Skip to main content
SpringerLink
Log in

BIONIC: discovering new biology through deep learning-based network integration

  • Research Briefing
  • Published:

From Nature Methods

View current issue Submit your manuscript

BIONIC (Biological Network Integration using Convolutions) is a scalable deep learning network integration approach that learns and combines diverse data representations across a range of biological network types to consolidate knowledge of gene function. BIONIC outperforms existing integration approaches by capturing biological information more comprehensively and with greater accuracy than previously possible.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1: BIONIC: Biological Network Integration using Convolutions.

References

  1. Mitra, K. et al. Integrative approaches for finding modular structure in biological networks. Nat. Rev. Genet. 14, 719–732 (2013). This review article outlines the importance of biological network integration.

    Article  CAS  Google Scholar 

  2. Fraser, A. G. & Marcotte, E. M. A probabilistic view of gene function. Nat. Genet. 36, 559 (2004). This perspectives article outlines the utility of biological networks.

    Article  CAS  Google Scholar 

  3. Costanzo, M. et al. A global genetic interaction network maps a wiring diagram of cellular function. Science 353, aaf1420 (2016). This paper describes the global yeast genetic interaction network, which served as an input network for BIONIC.

    Article  Google Scholar 

  4. Veličković, P. et al. Graph attention networks. Preprint at arXiv https://doi.org/10.48550/arXiv.1710.10903 (2017). This paper describes the graph attention network used in BIONIC.

  5. Piotrowski, J. S. et al. Functional annotation of chemical libraries across diverse biological processes. Nat. Chem. Biol. 13, 982–993 (2017). This paper describes a high-throughput chemical–genetic screening approach and data that were used by BIONIC to generate chemical–genetic interaction predictions.

    Article  CAS  Google Scholar 

Download references

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This is a summary of: Forster, D. T. et al. BIONIC: biological network integration using convolutions. Nat. Methods https://doi.org/10.1038/s41592-022-01616-x (2022).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

BIONIC: discovering new biology through deep learning-based network integration. Nat Methods 19, 1185–1186 (2022). https://doi.org/10.1038/s41592-022-01617-w

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41592-022-01617-w

  • Springer Nature America, Inc.

Search

Navigation