Topology Preserving Neural Networks for Peptide Design in Drug Discovery

Authors:
Jörg D. Wichard;Sebastian Bandholtz;Carsten Grötzinger;Ronald Kühne
Affiliations:
FMP Berlin, Berlin, Germany 13125;Department of Hepatology and Gastroenterology, Charité Universitätsmedizin Berlin, Berlin, Germany D-13353;Department of Hepatology and Gastroenterology, Charité Universitätsmedizin Berlin, Berlin, Germany D-13353;FMP Berlin, Berlin, Germany 13125
Venue:
Computational Intelligence Methods for Bioinformatics and Biostatistics
Year:
2009

Citing 5
Cited 0

Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Neural networks and the bias/variance dilemma

Neural Computation
Neural Network Ensembles

IEEE Transactions on Pattern Analysis and Machine Intelligence
Effiicient BackProp

Neural Networks: Tricks of the Trade, this book is an outgrowth of a 1996 NIPS workshop

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a construction method and a training procedure for a topology preserving neural network (TPNN) in order to model the sequence-activity relation of peptides. The building blocks of a TPNN are single cells (neurons) which correspond one-to-one to the amino acids of the peptide. The cells have adaptive internal weights and the local interactions between cells govern the dynamics of the system and mimic the topology of the peptide chain. The TPNN can be trained by gradient descent techniques, which rely on the efficient calculation of the gradient by back-propagation. We show an example how TPNNs could be used for peptide design and optimization in drug discovery.