On the design of optimization algorithms for prediction of molecular interactions

Darby Tien Hao Chang, Jung Hsin Lin, Chih Hung Hsieh, Yen Jen Oyang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This article presents a comprehensive study on the main characteristics of a novel optimization algorithm specifically designed for simulation of protein-ligand interactions. Though design of optimization algorithms has been a research issue extensively studied by computer scientists for decades, the emerging applications in bioinformatics such as simulation of protein-ligand interactions and protein folding introduce additional challenges due to (1) the high dimensionality nature of the problem and (2) the highly rugged landscape of the energy function. As a result, optimization algorithms that are not carefully designed to tackle these two challenges may fail to deliver satisfactory performance. This study has been motivated by the observation that the RAME (Rank-based Adaptive Mutation Evolutionary) optimization algorithm specifically designed for simulation of protein-ligand docking has consistently outperformed the conventional optimization algorithms by a significant degree. Accordingly, it is of interest to conduct a comprehensive investigation on the characteristics of the proposed algorithm and to learn how it will perform in the more general cases. The experimental results reveal that the RAME algorithm proposed in this article is capable of delivering superior performance to several alternative versions of the genetic algorithm in handling highly-rugged functions in the high-dimensional vector space. This article also reports experiments conducted to analyze the causes of the observed performance difference. The experiences learned provide valuable clues for how the proposed algorithm can be effectively exploited to tackle other computational biology problems.

Original languageEnglish
Title of host publicationProceedings of the 2009 9th IEEE International Conference on Bioinformatics and BioEngineering, BIBE 2009
Pages208-215
Number of pages8
DOIs
Publication statusPublished - 2009 Nov 18
Event2009 9th IEEE International Conference on Bioinformatics and BioEngineering, BIBE 2009 - Taichung, Taiwan
Duration: 2009 Jun 222009 Jun 24

Publication series

NameProceedings of the 2009 9th IEEE International Conference on Bioinformatics and BioEngineering, BIBE 2009

Other

Other2009 9th IEEE International Conference on Bioinformatics and BioEngineering, BIBE 2009
CountryTaiwan
CityTaichung
Period09-06-2209-06-24

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Biomedical Engineering
  • Health Informatics

Fingerprint Dive into the research topics of 'On the design of optimization algorithms for prediction of molecular interactions'. Together they form a unique fingerprint.

Cite this