Capsule Networks for Protein Structure Classification

Authors: Dan A. Rosa de Jesus (Lawrence Berkeley National Laboratory, University of Puerto Rico at Mayaguez), Julian Cuevas Paniagua (Lawrence Berkeley National Laboratory, University of Puerto Rico at Mayaguez), Wilson Rivera (Lawrence Berkeley National Laboratory, University of Puerto Rico at Mayaguez), Silvia Crivelli (Lawrence Berkeley National Laboratory)

Abstract: Capsule Networks have great potential to tackle problems in structural biology because of their attention to hierarchical relationships. This work describes the implementation and application of a capsule network architecture to the classification of RAS protein family structures on GPU-based computational resources. Our results show that the proposed capsule network trained on 2D and 3D structural encodings can successfully classify HRAS and KRAS structures. The capsule network can also classify a protein-based dataset derived from a PSI-BLAST search on sequences of KRAS and HRAS mutations. Experimental results show an accuracy improvement compared to traditional convolutional networks.

Best Poster Finalist (BP): no

Poster: pdf
Poster summary: PDF
Reproducibility Description Appendix: PDF


Back to Poster Archive Listing