Please use this identifier to cite or link to this item: https://doi.org/10.1109/BIBE.2007.4375747
Title: An HV-SVM classifier to infer TF-TF interactions using protein domains and GO annotations
Authors: Li, X.-L.
Veeravalli, B. 
Lee, J.-X.
Ng, S.-K.
Keywords: GO annotations
Protein domains
Support vector machine
Transcription factor
Issue Date: 2007
Source: Li, X.-L.,Veeravalli, B.,Lee, J.-X.,Ng, S.-K. (2007). An HV-SVM classifier to infer TF-TF interactions using protein domains and GO annotations. Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE : 1360-1364. ScholarBank@NUS Repository. https://doi.org/10.1109/BIBE.2007.4375747
Abstract: Interactions between transcription factors (TFs) are necessary for deciphering the complex mechanisms of transcription regulation in eukaryotes. In this paper, we proposed a novel HV-kernel based Support Vector Machine classifier (HV-SVM) to predict TF-TF interactions based on their protein domain information and GO annotations. Specifically, two types of pairwise kernels, namely, a horizontal kernel and a vertical kernel, were combined to evaluate the similarity between a pair of TFs, and a Genetic algorithm was used to obtain kernel and feature weights to optimize the classifier's performance. We applied our proposed HV-SVM method to predict TF interactions for Homo sapiens and Mus muculus. We obtained accuracy and F-measures of over 85% and an AUC of almost 93%, demonstrating that HV-SVM can accurately predict TF-TF interactions even in the higher and more complex eukaryotes. ©2007 IEEE.
Source Title: Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE
URI: http://scholarbank.nus.edu.sg/handle/10635/69319
ISBN: 1424415098
DOI: 10.1109/BIBE.2007.4375747
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

12
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.