DocumentCode :
3285960
Title :
Feature selection for in-silico drug design using genetic algorithms and neural networks
Author :
Ozdemir, Muhsin ; Embrechts, Mark J. ; Arciniegas, F. ; Breneman, Curt M. ; Lockwood, Larry ; Bennett, Kristin P.
Author_Institution :
Dept. of Eng. Sci., Rensselaer Polytech. Inst., Troy, NY, USA
fYear :
2001
fDate :
2001
Firstpage :
53
Lastpage :
57
Abstract :
QSAR (quantitative structure activity relationship) is a discipline within computational chemistry that deals with predictive modeling, often for relatively small datasets where the number of features might exceed the number of data points, leading to extreme dimensionality problems. The paper addresses a novel feature selection procedure for QSAR based on genetic algorithms to reduce the curse of dimensionality problem. In this case the genetic algorithm minimizes a cost function derived from the correlation matrix between the features and the activity of interest that is being modeled. From a QSAR dataset with 160 features, the genetic algorithm selected a feature subset (40 features), which built a better predictive model than with full feature set. The results for feature reduction with genetic algorithm were also compared with neural network sensitivity analysis
Keywords :
chemical structure; chemistry computing; feature extraction; genetic algorithms; medical computing; neural nets; QSAR; computational chemistry; correlation matrix; cost function; dimensionality problem; feature selection; genetic algorithms; in-silico drug design; neural networks; predictive modeling; quantitative structure activity relationship; Algorithm design and analysis; Artificial neural networks; Chemistry; Data engineering; Drugs; Filters; Genetic algorithms; Neural networks; Predictive models; Sensitivity analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Soft Computing in Industrial Applications, 2001. SMCia/01. Proceedings of the 2001 IEEE Mountain Workshop on
Conference_Location :
Blacksburg, VA
Print_ISBN :
0-7803-7154-2
Type :
conf
DOI :
10.1109/SMCIA.2001.936728
Filename :
936728
Link To Document :
بازگشت