TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions

PLoS Comput Biol. 2017 Jul 27;13(7):e1005690. doi: 10.1371/journal.pcbi.1005690. eCollection 2017 Jul.

Abstract

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes.

Availability: weilab.math.msu.edu/TDL/.

MeSH terms

  • Computational Biology / methods*
  • Image Processing, Computer-Assisted
  • Machine Learning
  • Membrane Proteins / chemistry
  • Membrane Proteins / metabolism
  • Membrane Proteins / physiology
  • Models, Statistical
  • Molecular Dynamics Simulation
  • Neural Networks, Computer*
  • Protein Binding
  • Protein Folding

Substances

  • Membrane Proteins

Grants and funding

Funds are received from National Science Foundation IIS-1302285 (https://www.nsf.gov/div/index.jsp?div=IIS) to GW, National Science Foundation DMS-1721024 (https://www.nsf.gov/div/index.jsp?div=DMS) to GW, and Michigan State University (https://vprgs.msu.edu/) to GW. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.