Volumetric macromolecule identification in cryo-electron tomograms using capsule networks.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: Despite recent advances in cellular cryo-electron tomography (CET), developing automated tools for macromolecule identification in submolecular resolution remains challenging due to the lack of annotated data and high structural complexities. To date, the extent of the deep learning methods constructed for this problem is limited to conventional Convolutional Neural Networks (CNNs). Identifying macromolecules of different types and sizes is a tedious and time-consuming task. In this paper, we employ a capsule-based architecture to automate the task of macromolecule identification, that we refer to as 3D-UCaps. In particular, the architecture is composed of three components: feature extractor, capsule encoder, and CNN decoder. The feature extractor converts voxel intensities of input sub-tomograms to activities of local features. The encoder is a 3D Capsule Network (CapsNet) that takes local features to generate a low-dimensional representation of the input. Then, a 3D CNN decoder reconstructs the sub-tomograms from the given representation by upsampling.

Authors

  • Noushin Hajarolasvadi
    Department of Visual and Data-Centric Computing, Zuse Institute Berlin, Takustraße 7, 14195, Berlin, Germany. hajarolasvadi@zib.de.
  • Vikram Sunkara
    Department of Visual and Data-Centric Computing, Zuse Institute Berlin, Takustraße 7, 14195, Berlin, Germany.
  • Sagar Khavnekar
    Department of CryoEM Technology, Max Planck Institute of Biochemistry, Am Klopferspitz 18, 82152, Martinsried, Germany.
  • Florian Beck
    Department of CryoEM Technology, Max Planck Institute of Biochemistry, Am Klopferspitz 18, 82152, Martinsried, Germany.
  • Robert Brandt
    Materials and Structural Analysis, Thermo Fisher Scientific, Takustraße 7, 14195, Berlin, Germany.
  • Daniel Baum
    Department of Visual and Data-Centric Computing, Zuse Institute Berlin, Takustraße 7, 14195, Berlin, Germany.