Skip to main content
SpringerLink
Log in

A predictor of transmembrane α-helix domains of proteins based on neural networks

  • Published:
European Biophysics Journal Aims and scope Submit manuscript

Abstract

Back-propagation, feed-forward neural networks are used to predict a-helical transmembrane segments of proteins. The networks are trained on the few membrane proteins whose transmembrane α-helix domains are known to atomic or nearly atomic resolution. When testing is performed with a jackknife procedure on the proteins of the training set, the fraction of total correct assignments is as high as 0.87, with an average length for the transmembrane segments of 20 residues. The method correctly fails to predict any transmembrane domain for porin, whose transmembrane segments are β-sheets. When tested on globular proteins, lower and upper limits of 1.6 and 3.5% for a total of 26826 residues are determined for the mispredicted cases, indicating that the predictor is highly specific for α-helical domains of membrane proteins. The predictor is also tested on 37 membrane proteins whose transmembrane topology is partially known. The overall accuracy is 0.90, two percentage points higher than that obtained with statistical methods. The reliability of the prediction is 100% for 60% of the total 18242 predicted residues of membrane proteins. Our results show that the local directional information automatically extracted by the neural networks during the training phase plays a key role in determining the accuracy of the prediction.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Argos P, Rao JKM, Hargrave PA (1982) Structural prediction of membrane-bound proteins. Eur J Biochem 128:565–575

    Google Scholar 

  • Bairoch A, Boeckmann B (1992) The SWISS-PROT protein sequence data bank. Nucl Acids Res 20:2019–2022

    Google Scholar 

  • Bernstein FC, Koetzle TF, Williams GJB, Meyer EF, Brice MD, Rodgers JR, Kennard O, Shimanouchi T, Tasumi M (1977) The protein data bank: a computer-based archival file for macromolecular structures. J Mol Biol 112:535–542

    Google Scholar 

  • Black SD, Coon MJ (1982) Structural features of liver microsomal NADPH-cytochrome P-450 reductase. J Biol Chem 257:5929–5938

    Google Scholar 

  • Bowie JU, Luthy R, Eisenberg DA (1991) Method to identify protein sequences that fold into a known three-dimensional structure. Science 235:164–170

    Google Scholar 

  • Brandl CJ, Green NM, Korczak B, MacLennan DH (1986) Two Ca2+ ATPasc genes: homologies and mechanistic implication of deduced amino acid sequences. Cell 44:597–607

    Google Scholar 

  • Brunisholz RA, Zuber H, Valentine J, Lindsay JG, Woolley KJ, Cogdell RJ (1986) The membrane location of the B890-complex from Rhodospirillum rubrum and the effect of carotenoid on the conformation of its two apoproteins exposed at the cytoplasmic surface. Biochim Biophys Acta 849:925–303

    Google Scholar 

  • Burgi R, Suter F, Zuber H (1987) Arrangement of the light-harvesting chlorophyll alb protein complex in the thylakoid membrane. Biochim Biophys Acta 890:346–351

    Google Scholar 

  • Chothia C (1992) One thousand families for the molecular biologist. Nature 357:543–544

    Google Scholar 

  • Chothia C, Finkelstein AV (1990) The classification and origins of protein folding patterns. Annu Rev Biochem 59:1007–1039

    Google Scholar 

  • Compiani M, Fariselli P, Casadio R (1991) Neural networks extracting general features of protein secondary structures. In: Caianiello ER (ed) Parallel Architectures and Neural Networks. World Scientific, Singapore, pp 227–237

    Google Scholar 

  • Compiani M, Fariselli P, Casadio R (1992) The statistical behaviour of perceptrons. In: Caianiello ER (ed) WIRN Vietri-92. World Scientific, Singapore, pp 111–117

    Google Scholar 

  • Cornette JL, Cease KB, Margalit H, Sponge JL, Berzofsky JA, De Lisi C (1987) Hydrophobicity scales and computational techniques for detecting amphipathic structures in proteins. J Mol Biol 195:659–685

    Google Scholar 

  • Degli Esposti M, Crimi M, Venturoli G (1990) A critical evaluation of the hydropathy profile of membrane proteins. Eur J Biochem 190:207–219

    Google Scholar 

  • Deisenhofer J, Epp O, Miki K, Huber R, Michel H (1985) Structure of the protein subunits in the photosynthetic reaction centre of Rhodopseudomonas viridis at 3 Å resolution. Nature 318:618–624

    Google Scholar 

  • Dohlman HG, Thorner J Caron, Lefkowitz M (1991) Model systems for the study of the seven-transmembrane segment receptors. Annu Rev Biochem 60:653–688

    Google Scholar 

  • Edelman J (1993) Quadratic minimization of predictors for protein secondary structure: application to transmembrane α-helixes. J Mol Biol 232:165–191

    Google Scholar 

  • Edelman J, White SH (1989) Linear optimization of predictors for secondary structure: application to transbilayer segments of membrane proteins. J Mol Biol 210:195–209

    Google Scholar 

  • Eisenberg D, Schwarz E, Komaromy M, Wall R (1984) Analysis of membrane and surface protein sequences with the hydrophobic moment plot. J Mol Biol 179:125–142

    Google Scholar 

  • Engelman DM, Steitz TA, Goldman A (1986) Identifying nonpolar transbilayer helixes in amino acid sequences of membrane proteins. Annu Rev Biophys Biophys Chem 15:321–353

    Google Scholar 

  • Fariselli P, Compiani M, Casadio R (1993) Predicting secondary structures of membrane proteins with neural networks. Eur Biophys J 22:41–51

    Google Scholar 

  • Fasman GD (1989) The development of the prediction of protein structure. In: Fasman GD (ed) Prediction of Protein Structure and the Principles of Protein Conformation. Plenum Press, New York, pp 193–316

    Google Scholar 

  • Fasman GD, Gilbert WA (1990) The prediction of transmembrane protein sequences and their conformation: an evaluation. TIBS 15:89–92

    Google Scholar 

  • Feher G, Allen JP, Okamura MY Rees DC (1989) Structure and function of bacterial photosynthetic reaction centers. Nature 339:111–116

    Google Scholar 

  • Foster DL, Boublik M, Kaback HR (1983) Structure of the lac carriers protein of Escherichia coli. J Biol Chem 258:31–34

    Google Scholar 

  • Fox RO, Richards FM (1982) A voltage gated ion channel model inferred from the crystal structure of alamethicin at 1.5 Å resolution. Nature 300:325–330

    Google Scholar 

  • Fujii-Kuriyama Y Mizukami Y Kawajiri K, Sogawa K, Muramatsu M (1982) Primary structure of a cytochrome P-450: coding nucleotide sequence of phenobarbital-inducible cytochrome P-450 messenger RNA from rat liver. Proc Natl Acad Sci, USA 79:2793–2797

    Google Scholar 

  • Garnier J, Robson B (1989) The GOR method for predicting secondary structures in proteins. In: Fasman GD (ed) Prediction of Protein Structure and the Principles of Protein Conformation. Plenum Press, New York, pp 417–465

    Google Scholar 

  • Garnier J, Levin JM (1991) The protein code: what is the present status? CABIOS 7:133–142

    Google Scholar 

  • Gibrat JF, Garnier J, Robson B (1987) Further developments of protein secondary structure prediction using information theory. J Mol Biol 198:425–443

    Google Scholar 

  • Gimlich RL, Kumar NM, Gilula NB (1988) Sequence and developmental expression of mRNA coding for a gap junction protein in Xenopus. J Cell Biol 107:1065–1073

    Google Scholar 

  • Grenningloh G, Rienitz A, Schmitt B, Methfessel C, Zensen M, Beyreuter K, Gundelfingr ED, Betz H (1987) The strychnine-binding subunit of the glycine receptor shows homology with nicotinic acetylcholine receptors. Nature 328:215–220

    Article  CAS  PubMed  Google Scholar 

  • Henderson R, Baldwin JM, Ceska TA, Zemlin F, Beckmann E, Downing KH (1990) Model for the structure of bacteriorhodopsin based on high resolution electron cryo-microscopy. J Mol Biol 213:899–929

    Google Scholar 

  • Hirst JD, Sternberg JE (1992) Prediction of structural and functional features of proteins and nucleic acid sequences by artificial neural networks. Biochemistry 31:7211–7218

    Google Scholar 

  • Holley HL, Karplus M (1989) Protein secondary structure prediction with a neural network. Proc Natl Acad Sci, USA 85:152–156

    Google Scholar 

  • Holm L, Saraste M, Wilkstrom M (1987) Structural models of the redox centres in cytochrome oxidase. EMBO J 6:2819–2823

    Google Scholar 

  • Jennings ML (1989) Topography of membrane proteins. Annu Rev Biochem 58:999–1027

    Google Scholar 

  • Jones DT, Taylor WR, Thornton JM (1994) A model recognition approach to the prediction of all-helical membrane protein structure and topology. Biochemistry 33:3038–3049

    Google Scholar 

  • Kabsch W Sander C (1983) Dictionary of protein secondary structure: pattern of hydrogen-bonded and geometrical features. Biopolymers 22:2577–2673

    CAS  PubMed  Google Scholar 

  • Kayano T, Noda M, Flockerzi V, Takahashi H, Numa S (1988) Primary structure of rat brain sodium channel III deduced from the cDNA sequence. FEBS Letters 228:187–194

    Google Scholar 

  • Khorana HG (1992) Rhodopsin, photoreceptor of the rod cell. J Biol Chem 267:1–4

    Google Scholar 

  • Klein P, Kanehisa M, De Lisi C (1985) The detection and classification of membrane-spanning proteins. Biochim Biophys Acta 815:468–476

    Google Scholar 

  • Kneller DG, Cohen FE, Langridge R (1990) Improvements in protein secondary structure prediction by an enhanced neural network. J Mol Biol 214:171–182

    Google Scholar 

  • Kopito RR, Lodish HF (1985) Primary structure and transmembrane orientation of the murine anion exchange protein. Nature 316:234–238

    Google Scholar 

  • Kyte J, Doolittle RF (1982) A simple method for displaying the hydrophobic character of a protein. J Mol Biol 157:103–132

    Google Scholar 

  • Kühlbrandt W, Wang DN, Fujiyoshi Y (1994) Atomic model of plant light-harvesting complex by electron crystallography. Nature 367:614–621

    Google Scholar 

  • Kuhn LA, Leigh JS (1985) A statistical technique for predicting membrane protein structure. Biochim Biophys Acta 828:351–361

    Google Scholar 

  • Lipman DJ, Pearson WL (1985) Rapid and sensitive protein similarity searches. Science 227:1435–1441

    Google Scholar 

  • Lippmann RP (1987) An introduction to computing with neural nets. IEEE ASSP Magazine 4:4–22

    Google Scholar 

  • Manoil C, Beckwith J (1986) A genetic approach to analyzing membrane protein topology. Science 233:1403–1408

    Google Scholar 

  • Matthews BW (1975) Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta 405:442–451

    Google Scholar 

  • McGovern K, Ehrmann M, Beckwith J (1991) Decoding signals for membrane proteins using alkaline phosphatase fusions. EMBO J 10:2773–2782

    Google Scholar 

  • Mellor IR, Thomas DH, Sansom MSP (1988) Properties of ion channels formed by Staphylococcus aureus δ-toxin. Biochim Biophys Acta 942:280–294

    Google Scholar 

  • Michel H (1983) Crystallization of membrane proteins. Trends Biochem Sci 8:56–59

    Google Scholar 

  • Michel H, Weyer KA, Gruenberg H, Dunger I, Osterhelt D, Lottspeich F (1986) The light and medium subunits of the photosynthetic reaction center from Rhodopseudomonas viridis: isolation of the genes, nucleotide and amino acid sequence. EMBO J 5:1149–1158

    Google Scholar 

  • Miller C (1991) 1990: annus mirabilis of potassium channels. Science 252:1092–1096

    Google Scholar 

  • Moore KE, Miura SA (1987) Small hydrophobic domain anchors leader peptidase to the cytoplasmic membrane of Escherichia coli. J Biol Chem 262:8806–8813

    Google Scholar 

  • Müller D, Reinhardt J (1990) Neural networks. Springer, Berlin Heidelberg New York

    Google Scholar 

  • Noda M, Takahashi H, Tanabe T, Toyosato M, Kikyotani S, Furutani Y, Hirose T, Takashima H, Inayama S, Miyata T, Numa S (1983a) Structural homology of Torpedo californica acetylcholine receptor subunits. Nature 302:528–532

    MathSciNet  Google Scholar 

  • Noda M, Takahashi H, Tanabe T, Toyosato M, Kikyotani S, Hirose T, Asai M, Takashima H, Inayama S, Miyata T, Numa S (1983b) Primary structure of β-and δ-subunit precursors of Torpedo californica deduced from cDNA sequences. Nature 301:251–255

    Google Scholar 

  • Ozols J, Carr SA, Strittmatter P (1984) Identification of the NH2-terminal blocking group of NADH-cytochrome b 5 reductase as myristic acid and the complete amino acid sequence of the membrane binding domain. J Biol Chem 259:13349–13354

    Google Scholar 

  • Peralta EG, Ashkenazi A, Winslow JW, Smith DH, Ramachandran J, Capon DJ (1987) Distinct primary structures, ligand-binding properties and tissue specific expression of four human muscarinic acetylcholine receptors. EMBO J 6:3923–3929

    Google Scholar 

  • Persson B. Argos P (1994) Prediction of transmembrane segments in proteins utilising multiple sequence alignments. J Mol Biol 237:182–192

    Google Scholar 

  • Popot JL, De Vitry C (1990) On the microassembly of integral membrane proteins. Annu Rev Biophys Biophys Chem 19:369–403

    Google Scholar 

  • Popot JL, Dinh DP, Dautigny A (1991) Major myelin proteolipid: the 4-α-helix topology. J Membr Biol 120:233–246

    Google Scholar 

  • Presnell SR, Cohen FE (1993) Artificial neural networks for pattern recognition in biochemical sequences. Annu Rev Biophys Biomol Struct 22:283–298

    Google Scholar 

  • Qian N, Sejnowski TJ (1988) Predicting the secondary structure of globular proteins using neural network models. J Mol Biol 202:865–884

    CAS  PubMed  Google Scholar 

  • Rao JKM, Argos P (1986) A conformational preference parameter to predict helices in integral membrane proteins. Biochim Biophys Acta 869:197–214

    Google Scholar 

  • Ross AH, Radhakrishnan R, Robson RJ, Khorana HG (1982) The transmembrane domain of glycophorin A as studied by crosslinking using photoactivable phospholipids. J Biol Chem 257:4152–4161

    Google Scholar 

  • Rost B, Sander C (1993) Prediction of protein secondary structure at better than 70% accuracy. J Mol Biol 232:584–599

    Article  CAS  PubMed  Google Scholar 

  • Rost B, Sander C, Schneider R (1994) Redefining the goals of protein secondary structure prediction. J Mol Biol 235:13–26

    Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representation by back-propagation errors. Nature 323:533–536

    Google Scholar 

  • Sayre RT, Andersson B, Bogorad L (1986) The topology of a membrane protein: the orientation of the 32 kD Qb-binding chloroplast thylakoid membrane proteins. Cell 47:601–608

    Google Scholar 

  • Schofield PR, Darlison MG, Fujita N, Burt DR, Stephenson FA (1987) Sequence and functional expression of the GABAA receptor shows a ligand-gated receptor super-family. Nature 328:221–227

    Google Scholar 

  • Schulz GE (1988) A critical evaluation of methods for prediction of protein secondary structures. Annu Rev Biophys Chem 17:1–21

    Google Scholar 

  • Schulz GE, Schirmer RH (1979) Principles of protein structure. Springer, Berlin Heidelberg New York

    Google Scholar 

  • Shull GE, Lane LK, Lingrel JB (1986) Amino acid sequence of the β-subunit of the (Na+ + K+)ATPase deduced from cDNA. Nature 321:429–431

    Google Scholar 

  • Stader J, Matsumura P, Vacante D, Dean DE, Macnab RM (1986) Nucleotide sequence of the Escherichia coli motB gene and sitelimited incorporation of its product into the cytoplasmic membrane. J Bacteriol 166:244–252

    Google Scholar 

  • Strosberg AD (1991) Structure/function relationship of proteins belonging to the family of receptors coupled to GTP-binding proteins. Eur J Biochem 29:11009–11023

    Google Scholar 

  • Stumher W, Ruppersberg JP, Schroter KH, Sakmann B, Stoker M, Giese KP, Perschke A, Baumann A, Pongs O (1989) Molecular basis of functional diversity of voltage-gated potassium channels in mammalian brain. EMBO J 8:3235–3244

    Google Scholar 

  • Von Heijne G (1988) Trascending the impenetrable: how proteins come to term with membrane. Biochim Biophys Acta 947:307–333

    Google Scholar 

  • Von Heijne G (1992) Hydrophobicity analysis and the positive-inside rule. J Mol Biol 225:487–494

    Google Scholar 

  • Takagaki Y, Radhakrishnan R, Gupta CM, Khorana HG (1983) The membrane-embedded segment of cytochrome b 5 as studied by cross-linking with photoactivable phospholipids. I. The transferable form. J Biol Chem 258:9128–9135

    Google Scholar 

  • Tanabe T, Takeshima H, Mikami A, Flockerzi V Takahashi H (1987) Primary structure of the receptor for calcium channel blockers from skeletal muscle. Nature 328:313–318

    Google Scholar 

  • Terwillinger TC, Weissman L, Eisenberg D (1982) The structure of melittin in the form I crystals and its implication for melittin's lytic and surface activities. Biophys J 27:353–361

    Google Scholar 

  • Traxler B, Boyd D, Beckwith J (1993) The topological analysis of integral membrane proteins. J Membr Biol 132:1–11

    Google Scholar 

  • Walker JE (1992) The NADH:ubiquinone oxidoreductase (complex I) of respiratory chains. Q Rev Biophys 25:253–324

    Google Scholar 

  • Weiss MS, Kreush A, Shiltz E, Nestel U, Welte W, Weckesser J, Schulz GE (1991) The structure of porin from Rhodobacter capsulatus at 1.8 Å resolution. FEBS Lett 280:379–382

    Google Scholar 

Download references

Author information

Author notes

  1. Mario Compiani

    Present address: Department of Chemical Sciences, University of Camerino, Camerino, Italy

Authors and Affiliations

  1. Laboratory of Biophysics, Department of Biology, University of Bologna, Via Irnerio 42, I-40126, Bologna, Italy

    Rita Casadio, Piero Fariselli, Chiara Taroni & Mario Compiani

Authors
  1. Rita Casadio
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Piero Fariselli
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chiara Taroni
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mario Compiani
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Correspondence to: R. Casadio

Rights and permissions

Reprints and permissions

About this article

Cite this article

Casadio, R., Fariselli, P., Taroni, C. et al. A predictor of transmembrane α-helix domains of proteins based on neural networks. Eur Biophys J 24, 165–178 (1996). https://doi.org/10.1007/BF00180274

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00180274

Key words

Search

Navigation