Peptide Design Aided by Neural Networks: Biological Activity of Artificial Signal Peptidase I Cleavage Sites

详细信息    查看全文

• 作者：Paul Wrede ; Olfert Landt ; Sven Klages ; Afshin Fatemi ; Ulrich Hahn ; and Gisbert Schneider
• 刊名：Biochemistry
• 出版年：1998
• 出版时间：March 17, 1998
• 年：1998
• 卷：37
• 期：11
• 页码：3588 - 3593
• 全文大小：95K
• 年卷期：v.37,no.11(March 17, 1998)
• ISSN：1520-4995

文摘

De novo designed signal peptidase I cleavage sites were tested fortheir biological activity invivo in an Escherichia coli expression and secretion system.The artificial cleavage site sequences weregenerated by two different computer-based design techniques, a simplestatistical method, and a neuralnetwork approach. In previous experiments, a neural network wasused for feature extraction from a setof known signal peptidase I cleavage sites and served as the fitnessfunction in an evolutionary designcycle leading to idealized cleavage site sequences. The cleavagesites proposed by the two algorithmswere active in vivo as predicted. There seems to be aninterdependence between several cleavage sitefeatures for the constitution of sequences recognized by signalpeptidase. It is concluded that neuralnetworks are useful tools for sequence-oriented peptidedesign.