Peptide design by artificial neural networks and computer-based evolutionary search

Abstract

A technique for systematic peptide variation by a combination of rational and evolutionary approaches is presented. The design scheme consists of five consecutive steps: (i) identification of a ''seed peptide'' with a desired activity, (ii) generation of variants selected from a physicochemical space around the seed peptide, (iii) synthesis and testing of this biased library, (iv) modeling of a quantitative sequence-activity relationship by an artificial neural network, and (v) de novo design by a computer-based evolutionary search in sequence space using the trained neural network as the fitness function. This strategy was successfully applied to the identification of novel peptides that fully prevent the positive chronotropic effect of anti-␤ 1 -adrenoreceptor autoantibodies from the serum of patients with dilated cardiomyopathy. The seed peptide, comprising 10 residues, was derived by epitope mapping from an extracellular loop of human ␤ 1 -adrenoreceptor. A set of 90 peptides was synthesized and tested to provide training data for neural network development. De novo design revealed peptides with desired activities that do not match the seed peptide sequence. These results demonstrate that computer-based evolutionary searches can generate novel peptides with substantial biological activity.Molecular design aims to identify compounds with a desired activity and to rationally modify molecular structures to yield desired or improved molecular properties. Two principal problems need to be solved: first, a search strategy must be developed for exploiting the potentially huge number of compounds; second, for any rational design approach a model must be available to guide the systematic modification of molecular structures. Rational molecular design can be successful only with profound knowledge of the inf luence of structural modifications on molecular function. An alternative approach is to use evolutionary strategies in which optimization of molecular properties is achieved by a cyclic variation-selection process; no detailed understanding of the respective structure-activity relationship is required. This process can be performed in vivo, in vitro, or even entirely by computer (''in machina '' or ''in silico''). Usually, a large number of compounds must be synthesized and tested per evolutionary cycle to avoid trapping into premature convergence, and the optimization process bears the danger of being merely superior to pure random search. If, however, this limitation can be overcome, e.g., by massively parallel screening and smart variation of molecular structures, evolutionary design can be a powerful method for rapid identification of potential lead compounds.We have developed a design approach combining the advantages of a computer-based evolutionary search with a knowledge-based rational access to reduce the time and effort needed to obtain desirable molecules. The goal is to minimize the number of bench experiments by making extensive use of the information provided by the results of each in vitro o...

Topology Preserving Neural Networks for Peptide Design in Drug Discovery

“…In the case of peptide design, any standard evolutionary algorithm [20][21][22][23] could be used in order search for new peptides that are selected with the previously learned TPNN. Similar attempts have been reported by Schneider and Wrede [13,24] and Schneider et al [15] termed simulated molecular evolution. In their approach an artificial neural network is used to model the locally encoded amino acid sequence features of the peptides.…”

“…This is done by training several (10)(11)(12)(13)(14)(15)(16)(17)(18)(19)(20) TPNNs on randomly chosen subsets of the training data where the training starts with random weight initializations. To compute the output of the ensemble for one input sequence, the output variables of all TPNNs belonging to the ensemble are averaged.…”

“…Their work was criticized by Darius and Rojas [14] who questioned the statistical significance of their results in general. But Schneider et al demonstrated later that their method can generate novel peptides with substantial biological activity in real world experiments [15]. Another group reported the effective application of a tailored genetic algorithm for the de novo construction of peptidic thrombin inhibitors [16].…”

A comprehensive survey of fitness approximation in evolutionary computation

“…Fitness approximation has also been reported in protein structure prediction using evolutionary algorithms [53,59]. A neural network has been used for feature extraction from amino acid sequence in evolutionary protein design and drug design [72,73,74]. -There is no explicit model for fitness computation.…”

Adaptive-surrogate based on a neuro-fuzzy network and granular computing

“…Techniques based on universal approximators, whose quality depends on the training data, are based on Artificial Neural Networks (ANN) [9,11,14,17,24,25]. In [15], selection of centers in the RBF surrogate model, is done in an unsupervised manner with Learning Vector Quantization (LVQ) and Self-Organizing Maps, this formulation tackles the problem of good generalization, that represents an estimation of objective functions for new individuals.…”