1868-1751/asset/2022_left.gif?v=1&s=55861aec609bfeb0bc3c0534a51214d53d9fdc7d)
1868-1751/asset/olbannerright.gif?v=1&s=ecd199dedfd0b2cddec070f1d2c6b8962951f728)
Methods Corner
Graph Kernels for Molecular Similarity
Article first published online: 20 APR 2010
DOI: 10.1002/minf.200900080
Copyright © 2010 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim
Additional Information
How to Cite
Rupp, M. and Schneider, G. (2010), Graph Kernels for Molecular Similarity. Molecular Informatics, 29: 266–273. doi: 10.1002/minf.200900080
Publication History
- Issue published online: 23 APR 2010
- Article first published online: 20 APR 2010
- Manuscript Accepted: 8 FEB 2010
- Manuscript Received: 10 DEC 2009
Keywords:
- Graph kernels;
- Molecular similarity;
- Machine learning;
- Structure graph
Graphical Abstract
Abstract
Molecular similarity measures are important for many cheminformatics applications like ligand-based virtual screening and quantitative structure-property relationships. Graph kernels are formal similarity measures defined directly on graphs, such as the (annotated) molecular structure graph. Graph kernels are positive semi-definite functions, i.e., they correspond to inner products. This property makes them suitable for use with kernel-based machine learning algorithms such as support vector machines and Gaussian processes. We review the major types of kernels between graphs (based on random walks, subgraphs, and optimal assignments, respectively), and discuss their advantages, limitations, and successful applications in cheminformatics.