Capsule Networks for Protein Structure Classification and Prediction
Machine Learning
2018-09-18 v1 Quantitative Methods
Machine Learning
Abstract
Capsule Networks have great potential to tackle problems in structural biology because of their attention to hierarchical relationships. This paper describes the implementation and application of a Capsule Network architecture to the classification of RAS protein family structures on GPU-based computational resources. 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. Our results show an accuracy improvement compared to traditional convolutional networks, while improving interpretability through visualization of activation vectors.
Cite
@article{arxiv.1808.07475,
title = {Capsule Networks for Protein Structure Classification and Prediction},
author = {Dan Rosa de Jesus and Julian Cuevas and Wilson Rivera and Silvia Crivelli},
journal= {arXiv preprint arXiv:1808.07475},
year = {2018}
}