Artificial neural networks for computer-based molecular design

• Published in: Progress in biophysics and molecular biology Vol. 70; no. 3; pp. 175 - 222
• Main Authors: Schneider, Gisbert, Wrede, Paul
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.01.1998
• Subjects: Combinatorial chemistry; Compound library; Computer-Aided Design; Drug Design; Genetic algorithm; Molecular Conformation; Molecular descriptor; Molecular diversity; Molecular Structure; Neural network; Neural Networks (Computer); Sequence analysis; Software; Structure–activity relationship; ART, adaptive resonance theory; CAMD, computer-aided molecular design; PCA, principle component analysis; SBB, structural building blocks; BAM, bi-directional associative memory; Combinatorial chemistry; bp, back-propagation-of-errors; Compound library; 2D, two-dimensional; SAR, structure–activity relationship; ReNDeR, reversible non-linear dimension reduction; Drug design; Molecular diversity; SNN, supervised neural networks; Molecular descriptor; Neural network; LMS, least-mean-square; 3D, three-dimensional; QSAR, quantitative structure–activity relationship; RBF, radial basis function; Genetic algorithm; UNN, unsupervised neural networks; ANN, artificial neural networks; CPN, counter-propagation network; Sequence analysis; Structure–activity relationship
• ISSN: 0079-6107; 1873-1732
• DOI: 10.1016/S0079-6107(98)00026-1

The theory of artificial neural networks is briefly reviewed focusing on supervised and unsupervised techniques which have great impact on current chemical applications. An introduction to molecular descriptors and representation schemes is given. In addition, worked examples of recent advances in this field are highlighted and pioneering publications are discussed. Applications of several types of artificial neural networks to compound classification, modelling of structure–activity relationships, biological target identification, and feature extraction from biopolymers are presented and compared to other techniques. Advantages and limitations of neural networks for computer-aided molecular design and sequence analysis are discussed.