A Transfer Learning Approach and Selective Integration of Multiple Types of Assays for Biological Network Inference
Authors:
- 5 February 2013
- book chapter
- Published by IGI Global Scientific Publishing
- p. 188-202
Abstract
The authors’ algorithm was favorably examined on two kinds of biological networks: a metabolic network and a protein interaction network. A statistical test confirmed that the weight that our algorithm assigned to each assay was meaningful.Keywords
This publication has 19 references indexed in Scilit:
- Supervised reconstruction of biological networks with local modelsBioinformatics, 2007
- Scale-Free Networks2007
- Exploiting indirect neighbours and topological weight to predict protein function from protein–protein interactionsBioinformatics, 2006
- Kernel methods for predicting protein-protein interactionsBioinformatics, 2005
- Evidence for dynamically organized modularity in the yeast protein–protein interaction networkNature, 2004
- Convex Optimization2004
- Multiple kernel learning, conic duality, and the SMO algorithm2004
- The Gene Ontology (GO) database and informatics resourceNucleic Acids Research, 2004
- Basic local alignment search toolJournal of Molecular Biology, 1990
- An improved algorithm for matching biological sequencesJournal of Molecular Biology, 1982