Bioinformatics Advance Access originally published online on November 17, 2008
Bioinformatics 2009 25(2):243-250; doi:10.1093/bioinformatics/btn602
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Training set expansion: an approach to improving the reconstruction of biological networks from limited and uneven reliable interactions
1Department of Computer Science, Yale University, 51 Prospect Street, New Haven, CT 06511, 2Program in Computational Biology and Bioinformatics, Yale University and 3Department of Molecular Biophysics and Biochemistry, Yale University, 266 Whitney Avenue, New Haven, CT 06520, USA
*To whom correspondence should be addressed.
 |
Abstract |
|---|
Motivation: An important problem in systems biology is reconstructing complete networks of interactions between biological objects by extrapolating from a few known interactions as examples. While there are many computational techniques proposed for this network reconstruction task, their accuracy is consistently limited by the small number of high-confidence examples, and the uneven distribution of these examples across the potential interaction space, with some objects having many known interactions and others few.
Results: To address this issue, we propose two computational methods based on the concept of training set expansion. They work particularly effectively in conjunction with kernel approaches, which are a popular class of approaches for fusing together many disparate types of features. Both our methods are based on semi-supervised learning and involve augmenting the limited number of gold-standard training instances with carefully chosen and highly confident auxiliary examples. The first method, prediction propagation, propagates highly confident predictions of one local model to another as the auxiliary examples, thus learning from information-rich regions of the training network to help predict the information-poor regions. The second method, kernel initialization, takes the most similar and most dissimilar objects of each object in a global kernel as the auxiliary examples. Using several sets of experimentally verified protein–protein interactions from yeast, we show that training set expansion gives a measurable performance gain over a number of representative, state-of-the-art network reconstruction methods, and it can correctly identify some interactions that are ranked low by other methods due to the lack of training examples of the involved proteins.
Contact: mark.gerstein{at}yale.edu
Availability: The datasets and additional materials can be found at http://networks.gersteinlab.org/tse.
Associate Editor: Olga Troyanskaya
Received on August 17, 2008; revised on October 15, 2008; accepted on November 13, 2008
CiteULike 
Connotea 
Del.icio.us What's this?