loading
Documents

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Markus Heinonen ; Niko Välimäki ; Veli Mäkinen and Juho Rousu

Affiliation: University of Helsinki, Finland

ISBN: 978-989-8425-90-4

Keyword(s): Graph kernels, Compressed data structures, XBW transform, Reaction graph, Hierarchical classification.

Related Ontology Subjects/Areas/Topics: Algorithms and Software Tools ; Bioinformatics ; Biomedical Engineering ; Data Mining and Machine Learning ; Pattern Recognition, Clustering and Classification ; Systems Biology

Abstract: Kernels for structured data are rapidly becoming an essential part of the machine learning toolbox. Graph kernels provide similarity measures for complex relational objects, such as molecules and enzymes. Graph kernels based on walks are popular due their fast computation but their predictive performance is often not satisfactory, while kernels based on subgraphs suffer from high computational cost and are limited to small substructures. Kernels based on paths offer a promising middle ground between these two extremes. However, the computation of path kernels has so far been assumed computationally too challenging. In this paper we introduce an effective method for computing path based kernels; we employ a Burrows-Wheeler transform based compressed path index for fast and space-efficient enumeration of paths. Unlike many kernel algorithms the index representation retains fast access to individual features. In our experiments with chemical reaction graphs, path based kernels surpass st ate-of-the-art graph kernels in prediction accuracy. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.80.4.76

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Heinonen, M.; Välimäki, N.; Mäkinen, V. and Rousu, J. (2012). EFFICIENT PATH KERNELS FOR REACTION FUNCTION PREDICTION.In Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms - Volume 1: BIOINFORMATICS, (BIOSTEC 2012) ISBN 978-989-8425-90-4, pages 202-207. DOI: 10.5220/0003779402020207

@conference{bioinformatics12,
author={Markus Heinonen. and Niko Välimäki. and Veli Mäkinen. and Juho Rousu.},
title={EFFICIENT PATH KERNELS FOR REACTION FUNCTION PREDICTION},
booktitle={Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms - Volume 1: BIOINFORMATICS, (BIOSTEC 2012)},
year={2012},
pages={202-207},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003779402020207},
isbn={978-989-8425-90-4},
}

TY - CONF

JO - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms - Volume 1: BIOINFORMATICS, (BIOSTEC 2012)
TI - EFFICIENT PATH KERNELS FOR REACTION FUNCTION PREDICTION
SN - 978-989-8425-90-4
AU - Heinonen, M.
AU - Välimäki, N.
AU - Mäkinen, V.
AU - Rousu, J.
PY - 2012
SP - 202
EP - 207
DO - 10.5220/0003779402020207

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.