High-order neural networks and kernel methods for peptide-MHC binding prediction.

Journal: Bioinformatics (Oxford, England)
PMID: 26206306

Abstract

MOTIVATION: Effective computational methods for peptide-protein binding prediction can greatly help clinical peptide vaccine search and design. However, previous computational methods fail to capture key nonlinear high-order dependencies between different amino acid positions. As a result, they often produce low-quality rankings of strong binding peptides. To solve this problem, we propose nonlinear high-order machine learning methods including high-order neural networks (HONNs) with possible deep extensions and high-order kernel support vector machines to predict major histocompatibility complex-peptide binding.

Authors

  • Pavel P Kuksa
    Institute for Biomedical Informatics, Department of Pathology and Laboratory Medicine, University of Pennsylvania School of Medicine, Philadelphia, PA 19104, USA, Department of Machine Learning, NEC Laboratories America, Princeton, NJ 08540, USA.
  • Martin Renqiang Min
    Department of Machine Learning, NEC Laboratories America, Princeton, NJ 08540, USA.
  • Rishabh Dugar
    Department of Machine Learning, NEC Laboratories America, Princeton, NJ 08540, USA.
  • Mark Gerstein
    Program of Computational Biology and Bioinformatics and Department of Molecular Biophysics and Biochemistry and Department of Computer Science, Yale University, New Haven, CT 06511, USA.

Keywords

External Resources

Popular Topics
Recent Journals