DOI: 10.1063/1.5019779. SchNet – A deep learning architecture for molecules and materials

SchNet – A deep learning architecture for molecules and materials

10.1063/1.5019779

Crossref journal-article

AIP Publishing

The Journal of Chemical Physics (317)

Abstract

Deep learning has led to a paradigm shift in artificial intelligence, including web, text, and image search, speech recognition, as well as bioinformatics, with growing impact in chemical physics. Machine learning, in general, and deep learning, in particular, are ideally suitable for representing quantum-mechanical interactions, enabling us to model nonlinear potential-energy surfaces or enhancing the exploration of chemical compound space. Here we present the deep learning architecture SchNet that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers. We demonstrate the capabilities of SchNet by accurately predicting a range of properties across chemical space for molecules and materials, where our model learns chemically plausible embeddings of atom types across the periodic table. Finally, we employ SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules and perform an exemplary study on the quantum-mechanical properties of C20-fullerene that would have been infeasible with regular ab initio molecular dynamics.

Bibliography

SchÃ¼tt, K. T., Sauceda, H. E., Kindermans, P.-J., Tkatchenko, A., & MÃ¼ller, K.-R. (2018). SchNet â A deep learning architecture for molecules and materials. The Journal of Chemical Physics, 148(24).

Authors 5

K. T. Schütt (first)
H. E. Sauceda (additional)
P.-J. Kindermans (additional)
A. Tkatchenko (additional)
K.-R. Müller (additional)

References 65 Referenced 1,546

10.1103/physrevlett.108.058301 / Phys. Rev. Lett. (2012)
10.1088/1367-2630/15/9/095003 / New J. Phys. (2013)
10.1021/ct400195d / J. Chem. Theory Comput. (2013)
10.1103/physrevb.89.205118 / Phys. Rev. B (2014)
10.1002/qua.24917 / Int. J. Quantum Chem. (2015)
10.1021/acs.jctc.5b00099 / J. Chem. Theory Comput. (2015)
10.1021/acs.jpclett.5b00831 / J. Phys. Chem. Lett. (2015)
10.1103/physrevlett.117.135502 / Phys. Rev. Lett. (2016)
10.1137/16m1075454 / Multiscale Model. Simul. (2017)
10.1021/acs.jctc.7b00577 / J. Chem. Theory Comput. (2017)
H. Huo and M. Rupp, preprint arXiv:1704.06439 (2017).
{'first-page': '6522', 'volume-title': 'Advances in Neural Information Processing Systems 30', 'year': '2017', 'key': '2023080301102866800_c12'} / Advances in Neural Information Processing Systems 30 (2017)
10.1038/ncomms15679 / Nat. Commun. (2017)
K. Ryczko, K. Mills, I. Luchak, C. Homenick, and I. Tamblyn, preprint arXiv:1706.09496 (2017).
I. Luchak, K. Mills, K. Ryczko, A. Domurad, and I. Tamblyn, preprint arXiv:1708.06686 (2017).
10.1103/physrevlett.98.146401 / Phys. Rev. Lett. (2007)
10.1063/1.3553717 / J. Chem. Phys. (2011)
10.1103/physrevlett.104.136403 / Phys. Rev. Lett. (2010)
10.1103/physrevb.87.184115 / Phys. Rev. B (2013)
10.1137/15m1054183 / Multiscale Model. Simul. (2016)
10.1126/sciadv.1603015 / Sci. Adv. (2017)
10.1038/s41467-017-00839-3 / Nat. Commun. (2017)
10.1039/c6sc05720a / Chem. Sci. (2017)
10.1016/j.commatsci.2017.08.031 / Comput. Mater. Sci. (2017)
10.1103/PhysRevB.97.054303 / Phys. Rev. B (2018)
{'first-page': '2224', 'year': '2015', 'author': 'Cortes', 'key': '2023080301102866800_c26'} by Cortes (2015)
10.1007/s10822-016-9938-8 / J. Comput.-Aided Mol. Des. (2016)
10.1038/ncomms13890 / Nat. Commun. (2017)
{'year': '2017', 'key': '2023080301102866800_c29', 'first-page': '1263'} (2017)
{'first-page': '992', 'volume-title': 'Advances in Neural Information Processing Systems 30', 'year': '2017', 'key': '2023080301102866800_c30'} / Advances in Neural Information Processing Systems 30 (2017)
{'key': '2023080301102866800_c31', 'first-page': '1803', 'volume': '11', 'year': '2010', 'journal-title': 'J. Mach. Learn. Res.'} / J. Mach. Learn. Res. (2010)
K. Simonyan, A. Vedaldi, and A. Zisserman, eprint arXiv:1312.6034 (2013).
10.1371/journal.pone.0130140 / PLoS One (2015)
{'key': '2023080301102866800_c34'}
10.1016/j.patcog.2016.11.008 / Pattern Recognit. (2017)
P.-J. Kindermans, K. T. Schütt, M. Alber, K.-R. Müller, D. Erhan, B. Kim, and S. Dähne, eprint arXiv:1705.05598 (2017).
10.1016/j.dsp.2017.10.011 / Digital Signal Process. (2018)
{'year': '2015', 'key': '2023080301102866800_c38', 'first-page': '2048'} (2015)
10.1103/physrevlett.77.3865 / Phys. Rev. Lett. (1996)
10.1103/physrevlett.102.073005 / Phys. Rev. Lett. (2009)
10.1039/c5sc03443d / Chem. Sci. (2016)
{'year': '2009', 'key': '2023080301102866800_c42', 'first-page': '1'} (2009)
10.1109/tasl.2012.2227738 / IEEE Trans. Audio, Speech, Lang. Process. (2013)
{'year': '2013', 'key': '2023080301102866800_c44', 'first-page': '1642'} (2013)
{'key': '2023080301102866800_c45', 'first-page': '667', 'volume-title': 'Advances in Neural Information Processing Systems 29', 'author': 'Lee', 'year': '2016'} / Advances in Neural Information Processing Systems 29 by Lee (2016)
10.1162/neco.1989.1.4.541 / Neural Comput. (1989)
{'first-page': '1097', 'volume-title': 'Advances in Neural Information Processing Systems', 'year': '2012', 'key': '2023080301102866800_c47'} / Advances in Neural Information Processing Systems (2012)
{'year': '2016', 'key': '2023080301102866800_c48'} (2016)
{'year': '2017', 'key': '2023080301102866800_c49', 'first-page': '1251'} (2017)
{'year': '2016', 'key': '2023080301102866800_c50', 'first-page': '770'} (2016)
10.1063/1.3095491 / J. Chem. Phys. (2009)
{'key': '2023080301102866800_c52'}
10.1038/sdata.2014.22 / Sci. Data (2014)
10.1021/ja902302h / J. Am. Chem. Soc. (2009)
10.1021/ar500432k / Acc. Chem. Res. (2015)
O. Vinyals, S. Bengio, and M. Kudlur, eprint arXiv:1511.06391 (2015).
10.1039/c7sc02267k / Chem. Sci. (2017)
10.1063/1.4812323 / APL Mater. (2013)
10.1016/j.commatsci.2012.10.028 / Comput. Mater. Sci. (2013)
10.1109/mcse.2011.35 / Comput. Sci. Eng. (2011)
Code and trained models are available at: https://github.com/atomistic-machine-learning/SchNet.
10.1063/1.5006596 / J. Chem. Phys. (2018)
10.1016/j.cpc.2009.06.022 / Comput. Phys. Commun. (2009)
10.1016/j.cpc.2013.10.027 / Comput. Phys. Commun. (2014)
10.1063/1.3489925 / J. Chem. Phys. (2010)

Dates

Type	When
Created	7 years, 4 months ago (March 29, 2018, 10:20 a.m.)
Deposited	2 years ago (Aug. 2, 2023, 9:10 p.m.)
Indexed	4 hours, 59 minutes ago (Aug. 21, 2025, 12:34 p.m.)
Issued	7 years, 4 months ago (March 29, 2018)
Published	7 years, 4 months ago (March 29, 2018)
Published Online	7 years, 4 months ago (March 29, 2018)
Published Print	7 years, 1 month ago (June 28, 2018)

Funders 6

Deutsche Forschungsgemeinschaft 10.13039/501100001659
Region: Europe
gov (National government)
Labels3
1. German Research Association
2. German Research Foundation
3. DFG
Awards1
1. MU 987/20-1
National Research Foundation of Korea 10.13039/501100003725
Region: Asia
pri (Trusts, charities, foundations (both public and private))
Labels3
1. 한국연구재단이 창의적 연구와
2. National Research Foundation (South Korea)
3. NRF
Awards1
1. 2012-005741
Ministry of Science, ICT and Future Planning 10.13039/501100003621
Region: Asia
gov (National government)
Labels1
1. MSIP
Awards1
1. 2017-0-00451
Bundesministerium für Bildung und Forschung 10.13039/501100002347
Region: Europe
gov (National government)
Labels2
1. Federal Ministry of Education and Research
2. BMBF
Awards1
1. 01IS14013A
H2020 European Research Council 10.13039/100010663
Region: Europe
gov (National government)
Labels17
1. H2020 Excellent Science - European Research Council
2. European Research Council
3. H2020 Wissenschaftsexzellenz - Für das Einzelziel 'Europäischer Forschungsrat (ERC)'
4. H2020 Ciencia Excelente - Consejo Europeo de Investigación (CEI)
5. H2020 Excellence Scientifique - Conseil européen de la recherche (CER)
6. H2020 Eccellenza Scientifica - Consiglio europeo della ricerca (CER)
7. H2020 Doskonała Baza Naukowa - Europejska Rada ds. Badań Naukowych (ERBN)
8. EXCELLENT SCIENCE - European Research Council
9. WISSENSCHAFTSEXZELLENZ - Für das Einzelziel 'Europäischer Forschungsrat
10. CIENCIA EXCELENTE - Consejo Europeo de Investigación
11. EXCELLENCE SCIENTIFIQUE - Conseil européen de la recherche
12. ECCELLENZA SCIENTIFICA - Consiglio europeo della ricerca
13. DOSKONAŁA BAZA NAUKOWA - Europejska Rada ds. Badań Naukowych
14. ERC
15. CEI
16. CER
17. ERBN
Awards1
1. BeStMo
H2020 Marie Skłodowska-Curie Actions 10.13039/100010665
Region: Europe
gov (National government)
Labels22
1. H2020 Excellent Science - Marie Skłodowska-Curie Actions
2. H2020 EXCELLENCE SCIENTIFIQUE - Actions Marie Skłodowska-Curie
3. H2020 WISSENSCHAFTSEXZELLENZ- Marie Skłodowska-Curie Maßnahmen
4. H2020 CIENCIA EXCELENTE - Acciones Marie Skłodowska-Curie
5. H2020 ECCELLENZA SCIENTIFICA - Azioni Marie Skłodowska-Curie
6. H2020 DOSKONAŁA BAZA NAUKOWA - Działania „Maria Skłodowska-Curie'
7. Marie Skłodowska-Curie Actions
8. Excellent Science: Marie Skłodowska-Curie Actions
9. Actions Marie Skłodowska-Curie
10. Marie-Skłodowska-Curie-Maßnahmen
11. Acciones Marie Skłodowska-Curie
12. Azioni Marie Skłodowska-Curie
13. Działania „Maria Skłodowska-Curie'
14. EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions
15. EXCELLENCE SCIENTIFIQUE - Actions Marie Skłodowska-Curie
16. WISSENSCHAFTSEXZELLENZ- Marie Skłodowska-Curie Maßnahmen
17. CIENCIA EXCELENTE - Acciones Marie Skłodowska-Curie
18. ECCELLENZA SCIENTIFICA - Azioni Marie Skłodowska-Curie
19. DOSKONAŁA BAZA NAUKOWA - Działania „Maria Skłodowska-Curie'
20. MSCA
21. MSCM
22. AMSC
Awards1
1. 657679

BibTeX

@article{Sch_tt_2018, title={SchNet – A deep learning architecture for molecules and materials}, volume={148}, ISSN={1089-7690}, url={http://dx.doi.org/10.1063/1.5019779}, DOI={10.1063/1.5019779}, number={24}, journal={The Journal of Chemical Physics}, publisher={AIP Publishing}, author={Schütt, K. T. and Sauceda, H. E. and Kindermans, P.-J. and Tkatchenko, A. and Müller, K.-R.}, year={2018}, month=mar }

JSON

{
  "indexed": {
    "date-parts": [
      [
        2025,
        8,
        21
      ]
    ],
    "date-time": "2025-08-21T16:34:43Z",
    "timestamp": 1755794083092,
    "version": "3.41.2"
  },
  "reference-count": 65,
  "publisher": "AIP Publishing",
  "issue": "24",
  "funder": [
    {
      "DOI": "10.13039/501100001659",
      "name": "Deutsche Forschungsgemeinschaft",
      "doi-asserted-by": "publisher",
      "award": [
        "MU 987/20-1"
      ],
      "id": [
        {
          "id": "10.13039/501100001659",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    },
    {
      "DOI": "10.13039/501100003725",
      "name": "National Research Foundation of Korea",
      "doi-asserted-by": "publisher",
      "award": [
        "2012-005741"
      ],
      "id": [
        {
          "id": "10.13039/501100003725",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    },
    {
      "DOI": "10.13039/501100003621",
      "name": "Ministry of Science, ICT and Future Planning",
      "doi-asserted-by": "publisher",
      "award": [
        "2017-0-00451"
      ],
      "id": [
        {
          "id": "10.13039/501100003621",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    },
    {
      "DOI": "10.13039/501100002347",
      "name": "Bundesministerium f\u00fcr Bildung und Forschung",
      "doi-asserted-by": "publisher",
      "award": [
        "01IS14013A"
      ],
      "id": [
        {
          "id": "10.13039/501100002347",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    },
    {
      "DOI": "10.13039/100010663",
      "name": "H2020 European Research Council",
      "doi-asserted-by": "publisher",
      "award": [
        "BeStMo"
      ],
      "id": [
        {
          "id": "10.13039/100010663",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    },
    {
      "DOI": "10.13039/100010665",
      "name": "H2020 Marie Sk\u0142odowska-Curie Actions",
      "doi-asserted-by": "publisher",
      "award": [
        "657679"
      ],
      "id": [
        {
          "id": "10.13039/100010665",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    }
  ],
  "content-domain": {
    "domain": [
      "pubs.aip.org"
    ],
    "crossmark-restriction": true
  },
  "published-print": {
    "date-parts": [
      [
        2018,
        6,
        28
      ]
    ]
  },
  "abstract": "<jats:p>Deep learning has led to a paradigm shift in artificial intelligence, including web, text, and image search, speech recognition, as well as bioinformatics, with growing impact in chemical physics. Machine learning, in general, and deep learning, in particular, are ideally suitable for representing quantum-mechanical interactions, enabling us to model nonlinear potential-energy surfaces or enhancing the exploration of chemical compound space. Here we present the deep learning architecture SchNet that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers. We demonstrate the capabilities of SchNet by accurately predicting a range of properties across chemical space for molecules and materials, where our model learns chemically plausible embeddings of atom types across the periodic table. Finally, we employ SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules and perform an exemplary study on the quantum-mechanical properties of C20-fullerene that would have been infeasible with regular ab initio molecular dynamics.</jats:p>",
  "DOI": "10.1063/1.5019779",
  "type": "journal-article",
  "created": {
    "date-parts": [
      [
        2018,
        3,
        29
      ]
    ],
    "date-time": "2018-03-29T14:20:49Z",
    "timestamp": 1522333249000
  },
  "update-policy": "https://doi.org/10.1063/aip-crossmark-policy-page",
  "source": "Crossref",
  "is-referenced-by-count": 1546,
  "title": "SchNet \u2013 A deep learning architecture for molecules and materials",
  "prefix": "10.1063",
  "volume": "148",
  "author": [
    {
      "ORCID": "https://orcid.org/0000-0001-8342-0964",
      "authenticated-orcid": false,
      "given": "K. T.",
      "family": "Sch\u00fctt",
      "sequence": "first",
      "affiliation": [
        {
          "name": "Machine Learning Group, Technische Universit\u00e4t Berlin 1 , 10587 Berlin, Germany"
        }
      ]
    },
    {
      "given": "H. E.",
      "family": "Sauceda",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Fritz-Haber-Institut der Max-Planck-Gesellschaft 2 , 14195 Berlin, Germany"
        }
      ]
    },
    {
      "given": "P.-J.",
      "family": "Kindermans",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Machine Learning Group, Technische Universit\u00e4t Berlin 1 , 10587 Berlin, Germany"
        }
      ]
    },
    {
      "given": "A.",
      "family": "Tkatchenko",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Physics and Materials Science Research Unit, University of Luxembourg 3 , L-1511 Luxembourg, Luxembourg"
        }
      ]
    },
    {
      "given": "K.-R.",
      "family": "M\u00fcller",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Machine Learning Group, Technische Universit\u00e4t Berlin 1 , 10587 Berlin, Germany"
        },
        {
          "name": "Max-Planck-Institut f\u00fcr Informatik 4 , Saarbr\u00fccken, Germany"
        },
        {
          "name": "Department of Brain and Cognitive Engineering, Korea University 5 , Anam-dong, Seongbuk-gu, Seoul 136-713, South Korea"
        }
      ]
    }
  ],
  "member": "317",
  "published-online": {
    "date-parts": [
      [
        2018,
        3,
        29
      ]
    ]
  },
  "reference": [
    {
      "key": "2023080301102866800_c1",
      "doi-asserted-by": "publisher",
      "first-page": "058301",
      "DOI": "10.1103/physrevlett.108.058301",
      "volume": "108",
      "year": "2012",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "2023080301102866800_c2",
      "doi-asserted-by": "publisher",
      "first-page": "095003",
      "DOI": "10.1088/1367-2630/15/9/095003",
      "volume": "15",
      "year": "2013",
      "journal-title": "New J. Phys."
    },
    {
      "key": "2023080301102866800_c3",
      "doi-asserted-by": "publisher",
      "first-page": "3404",
      "DOI": "10.1021/ct400195d",
      "volume": "9",
      "year": "2013",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "key": "2023080301102866800_c4",
      "doi-asserted-by": "publisher",
      "first-page": "205118",
      "DOI": "10.1103/physrevb.89.205118",
      "volume": "89",
      "year": "2014",
      "journal-title": "Phys. Rev. B"
    },
    {
      "key": "2023080301102866800_c5",
      "doi-asserted-by": "publisher",
      "first-page": "1094",
      "DOI": "10.1002/qua.24917",
      "volume": "115",
      "year": "2015",
      "journal-title": "Int. J. Quantum Chem."
    },
    {
      "key": "2023080301102866800_c6",
      "doi-asserted-by": "publisher",
      "first-page": "2087",
      "DOI": "10.1021/acs.jctc.5b00099",
      "volume": "11",
      "year": "2015",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "key": "2023080301102866800_c7",
      "doi-asserted-by": "publisher",
      "first-page": "2326",
      "DOI": "10.1021/acs.jpclett.5b00831",
      "volume": "6",
      "year": "2015",
      "journal-title": "J. Phys. Chem. Lett."
    },
    {
      "key": "2023080301102866800_c8",
      "doi-asserted-by": "publisher",
      "first-page": "135502",
      "DOI": "10.1103/physrevlett.117.135502",
      "volume": "117",
      "year": "2016",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "2023080301102866800_c9",
      "doi-asserted-by": "publisher",
      "first-page": "827",
      "DOI": "10.1137/16m1075454",
      "volume": "15",
      "year": "2017",
      "journal-title": "Multiscale Model. Simul."
    },
    {
      "issue": "11",
      "key": "2023080301102866800_c10",
      "doi-asserted-by": "publisher",
      "first-page": "5255",
      "DOI": "10.1021/acs.jctc.7b00577",
      "volume": "13",
      "year": "2017",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "key": "2023080301102866800_c11",
      "unstructured": "H.\u2008Huo and M.\u2008Rupp, preprint arXiv:1704.06439 (2017)."
    },
    {
      "first-page": "6522",
      "volume-title": "Advances in Neural Information Processing Systems 30",
      "year": "2017",
      "key": "2023080301102866800_c12"
    },
    {
      "key": "2023080301102866800_c13",
      "doi-asserted-by": "publisher",
      "first-page": "15679",
      "DOI": "10.1038/ncomms15679",
      "volume": "8",
      "year": "2017",
      "journal-title": "Nat. Commun."
    },
    {
      "key": "2023080301102866800_c14",
      "unstructured": "K.\u2008Ryczko, K.\u2008Mills, I.\u2008Luchak, C.\u2008Homenick, and I.\u2008Tamblyn, preprint arXiv:1706.09496 (2017)."
    },
    {
      "key": "2023080301102866800_c15",
      "unstructured": "I.\u2008Luchak, K.\u2008Mills, K.\u2008Ryczko, A.\u2008Domurad, and I.\u2008Tamblyn, preprint arXiv:1708.06686 (2017)."
    },
    {
      "key": "2023080301102866800_c16",
      "doi-asserted-by": "publisher",
      "first-page": "146401",
      "DOI": "10.1103/physrevlett.98.146401",
      "volume": "98",
      "year": "2007",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "2023080301102866800_c17",
      "doi-asserted-by": "publisher",
      "first-page": "074106",
      "DOI": "10.1063/1.3553717",
      "volume": "134",
      "year": "2011",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "2023080301102866800_c18",
      "doi-asserted-by": "publisher",
      "first-page": "136403",
      "DOI": "10.1103/physrevlett.104.136403",
      "volume": "104",
      "year": "2010",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "2023080301102866800_c19",
      "doi-asserted-by": "publisher",
      "first-page": "184115",
      "DOI": "10.1103/physrevb.87.184115",
      "volume": "87",
      "year": "2013",
      "journal-title": "Phys. Rev. B"
    },
    {
      "key": "2023080301102866800_c20",
      "doi-asserted-by": "publisher",
      "first-page": "1153",
      "DOI": "10.1137/15m1054183",
      "volume": "14",
      "year": "2016",
      "journal-title": "Multiscale Model. Simul."
    },
    {
      "key": "2023080301102866800_c21",
      "doi-asserted-by": "publisher",
      "first-page": "e1603015",
      "DOI": "10.1126/sciadv.1603015",
      "volume": "3",
      "year": "2017",
      "journal-title": "Sci. Adv."
    },
    {
      "key": "2023080301102866800_c22",
      "doi-asserted-by": "publisher",
      "first-page": "872",
      "DOI": "10.1038/s41467-017-00839-3",
      "volume": "8",
      "year": "2017",
      "journal-title": "Nat. Commun."
    },
    {
      "key": "2023080301102866800_c23",
      "doi-asserted-by": "publisher",
      "first-page": "3192",
      "DOI": "10.1039/c6sc05720a",
      "volume": "8",
      "year": "2017",
      "journal-title": "Chem. Sci."
    },
    {
      "key": "2023080301102866800_c24",
      "doi-asserted-by": "publisher",
      "first-page": "171",
      "DOI": "10.1016/j.commatsci.2017.08.031",
      "volume": "140",
      "year": "2017",
      "journal-title": "Comput. Mater. Sci."
    },
    {
      "issue": "5",
      "key": "2023080301102866800_c25",
      "doi-asserted-by": "publisher",
      "first-page": "054303",
      "DOI": "10.1103/PhysRevB.97.054303",
      "volume": "97",
      "year": "2018",
      "journal-title": "Phys. Rev. B"
    },
    {
      "first-page": "2224",
      "year": "2015",
      "author": "Cortes",
      "key": "2023080301102866800_c26"
    },
    {
      "key": "2023080301102866800_c27",
      "doi-asserted-by": "publisher",
      "first-page": "595",
      "DOI": "10.1007/s10822-016-9938-8",
      "volume": "30",
      "year": "2016",
      "journal-title": "J. Comput.-Aided Mol. Des."
    },
    {
      "key": "2023080301102866800_c28",
      "doi-asserted-by": "publisher",
      "first-page": "13890",
      "DOI": "10.1038/ncomms13890",
      "volume": "8",
      "year": "2017",
      "journal-title": "Nat. Commun."
    },
    {
      "year": "2017",
      "key": "2023080301102866800_c29",
      "first-page": "1263"
    },
    {
      "first-page": "992",
      "volume-title": "Advances in Neural Information Processing Systems 30",
      "year": "2017",
      "key": "2023080301102866800_c30"
    },
    {
      "key": "2023080301102866800_c31",
      "first-page": "1803",
      "volume": "11",
      "year": "2010",
      "journal-title": "J. Mach. Learn. Res."
    },
    {
      "key": "2023080301102866800_c32",
      "unstructured": "K.\u2008Simonyan, A.\u2008Vedaldi, and A.\u2008Zisserman, eprint arXiv:1312.6034 (2013)."
    },
    {
      "key": "2023080301102866800_c33",
      "doi-asserted-by": "publisher",
      "first-page": "e0130140",
      "DOI": "10.1371/journal.pone.0130140",
      "volume": "10",
      "year": "2015",
      "journal-title": "PLoS One"
    },
    {
      "key": "2023080301102866800_c34"
    },
    {
      "key": "2023080301102866800_c35",
      "doi-asserted-by": "publisher",
      "first-page": "211",
      "DOI": "10.1016/j.patcog.2016.11.008",
      "volume": "65",
      "year": "2017",
      "journal-title": "Pattern Recognit."
    },
    {
      "key": "2023080301102866800_c36",
      "unstructured": "P.-J.\u2008Kindermans, K. T.\u2008Sch\u00fctt, M.\u2008Alber, K.-R.\u2008M\u00fcller, D.\u2008Erhan, B.\u2008Kim, and S.\u2008D\u00e4hne, eprint arXiv:1705.05598 (2017)."
    },
    {
      "key": "2023080301102866800_c37",
      "doi-asserted-by": "publisher",
      "first-page": "1",
      "DOI": "10.1016/j.dsp.2017.10.011",
      "volume": "73",
      "year": "2018",
      "journal-title": "Digital Signal Process."
    },
    {
      "year": "2015",
      "key": "2023080301102866800_c38",
      "first-page": "2048"
    },
    {
      "key": "2023080301102866800_c39",
      "doi-asserted-by": "publisher",
      "first-page": "3865",
      "DOI": "10.1103/physrevlett.77.3865",
      "volume": "77",
      "year": "1996",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "2023080301102866800_c40",
      "doi-asserted-by": "publisher",
      "first-page": "073005",
      "DOI": "10.1103/physrevlett.102.073005",
      "volume": "102",
      "year": "2009",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "2023080301102866800_c41",
      "doi-asserted-by": "publisher",
      "first-page": "1368",
      "DOI": "10.1039/c5sc03443d",
      "volume": "7",
      "year": "2016",
      "journal-title": "Chem. Sci."
    },
    {
      "year": "2009",
      "key": "2023080301102866800_c42",
      "first-page": "1"
    },
    {
      "key": "2023080301102866800_c43",
      "doi-asserted-by": "publisher",
      "first-page": "388",
      "DOI": "10.1109/tasl.2012.2227738",
      "volume": "21",
      "year": "2013",
      "journal-title": "IEEE Trans. Audio, Speech, Lang. Process."
    },
    {
      "year": "2013",
      "key": "2023080301102866800_c44",
      "first-page": "1642"
    },
    {
      "key": "2023080301102866800_c45",
      "first-page": "667",
      "volume-title": "Advances in Neural Information Processing Systems 29",
      "author": "Lee",
      "year": "2016"
    },
    {
      "key": "2023080301102866800_c46",
      "doi-asserted-by": "publisher",
      "first-page": "541",
      "DOI": "10.1162/neco.1989.1.4.541",
      "volume": "1",
      "year": "1989",
      "journal-title": "Neural Comput."
    },
    {
      "first-page": "1097",
      "volume-title": "Advances in Neural Information Processing Systems",
      "year": "2012",
      "key": "2023080301102866800_c47"
    },
    {
      "year": "2016",
      "key": "2023080301102866800_c48"
    },
    {
      "year": "2017",
      "key": "2023080301102866800_c49",
      "first-page": "1251"
    },
    {
      "year": "2016",
      "key": "2023080301102866800_c50",
      "first-page": "770"
    },
    {
      "key": "2023080301102866800_c51",
      "doi-asserted-by": "publisher",
      "first-page": "134101",
      "DOI": "10.1063/1.3095491",
      "volume": "130",
      "year": "2009",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "2023080301102866800_c52"
    },
    {
      "key": "2023080301102866800_c53",
      "doi-asserted-by": "publisher",
      "first-page": "140022",
      "DOI": "10.1038/sdata.2014.22",
      "volume": "1",
      "year": "2014",
      "journal-title": "Sci. Data"
    },
    {
      "key": "2023080301102866800_c54",
      "doi-asserted-by": "publisher",
      "first-page": "8732",
      "DOI": "10.1021/ja902302h",
      "volume": "131",
      "year": "2009",
      "journal-title": "J. Am. Chem. Soc."
    },
    {
      "key": "2023080301102866800_c55",
      "doi-asserted-by": "publisher",
      "first-page": "722",
      "DOI": "10.1021/ar500432k",
      "volume": "48",
      "year": "2015",
      "journal-title": "Acc. Chem. Res."
    },
    {
      "key": "2023080301102866800_c56",
      "unstructured": "O.\u2008Vinyals, S.\u2008Bengio, and M.\u2008Kudlur, eprint arXiv:1511.06391 (2015)."
    },
    {
      "issue": "10",
      "key": "2023080301102866800_c57",
      "doi-asserted-by": "publisher",
      "first-page": "6924",
      "DOI": "10.1039/c7sc02267k",
      "volume": "8",
      "year": "2017",
      "journal-title": "Chem. Sci."
    },
    {
      "key": "2023080301102866800_c58",
      "doi-asserted-by": "publisher",
      "first-page": "011002",
      "DOI": "10.1063/1.4812323",
      "volume": "1",
      "year": "2013",
      "journal-title": "APL Mater."
    },
    {
      "key": "2023080301102866800_c59",
      "doi-asserted-by": "publisher",
      "first-page": "314",
      "DOI": "10.1016/j.commatsci.2012.10.028",
      "volume": "68",
      "year": "2013",
      "journal-title": "Comput. Mater. Sci."
    },
    {
      "key": "2023080301102866800_c60",
      "doi-asserted-by": "publisher",
      "first-page": "40",
      "DOI": "10.1109/mcse.2011.35",
      "volume": "13",
      "year": "2011",
      "journal-title": "Comput. Sci. Eng."
    },
    {
      "key": "2023080301102866800_c61",
      "unstructured": "Code and trained models are available at: https://github.com/atomistic-machine-learning/SchNet."
    },
    {
      "key": "2023080301102866800_c62",
      "doi-asserted-by": "publisher",
      "first-page": "102325",
      "DOI": "10.1063/1.5006596",
      "volume": "148",
      "year": "2018",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "2023080301102866800_c63",
      "doi-asserted-by": "publisher",
      "first-page": "2175",
      "DOI": "10.1016/j.cpc.2009.06.022",
      "volume": "180",
      "year": "2009",
      "journal-title": "Comput. Phys. Commun."
    },
    {
      "key": "2023080301102866800_c64",
      "doi-asserted-by": "publisher",
      "first-page": "1019",
      "DOI": "10.1016/j.cpc.2013.10.027",
      "volume": "185",
      "year": "2014",
      "journal-title": "Comput. Phys. Commun."
    },
    {
      "key": "2023080301102866800_c65",
      "doi-asserted-by": "publisher",
      "first-page": "124104",
      "DOI": "10.1063/1.3489925",
      "volume": "133",
      "year": "2010",
      "journal-title": "J. Chem. Phys."
    }
  ],
  "container-title": "The Journal of Chemical Physics",
  "original-title": [],
  "language": "en",
  "link": [
    {
      "URL": "https://pubs.aip.org/aip/jcp/article-pdf/doi/10.1063/1.5019779/16655678/241722_1_online.pdf",
      "content-type": "application/pdf",
      "content-version": "vor",
      "intended-application": "syndication"
    },
    {
      "URL": "https://pubs.aip.org/aip/jcp/article-pdf/doi/10.1063/1.5019779/16655678/241722_1_online.pdf",
      "content-type": "unspecified",
      "content-version": "vor",
      "intended-application": "similarity-checking"
    }
  ],
  "deposited": {
    "date-parts": [
      [
        2023,
        8,
        3
      ]
    ],
    "date-time": "2023-08-03T01:10:45Z",
    "timestamp": 1691025045000
  },
  "score": 1,
  "resource": {
    "primary": {
      "URL": "https://pubs.aip.org/jcp/article/148/24/241722/962591/SchNet-A-deep-learning-architecture-for-molecules"
    }
  },
  "subtitle": [],
  "short-title": [],
  "issued": {
    "date-parts": [
      [
        2018,
        3,
        29
      ]
    ]
  },
  "references-count": 65,
  "journal-issue": {
    "issue": "24",
    "published-print": {
      "date-parts": [
        [
          2018,
          6,
          28
        ]
      ]
    }
  },
  "URL": "http://dx.doi.org/10.1063/1.5019779",
  "relation": {},
  "ISSN": [
    "0021-9606",
    "1089-7690"
  ],
  "subject": [],
  "published-other": {
    "date-parts": [
      [
        2018,
        6,
        28
      ]
    ]
  },
  "published": {
    "date-parts": [
      [
        2018,
        3,
        29
      ]
    ]
  },
  "article-number": "241722"
}