DOI: 10.1002/adfm.201501919. Learning from the Harvard Clean Energy Project: The Use of Neural Networks to Accelerate Materials Discovery

Learning from the Harvard Clean Energy Project: The Use of Neural Networks to Accelerate Materials Discovery

10.1002/adfm.201501919

Crossref journal-article

Wiley

Advanced Functional Materials (311)

Abstract

Here, the employment of multilayer perceptrons, a type of artificial neural network, is proposed as part of a computational funneling procedure for high‐throughput organic materials design. Through the use of state of the art algorithms and a large amount of data extracted from the Harvard Clean Energy Project, it is demonstrated that these methods allow a great reduction in the fraction of the screening library that is actually calculated. Neural networks can reproduce the results of quantum‐chemical calculations with a large level of accuracy. The proposed approach allows to carry out large‐scale molecular screening projects with less computational time. This, in turn, allows for the exploration of increasingly large and diverse libraries.

Bibliography

PyzerâKnapp, E. O., Li, K., & AspuruâGuzik, A. (2015). Learning from the Harvard Clean Energy Project: The Use of Neural Networks to Accelerate Materials Discovery. Advanced Functional Materials, 25(41), 6495â6502. Portico.

Authors 3

Edward O. Pyzer‐Knapp (first)
Kewei Li (additional)
Alan Aspuru‐Guzik (additional)

References 52 Referenced 179

10.1039/c4sc00095a
10.1038/nature12909
10.1039/C3EE42756K
10.1016/j.jpowsour.2009.09.024
10.6026/97320630003014
10.1038/nature03197
10.1021/jm400870h
10.1039/C4CP00547C
10.1021/ja9061344
10.1002/wcms.1104
10.1146/annurev-matsci-070214-020823
10.1021/ci9003865
10.1021/ci00068a023
10.2174/138620708785739899
10.1021/ci3003039
10.1021/ci0500132
10.1021/ci400187y
10.1021/ci4005805
10.1088/1367-2630/15/9/095003
10.1021/acs.jctc.5b00099
10.2533/chimia.2015.182
{'volume-title': 'Gaussian Processes for Machine Learning', 'year': '2006', 'author': 'Rasmussen C. E.', 'key': 'e_1_2_7_22_1'} / Gaussian Processes for Machine Learning by Rasmussen C. E. (2006)
E. O.Pyzer‐Knapp C.Suh R. P.Adams A.Aspuru‐Guzik unpublished.
G.Simm E. O.Pyzer‐Knapp A.Aspuru‐Guzik unpublished.
10.1088/0954-898X_6_3_011
10.1037/h0042519
10.1016/S0003-2670(00)80865-X
{'key': 'e_1_2_7_28_1', 'first-page': '114', 'volume-title': 'Proc. IEEE‐INNS‐ENNS Int. Joint Conf. Neural Networks IJCNN 2000', 'author': 'Lawrence S.', 'year': '2000'} / Proc. IEEE‐INNS‐ENNS Int. Joint Conf. Neural Networks IJCNN 2000 by Lawrence S. (2000)
10.1016/S0893-6080(98)00010-0
10.1016/B978-1-4832-1446-7.50035-2
{'key': 'e_1_2_7_31_1', 'first-page': '177', 'volume-title': 'Proc. COMPSTAT', 'author': 'Bottou L.', 'year': '2010'} / Proc. COMPSTAT by Bottou L. (2010)
G.Hinton T.Tielman Lecture 6.5 – rmsprop COURSERA: Neural Networks for Machine Learning.
T.Schaul I.Antonoglou D.Silver 2013 arXiv:1406.1231.
{'key': 'e_1_2_7_34_1', 'first-page': '693', 'volume-title': 'Advances in Neural Information Processing Systems 24', 'author': 'Recht B.', 'year': '2011'} / Advances in Neural Information Processing Systems 24 by Recht B. (2011)
{'key': 'e_1_2_7_35_1', 'first-page': '571', 'volume-title': '11th USENIX Symp. Oper. Syst. Design Implementation (OSDI 14)', 'author': 'Chilimbi T.', 'year': '2014'} / 11th USENIX Symp. Oper. Syst. Design Implementation (OSDI 14) by Chilimbi T. (2014)
10.1002/adma.200501717
{'key': 'e_1_2_7_37_1', 'first-page': '440', 'volume-title': 'Advances in Neural Information Processing Systems 25', 'author': 'Montavon G.', 'year': '2012'} / Advances in Neural Information Processing Systems 25 by Montavon G. (2012)
10.1103/PhysRevLett.108.058301
{'journal-title': 'RDKit: Open‐Source Cheminformatics', 'author': 'Landrum G.', 'key': 'e_1_2_7_39_1'} / RDKit: Open‐Source Cheminformatics by Landrum G.
10.1021/ci00046a002
10.1021/ci010132r
10.1021/ci100050t
10.1021/ci00054a008
10.1177/1087057105281365
10.1080/00268976.2014.952696
10.1103/PhysRevB.33.8822
10.1103/PhysRevA.38.3098
10.1039/b508541a
{'journal-title': 'MAML – Molecular Applied Machine Learning.', 'author': 'Pyzer‐Knapp E. O.', 'key': 'e_1_2_7_49_1'} / MAML – Molecular Applied Machine Learning. by Pyzer‐Knapp E. O.
G. E.Dahl N.Jaitly R.Salakhutdinov 2014 arXiv:1406.1231.
10.1021/jz200866s
World Community Grid http://www.worldcommunitygrid.org/. (accessed February2015)

Dates

Type	When
Created	9 years, 11 months ago (Sept. 18, 2015, 8:40 a.m.)
Deposited	1 year, 10 months ago (Oct. 6, 2023, 12:03 a.m.)
Indexed	1 day, 17 hours ago (Aug. 21, 2025, 1:39 p.m.)
Issued	9 years, 11 months ago (Sept. 18, 2015)
Published	9 years, 11 months ago (Sept. 18, 2015)
Published Online	9 years, 11 months ago (Sept. 18, 2015)
Published Print	9 years, 9 months ago (Nov. 1, 2015)

Funders 2

Department of Energy 10.13039/100000015 U.S. Department of Energy
Region: Americas
gov (National government)
Labels8
1. Energy Department
2. Department of Energy
3. United States Department of Energy
4. ENERGY.GOV
5. US Department of Energy
6. USDOE
7. DOE
8. USADOE
Awards1
1. DE-SC0008733
Harvard College Research Plan

BibTeX

@article{Pyzer_Knapp_2015, title={Learning from the Harvard Clean Energy Project: The Use of Neural Networks to Accelerate Materials Discovery}, volume={25}, ISSN={1616-3028}, url={http://dx.doi.org/10.1002/adfm.201501919}, DOI={10.1002/adfm.201501919}, number={41}, journal={Advanced Functional Materials}, publisher={Wiley}, author={Pyzer‐Knapp, Edward O. and Li, Kewei and Aspuru‐Guzik, Alan}, year={2015}, month=sep, pages={6495–6502} }

JSON

{
  "indexed": {
    "date-parts": [
      [
        2025,
        8,
        21
      ]
    ],
    "date-time": "2025-08-21T17:39:15Z",
    "timestamp": 1755797955534,
    "version": "3.37.3"
  },
  "reference-count": 52,
  "publisher": "Wiley",
  "issue": "41",
  "license": [
    {
      "start": {
        "date-parts": [
          [
            2015,
            9,
            18
          ]
        ],
        "date-time": "2015-09-18T00:00:00Z",
        "timestamp": 1442534400000
      },
      "content-version": "vor",
      "delay-in-days": 0,
      "URL": "http://onlinelibrary.wiley.com/termsAndConditions#vor"
    }
  ],
  "funder": [
    {
      "DOI": "10.13039/100000015",
      "name": "Department of Energy",
      "doi-asserted-by": "crossref",
      "award": [
        "DE-SC0008733"
      ],
      "id": [
        {
          "id": "10.13039/100000015",
          "id-type": "DOI",
          "asserted-by": "crossref"
        }
      ]
    },
    {
      "name": "Harvard College Research Plan"
    }
  ],
  "content-domain": {
    "domain": [],
    "crossmark-restriction": false
  },
  "published-print": {
    "date-parts": [
      [
        2015,
        11
      ]
    ]
  },
  "abstract": "<jats:p>Here, the employment of multilayer perceptrons, a type of artificial neural network, is proposed as part of a computational funneling procedure for high\u2010throughput organic materials design. Through the use of state of the art algorithms and a large amount of data extracted from the Harvard Clean Energy Project, it is demonstrated that these methods allow a great reduction in the fraction of the screening library that is actually calculated. Neural networks can reproduce the results of quantum\u2010chemical calculations with a large level of accuracy. The proposed approach allows to carry out large\u2010scale molecular screening projects with less computational time. This, in turn, allows for the exploration of increasingly large and diverse libraries.</jats:p>",
  "DOI": "10.1002/adfm.201501919",
  "type": "journal-article",
  "created": {
    "date-parts": [
      [
        2015,
        9,
        18
      ]
    ],
    "date-time": "2015-09-18T12:40:49Z",
    "timestamp": 1442580049000
  },
  "page": "6495-6502",
  "source": "Crossref",
  "is-referenced-by-count": 179,
  "title": "Learning from the Harvard Clean Energy Project: The Use of Neural Networks to Accelerate Materials Discovery",
  "prefix": "10.1002",
  "volume": "25",
  "author": [
    {
      "given": "Edward O.",
      "family": "Pyzer\u2010Knapp",
      "sequence": "first",
      "affiliation": [
        {
          "name": "Department of Chemistry and Chemical Biology  12 Oxford Street Cambridge MA 02138 USA"
        }
      ]
    },
    {
      "given": "Kewei",
      "family": "Li",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Department of Chemistry and Chemical Biology  12 Oxford Street Cambridge MA 02138 USA"
        }
      ]
    },
    {
      "given": "Alan",
      "family": "Aspuru\u2010Guzik",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Department of Chemistry and Chemical Biology  12 Oxford Street Cambridge MA 02138 USA"
        }
      ]
    }
  ],
  "member": "311",
  "published-online": {
    "date-parts": [
      [
        2015,
        9,
        18
      ]
    ]
  },
  "reference": [
    {
      "key": "e_1_2_7_1_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1039/c4sc00095a"
    },
    {
      "key": "e_1_2_7_2_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1038/nature12909"
    },
    {
      "key": "e_1_2_7_3_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1039/C3EE42756K"
    },
    {
      "key": "e_1_2_7_4_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/j.jpowsour.2009.09.024"
    },
    {
      "key": "e_1_2_7_5_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.6026/97320630003014"
    },
    {
      "key": "e_1_2_7_6_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1038/nature03197"
    },
    {
      "key": "e_1_2_7_7_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/jm400870h"
    },
    {
      "key": "e_1_2_7_8_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1039/C4CP00547C"
    },
    {
      "key": "e_1_2_7_9_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ja9061344"
    },
    {
      "key": "e_1_2_7_10_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1002/wcms.1104"
    },
    {
      "key": "e_1_2_7_11_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1146/annurev-matsci-070214-020823"
    },
    {
      "key": "e_1_2_7_12_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci9003865"
    },
    {
      "key": "e_1_2_7_13_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci00068a023"
    },
    {
      "key": "e_1_2_7_14_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.2174/138620708785739899"
    },
    {
      "key": "e_1_2_7_15_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci3003039"
    },
    {
      "key": "e_1_2_7_16_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci0500132"
    },
    {
      "key": "e_1_2_7_17_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci400187y"
    },
    {
      "key": "e_1_2_7_18_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci4005805"
    },
    {
      "key": "e_1_2_7_19_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1088/1367-2630/15/9/095003"
    },
    {
      "key": "e_1_2_7_20_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/acs.jctc.5b00099"
    },
    {
      "key": "e_1_2_7_21_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.2533/chimia.2015.182"
    },
    {
      "volume-title": "Gaussian Processes for Machine Learning",
      "year": "2006",
      "author": "Rasmussen C. E.",
      "key": "e_1_2_7_22_1"
    },
    {
      "key": "e_1_2_7_23_1",
      "unstructured": "E. O.Pyzer\u2010Knapp C.Suh R. P.Adams A.Aspuru\u2010Guzik unpublished."
    },
    {
      "key": "e_1_2_7_24_1",
      "unstructured": "G.Simm E. O.Pyzer\u2010Knapp A.Aspuru\u2010Guzik unpublished."
    },
    {
      "key": "e_1_2_7_25_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1088/0954-898X_6_3_011"
    },
    {
      "key": "e_1_2_7_26_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1037/h0042519"
    },
    {
      "key": "e_1_2_7_27_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/S0003-2670(00)80865-X"
    },
    {
      "key": "e_1_2_7_28_1",
      "first-page": "114",
      "volume-title": "Proc. IEEE\u2010INNS\u2010ENNS Int. Joint Conf. Neural Networks IJCNN 2000",
      "author": "Lawrence S.",
      "year": "2000"
    },
    {
      "key": "e_1_2_7_29_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/S0893-6080(98)00010-0"
    },
    {
      "key": "e_1_2_7_30_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/B978-1-4832-1446-7.50035-2"
    },
    {
      "key": "e_1_2_7_31_1",
      "first-page": "177",
      "volume-title": "Proc. COMPSTAT",
      "author": "Bottou L.",
      "year": "2010"
    },
    {
      "key": "e_1_2_7_32_1",
      "unstructured": "G.Hinton T.Tielman Lecture 6.5 \u2013 rmsprop COURSERA: Neural Networks for Machine Learning."
    },
    {
      "key": "e_1_2_7_33_1",
      "unstructured": "T.Schaul I.Antonoglou D.Silver 2013 arXiv:1406.1231."
    },
    {
      "key": "e_1_2_7_34_1",
      "first-page": "693",
      "volume-title": "Advances in Neural Information Processing Systems 24",
      "author": "Recht B.",
      "year": "2011"
    },
    {
      "key": "e_1_2_7_35_1",
      "first-page": "571",
      "volume-title": "11th USENIX Symp. Oper. Syst. Design Implementation (OSDI 14)",
      "author": "Chilimbi T.",
      "year": "2014"
    },
    {
      "key": "e_1_2_7_36_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1002/adma.200501717"
    },
    {
      "key": "e_1_2_7_37_1",
      "first-page": "440",
      "volume-title": "Advances in Neural Information Processing Systems 25",
      "author": "Montavon G.",
      "year": "2012"
    },
    {
      "key": "e_1_2_7_38_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1103/PhysRevLett.108.058301"
    },
    {
      "journal-title": "RDKit: Open\u2010Source Cheminformatics",
      "author": "Landrum G.",
      "key": "e_1_2_7_39_1"
    },
    {
      "key": "e_1_2_7_40_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci00046a002"
    },
    {
      "key": "e_1_2_7_41_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci010132r"
    },
    {
      "key": "e_1_2_7_42_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci100050t"
    },
    {
      "key": "e_1_2_7_43_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/ci00054a008"
    },
    {
      "key": "e_1_2_7_44_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1177/1087057105281365"
    },
    {
      "key": "e_1_2_7_45_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1080/00268976.2014.952696"
    },
    {
      "key": "e_1_2_7_46_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1103/PhysRevB.33.8822"
    },
    {
      "key": "e_1_2_7_47_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1103/PhysRevA.38.3098"
    },
    {
      "key": "e_1_2_7_48_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1039/b508541a"
    },
    {
      "journal-title": "MAML \u2013 Molecular Applied Machine Learning.",
      "author": "Pyzer\u2010Knapp E. O.",
      "key": "e_1_2_7_49_1"
    },
    {
      "key": "e_1_2_7_50_1",
      "unstructured": "G. E.Dahl N.Jaitly R.Salakhutdinov 2014 arXiv:1406.1231."
    },
    {
      "key": "e_1_2_7_51_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1021/jz200866s"
    },
    {
      "key": "e_1_2_7_52_1",
      "unstructured": "World Community Grid http://www.worldcommunitygrid.org/. (accessed February2015)"
    }
  ],
  "container-title": "Advanced Functional Materials",
  "original-title": [],
  "language": "en",
  "link": [
    {
      "URL": "https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fadfm.201501919",
      "content-type": "application/pdf",
      "content-version": "vor",
      "intended-application": "text-mining"
    },
    {
      "URL": "https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fadfm.201501919",
      "content-type": "unspecified",
      "content-version": "vor",
      "intended-application": "text-mining"
    },
    {
      "URL": "https://onlinelibrary.wiley.com/doi/pdf/10.1002/adfm.201501919",
      "content-type": "unspecified",
      "content-version": "vor",
      "intended-application": "similarity-checking"
    }
  ],
  "deposited": {
    "date-parts": [
      [
        2023,
        10,
        6
      ]
    ],
    "date-time": "2023-10-06T04:03:59Z",
    "timestamp": 1696565039000
  },
  "score": 1,
  "resource": {
    "primary": {
      "URL": "https://onlinelibrary.wiley.com/doi/10.1002/adfm.201501919"
    }
  },
  "subtitle": [],
  "short-title": [],
  "issued": {
    "date-parts": [
      [
        2015,
        9,
        18
      ]
    ]
  },
  "references-count": 52,
  "journal-issue": {
    "issue": "41",
    "published-print": {
      "date-parts": [
        [
          2015,
          11
        ]
      ]
    }
  },
  "alternative-id": [
    "10.1002/adfm.201501919"
  ],
  "URL": "http://dx.doi.org/10.1002/adfm.201501919",
  "relation": {},
  "ISSN": [
    "1616-301X",
    "1616-3028"
  ],
  "subject": [],
  "container-title-short": "Adv Funct Materials",
  "published": {
    "date-parts": [
      [
        2015,
        9,
        18
      ]
    ]
  }
}