DOI: 10.1063/1.5006882. Internal force corrections with machine learning for quantum mechanics/molecular mechanics simulations

Internal force corrections with machine learning for quantum mechanics/molecular mechanics simulations

10.1063/1.5006882

Crossref journal-article

AIP Publishing

The Journal of Chemical Physics (317)

Abstract

Ab initio quantum mechanics/molecular mechanics (QM/MM) molecular dynamics simulation is a useful tool to calculate thermodynamic properties such as potential of mean force for chemical reactions but intensely time consuming. In this paper, we developed a new method using the internal force correction for low-level semiempirical QM/MM molecular dynamics samplings with a predefined reaction coordinate. As a correction term, the internal force was predicted with a machine learning scheme, which provides a sophisticated force field, and added to the atomic forces on the reaction coordinate related atoms at each integration step. We applied this method to two reactions in aqueous solution and reproduced potentials of mean force at the ab initio QM/MM level. The saving in computational cost is about 2 orders of magnitude. The present work reveals great potentials for machine learning in QM/MM simulations to study complex chemical processes.

Bibliography

Wu, J., Shen, L., & Yang, W. (2017). Internal force corrections with machine learning for quantum mechanics/molecular mechanics simulations. The Journal of Chemical Physics, 147(16).

Authors 3

Jingheng Wu (first)
Lin Shen (additional)
Weitao Yang (additional)

References 45 Referenced 33

10.1073/pnas.100127697 / Proc. Natl. Acad. Sci. U. S. A. (2000)
10.1007/978-3-540-38448-9 / Free Energy Calculations: Theory and Applications in Chemistry and Biology by Chipot (2007)
10.1002/jcc.21332 / J. Comput. Chem. (2009)
10.1080/00268976.2013.813594 / Mol. Phys. (2013)
10.1021/cr4005988 / Chem. Rev. (2014)
10.1016/0009-2614(74)80109-0 / Chem. Phys. Lett. (1974)
10.1016/0021-9991(77)90121-8 / J. Comput. Phys. (1977)
10.1021/ja075896n / J. Am. Chem. Soc. (2008)
10.1021/ja807269j / J. Am. Chem. Soc. (2008)
10.1146/annurev.physchem.59.032607.093618 / Annu. Rev. Phys. Chem. (2008)
10.1016/j.theochem.2008.12.025 / J. Mol. Struct.: THEOCHEM (2009)
10.1080/08927022.2015.1132317 / Mol. Simul. (2016)
10.1209/0295-5075/26/8/005 / Europhys. Lett. (1994)
10.1021/ct600284f / J. Chem. Theory Comput. (2007)
10.1021/ct4009624 / J. Chem. Theory Comput. (2014)
10.1021/jp049633g / J. Phys. Chem. B (2004)
10.1021/jp063520a / J. Phys. Chem. B (2006)
10.1103/physrevb.92.094306 / Phys. Rev. B (2015)
10.1103/physrevlett.114.096405 / Phys. Rev. Lett. (2015)
10.1021/ct500438v / J. Chem. Theory Comput. (2014)
10.1021/acs.jctc.6b00663 / J. Chem. Theory Comput. (2016)
{'edition': '2nd ed.', 'volume-title': 'The Elements of Statistical Learning: Data Mining, Inference, and Prediction', 'year': '2009', 'key': '2023061919413622000_c22'} / The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2009)
{'volume-title': 'Understanding Molecular Simulation: From Algorithms to Applications', 'year': '2001', 'key': '2023061919413622000_c23'} / Understanding Molecular Simulation: From Algorithms to Applications (2001)
10.1126/science.290.5500.2323 / Science (2000)
10.1063/1.445869 / J. Chem. Phys. (1983)
10.1021/acs.jctc.5b00255 / J. Chem. Theory Comput. (2015)
10.1103/physrevb.58.7260 / Phys. Rev. B (1998)
10.1021/jp070071l / J. Phys. Chem. A (2007)
10.1063/1.448118 / J. Chem. Phys. (1984)
{'volume-title': 'AMBER 14', 'year': '2014', 'key': '2023061919413622000_c30'} / AMBER 14 (2014)
{'year': '2004', 'key': '2023061919413622000_c31'} (2004)
10.1103/physrevlett.63.1195 / Phys. Rev. Lett. (1989)
10.1002/jcc.540130812 / J. Comput. Chem. (1992)
10.1021/jp511057f / J. Phys. Chem. B (2015)
10.1021/acs.jpcb.5b08690 / J. Phys. Chem. B (2015)
10.1063/1.1691404 / J. Chem. Phys. (2004)
10.1063/1.2163875 / J. Chem. Phys. (2006)
10.1021/ct600240y / J. Chem. Theory Comput. (2007)
10.1063/1.2816557 / J. Chem. Phys. (2008)
10.1063/1.4887340 / J. Chem. Phys. (2014)
10.1063/1.4973607 / J. Chem. Phys. (2017)
10.1021/acs.jpcc.6b10908 / J. Phys. Chem. C (2017)
10.1080/08927028808080941 / Mol. Simul. (1988)
10.1039/c5sc04786b / Chem. Sci. (2016)
10.1103/physrevlett.93.175503 / Phys. Rev. Lett. (2004)

Dates

Type	When
Created	7 years, 10 months ago (Oct. 12, 2017, 10:48 a.m.)
Deposited	2 years, 2 months ago (June 19, 2023, 3:41 p.m.)
Indexed	1 month ago (July 30, 2025, 7:08 a.m.)
Issued	7 years, 10 months ago (Oct. 12, 2017)
Published	7 years, 10 months ago (Oct. 12, 2017)
Published Online	7 years, 10 months ago (Oct. 12, 2017)
Published Print	7 years, 10 months ago (Oct. 28, 2017)

Funders 1

Foundation for the National Institutes of Health 10.13039/100000009
Region: Americas
gov (Trusts, charities, foundations (both public and private))
Labels5
1. Foundation for the National Institutes of Health, Inc.
2. Foundation for the NIH
3. Foundation for NIH
4. The Foundation for the National Institutes of Health
5. FNIH
Awards1
1. R01 GM061870-13

BibTeX

@article{Wu_2017, title={Internal force corrections with machine learning for quantum mechanics/molecular mechanics simulations}, volume={147}, ISSN={1089-7690}, url={http://dx.doi.org/10.1063/1.5006882}, DOI={10.1063/1.5006882}, number={16}, journal={The Journal of Chemical Physics}, publisher={AIP Publishing}, author={Wu, Jingheng and Shen, Lin and Yang, Weitao}, year={2017}, month=oct }

JSON

{
  "indexed": {
    "date-parts": [
      [
        2025,
        7,
        30
      ]
    ],
    "date-time": "2025-07-30T11:08:39Z",
    "timestamp": 1753873719297,
    "version": "3.41.2"
  },
  "reference-count": 45,
  "publisher": "AIP Publishing",
  "issue": "16",
  "funder": [
    {
      "DOI": "10.13039/100000009",
      "name": "Foundation for the National Institutes of Health",
      "doi-asserted-by": "publisher",
      "award": [
        "R01 GM061870-13"
      ],
      "id": [
        {
          "id": "10.13039/100000009",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    }
  ],
  "content-domain": {
    "domain": [
      "pubs.aip.org"
    ],
    "crossmark-restriction": true
  },
  "published-print": {
    "date-parts": [
      [
        2017,
        10,
        28
      ]
    ]
  },
  "abstract": "<jats:p>Ab initio quantum mechanics/molecular mechanics (QM/MM) molecular dynamics simulation is a useful tool to calculate thermodynamic properties such as potential of mean force for chemical reactions but intensely time consuming. In this paper, we developed a new method using the internal force correction for low-level semiempirical QM/MM molecular dynamics samplings with a predefined reaction coordinate. As a correction term, the internal force was predicted with a machine learning scheme, which provides a sophisticated force field, and added to the atomic forces on the reaction coordinate related atoms at each integration step. We applied this method to two reactions in aqueous solution and reproduced potentials of mean force at the ab initio QM/MM level. The saving in computational cost is about 2 orders of magnitude. The present work reveals great potentials for machine learning in QM/MM simulations to study complex chemical processes.</jats:p>",
  "DOI": "10.1063/1.5006882",
  "type": "journal-article",
  "created": {
    "date-parts": [
      [
        2017,
        10,
        12
      ]
    ],
    "date-time": "2017-10-12T14:48:13Z",
    "timestamp": 1507819693000
  },
  "update-policy": "https://doi.org/10.1063/aip-crossmark-policy-page",
  "source": "Crossref",
  "is-referenced-by-count": 33,
  "title": "Internal force corrections with machine learning for quantum mechanics/molecular mechanics simulations",
  "prefix": "10.1063",
  "volume": "147",
  "author": [
    {
      "given": "Jingheng",
      "family": "Wu",
      "sequence": "first",
      "affiliation": [
        {
          "name": "Department of Chemistry, Duke University 1 , Durham, North Carolina 27708, USA"
        },
        {
          "name": "School of Chemistry and Chemical Engineering, Sun Yat-sen University 2 , Guangzhou 510275, People\u2019s Republic of China"
        }
      ]
    },
    {
      "given": "Lin",
      "family": "Shen",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Department of Chemistry, Duke University 1 , Durham, North Carolina 27708, USA"
        }
      ]
    },
    {
      "ORCID": "https://orcid.org/0000-0001-5576-2828",
      "authenticated-orcid": false,
      "given": "Weitao",
      "family": "Yang",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Department of Chemistry, Duke University 1 , Durham, North Carolina 27708, USA"
        }
      ]
    }
  ],
  "member": "317",
  "published-online": {
    "date-parts": [
      [
        2017,
        10,
        12
      ]
    ]
  },
  "reference": [
    {
      "key": "2023061919413622000_c1",
      "doi-asserted-by": "publisher",
      "first-page": "5877",
      "DOI": "10.1073/pnas.100127697",
      "volume": "97",
      "year": "2000",
      "journal-title": "Proc. Natl. Acad. Sci. U. S. A."
    },
    {
      "key": "2023061919413622000_c2",
      "doi-asserted-by": "crossref",
      "DOI": "10.1007/978-3-540-38448-9",
      "volume-title": "Free Energy Calculations: Theory and Applications in Chemistry and Biology",
      "author": "Chipot",
      "year": "2007"
    },
    {
      "key": "2023061919413622000_c3",
      "doi-asserted-by": "publisher",
      "first-page": "1737",
      "DOI": "10.1002/jcc.21332",
      "volume": "30",
      "year": "2009",
      "journal-title": "J. Comput. Chem."
    },
    {
      "key": "2023061919413622000_c4",
      "doi-asserted-by": "publisher",
      "first-page": "3345",
      "DOI": "10.1080/00268976.2013.813594",
      "volume": "111",
      "year": "2013",
      "journal-title": "Mol. Phys."
    },
    {
      "key": "2023061919413622000_c5",
      "doi-asserted-by": "publisher",
      "first-page": "3353",
      "DOI": "10.1021/cr4005988",
      "volume": "114",
      "year": "2014",
      "journal-title": "Chem. Rev."
    },
    {
      "key": "2023061919413622000_c6",
      "doi-asserted-by": "publisher",
      "first-page": "578",
      "DOI": "10.1016/0009-2614(74)80109-0",
      "volume": "28",
      "year": "1974",
      "journal-title": "Chem. Phys. Lett."
    },
    {
      "key": "2023061919413622000_c7",
      "doi-asserted-by": "publisher",
      "first-page": "187",
      "DOI": "10.1016/0021-9991(77)90121-8",
      "volume": "23",
      "year": "1977",
      "journal-title": "J. Comput. Phys."
    },
    {
      "key": "2023061919413622000_c8",
      "doi-asserted-by": "publisher",
      "first-page": "3806",
      "DOI": "10.1021/ja075896n",
      "volume": "130",
      "year": "2008",
      "journal-title": "J. Am. Chem. Soc."
    },
    {
      "key": "2023061919413622000_c9",
      "doi-asserted-by": "publisher",
      "first-page": "16721",
      "DOI": "10.1021/ja807269j",
      "volume": "130",
      "year": "2008",
      "journal-title": "J. Am. Chem. Soc."
    },
    {
      "key": "2023061919413622000_c10",
      "doi-asserted-by": "publisher",
      "first-page": "573",
      "DOI": "10.1146/annurev.physchem.59.032607.093618",
      "volume": "59",
      "year": "2008",
      "journal-title": "Annu. Rev. Phys. Chem."
    },
    {
      "key": "2023061919413622000_c11",
      "doi-asserted-by": "publisher",
      "first-page": "17",
      "DOI": "10.1016/j.theochem.2008.12.025",
      "volume": "898",
      "year": "2009",
      "journal-title": "J. Mol. Struct.: THEOCHEM"
    },
    {
      "key": "2023061919413622000_c12",
      "doi-asserted-by": "publisher",
      "first-page": "1056",
      "DOI": "10.1080/08927022.2015.1132317",
      "volume": "42",
      "year": "2016",
      "journal-title": "Mol. Simul."
    },
    {
      "key": "2023061919413622000_c13",
      "doi-asserted-by": "publisher",
      "first-page": "583",
      "DOI": "10.1209/0295-5075/26/8/005",
      "volume": "26",
      "year": "1994",
      "journal-title": "Europhys. Lett."
    },
    {
      "key": "2023061919413622000_c14",
      "doi-asserted-by": "publisher",
      "first-page": "628",
      "DOI": "10.1021/ct600284f",
      "volume": "3",
      "year": "2007",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "key": "2023061919413622000_c15",
      "doi-asserted-by": "publisher",
      "first-page": "3038",
      "DOI": "10.1021/ct4009624",
      "volume": "10",
      "year": "2014",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "key": "2023061919413622000_c16",
      "doi-asserted-by": "publisher",
      "first-page": "8427",
      "DOI": "10.1021/jp049633g",
      "volume": "108",
      "year": "2004",
      "journal-title": "J. Phys. Chem. B"
    },
    {
      "key": "2023061919413622000_c17",
      "doi-asserted-by": "publisher",
      "first-page": "17663",
      "DOI": "10.1021/jp063520a",
      "volume": "110",
      "year": "2006",
      "journal-title": "J. Phys. Chem. B"
    },
    {
      "key": "2023061919413622000_c18",
      "doi-asserted-by": "publisher",
      "first-page": "094306",
      "DOI": "10.1103/physrevb.92.094306",
      "volume": "92",
      "year": "2015",
      "journal-title": "Phys. Rev. B"
    },
    {
      "key": "2023061919413622000_c19",
      "doi-asserted-by": "publisher",
      "first-page": "096405",
      "DOI": "10.1103/physrevlett.114.096405",
      "volume": "114",
      "year": "2015",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "2023061919413622000_c20",
      "doi-asserted-by": "publisher",
      "first-page": "4079",
      "DOI": "10.1021/ct500438v",
      "volume": "10",
      "year": "2014",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "key": "2023061919413622000_c21",
      "doi-asserted-by": "publisher",
      "first-page": "4934",
      "DOI": "10.1021/acs.jctc.6b00663",
      "volume": "12",
      "year": "2016",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "edition": "2nd ed.",
      "volume-title": "The Elements of Statistical Learning: Data Mining, Inference, and Prediction",
      "year": "2009",
      "key": "2023061919413622000_c22"
    },
    {
      "volume-title": "Understanding Molecular Simulation: From Algorithms to Applications",
      "year": "2001",
      "key": "2023061919413622000_c23"
    },
    {
      "key": "2023061919413622000_c24",
      "doi-asserted-by": "publisher",
      "first-page": "2323",
      "DOI": "10.1126/science.290.5500.2323",
      "volume": "290",
      "year": "2000",
      "journal-title": "Science"
    },
    {
      "key": "2023061919413622000_c25",
      "doi-asserted-by": "publisher",
      "first-page": "926",
      "DOI": "10.1063/1.445869",
      "volume": "79",
      "year": "1983",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "2023061919413622000_c26",
      "doi-asserted-by": "publisher",
      "first-page": "3696",
      "DOI": "10.1021/acs.jctc.5b00255",
      "volume": "11",
      "year": "2015",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "key": "2023061919413622000_c27",
      "doi-asserted-by": "publisher",
      "first-page": "7260",
      "DOI": "10.1103/physrevb.58.7260",
      "volume": "58",
      "year": "1998",
      "journal-title": "Phys. Rev. B"
    },
    {
      "key": "2023061919413622000_c28",
      "doi-asserted-by": "publisher",
      "first-page": "5655",
      "DOI": "10.1021/jp070071l",
      "volume": "111",
      "year": "2007",
      "journal-title": "J. Phys. Chem. A"
    },
    {
      "key": "2023061919413622000_c29",
      "doi-asserted-by": "publisher",
      "first-page": "3684",
      "DOI": "10.1063/1.448118",
      "volume": "81",
      "year": "1984",
      "journal-title": "J. Chem. Phys."
    },
    {
      "volume-title": "AMBER 14",
      "year": "2014",
      "key": "2023061919413622000_c30"
    },
    {
      "year": "2004",
      "key": "2023061919413622000_c31"
    },
    {
      "key": "2023061919413622000_c32",
      "doi-asserted-by": "publisher",
      "first-page": "1195",
      "DOI": "10.1103/physrevlett.63.1195",
      "volume": "63",
      "year": "1989",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "2023061919413622000_c33",
      "doi-asserted-by": "publisher",
      "first-page": "1011",
      "DOI": "10.1002/jcc.540130812",
      "volume": "13",
      "year": "1992",
      "journal-title": "J. Comput. Chem."
    },
    {
      "key": "2023061919413622000_c34",
      "doi-asserted-by": "publisher",
      "first-page": "5518",
      "DOI": "10.1021/jp511057f",
      "volume": "119",
      "year": "2015",
      "journal-title": "J. Phys. Chem. B"
    },
    {
      "key": "2023061919413622000_c35",
      "doi-asserted-by": "publisher",
      "first-page": "14505",
      "DOI": "10.1021/acs.jpcb.5b08690",
      "volume": "119",
      "year": "2015",
      "journal-title": "J. Phys. Chem. B"
    },
    {
      "key": "2023061919413622000_c36",
      "doi-asserted-by": "publisher",
      "first-page": "8039",
      "DOI": "10.1063/1.1691404",
      "volume": "120",
      "year": "2004",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "2023061919413622000_c37",
      "doi-asserted-by": "publisher",
      "first-page": "054109",
      "DOI": "10.1063/1.2163875",
      "volume": "124",
      "year": "2006",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "2023061919413622000_c38",
      "doi-asserted-by": "publisher",
      "first-page": "390",
      "DOI": "10.1021/ct600240y",
      "volume": "3",
      "year": "2007",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "key": "2023061919413622000_c39",
      "doi-asserted-by": "publisher",
      "first-page": "034105",
      "DOI": "10.1063/1.2816557",
      "volume": "128",
      "year": "2008",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "2023061919413622000_c40",
      "doi-asserted-by": "publisher",
      "first-page": "044108",
      "DOI": "10.1063/1.4887340",
      "volume": "141",
      "year": "2014",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "2023061919413622000_c41",
      "doi-asserted-by": "publisher",
      "first-page": "024103",
      "DOI": "10.1063/1.4973607",
      "volume": "146",
      "year": "2017",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "2023061919413622000_c42",
      "doi-asserted-by": "publisher",
      "first-page": "511",
      "DOI": "10.1021/acs.jpcc.6b10908",
      "volume": "121",
      "year": "2017",
      "journal-title": "J. Phys. Chem. C"
    },
    {
      "key": "2023061919413622000_c43",
      "doi-asserted-by": "publisher",
      "first-page": "173",
      "DOI": "10.1080/08927028808080941",
      "volume": "1",
      "year": "1988",
      "journal-title": "Mol. Simul."
    },
    {
      "key": "2023061919413622000_c44",
      "doi-asserted-by": "publisher",
      "first-page": "5139",
      "DOI": "10.1039/c5sc04786b",
      "volume": "7",
      "year": "2016",
      "journal-title": "Chem. Sci."
    },
    {
      "key": "2023061919413622000_c45",
      "doi-asserted-by": "publisher",
      "first-page": "175503",
      "DOI": "10.1103/physrevlett.93.175503",
      "volume": "93",
      "year": "2004",
      "journal-title": "Phys. Rev. Lett."
    }
  ],
  "container-title": "The Journal of Chemical Physics",
  "original-title": [],
  "language": "en",
  "link": [
    {
      "URL": "https://pubs.aip.org/aip/jcp/article-pdf/doi/10.1063/1.5006882/15536884/161732_1_online.pdf",
      "content-type": "application/pdf",
      "content-version": "vor",
      "intended-application": "syndication"
    },
    {
      "URL": "https://pubs.aip.org/aip/jcp/article-pdf/doi/10.1063/1.5006882/15536884/161732_1_online.pdf",
      "content-type": "unspecified",
      "content-version": "vor",
      "intended-application": "similarity-checking"
    }
  ],
  "deposited": {
    "date-parts": [
      [
        2023,
        6,
        19
      ]
    ],
    "date-time": "2023-06-19T19:41:46Z",
    "timestamp": 1687203706000
  },
  "score": 1,
  "resource": {
    "primary": {
      "URL": "https://pubs.aip.org/jcp/article/147/16/161732/76918/Internal-force-corrections-with-machine-learning"
    }
  },
  "subtitle": [],
  "short-title": [],
  "issued": {
    "date-parts": [
      [
        2017,
        10,
        12
      ]
    ]
  },
  "references-count": 45,
  "journal-issue": {
    "issue": "16",
    "published-print": {
      "date-parts": [
        [
          2017,
          10,
          28
        ]
      ]
    }
  },
  "URL": "http://dx.doi.org/10.1063/1.5006882",
  "relation": {},
  "ISSN": [
    "0021-9606",
    "1089-7690"
  ],
  "subject": [],
  "published-other": {
    "date-parts": [
      [
        2017,
        10,
        28
      ]
    ]
  },
  "published": {
    "date-parts": [
      [
        2017,
        10,
        12
      ]
    ]
  },
  "article-number": "161732"
}