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

被引:167
作者
Pyzer-Knapp, Edward O. [1 ]
Li, Kewei [1 ]
Aspuru-Guzik, Alan [1 ]
机构
[1] Dept Chem & Chem Biol, Cambridge, MA 02138 USA
基金
美国国家科学基金会;
关键词
ORGANIC PHOTOVOLTAICS; AQUEOUS SOLUBILITY; QUANTUM-CHEMISTRY; PREDICTION; DESIGN; APPROXIMATION;
D O I
10.1002/adfm.201501919
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
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.
引用
收藏
页码:6495 / 6502
页数:8
相关论文
共 51 条
  • [1] Ranking Chemical Structures for Drug Discovery: A New Machine Learning Approach
    Agarwal, Shivani
    Dugar, Deepak
    Sengupta, Shiladitya
    [J]. JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2010, 50 (05) : 716 - 731
  • [2] DENSITY-FUNCTIONAL EXCHANGE-ENERGY APPROXIMATION WITH CORRECT ASYMPTOTIC-BEHAVIOR
    BECKE, AD
    [J]. PHYSICAL REVIEW A, 1988, 38 (06): : 3098 - 3100
  • [3] Large-Scale Machine Learning with Stochastic Gradient Descent
    Bottou, Leon
    [J]. COMPSTAT'2010: 19TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL STATISTICS, 2010, : 177 - 186
  • [4] ATOM PAIRS AS MOLECULAR-FEATURES IN STRUCTURE ACTIVITY STUDIES - DEFINITION AND APPLICATIONS
    CARHART, RE
    SMITH, DH
    VENKATARAGHAVAN, R
    [J]. JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1985, 25 (02): : 64 - 73
  • [5] Chilimbi Trishul M, 2014, P OSDI, V14, P571, DOI DOI 10.1108/01439911111122716
  • [6] Dahl George E, 2014, arXiv
  • [7] Reoptimization of MDL keys for use in drug discovery
    Durant, JL
    Leland, BA
    Henry, DR
    Nourse, JG
    [J]. JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2002, 42 (06): : 1273 - 1280
  • [8] BUILDING AND REFINING A KNOWLEDGE BASE FOR SYNTHETIC ORGANIC-CHEMISTRY VIA THE METHODOLOGY OF INDUCTIVE AND DEDUCTIVE MACHINE LEARNING
    GELERNTER, H
    ROSE, JR
    CHEN, CH
    [J]. JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1990, 30 (04): : 492 - 504
  • [9] Lead candidates for high-performance organic photovoltaics from high-throughput quantum chemistry - the Harvard Clean Energy Project
    Hachmann, Johannes
    Olivares-Amaya, Roberto
    Jinich, Adrian
    Appleton, Anthony L.
    Blood-Forsythe, Martin A.
    Seress, Laszlo R.
    Roman-Salgado, Carolina
    Trepte, Kai
    Atahan-Evrenk, Sule
    Er, Sueleyman
    Shrestha, Supriya
    Mondal, Rajib
    Sokolov, Anatoliy
    Bao, Zhenan
    Aspuru-Guzik, Alan
    [J]. ENERGY & ENVIRONMENTAL SCIENCE, 2014, 7 (02) : 698 - 704
  • [10] The Harvard Clean Energy Project: Large-Scale Computational Screening and Design of Organic Photovoltaics on the World Community Grid
    Hachmann, Johannes
    Olivares-Amaya, Roberto
    Atahan-Evrenk, Sule
    Amador-Bedolla, Carlos
    Sanchez-Carrera, Roel S.
    Gold-Parker, Aryeh
    Vogt, Leslie
    Brockway, Anna M.
    Aspuru-Guzik, Alan
    [J]. JOURNAL OF PHYSICAL CHEMISTRY LETTERS, 2011, 2 (17): : 2241 - 2251