PEPTIDE DESIGN AIDED BY NEURAL NETWORKS - BIOLOGICAL-ACTIVITY OF ARTIFICIAL SIGNAL PEPTIDASE-I CLEAVAGE SITES

De novo designed signal peptidase I cleavage sites were tested for the ir biological activity in vivo in an Escherichia coli expression and s ecretion system, The artificial cleavage site sequences were generated by two different computer-based design techniques, a simple statistic al method, and a neural network approach. In previous experiments, a n eural network was used for feature extraction from a set of known sign al peptidase I cleavage sites and served as the fitness function in an evolutionary design cycle leading to idealized cleavage site sequence s, The cleavage sites proposed by the two algorithms were active in vi vo as predicted, There seems to be an interdependence between several cleavage site features for the constitution of sequences recognized by signal peptidase, It is concluded that neural networks are useful too ls for sequence-oriented peptide design.