |
title_fullStr | Building an ab initio solvated DNA model using Euclidean neural networks. |
title_full_unstemmed | Building an ab initio solvated DNA model using Euclidean neural networks. |
title_short | Building an ab initio solvated DNA model using Euclidean neural networks. |
title_sort | building an ab initio solvated dna model using euclidean neural networks |
url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0297502&type=printable |
work_keys_str_mv | AT alexjlee buildinganabinitiosolvateddnamodelusingeuclideanneuralnetworks AT joshuaarackers buildinganabinitiosolvateddnamodelusingeuclideanneuralnetworks AT shiveshpathak buildinganabinitiosolvateddnamodelusingeuclideanneuralnetworks AT williampbricker buildinganabinitiosolvateddnamodelusingeuclideanneuralnetworks |