Fuzzy KNN for predicting membrane protein types from pseudo-amino acid composition
Journal of Theoretical BiologyPublished 29 September 2005
Hong‐Bin Shen, Jie Yang, Kuo‐Chen Chou
Citations175
SJR quartileQ2
SJR score0.53
SNIP0.71
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.
Abstract
Cell membranes are vitally important to the life of a cell. Although the basic structure of biological membrane is provided by the lipid bilayer, membrane proteins perform most of the specific functions. Membrane proteins are putatively classified into five different types. Identification of their types is currently an important topic in bioinformatics and proteomics. In this paper, based on the concept of representing protein samples in terms of their pseudo-amino acid composition, the fuzzy K-nearest neighbors (KNN) algorithm has been introduced to predict membrane protein types, and high success rates were observed. It is anticipated that, the current approach, which is based on a branch of fuzzy mathematics and represents a new strategy, may play an important complementary role to the existing methods in this area. The novel approach may also have notable impact on prediction of the other attributes, such as protein structural class, protein subcellular localization, and enzyme family class, among many others.
Keywords
Biochemistry, Genetics and Molecular Biology
IEEE Transactions on Information TheoryNearest neighbor pattern classification
16,134 Citations1967Thomas M. Cover, Peter E. Hart
The nearest neighbor decision rule assigns to an unclassified sample point the classification of the nearest of a set of previously classified points, so it may be said that half the classification information in an infinite sample set is contained in the nearest neighbor.
Molecular Cell Biology
5,646 Citations1986Harvey F. Lodish
IEEE Transactions on Systems Man and CyberneticsA fuzzy K-nearest neighbor algorithm
2,614 Citations1985James M. Keller, Michael Gray +1 more
The theory of fuzzy sets is introduced into the K-nearest neighbor technique to develop a fuzzy version of the algorithm, and three methods of assigning fuzzy memberships to the labeled samples are proposed.
Trends in Biochemical SciencesPSORT: a program for detecting sorting signals in proteins and predicting their subcellular localization
2,191 Citations1999Kenta Nakai, Kenta Nakai +1 more
Proteins Structure Function and BioinformaticsPrediction of protein cellular attributes using pseudo‐amino acid composition
1,967 Citations2001Kuo‐Chen Chou
A remarkable improvement in prediction quality has been observed by using the pseudo‐amino acid composition and its mathematical framework and biochemical implication may also have a notable impact on improving the prediction quality of other protein features.
Critical Reviews in Biochemistry and Molecular BiologyPrediction of Protein Structural Classes
1,062 Citations1995Kuo‐Chen Chou, Chun‐Ting Zhang
The very high success rate for both the training- set proteins and the testing-set proteins, which has been further validated by a simulated analysis and a jackknife analysis, indicates that it is possible to predict the structural class of a protein according to its amino acid composition if an ideal and complete database can be established.
BioinformaticsUsing amphiphilic pseudo amino acid composition to predict enzyme subfamily classes
1,028 Citations2004Kuo‐Chen Chou
The success rates obtained by the new predictor are all significantly higher than those by the previous predictors, which implies that the distribution of hydrophobicity and hydrophilicity of the amino acid residues along a protein chain plays a very important role to its structure and function.
Prediction of Protein Structure and the Principles of Protein Conformation
819 Citations1989Gerald D. Fasman
The prediction of protein structure and the principles of protein conformation is one of the literary work in this world in suitable to be reading material and this book will show the amazing benefits of reading a book.
Current Medicinal ChemistryStructural Bioinformatics and its Impact to Biomedical Science
602 Citations2004Kuo‐Chen Chou
In this review, three main strategies developed in structural bioinformatics, i.e., pure energetic approach, heuristic approach, and homology modeling approach, are briefly introduced and a series of demonstrations are presented to show how the structural bio informatics has been applied to timely derive the 3D structures of some functionally important proteins, helping to understand their action mechanisms and stimulating the course of drug discovery.
Journal of Biological ChemistryUsing Functional Domain Composition and Support Vector Machines for Prediction of Protein Subcellular Location
487 Citations2002Kuo‐Chen Chou, Yu‐Dong Cai
With such a novel representation for a protein, the support vector machine (SVM) algorithm is introduced for predicting protein subcellular location and high success rates are obtained by the self-consistency test, jackknife test, and independent dataset test.
The Journal of BiochemistryThe Folding Type of a Protein Is Relevant to the Amino Acid Composition
462 Citations1986Hiroshi Nakashima, Ken Nishikawa +1 more
The results show that amino acid compositions of the alpha, beta, and alpha/beta types are located in different regions in the composition space, thus allowing distinct of proteins depending on the folding types.
Proteins Structure Function and BioinformaticsA novel approach to predicting protein structural classes in a (20–1)‐D amino acid composition space
431 Citations1995Kuo‐Chen Chou
A method has been developed that makes allowance for taking into account the coupling effect among different amino acid components of a protein by a covariance matrix and a theorem is presented and proved in Appendix A that is instructive for understanding the novel method at a deeper level.
Journal of Molecular BiologyRelation between amino acid composition and cellular location of proteins 1 1Edited by F. E. Cohen
403 Citations1997Juan Cedano, Patrick Aloy +2 more
A correlation analysis of the amino acid composition and the cellular location of a protein is presented and a program (ProtLock) to predict the cellular where a protein has been designed is designed.
Protein Engineering Design and SelectionProtein subcellular location prediction
375 Citations1999Kuo‐Chen Chou, David W. Elrod
It is anticipated that the classification scheme and concept and also the prediction algorithm can expedite the functionality determination of new proteins, which can also be of use in the prioritization of genes and proteins identified by genomic efforts as potential molecular targets for drug design.
Proteins Structure Function and BioinformaticsSubcellular location prediction of apoptosis proteins
352 Citations2002Guo‐Ping Zhou, Kutbuddin S. Doctor
An attempt to identify the subcellular location of apoptosis proteins according to their sequences by means of the covariant discriminant function, which was established based on the Mahalanobis distance and Chou's invariance theorem.
Journal of Protein ChemistryAn Intriguing Controversy over Protein Structural Class Prediction
343 Citations1998Guo‐Ping Zhou
The results obtained by both self-consistency and jackknife tests indicate that the overall rates of correct prediction by the algorithm incorporating the coupling effect among different amino acid components are significantly higher than those by the algorithms without counting such an effect.
Biophysical JournalSupport Vector Machines for Predicting Membrane Protein Types by Using Functional Domain Composition
283 Citations2003Yu‐Dong Cai, Guo‐Ping Zhou +1 more
The Support Vector Machine algorithm, developed for predicting the membrane protein type based on the pseudo-amino acid composition that has incorporated quasi-sequence-order effect as recently proposed by K. C. Chou (2001), may become a very useful high-throughput tool in the area of bioinformatics and proteomics.
Proteins Structure Function and BioinformaticsSome insights into protein structural class prediction
270 Citations2001Guo‐Ping Zhou, Nuria Assa‐Munt
In this communication, a simple, rigorous derivation is provided to prove that the Bayes decision rule introduced recently for protein structural class prediction is completely the same as the earlier component‐coupled algorithm.
Proteins Structure Function and BioinformaticsPrediction of membrane protein types and subcellular locations
247 Citations1999Kuo‐Chen Chou, David W. Elrod
The results imply that the types of membrane proteins, as well as their cellular locations and other attributes, are closely correlated with their amino acid composition.
Journal of Biological ChemistryPredicting protein folding types by distance functions that make allowances for amino acid interactions.
213 Citations1994Kuo‐Chen Chou, C.T. Zhang
A new method has been developed in which the similarity between two protein molecules is based on the scale of Mahalanobis distance rather than on the ordinary intuitive geometric distances, such as Minkowski's distance and Euclidian distance, which can avoid the bias due to the limited number of testing proteins selected arbitrarily by different investigators.
Protein Engineering Design and SelectionWeighted-support vector machines for predicting membrane protein types based on pseudo-amino acid composition
184 Citations2004M. Wang, Jing Yang +3 more
The spectral analysis technique is introduced to represent the statistical sample of a protein and the weighted support vector machine (SVM) algorithm is applied, showing remarkable power in dealing with the bias caused by the situation when one subset in the training dataset contains many more samples than the other.
Biochemical and Biophysical Research CommunicationsPredicting protein structural class by functional domain composition
177 Citations2004Kuo‐Chen Chou, Yu‐Dong Cai
The jackknife cross-validation test indicates that using the functional domain composition to represent the sample of a protein for statistical prediction is very promising, and that the functional type of a domain is closely correlated with its structural class.
Journal of Chemical Information and ModelingPrediction of Membrane Protein Types by Incorporating Amphipathic Effects
175 Citations2005Kuo‐Chen Chou, Yu‐Dong Cai
The amphiphilic pseudo amino acid composition has been formulated that contains a series of hydrophobic and hydrophilic correlation factors that have been remarkably enhanced in identifying the types of membrane proteins, as demonstrated by the jackknife test and independent data set test.
Journal of Cellular BiochemistryPrediction and classification of protein subcellular location—sequence‐order effect and pseudo amino acid composition
174 Citations2003Kuo‐Chen Chou, Yu‐Dong Cai
A dataset has been established that allows the identification of protein sequences among the following 14 subcellular locations and the series‐mode pseudo‐amino‐acid‐composition has been introduced as a representation for a protein.
Prediction of Protein Structural Classes from Amino Acid Compositions
173 Citations1989Peter Y. Chou
Proteins are simple and yet quite complex biological macromolecules, and the link between the simple and the complex in that the protein’s conformation is coded in its amino acid sequence.
Journal of Proteome ResearchBioinformatical Analysis of G-Protein-Coupled Receptors
170 Citations2002Kuo‐Chen Chou, David W. Elrod
The results indicate that the types of G-protein-coupled receptors are predictable to a considerable accurate extent if a good training data set can be established for such a goal.
Amino AcidsUsing complexity measure factor to predict protein subcellular location
167 Citations2004Xuan Xiao, Shuai Shao +4 more
High success rates were obtained by both the jackknife cross-validation test and independent dataset test, suggesting that introduction of the concept of the complexity measure into prediction of protein subcellular location is quite promising, and might also hold a great potential as a useful vehicle for the other areas of molecular biology.
Protein Engineering Design and SelectionDomain structural class prediction
159 Citations1998K.-C. Chou, Gerald M. Maggiora
It is revealed through an analysis that the reasons for reaching the opposite conclusion are mainly due to misclassifying structural classes according to a conceptually incorrect rule, misapplying the component-coupled algorithm by ignoring some important factors and misrepresenting structural classes with statistically insignificant training subsets.
Journal of Theoretical BiologyApplication of SVM to predict membrane protein types
157 Citations2003Yu‐Dong Cai, Ricardo Pong‐Wong +2 more
Results obtained through re-substitution, jackknife, and independent data set tests, respectively, have indicated that the SVM approach is quite a promising one, suggesting that the covariant discriminant algorithm and SVM, if effectively complemented with each other, will become a powerful tool for predicting membrane protein types and the other protein attributes as well.
Journal of Theoretical BiologySLLE for predicting membrane protein types
147 Citations2004Meng Wang, Jie Yang +2 more
The Supervised Locally Linear Embedding technique for nonlinear dimensionality reduction is introduced and represents a new strategy to deal with the problems of protein attribute prediction, and hence may become a useful vehicle in the area of bioinformatics and proteomics.
Proteins Structure Function and BioinformaticsPredicting protein quaternary structure by pseudo amino acid composition
146 Citations2003Kuo‐Chen Chou, Yu‐Dong Cai
The pseudo amino acid composition originally proposed for improving the prediction of protein subcellular location was adopted, and results obtained have indicated that the current approach might be quite promising in dealing with such an extremely complicated and difficult problem.
Journal of Protein ChemistryPrediction of Membrane Protein Types Based on the Hydrophobic Index of Amino Acids
145 Citations2000Zhiping Feng, Chun‐Ting Zhang
The overall predictive accuracy is remarkably increased for the database of 2054 membrane proteins studied here and the predictive accuracy would be further increased for a larger and more class-balanced database.
Journal of Protein ChemistryApplication of Pseudo Amino Acid Composition for Predicting Protein Subcellular Location: Stochastic Signal Processing Approach
141 Citations2003Yuxi Pan, Zhizhou Zhang +4 more
The results thus obtained are quite encouraging and it is anticipated that the digital signal processing approach has been introduced to partially incorporate the sequence order effect and may serve as a useful vehicle for many other protein science areas as well.
Amino AcidsUsing pseudo amino acid composition to predict protein subcellular location: Approached with Lyapunov index, Bessel function, and Chebyshev filter
137 Citations2005Yinrui Gao, Shuai Shao +5 more
Three pseudo amino acid components are introduced via Lyapunov index, Bessel function, Chebyshev filter that can be more efficiently used to deal with the chaos and complexity in protein sequences, leading to a higher success rate in predicting protein subcellular location.
Journal of Proteome ResearchPrediction of G-Protein-Coupled Receptor Classes
129 Citations2005Kuo‐Chen Chou
The high success rate suggests that the CD predictor holds very high potential to become a useful tool for understanding the actions of drugs that target GPCRs and designing new medications with fewer side effects and greater efficacy.
Journal of Proteome ResearchPrediction of Enzyme Family Classes
124 Citations2003Kuo‐Chen Chou, David W. Elrod
In this study, a bioinformatical analysis was conducted for 2640 oxidoreductases classified into 16 subclasses according to the different types of substrates they act on during the catalytic process.
Biochemical and Biophysical Research CommunicationsInsights from modelling the 3D structure of the extracellular domain of α7 nicotinic acetylcholine receptor
122 Citations2004Kuo‐Chen Chou
Based on the crystal structure of acetylcholine-binding protein, the three-dimensional structures of the extracellular domain, or the ligand-binding domains, of the monomer, homodimer, and homopentamer of the alpha7 nicotinic acetyl choline receptor were derived.
Journal of Cellular BiochemistrySupport vector machines for prediction of protein subcellular location by incorporating quasi‐sequence‐order effect
113 Citations2001Yu‐Dong Cai, Xiaojun Liu +2 more
Support Vector Machine (SVM), which is one class of learning machines, was applied to predict the subcellular location of proteins by incorporating the quasi‐sequence‐order effect, with good results for self‐consistency and jackknife testing.
Proteins Structure Function and BioinformaticsPrediction and classification of domain structural classes
111 Citations1998Kou-Chen Chou, Weimin Liu +2 more
The results from both resubstitution tests and jackknife tests indicate that the overall rates of correct prediction by the algorithm incorporated with the coupling effect among different amino acid components are significantly higher than those by the algorithms without using such an effect.
Biochemical and Biophysical Research CommunicationsModelling extracellular domains of GABA-A receptors: subtypes 1, 2, 3, and 5
106 Citations2004Kuo‐Chen Chou
The predicted structures have further clarified some ambiguities that could not been uniquely determined by the existing experimental data, such as the directionality of the subunit arrangement in the heteropentameric structures.
BioinformaticsPredicting protein localization in budding Yeast
103 Citations2004Kuo‐Chen Chou, Yu‐Dong Cai
A new method has been developed that can be used to predict subcellular localization of proteins with multiplex location feature by hybridizing gene ontology, functional domain and pseudo amino acid composition approaches.
Protein Engineering Design and SelectionPrediction of protein secondary structure content
97 Citations1999Weimin Liu, Kou-Chen Chou
An algorithm was developed for predicting the content of protein secondary structure elements that was based on a new amino-acid-composition, in which the sequence coupling effects are explicitly included through a series of conditional probability elements.
Protein SciencePredicting enzyme family class in a hybridization space
91 Citations2004Kuo‐Chen Chou, Yu‐Dong Cai
By hybridizing the gene ontology and pseudo‐amino‐acid composition, a new method that is called GO‐PseAA predictor is introduced and operated in a hybridization space to develop an automated method that can be used to give fast answers to questions given the sequence of a protein.
Journal of Protein ChemistryUsing Pair-Coupled Amino Acid Composition to Predict Protein Secondary Structure Content
85 Citations1999Kuo‐Chen Chou
It is anticipated that the concept of the pair-coupled amino acid composition can be used to simplify the formulation of sequence coupling (or sequence order) effects and to study many other features of proteins as well.
Journal of Proteome ResearchInsights from Modeling Three-Dimensional Structures of the Human Potassium and Sodium Channels
73 Citations2004Kuo‐Chen Chou
Since both of the two ion channels are important targets for drug discovery, the 3D structures of their pore regions were developed and some important molecular biological mechanisms were discussed that may stimulate novel strategies for therapeutic treatment of the diseases related to ion channel disorders.
Journal of Theoretical BiologyA Joint Prediction of the Folding Types of 1490 Human Proteins from their Genetic Codons
68 Citations1993James J. Chou, Chun‐Ting Zhang
It has been demonstrated that the accuracy of prediction for the 1490 human proteins is at least 80% by examining the predicted results of some structurally known proteins with these methods, and it is shown that the folding type of a protein is strongly dependent on the ratio of frequency of base G in the first codon position with that in the secondcodon position.
Proteins Structure Function and BioinformaticsPrediction of protein cellular attributes using pseudo‐amino acid composition
66 Citations2001Kuo‐Chen Chou
European Journal of BiochemistryA correlation‐coefficient method to predicting protein‐structural classes from amino acid compositions
60 Citations1992Kuo‐Chen Chou, Chun‐Ting Zhang
Based on the maximum correlation-coefficient principle, a new formulation is proposed for predicting the structural class of a protein according to its amino acid composition, and results showed that the new method gave a considerably higher rate of correct prediction than any of the previous methods.
Protein Engineering Design and SelectionA study on the correlation of G-protein-coupled receptor types with amino acid composition
54 Citations2002David W. Elrod, Kuo‐Chen Chou
It has been found that different types of G-protein-coupled receptors are quite closely correlated with the amino acid composition, implying that the types of SOTA receptors are predictable to a considerably accurate extent if a good training data set can be established for that purpose.
Biochemical and Biophysical Research CommunicationsUsing GO-PseAA predictor to predict enzyme sub-class
44 Citations2004Kuo‐Chen Chou, Yu‐Dong Cai
It has been observed that, even for the much more stringent datasets in which none of the enzymes has 25% sequence identity to any others, the overall success rates are 73-95%, suggesting that the GO-PseAA predictor can catch the core features of the statistical samples concerned and may become a useful high throughput tool in proteomics and bioinformatics.