Short communication: Specificity rule discovery in HIV-1 protease cleavage site analysis

Authors:
Hyeoncheol Kim;Yiying Zhang;Yong-Seok Heo;Heung-Bum Oh;Su-Shing Chen
Affiliations:
Department of Computer Science Education, Korea University, Seoul 136-701, Republic of Korea;Computer & Info. Sciences and Engineering, University of Florida, Gainesville, FL 32611, USA;Department of Chemistry, Konkuk University, Seoul 143-701, Republic of Korea;Department of Laboratory Medicine, Asan Medical Center and University of Ulsan, Seoul, Republic of Korea;Computer & Info. Sciences and Engineering, University of Florida, Gainesville, FL 32611, USA
Venue:
Computational Biology and Chemistry
Year:
2008

Citing 9
Cited 3

A penalty-function approach for pruning feedforward neural networks

Neural Computation
Artificial neural network model for predicting HIV protease cleavage sites in protein

Advances in Engineering Software
Symbolic Interpretation of Artificial Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Feature selection for high-dimensional genomic microarray data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Computationally Efficient Heuristics for If-Then Rule Extraction from Freed-Forward Neural Networks

DS '00 Proceedings of the Third International Conference on Discovery Science
Data Mining: Concepts and Techniques

Data Mining: Concepts and Techniques
Bio-support vector machines for computational proteomics

Bioinformatics
Why neural networks should not be used for HIV-1 protease cleavage site prediction

Bioinformatics
Mining HIV protease cleavage data using genetic programming with a sum-product function

Bioinformatics

On Utilizing Optimal and Information Theoretic Syntactic Modeling for Peptide Classification

PRIB '09 Proceedings of the 4th IAPR International Conference on Pattern Recognition in Bioinformatics
An MLP-based feature subset selection for HIV-1 protease cleavage site analysis

Artificial Intelligence in Medicine
Peptide classification using optimal and information theoretic syntactic modeling

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Several machine learning algorithms have recently been applied to modeling the specificity of HIV-1 protease. The problem is challenging because of the three issues as follows: (1) datasets with high dimensionality and small number of samples could misguide classification modeling and its interpretation; (2) symbolic interpretation is desirable because it provides us insight to the specificity in the form of human-understandable rules, and thus helps us to design effective HIV inhibitors; (3) the interpretation should take into account complexity or dependency between positions in sequences. Therefore, it is neccessary to investigate multivariate and feature-selective methods to model the specificity and to extract rules from the model. We have tested extensively various machine learning methods, and we have found that the combination of neural networks and decompositional approach can generate a set of effective rules. By validation to experimental results for the HIV-1 protease, the specificity rules outperform the ones generated by frequency-based, univariate or black-box methods.