Abstract
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.
Similar content being viewed by others
References
Arretz M, Schneider H, Wienhues U, Neupert W (1991) Processing of mitochondrial precursor proteins. Biomed Biochim Acta 50:403–412
Bäck T, Schwefel HP (1993) An overview of evolutionary algorithms for parameter optimization. Evol Comput 1:1–24
Bernstein HD, Poritz MA, Strub K, Hoben PJ, Brenner S, Walter P (1989) Model for signal sequence recognition from amino acid sequence of 54 kD subunit of signal recognition particle. Nature 340:482–483
Bird P, Gething MJ, Sambrook J (1990) The functional efficiency of a mammalian signal peptide is directly related to its hydorphobicity. J Biol Chem 265:8420–8425
Cornette JL, Cease KB, Margalit H, Spouge JL, Berzofsky JA, DeLisi C (1987) Hydrophobicity scales and computational techniques for detecting amphipathic structures in proteins. J Mol Biol 195:659–685
Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2:303–314
Dobberstein B (1994) Protein transport: on the beaten pathway. Nature 367:599–600
Engelman DA, Steitz TA, Goldman A (1986) Identifying nonpolar transbilayer helices in amino acid sequences of membrane proteins. Annu Rev Biophys Biophys Chem 15:321–353
Fasman G (eds) (1989) Prediction of protein structure and the principles of protein conformation. Plenum Press, New York
Fontana W, Stadler PF, Bornberg-Bauer EG, Griesmacher T, Hofacker IL, Tacker M, Tarazona P, Weinberger ED, Schuster P (1993) RNA folding and combinatory landscapes. Phys Rev E 47:2083–2099
Gallop MA, Barrett RW, Dower WJ, Fodor SPA, Gordon EM (1994) Applications of combinatorial technologies to drug discovery, 1. Background and peptide combinatorial libraries. J Med Chem 37:1233–1251
Gavel Y, Heijne G von (1990) Cleavage site motifs in mitocondrial targeting peptides. Protein Eng 4:33–37
George DG, Barker WC, Hunt LT (1990) Mutation data matrix and its uses. Methods Enzymol 183:333–351
Glick BS (1995) Can hsp70 proteins act as force-generating motors? Cell 80:11–14
Graddis TJ, Oxender DL (1994) An introduction to protein engineering. In: Wrede P, Schneider G, (eds) Concepts in protein engineering and design. Walter de Gruyter, Berlin, pp 1–45
Harpaz Y, Gerstein M, Chothia C (1994) Volume changes on protein folding. Structure 2:641–649
Hartl FU, Lecker S, Schiebel E, Hendrick JP, Wickner W (1990) The binding cascade of SecB to SecA to SecY/E mediates preprotein targeting to the E. coli plasma membrane. Cell 63:269–279
Hartman EJ, Keeler JD, Kowalski JM (1990) Layered neural networks with Gaussian hidden units as universal approximations. Neural Comput 2:210–215
Hecht-Nielsen R (1987a) Counterpropagation networks. Proceedings of the IEEE First International Conference on Neural Networks II, pp 19–32
Hecht-Nielsen R (1987b) Counterpropagation networks. Appl Optics 26:4979–4984
Heijne G von (1983) Patterns of amino acids near signal-sequence cleavage sites. Eur J Biochem 133:17–21
Hendrick JP, Hodges PE, Rosenberg LE (1989) Survey of aminoterminal proteolytic cleavage sites in mitochondrial precursor proteins: leader peptides cleaved by two matrix proteases share a three-amino acid motif. Proc Natl Acad Sci USA 86:4056–4060
Hertz J, Krogh A, Palmer RG (1991) Introduction to the theory of neural computation. Addison-Wesley, Redwood City
Hirst JD, Sternberg MJE (1992) Prediction of structural and functional features of protein and nucleic acid sequences by artificial neural networks. Biochemistry 31:7211–7218
Holley HL, Karplus M (1991) Neural networks for protein structure prediction. Methods Enzymol 210:610–636
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Networks 2:359–366
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43:59–69
Kosko B (1992) Neural networks and fuzzy systems. Prentice-Hall, London
Lohmann R, Schneider G, Behrens D, Wrede P (1994) A neural filter system predicting membrane-spanning regions in amino acid sequences. Prot Sci 3:1597–1601
Lorimer GH (1992) Role of accessory proteins in protein folding. Curr Opin Struct Biol 2:26–34
Manning-Krieg UC, Scherer PE, Schatz G (1991) Sequential action of mitochondrial chaperones in protein import into mitochondria. EMBO J 10:3273–3280
Mathews BW (1975) Comparison of the predicted and observed secondary structure of T4 phase lysozyme. Biochim Biophys Acta 405:442–451
Mayer A, Neupert W, Lill R (1995) Mitochondrial protein import: reversible binding of the presequences at the trans side of the outer membrane drives partial translocation and unfolding. Cell 80:127–137
McInerny JM, Haines KG, Biafore S, Hecht-Nielsen R (1989) Back-propagation error surfaces can have local optima. International Joint Conference on Neural Networks II, 627
Mewes HW, Doelz R, George DG (1994) Sequence databases: an indispensible source for biotechnological research. J Biotechnol 35:239–256
Moody J, Darken C (1989) Fast learning in networks of locally-tuned processing units. Neural Comput 1:281–294
Murakami K, Tokunaga F, Iwanaga S, Mori M (1990) Presequence does not prevent folding of a purified mitochondrial precursor protein and is essential for association with a reticulocyte cytosolic factor(s). J Biochem 108:207–214
Neupert W, Hartl FU, Craig EA, Pfanner N (1990) How do polypeptides cross the mitochondrial membrane? Cell 63:447–450
Niranjan M, Fallside F (1990) Neural networks and radial basis functions in classifying static speech pattens. Comput Speech Lang 4:275–289
Park S, Liu G, Topping TB, Cover WH, Randall LL (1988) Modulation of folding pathways of exported proteins by the leader sequence. Science 239:1033–1035
Parker GA, Maynard Smith J (1990) Optimality theory in evolutionary biology. Nature 348:27–33
Perham RN (1994) Structural aspects of biomolecular recognition and self-assembly. Biosens Bioelectron 9:753–760
Perlman D, Halvorson HA (1983) A putative signal peptidase recognition site and sequence in eukaryotic and prokaryotic signal peptides. J Mol Biol 167:391–409
Poggio T, Girosi F (1990) Regularization algorithms for learning that are equivalent to multilayer networks. Science 247:978–982
Poritz MA, Siegel V, Hansen W, Walter P (1988) Small ribonucleoproteins in S. pombe and Yarrowia lipolytica homologous to signal recognition particle. Proc Natl Acad Sci USA 85:4315–4319
Qian N, Sejnowski TJ (1988) Predicting the secondary structure of globular proteins using neural network models. J Mol Biol 202:865–884
Rechenberg I (1973) Evolutionsstrategie — Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. Frommann-Holzboog, Stuttgart
Rechenberg I (1994) Evolutionsstrategie '94. Frommann-Holzboog, Stuttgart
Ribes V, Römisch K, Giner A, Dobberstein B, Tollervey D (1990) E. coli 4. 5S RNA is a part of a ribonucleoprotein particle that has properties related to signal recognition particle. Cell 63:591–600
Richardson JS, Richardson DC, Tweedy NB, Gernert KM, Quinn TP, Hecht MH, Erickson BW, Yan Y, McClain RD, Donlan ME, Surles MC (1992) Looking at proteins: representations, folding, packing, and design. Biophys J 63:1186–1209
Römisch K, Webb J, Herz J, Prehn S, Frank R, Vingron M, Dobberstein B (1989) Homology of 54kD protein of signal recognition particle, docking protein and two E. jtcoli proteins with putative GTP-binding domains. Nature 340:478–482
Rost B, Schneider R, Sander C (1993) Progress in protein structure prediction? Trends Biochem Sci 18:120–123
Rumelhart DE, McClelland JL, The PDP Research Group (eds) (1986) Parallel distributed processing, Vol I. MIT Press, Cambridge, Mass.
Schatz G (1993) The protein import machinery of mitochondria. Prot Sci 2:141–146
Schneider G, Wrede P (1993) Development of artificial neural filters for pattern recognition in protein sequences. J Mol Evol 36:586–595
Schneider G, Wrede P (1994) 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. Biophys J 66:335–344
Schneider G, Schuchhardt J, Wrede P (1994a) Artificial neural networks and simulated molecular evolution are potential tools for sequence-oriented protein design. Comput Appl Biosci 10:635–645
Schneider G, Lohmann R, Wrede P (1994b) The rational design of amino acid sequences. In: Wrede P, Schneider G (eds) Concepts in protein engineering and design. Walter de Gruyter, Berlin, 281–317
Schneider G, Schuchhardt J, Wrede P (1995) Peptide design in machina: development of artificial mitochondrial protein precursor cleavagesites by simulated molecular evolution. Biophys J 68:434–477
Schomburg D (1994) Rational design of proteins with new properties. In: Wrede P, Schneider G (eds) Concepts in protein engineering and design. Walter de Gruyter, Berlin, pp 169–208
Specht DF (1990) Probabilistic neural networks. Neural Networks 3:109–118
Steeg E (1993) Neural networks, adaptive optimization, and RNA secondary structure prediction. In: Hunter L (ed) Artificial intelligence and molecular biology. AAAI Press MIT Press, Menlo Park Cambridge, Mass. pp 121–160
Stolorz P, Lapedes A, Xia Y (1992) Predicting protein secondary structure using neural net and statistical methods. J Mol Biol 225:363–377
Tetko IV, Tanchuk VY, Chentsova NP, Antonenko SV, Poda GI, Kukhar VP, Luik A (1994) HIV-1 reverse transcriptase inhibitor design using artificial neural networks. J Med Chem 37:2520–2526
Thornton J (1992) Lessons from analyzing protein structures. Curr Opin Struct Biol 2:888–894
Verlinde CLMJ, Hol WGJ (1994) Structure-based drug design: progress, results and challenges. Structure 2:577–587
Wells JA, Lowman HB (1992) Rapid evolution of peptide and protein binding properties in vitro. Curr Opin Struct Biol 2:597–604
Whittle PJ, Blundell TL (1994) Protein structure-based drug design. Annu Rev Biophys Biomol Struct 23:349–375
Wrede P, Schneider G (eds) (1994) Concepts in protein engineering and design. Walter de Gruyter, Berlin
Zamyatnin AA (1972) Protein volume in solution. Prog Biophys Mol Biol 24:107–123
Zuckermann RN (1993) The chemical synthesis of peptidomimetic libraries. Curr Opin Struct Biol 3:580–584
Zupan J, Gasteiger J (1993) Neural networks for chemists. VCH, Weinheim
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Schneider, G., Schuchhardt, J. & Wrede, P. Development of simple fitness landscapes for peptides by artificial neural filter systems. Biol. Cybern. 73, 245–254 (1995). https://doi.org/10.1007/BF00201426
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00201426