Jump to main content
Jump to site search


A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification

Author affiliations

Abstract

Deep neural networks have been increasingly used in various chemical fields. In the nature of a data-driven approach, their performance strongly depends on data used in training. Therefore, models developed in data-deficient situations can cause highly uncertain predictions, leading to vulnerable decision making. Here, we show that Bayesian inference enables more reliable prediction with quantitative uncertainty analysis. Decomposition of the predictive uncertainty into model- and data-driven uncertainties allows us to elucidate the source of errors for further improvements. For molecular applications, we devised a Bayesian graph convolutional network (GCN) and evaluated its performance for molecular property predictions. Our study on the classification problem of bio-activity and toxicity shows that the confidence of prediction can be quantified in terms of the predictive uncertainty, leading to more accurate virtual screening of drug candidates than standard GCNs. The result of log P prediction illustrates that data noise affects the data-driven uncertainty more significantly than the model-driven one. Based on this finding, we could identify artefacts that arose from quantum mechanical calculations in the Harvard Clean Energy Project dataset. Consequently, the Bayesian GCN is critical for molecular applications under data-deficient conditions.

Graphical abstract: A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification

Back to tab navigation

Supplementary files

Publication details

The article was received on 22 Apr 2019, accepted on 21 Jul 2019 and first published on 22 Jul 2019


Article type: Edge Article
DOI: 10.1039/C9SC01992H
Chem. Sci., 2019, Advance Article
  • Open access: Creative Commons BY-NC license
    All publication charges for this article have been paid for by the Royal Society of Chemistry

  •   Request permissions

    A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification

    S. Ryu, Y. Kwon and W. Y. Kim, Chem. Sci., 2019, Advance Article , DOI: 10.1039/C9SC01992H

    This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence. Material from this article can be used in other publications provided that the correct acknowledgement is given with the reproduced material and it is not used for commercial purposes.

    Reproduced material should be attributed as follows:

    • For reproduction of material from NJC:
      [Original citation] - Published by The Royal Society of Chemistry (RSC) on behalf of the Centre National de la Recherche Scientifique (CNRS) and the RSC.
    • For reproduction of material from PCCP:
      [Original citation] - Published by the PCCP Owner Societies.
    • For reproduction of material from PPS:
      [Original citation] - Published by The Royal Society of Chemistry (RSC) on behalf of the European Society for Photobiology, the European Photochemistry Association, and RSC.
    • For reproduction of material from all other RSC journals:
      [Original citation] - Published by The Royal Society of Chemistry.

    Information about reproducing material from RSC articles with different licences is available on our Permission Requests page.

Search articles by author

Spotlight

Advertisements