An introduction to support Vector Machines: and other kernel-based learning methods
An introduction to support Vector Machines: and other kernel-based learning methods
Introduction to Algorithms: A Creative Approach
Introduction to Algorithms: A Creative Approach
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
Algorithms for estimating relative importance in networks
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Shortest-Path Kernels on Graphs
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Bioinformatics
Protein function prediction based on patterns in biological networks
RECOMB'08 Proceedings of the 12th annual international conference on Research in computational molecular biology
Automatic parameter learning for multiple network alignment
RECOMB'08 Proceedings of the 12th annual international conference on Research in computational molecular biology
Fast and accurate alignment of multiple protein networks
RECOMB'08 Proceedings of the 12th annual international conference on Research in computational molecular biology
Concurrency by modularity: design patterns, a case in point
Proceedings of the ACM international conference on Object oriented programming systems languages and applications
| Hi-index | 0.00 |
Comparative analysis of biomolecular networks constructed using measurements from different conditions, tissues, and organisms offer a powerful approach to understanding the structure, function, dynamics, and evolution of complex biological systems. We explore a class of algorithms for aligning large biomolecular networks by breaking down such networks into subgraphs and computing the alignment of the networks based on the alignment of their subgraphs. The resulting subnetworks are compared using graph kernels as scoring functions. We provide implementations of the resulting algorithms as part of BiNA, an open source biomolecular network alignment toolkit. Our experiments using Drosophila melanogaster, Saccharomyces cerevisiae, Mus musculus and Homo sapiens protein-protein interaction networks extracted from the DIP repository of protein-protein interaction data demonstrate that the performance of the proposed algorithms (as measured by % GO term enrichment of subnetworks identified by the alignment) is competitive with some of the state-of-the-art algorithms for pair-wise alignment of large protein-protein interaction networks. Our results also show that the inter-species similarity scores computed based on graph kernels can be used to cluster the species into a species tree that is consistent with the known phylogenetic relationships among the species.