Handling missing features with boosting algorithms for protein-protein interaction prediction

Authors:
Fabrizio Smeraldi;Michael Defoin-Platel;Mansoor Saqi
Affiliations:
School of Electronic Engineering and Computer Science, Queen Mary University of London, London;Biomathematics and Bioinformatics, Rothamsted Research, Harpenden;Biomathematics and Bioinformatics, Rothamsted Research, Harpenden
Venue:
DILS'10 Proceedings of the 7th international conference on Data integration in the life sciences
Year:
2010

Citing 8
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
A decision-theoretic generalization of on-line learning and an application to boosting

Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Improved Boosting Algorithms Using Confidence-rated Predictions

Machine Learning - The Eleventh Annual Conference on computational Learning Theory
An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants

Machine Learning
Kernel methods for predicting protein--protein interactions

Bioinformatics
Handling missing values in support vector machine classifiers

Neural Networks - 2005 Special issue: IJCNN 2005
Efficient Margin Maximizing with Boosting

The Journal of Machine Learning Research
Data Analysis and Visualization in Genomics and Proteomics

Data Analysis and Visualization in Genomics and Proteomics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Combining information from multiple heterogeneous data sources can aid prediction of protein-protein interaction. This information can be arranged into a feature vector for classification. However, missing values in the data can impact on the prediction accuracy. Boosting has emerged as a powerful tool for feature selection and classification. Bayesian methods have traditionally been used to cope with missing data, with boosting being applied to the output of Bayesian classifiers. We explore a variation of Adaboost that deals with the missing values at the level of the boosting algorithm itself, without the need for any density estimation step. Experiments on a publicly available PPI dataset suggest this overall simpler and mathematically coherent approach may be more accurate.