Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Spherical convolutions on molecular graphs for protein model quality assessment

Ilia Igashov 1, 2 Nikita Pavlichenko 1 Sergei Grudinin 2
2 NANO-D - Algorithms for Modeling and Simulation of Nanosystems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : Processing information on 3D objects requires methods stable to rigid-body transformations, in particular rotations, of the input data. In image processing tasks, convolutional neural networks achieve this property using rotation-equivariant operations. However, contrary to images, graphs generally have irregular topology. This makes it challenging to define a rotation-equivariant convolution operation on these structures. In this work, we propose Spherical Graph Convolutional Network (S-GCN) that processes 3D models of proteins represented as molecular graphs. In a protein molecule, individual amino acids have common topological elements. This allows us to unambiguously associate each amino acid with a local coordinate system and construct rotation-equivariant spherical filters that operate on angular information between graph nodes. Within the framework of the protein model quality assessment problem, we demonstrate that the proposed spherical convolution method significantly improves the quality of model assessment compared to the standard message-passing approach. It is also comparable to state-of-the-art methods, as we demonstrate on Critical Assessment of Structure Prediction (CASP) benchmarks. The proposed technique operates only on geometric features of protein 3D models. This makes it universal and applicable to any other geometric-learning task where the graph structure allows constructing local coordinate systems.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.inria.fr/hal-03006448
Contributor : Sergei Grudinin <>
Submitted on : Monday, November 16, 2020 - 3:09:52 PM
Last modification on : Friday, November 27, 2020 - 9:32:27 AM

Licence


Distributed under a Creative Commons Attribution - NonCommercial 4.0 International License

Identifiers

  • HAL Id : hal-03006448, version 1
  • ARXIV : 2011.07980

Collections

Citation

Ilia Igashov, Nikita Pavlichenko, Sergei Grudinin. Spherical convolutions on molecular graphs for protein model quality assessment. 2020. ⟨hal-03006448⟩

Share

Metrics

Record views

53

Files downloads

37