Development of simple fitness landscapes for peptides by artificial neural filter systems

The applicability of artificial neural filter systems as fitness functions for sequence-oriented peptide design was evaluated. Two example applications were selected: classification of dipeptides according to their hydrophobicity and classification of proteolytic cleavage-sites of protein precursor sequences according to their mean hydrophobicities and mean side-chain volumes. The cleavage-sites covered 12 residues. In the dipeptide experiments the objective was to separate a selected set of molecules from all other possible dipeptide sequences. Perceptrons, feedforward networks with one hidden layer, and a hybrid network were applied. The filters were trained by a (1,λ) evolution strategy. Two types of network units employing either a sigmoidal or a unimodal transfer function were used in the feedforward filters, and their influence on classification was investigated. The two-layer hybrid network employed gaussian activation functions. To analyze classification of the different filter systems, their output was plotted in the two-dimensional sequence space. The diagrams were interpreted as fitness landscapes qualifying the markedness of a characteristic peptide feature which can be used as a guide through sequence space for rational peptide design. It is demonstrated that the applicability of neural filter systems as a heuristic method for sequence optimization depends on both the appropriate network architecture and selection of representative sequence data. The networks with unimodal activation functions and the hybrid networks both led to a number of local optima. However, the hybrid networks produced the best prediction results. In contrast, the filters with sigmoidal activation produced good reclassification results leading to fitness landscapes lacking unreasonable local optima. Similar results were obtained for classification of both dipeptides and cleavage-site sequences.

[1]  Weinberger,et al.  RNA folding and combinatory landscapes. , 1993, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[2]  Mahesan Niranjan,et al.  Neural networks and radial basis functions in classifying static speech patterns , 1990 .

[3]  D G George,et al.  Sequence databases: an indispensible source for biotechnological research. , 1994, Journal of biotechnology.

[4]  R. Hecht-Nielsen,et al.  Back propagation error surfaces can have local minima , 1989, International 1989 Joint Conference on Neural Networks.

[5]  Small ribonucleoproteins in Schizosaccharomyces pombe and Yarrowia lipolytica homologous to signal recognition particle. , 1988, Proceedings of the National Academy of Sciences of the United States of America.

[6]  B. Dobberstein.  On the beaten pathway , 1994, Nature.

[7]  Ingo Rechenberg,et al.  Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[8]  R. Jaenicke.  Role of accessory proteins in protein folding , 1993 .

[9]  F. Hartl,et al.  How do polypeptides cross the mitochondrial membranes? , 1990, Cell.

[10]  A. Zamyatnin,et al.  Protein volume in solution. , 1972, Progress in biophysics and molecular biology.

[11]  W. Neupert,et al.  Processing of mitochondrial precursor proteins. , 1991, Biomedica biochimica acta.

[12]  William T. Katz,et al.  Artificial Neural Networks , 2018, Encyclopedia of Image Processing.

[13]  G. Fasman.  Prediction of Protein Structure and the Principles of Protein Conformation , 2012, Springer US.

[14]  T. Sejnowski,et al.  Predicting the secondary structure of globular proteins using neural network models. , 1988, Journal of molecular biology.

[15]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[16]  S. V. Antonenko,et al.  HIV-1 reverse transcriptase inhibitor design using artificial neural networks. , 1994, Journal of medicinal chemistry.

[17]  T L Blundell,et al.  Protein structure--based drug design. , 1994, Annual review of biophysics and biomolecular structure.

[18]  Rapid evolution of peptide and protein binding properties in vitro. , 1992, Current opinion in biotechnology.

[19]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[20]  R. Perham.  Structural aspects of biomolecular recognition and self-assembly. , 1994, Biosensors & bioelectronics.

[21]  J. Sambrook,et al.  The functional efficiency of a mammalian signal peptide is directly related to its hydrophobicity. , 1990, The Journal of biological chemistry.

[22]  Evan W. Steeg,et al.  Neural networks, adaptive optimization, and RNA secondary structure prediction , 1993 .

[23]  C. DeLisi,et al.  Hydrophobicity scales and computational techniques for detecting amphipathic structures in proteins. , 1987, Journal of molecular biology.

[24]  G von Heijne,et al.  Cleavage-site motifs in mitochondrial targeting peptides. , 1990, Protein engineering.

[25]  J. M. Smith,et al.  Optimality theory in evolutionary biology , 1990, Nature.

[26]  S. P. Fodor,et al.  Applications of combinatorial technologies to drug discovery. 1. Background and peptide combinatorial libraries. , 1994, Journal of medicinal chemistry.

[27]  W. Vent,et al.  Rechenberg, Ingo, Evolutionsstrategie — Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. 170 S. mit 36 Abb. Frommann‐Holzboog‐Verlag. Stuttgart 1973. Broschiert , 1975 .

[28]  Thomas Bäck,et al.  An Overview of Evolutionary Algorithms for Parameter Optimization , 1993, Evolutionary Computation.

[29]  W. Neupert,et al.  Mitochondrial protein import: Reversible binding of the presequence at the trans side of the outer membrane drives partial translocation and unfolding , 1995, Cell.

[30]  M Karplus,et al.  Neural networks for protein structure prediction. , 1991, Methods in enzymology.

[31]  Gunnar von Heijne,et al.  Patterns of Amino Acids near Signal‐Sequence Cleavage Sites , 1983 .

[32]  T. Steitz,et al.  Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. , 1986, Annual review of biophysics and biophysical chemistry.

[33]  Martin Vingron,et al.  Homology of 54K protein of signal-recognition particle, docking protein and two E. coli proteins with putative GTP–binding domains , 1989, Nature.

[34]  T Poggio,et al.  Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks , 1990, Science.

[35]  David C. Jones,et al.  Progress in protein structure prediction. , 1997, Current opinion in structural biology.

[36]  R. Hecht-Nielsen.  Counterpropagation networks. , 1987, Applied optics.

[37]  D Perlman,et al.  A putative signal peptidase recognition site and sequence in eukaryotic and prokaryotic signal peptides. , 1983, Journal of molecular biology.

[38]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[39]  F. Hartl,et al.  The binding cascade of SecB to SecA to SecY E mediates preprotein targeting to the E. coli plasma membrane , 1990, Cell.

[40]  M J Sternberg,et al.  Prediction of structural and functional features of protein and nucleic acid sequences by artificial neural networks. , 1992, Biochemistry.

[41]  B. Glick.  Can Hsp70 proteins act as force-generating motors? , 1995, Cell.

[42]  Introduction: Protein engineering , 1988 .

[43]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[44]  Shigeo Abe,et al.  Neural Networks and Fuzzy Systems , 1996, Springer US.

[45]  D. G. George,et al.  Mutation data matrix and its uses. , 1990, Methods in enzymology.

[46]  D C Richardson,et al.  Looking at proteins: representations, folding, packing, and design. Biophysical Society National Lecture, 1992. , 1992, Biophysical journal.

[47]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[48]  R. Lohmann,et al.  A neural network model for the prediction of membrane‐spanning amino acid sequences , 1994, Protein science : a publication of the Protein Society.

[49]  Gisbert Schneider,et al.  Artificial neural networks and simulated molecular evolution are potential tools for sequence-oriented protein design , 1994, Comput. Appl. Biosci..

[50]  C L Verlinde,et al.  Structure-based drug design: progress, results and challenges. , 1994, Structure.

[51]  Gisbert Schneider,et al.  Concepts in Protein Engineering and Design: An Introduction , 1994 .

[52]  Johann Gasteiger,et al.  Neural Networks for Chemists: An Introduction , 1993 .

[53]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[54]  C Sander,et al.  Progress in protein structure prediction? , 1993, Trends in biochemical sciences.

[55]  L. Randall,et al.  Modulation of folding pathways of exported proteins by the leader sequence. , 1988, Science.

[56]  J. Hendrick,et al.  Survey of amino-terminal proteolytic cleavage sites in mitochondrial precursor proteins: leader peptides cleaved by two matrix proteases share a three-amino acid motif. , 1989, Proceedings of the National Academy of Sciences of the United States of America.

[57]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[58]  N. Pfanner,et al.  The protein import machinery of mitochondria , 2007 .

[59]  Ronald N. Zuckermann,et al.  The chemical synthesis of peptidomimetic libraries: Current opinion in structural biology 1993, 3:580–584 , 1993 .

[60]  P Stolorz,et al.  Predicting protein secondary structure using neural net and statistical methods. , 1992, Journal of molecular biology.

[61]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[62]  Peter Walter,et al.  Model for signal sequence recognition from amino-acid sequence of 54K subunit of signal recognition particle , 1989, Nature.

[63]  G Schneider,et al.  The rational design of amino acid sequences by artificial neural networks and simulated molecular evolution: de novo design of an idealized leader peptidase cleavage site. , 1994, Biophysical journal.

[64]  G Schneider,et al.  Peptide design in machina: development of artificial mitochondrial protein precursor cleavage sites by simulated molecular evolution. , 1995, Biophysical journal.

[65]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[66]  M Gerstein,et al.  Volume changes on protein folding. , 1994, Structure.

[67]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[68]  G. Schneider,et al.  Development of artificial neural filters for pattern recognition in protein sequences , 1993, Journal of Molecular Evolution.

[69]  G. Schatz,et al.  Sequential action of mitochondrial chaperones in protein import into the matrix. , 1991, The EMBO journal.

[70]  D. Tollervey,et al.  E. coli 4.5S RNA is part of a ribonucleoprotein particle that has properties related to signal recognition particle , 1990, Cell.

[71]  Janet M. Thornton,et al.  Lessons from analyzing protein structures , 1992 .