A neural network model for the prediction of membrane‐spanning amino acid sequences
Protein SciencePublished 1 September 1994Open access
Reinhard Lohmann, Gisbert Schneider, Dirk Behrens, Paul Wrede
Citations46
SJR quartileQ1
SJR score4.66
SNIP2.34
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The architecture and weights of an artificial neural network model that predicts putative transmembrane sequences have been developed and optimized by the algorithm of structure evolution and the resulting filter is able to classify membrane/non Membrane transition regions in sequences of integral human membrane proteins with high accuracy.
Abstract
The architecture and weights of an artificial neural network model that predicts putative transmembrane sequences have been developed and optimized by the algorithm of structure evolution. The resulting filter is able to classify membrane/nonmembrane transition regions in sequences of integral human membrane proteins with high accuracy. Similar results have been obtained for both training and test set data, indicating that the network has focused on general features of transmembrane sequences rather than specializing on the training data. Seven physicochemical amino acid properties have been used for sequence encoding. The predictions are compared to hydrophobicity plots.
Keywords
NeuroscienceBiochemistry, Genetics and Molecular Biology
Choice Reviews OnlineGenetic algorithms in search, optimization, and machine learning
49,278 Citations1989
This book brings together the computer techniques, mathematical tools, and research results that will enable both students and practitioners to apply genetic algorithms to problems in many fields.
The MIT Press eBooksAdaptation in Natural and Artificial Systems
35,568 Citations1992John H. Holland
Initially applying his concepts to simply defined artificial systems with limited numbers of parameters, Holland goes on to explore their use in the study of a wide range of complex, naturally occuring processes, concentrating on systems having multiple factors that interact in nonlinear ways.
Journal of Molecular BiologyA simple method for displaying the hydropathic character of a protein
23,075 Citations1982Jack Kyte, Russell F. Doolittle
A computer program that progressively evaluates the hydrophilicity and hydrophobicity of a protein along its amino acid sequence has been devised and its simplicity and its graphic nature make it a very useful tool for the evaluation of protein structures.
The MIT Press eBooksParallel Distributed Processing
15,227 Citations1986David E. Rumelhart, James L. McClelland +1 more
Medical Entomology and ZoologyGenetic Programming: On the Programming of Computers by Means of Natural Selection
13,257 Citations1992John R. Koza
This book discusses the evolution of architecture, primitive functions, terminals, sufficiency, and closure, and the role of representation and the lens effect in genetic programming.
Proceedings of the National Academy of SciencesPrediction of protein antigenic determinants from amino acid sequences.
3,740 Citations1981Thomas P. Hopp, Kenneth R. Woods
The method was developed using 12 proteins for which extensive immunochemical analysis has been carried out and subsequently was used to predict antigenic determinants for the following proteins, finding that the prediction success rate depended on averaging group length.
Journal of Molecular BiologySignal sequences
2,163 Citations1985Gunnar von Heijne
The results show subtle differences between eukaryotic and prokaryotic sequences, but the general impression of signal sequences as being highly variable is reinforced.
Nature New BiologyRhodopsin-like Protein from the Purple Membrane of Halobacterium halobium
2,141 Citations1971Dieter Oesterhelt, Walther Stoeckenius
It is shown that the purple colour is due to retinal bound to an opsin-like protein, the only protein present in this membrane fragment, which has been isolated in relatively pure form from Halobacterium halobium.
Evolutionary ComputationAn Overview of Evolutionary Algorithms for Parameter Optimization
2,110 Citations1993Thomas Bäck, Hans–Paul Schwefel
Three main streams of evolutionary algorithms (EAs), probabilistic optimization algorithms based on the model of natural evolution, are compared in this article: evolution strategies (ESs), evolutionary programming (EP), and genetic algorithms (GAs).
Annual Review of Biophysics and Biophysical ChemistryIDENTIFYING NONPOLAR TRANSBILAYER HELICES IN AMINO ACID SEQUENCES OF MEMBRANE PROTEINS
1,505 Citations1986Donald M. Engelman, T.A. Steitz +1 more
The next generation of autonomous vehicles will be able to communicate with each other in a much more efficient and efficient manner than the current generation of vehicles that can communicate solely with the human eye.
Journal of Molecular BiologyPredicting the secondary structure of globular proteins using neural network models
1,234 Citations1988Ning Qian, Terrence J. Sejnowski
It is concluded from computational experiments on real and artificial structures that no method based solely on local information in the protein sequence is likely to produce significantly better results for non-homologous proteins.
ScienceHydrophobicity of Amino Acid Residues in Globular Proteins
1,197 Citations1985George D. Rose, Ari Geselowitz +3 more
In the experiment reported in this article, proteins of known structure were used to measure the average area that each residue buries upon folding, and this characteristic quantity, theaverage area buried, is correlated with residue hydrophobicity.
Journal of Molecular BiologyThe nature of the accessible and buried surfaces in proteins
1,161 Citations1976Cyrus Chothia
The accessible surface areas have been calculated for the individual residues in 12 proteins, and for the extended chains, the secondary structures and tertiary structure of six proteins and it is shown that the accessible surface area of folded proteins is simply proportional to the two-thirds power of their molecular weight.
BiochemistryMembrane protein folding and oligomerization: the two-stage model
930 Citations1990J.-L. Popot, Donald M. Engelman
The view that the folding of many, perhaps most, integral membrane proteins can be considered as a two-stage process, where hydrophobic alpha-helices are established across the lipid bilayer and interact to form functional transmembrane structures is discussed.
Proceedings of the National Academy of SciencesThe hydrophobic moment detects periodicity in protein hydrophobicity.
905 Citations1984David Eisenberg, Robert M. Weiss +1 more
The observation that many protein sequences tend to form segments of maximum amphiphilicity suggests that segments of secondary structure fold at a hydrophobic surface, probably formed from other parts of the folding protein.
Biochimica et Biophysica Acta (BBA) - BiomembranesThe detection and classification of membrane-spanning proteins
839 Citations1985Petr Klein, Minoru Kanehisa +1 more
Discriminant analysis can be used to precisely classify membrane proteins as integral or peripheral and to estimate the odds that the classification is correct, and it is found that discrimination between integral and peripheral membrane proteins can be achieved with 99% reliability.
Proceedings of the National Academy of SciencesImproved prediction of protein secondary structure by use of sequence profiles and neural networks.
518 Citations1993Burkhard Rost, Chris Sander
A substantial increase in both the accuracy and quality of secondary-structure predictions, using a neural-network algorithm, and the predicted structures have a more realistic distribution of helix and strand segments.
Proceedings of the National Academy of SciencesAmphipathic analysis and possible formation of the ion channel in an acetylcholine receptor.
512 Citations1984Janet Finer-Moore, R. M. Stroud
Knowing the three-dimensional structure of acetylcholine receptors is consistent with features of the model proposed and provides some constraints and prediction of a consensus secondary structure based on this analysis and on an empirical prediction method leads to a testable hypothesis about how the ion channel is formed and might function.
Proceedings of the National Academy of SciencesIsolation and nucleotide sequence of the gene encoding human rhodopsin.
499 Citations1984Jeremy Nathans, David S. Hogness
Interestingly, those portions of the polypeptide chain predicted to form loops on the cytoplasmic face of rhodopsin are perfectly conserved between the human and bovine proteins.
Proceedings of the National Academy of SciencesAmino acid sequence of bacteriorhodopsin.
411 Citations1979H. Gobind Khorana, Gerhard E. Gerber +5 more
The complete primary structure of the purple membrane protein bacteriorhodopsin, which contains 248 amino acid residues, has been determined and the present sequence differs from that recently reported by Ovchinnikov and coworkers with respect to an additional tryptophan and several amino acid assignments.
Journal of Theoretical BiologyAmino acid properties and side-chain orientation in proteins: A cross correlation approach
232 Citations1975Daniel D. Jones
The magnitude of the cross correlations does not appear to be satisfactory for construction of a transfer function model for the prediction of general features of protein structure from amino acid sequences.
The EMBO JournalFolding patterns of porin and bacteriorhodopsin.
206 Citations1985Craig Don Paul, J.P. Rosenbusch
Application to a paradigm of hydrophobic membrane proteins, bacteriorhodopsin, reveals a pattern consistent with its alpha‐helical folding, and the postulated structure includes significantly more polar residues in the membrane domain than have been assumed previously, suggesting that there are also hydrogen bonding networks in bacteriorodopsin.
FEBS LettersProtein secondary structure and homology by neural networks The α‐helices in rhodopsin
177 Citations1988Henrik Bohr, J. Bohr +6 more
A new measure of homology between proteins is provided by the network approach, which thereby leads to quantification of the differences between the primary structures of proteins.
Biophysical JournalThe rational design of amino acid sequences by artificial neural networks and simulated molecular evolution: de novo design of an idealized leader peptidase cleavage site
167 Citations1994Gisbert Schneider, Paul Wrede
A method for the rational design of locally encoded amino acid sequence features using artificial neural networks and a technique for simulating molecular evolution has been developed and it is concluded that amino acid distances are context dependent.
Trends in Biochemical SciencesStructure predictions of membrane proteins are not that bad
162 Citations1990Fritz Jähnig
Protein Engineering Design and SelectionMembrane proteins: from sequence to structure
137 Citations1990Gunnar von Heijne, Colin Manoil
This review sketches the most important structural rules relating amino acid sequence to membrane insertion to fully folded molecule, and their use for prediction and protein-engineering purposes.
BiochemistryPrediction of structural and functional features of protein and nucleic acid sequences by artificial neural networks
134 Citations1992Jonathan D. Hirst, Michael J.E. Sternberg
The problems in nucleic acid analysis tackled by neural networks are the prediction of translation initiation sites in Escherichia coli, the recognition of splice junctions in human mRNA, and the Prediction of promoter sites in E. coli.
The EMBO JournalThe structure of the lactose permease derived from Raman spectroscopy and prediction methods.
132 Citations1985Horst Vogel, J. Keith Wright +1 more
The secondary structure of the lactose permease of Escherichia coli reconstituted in lipid membranes was determined by Raman spectroscopy using a method for structural prediction which accounts for amphipathic helices.
Trends in Biochemical SciencesThe prediction of transmembrane protein sequences and their conformation: an evaluation
114 Citations1990Gerald D. Fasman, William A. Gilbert
The prediction of transmembrane protein sequences can be performed with reasonable accuracy, however, the prediction of their conformation leaves room for significant improvement.
Proteins Structure Function and BioinformaticsA method for α‐helical integral membrane protein fold prediction
109 Citations1994William R. Taylor, D. T. Jones +1 more
This method provides the first completely automatic method that can proceed from a scan of the protein sequence databanks to a predicted three‐dimensional structure with no intervention required from the investigator.
Protein Engineering Design and SelectionModeling of transmembrane seven helix bundles
103 Citations1993Philippe Cronet, Chris Sander +1 more
A new approach is described for the modeling of transmembrane seven helix bundles based on statistically derived environmental preference parameters combined with experimentally determined features of the receptors to create a model for the human beta 2-adrenoreceptor.
Methods in enzymology on CD-ROM/Methods in enzymology[29] Artificial neural networks
94 Citations1992William T. Katz, John W. Snell +1 more
This chapter focuses on two classes of widely used artificial neural networks, the perceptron-back-propagation and the Hopfield–Boltzmann machine models, and explores the characteristics of a simple feedforward ANN model.
European Journal of BiochemistryA critical evaluation of the hydropathy profile of membrane proteins
89 Citations1990Mauro Degli Esposti, Massimo Crimi +1 more
New membrane-preference scales are introduced for categories of membrane proteins with different functions and a statistical analysis is carried out with several scales to verify the relative accuracy in the prediction of the transmembrane segments of polytopic membrane proteins.
Journal of Molecular EvolutionDevelopment of artificial neural filters for pattern recognition in protein sequences
50 Citations1993Gisbert Schneider, Paul Wrede
Four different artificial neural network architectures have been tested for their suitability to extract and predict sequence features and this network architecture appears to be most suited for the analysis of E. coli signal peptidase cleavage sites.
Biochemical and Biophysical Research CommunicationsThree novel molecular forms of biliary glycoprotein deduced from cDNA clones from a human leukocyte library
43 Citations1991Motomu Kuroki, Fumiko Arakawa +4 more
Three cDNA clones that encode three novel variants of biliary glycoprotein a (BGPa), a glycop protein belonging to the CEA gene family, were identified in a human leukocyte cDNA library.
Analytical BiochemistryData-sieving hydrophobicity plots
37 Citations1988Jenny Bangham
Data-sieving is described here as an alternative method for identifying domains within amino acid sequences that could be applied to other series data and, in multidimensions, to images in the same way as a median filter.
Methods in enzymology on CD-ROM/Methods in enzymology[10] Neural networks for protein structure prediction
34 Citations1991L. Howard Holley, Martin Karplus
This chapter describes the neural network method and reviews results obtained by applying the method to globular proteins, using a large number of identical units and a pattern of connections among these units to solve certain optimization problems.
The Journal of Membrane BiologyObservations concerning topology and locations of helix ends of membrane proteins of known structure
33 Citations1990Stephen H. White, Russell E. Jacobs
An “augmented” hydropathy plot analysis of the three membrane proteins of known structure is described, which suggests that side-chain hydrogen bonding with membrane components during folding may play a key role in insertion.
Angewandte Chemie International Edition in EnglishPrediction of the Secondary Structure of Proteins from the Amino Acid Sequence with Artificial Neural Networks
17 Citations1993Gisbert Schneider, Paul Wrede
Biological CyberneticsStructure evolution and incomplete induction
16 Citations1993Reinhard Lohmann
The effect of “overlearning” can be avoided by a learning procedure called “incomplete induction”, which fits best with the algorithm of structure evolution, which can perform a most effective search.
Lecture notes in computer scienceSelforganization by evolution strategy in visual systems
9 Citations1991Reinhard Lohmann
Within the system of parallel distributed pattern recognition being developed at the Department for Bionics and Evolution Techniques a certain feature is given by a local filter which is described by its structure and by some parameters contained in the structure and the result is a global value of that particular feature.