Novel machine learning methods for MHC Class I binding prediction

Authors:
Christian Widmer;Nora C. Toussaint;Yasemin Altun;Oliver Kohlbacher;Gunnar Rätsch
Affiliations:
Friedrich Miescher Laboratory, Max Planck Society, Tübingen, Germany;Center for Bioinformatics Tübingen, Eberhard-Karls-Universität, Tübingen, Germany;Max Planck Institute for Biological Cybernetics, Tübingen, Germany;Center for Bioinformatics Tübingen, Eberhard-Karls-Universität, Tübingen, Germany;Friedrich Miescher Laboratory, Max Planck Society, Tübingen, Germany
Venue:
PRIB'10 Proceedings of the 5th IAPR international conference on Pattern recognition in bioinformatics
Year:
2010

Citing 8
Cited 0

Advances in kernel methods: support vector learning

Advances in kernel methods: support vector learning
Regularized multi--task learning

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Profile-Based String Kernels for Remote Homology Detection and Motif Extraction

CSB '04 Proceedings of the 2004 IEEE Computational Systems Bioinformatics Conference
New Support Vector Algorithms

Neural Computation
Large Scale Multiple Kernel Learning

The Journal of Machine Learning Research
POPI

Bioinformatics
Efficient peptide–MHC-I binding prediction for alleles with few known binders

Bioinformatics
Multiple Instance Learning Allows MHC Class II Epitope Predictions Across Alleles

WABI '08 Proceedings of the 8th international workshop on Algorithms in Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

MHC class I molecules are key players in the human immune system. They bind small peptides derived from intracellular proteins and present them on the cell surface for surveillance by the immune system. Prediction of such MHC class I binding peptides is a vital step in the design of peptide-based vaccines and therefore one of the major problems in computational immunology. Thousands of different types of MHC class I molecules exist, each displaying a distinct binding specificity. The lack of sufficient training data for the majority of these molecules hinders the application of Machine Learning to this problem. We propose two approaches to improve the predictive power of kernel-based Machine Learning methods for MHC class I binding prediction: First, a modification of the Weighted Degree string kernel that allows for the incorporation of amino acid properties. Second, we propose an enhanced Multitask kernel and an optimization procedure to fine-tune the kernel parameters. The combination of both approaches yields improved performance, which we demonstrate on the IEDB benchmark data set.