DocumentCode :
2564874
Title :
Evolutionary optimization of interval rules for drug design
Author :
Paetz, Jürgen
Author_Institution :
Dept. of Chem. & Pharm. Sci., J. W. Goethe-Univ. Frankfurt am Main, Germany
fYear :
2004
fDate :
7-8 Oct. 2004
Firstpage :
238
Lastpage :
243
Abstract :
An active area of current research is the discovery of novel drugs for diseases for which no satisfactory drugs have yet been found. To save experimental costs, this knowledge discovery task is assisted greatly by computational experiments because these can reduce the amount of actual experimentation required. This work demonstrates how an adaptive neurofuzzy computation is able to separate molecular data that is bioactive from that which is not bioactive. The resulting classification rules may prove useful in "virtual screening" by means of runtime, effectiveness, and explanatory power. The rules are further improved by using an additional evolutionary strategy to offer a more enriched selection of bioactive molecules.
Keywords :
biology computing; data mining; diseases; drugs; evolutionary computation; fuzzy neural nets; fuzzy systems; molecular biophysics; adaptive neurofuzzy computation; bioactive molecules; computational experiment; diseases; drug design; evolutionary optimization; explanatory power; interval rules; knowledge discovery task; satisfactory drugs; virtual screening; Algorithm design and analysis; Costs; Design optimization; Diseases; Drugs; Evolutionary computation; Laboratories; Libraries; Organic chemicals; Process design;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence in Bioinformatics and Computational Biology, 2004. CIBCB '04. Proceedings of the 2004 IEEE Symposium on
Print_ISBN :
0-7803-8728-7
Type :
conf
DOI :
10.1109/CIBCB.2004.1393959
Filename :
1393959
Link To Document :
بازگشت