DocumentCode :
1750633
Title :
Integrating rules and neural nets for carcinogenicity prediction
Author :
Gini, Giuseppina ; Lorenzini, Marco ; Benfenati, Emilio ; Brambilla, Raffaella ; Malvè, Luca
Author_Institution :
Dipt. di Elettronica e Inf., Politecnico di Milano, Italy
fYear :
2001
fDate :
25-28 July 2001
Firstpage :
3003
Abstract :
One approach to deal with real complex systems is to use more techniques in order to combine their different strengths and overcome each other´s weakness to generate hybrid solutions. In this project we pointed out the needs of an improved system in toxicology prediction. An architecture able to satisfy these needs has been developed. The main tools we integrated are rules and ANN. We defined chemical structures of fragments responsible for carcinogenicity according to human experts, developing a module able to recognize these fragments in a chemical. Furthermore, we developed an ANN, using molecular descriptors as inputs to predict carcinogenicity as a numerical value. Finally, we developed an automatic learning program to combine the results into a classifications of carcinogenicity to man
Keywords :
chemistry computing; expert systems; medical computing; molecular configurations; neural nets; pattern recognition; ANN; automatic learning program; carcinogenicity prediction; classifications; hybrid architecture; molecular structures; neural nets; rules; Animals; Cancer; Chemical industry; Databases; Frequency; Gold; Neoplasms; Neural networks; Testing; Toxicology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
IFSA World Congress and 20th NAFIPS International Conference, 2001. Joint 9th
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-7078-3
Type :
conf
DOI :
10.1109/NAFIPS.2001.943706
Filename :
943706
Link To Document :
بازگشت