2020

Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules

Gasteiger, Johannes, Giri, Shankari, Margraf, Johannes T. et al.

Understand

Many important tasks in chemistry revolve around molecules during reactions.

  • This requires predictions far from the equilibrium, while most recent work in machine learning for molecules has been focused on equilibrium or near-equilibrium states.
  • In this paper we aim to extend this scope in three ways.
  • First, we propose the DimeNet++ model, which is 8x faster and 10% more accurate than the original DimeNet on the QM9 benchmark of equilibrium molecules.

Built on

  • Neural network ensembles

    L.K. Hansen and P. Salamon · 1990

    Earlier work this paper cites.

  • Estimating the mean and variance of the target probability distribution

    D.A. Nix and A.S. Weigend · 1994

    Earlier work this paper cites.

  • Comment on “generalized gradient approximation made simple”

    Yingkai Zhang and Weitao Yang · 1998

    Earlier work this paper cites.

  • Quantum chemistry structures and properties of 134 kilo molecules

    Raghunathan Ramakrishnan, Pavlo O. Dral, Matthias Rupp, and O. Anatole von Lilienfeld · 2014

    Earlier work this paper cites.

  • A Practicable Real-Space Measure and Visualization of Static Electron-Correlation Effects

    Stefan Grimme and Andreas Hansen · 2015

    Earlier work this paper cites.

  • Machine learning of accurate energy-conserving molecular force fields

    Stefan Chmiela, Alexandre Tkatchenko, Huziel E. Sauceda, Igor Poltavsky, Kristof T. Schütt, and Klaus-Robert Müller · 2017

    Earlier work this paper cites.

Similar

  • SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

    Kristof Schütt, Pieter-Jan Kindermans, Huziel Enoc Sauceda Felix, Stefan Chmiela, Alexandre Tkatchenko, and Klaus-Robert Müller · 2017

    Cited alongside, same era.

  • ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost

    J.S. Smith, O. Isayev, and A.E. Roitberg · 2017

    Cited alongside, same era.

  • GFN2-xTB—An Accurate and Broadly Parametrized Self-Consistent Tight-Binding Quantum Chemical Method with Multipole Electrostatics and Density-Dependent Dispersion Contributions

    Christoph Bannwarth, Sebastian Ehlert, and Stefan Grimme · 2019

    Cited alongside, same era.

  • Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective

    Chengqiang Lu, Qi Liu, Chao Wang, Zhenya Huang, Peize Lin, and Lixin He · 2019

    Cited alongside, same era.

  • Fast and Accurate Uncertainty Estimation in Chemical Machine Learning

    Félix Musil, Michael J. Willatt, Mikhail A. Langovoy, and Michele Ceriotti · 2019

    Cited alongside, same era.

Then

  • Directional Message Passing for Molecular Graphs

    Johannes Gasteiger, Janek Groß, and Stephan Günnemann · 2020

    Closest in time.

  • Uncertainty Quantification Using Neural Networks for Molecular Property Prediction

    Lior Hirschfeld, Kyle Swanson, Kevin Yang, Regina Barzilay, and Connor W. Coley · 2020

    Closest in time.

  • QM7-X: A comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules

    Johannes Hoja, Leonardo Medrano Sandonas, Brian G. Ernst, Alvaro Vazquez-Mayagoitia, Robert A. DiStasio Jr., and Alexandre Tkatchenko · 2020

    Closest in time.

  • Transferable Multi-level Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multi-task Learning

    Ziteng Liu, Liqiang Lin, Qingqing Jia, Zheng Cheng, Yanyan Jiang, Yanwen Guo, and Jing Ma · 2020

    Closest in time.

  • OrbNet: Deep learning for quantum chemistry using symmetry-adapted atomic-orbital features

    Zhuoran Qiao, Matthew Welborn, Animashree Anandkumar, Frederick R. Manby, and Thomas F. Miller · 2020

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…