id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-017668-my2l85bn	Cho, Yeon-Jin	Rule Generation Using NN and GA for SARS-CoV Cleavage Site Prediction	2005		.txt	text/plain	2084	140	60	title: Rule Generation Using NN and GA for SARS-CoV Cleavage Site Prediction We present a new method that generates prediction rules for SARS-CoV protease cleavage sites. Experimental results show that the method could generate new rules for cleavage site prediction, which are more general and accurate than consensus patterns. In this paper, we present new approaches to rule generation for the cleavage site prediction, and the rule is represented in an explicit form such as "if L@p2 and R@p3, then cleavage". We used the methods of rule extraction from neural networks and knowledge-based genetic algorithms in this paper. used feed-forward neural networks for SARS-CoV cleavage site analysis [11] . Domain knowledge was obtained by extracting rules from consensus patterns, decision tree and neural networks. Finally, we compare the rule performances between decision tree, neural network and knowledge-based genetic algorithm (KBGA). We presented a new method that generates rules and improves quality of the rules with the subject of SARS-CoV protease cleav-age site prediction.	./cache/cord-017668-my2l85bn.txt	./txt/cord-017668-my2l85bn.txt