Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network

@article{Brusic1998PredictionOM,
  title={Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network},
  author={Vladimir Brusic and George B. Rudy and G. Honeyman and J{\"u}rgen Hammer and Leonard Charles Harrison},
  journal={Bioinformatics},
  year={1998},
  volume={14 2},
  pages={
          121-30
        }
}
MOTIVATION Prediction methods for identifying binding peptides could minimize the number of peptides required to be synthesized and assayed, and thereby facilitate the identification of potential T-cell epitopes. We developed a bioinformatic method for the prediction of peptide binding to MHC class II molecules. RESULTS Experimental binding data and expert knowledge of anchor positions and binding motifs were combined with an evolutionary algorithm (EA) and an artificial neural network (ANN… 
View on PubMed
academic.oup.com
317 Citations
Highly Influential Citations
21
Background Citations
62
Methods Citations
78
Results Citations
6

Figures and Tables from this paper

317 Citations

Citation Type

Citation Type

Fuzzy neural network-based prediction of the motif for MHC class II binding peptides.
Methods for Prediction of Peptide Binding to MHC Molecules: A Comparative Study
TLDR
The ability of bioinformatic methods to reliably predict MHC binding peptides, and thereby potential T-cell epitopes, has major implications for clinical immunology, particularly in the area of vaccine design.
Prediction of MHC class II binding peptides based on an iterative learning model
TLDR
An iterative supervised learning model is developed that offers an alternative approach to this important predictionproblem of MHC class II binding peptides and achieves an accuracy of prediction that is competitive compared to the advanced predictors.
Prediction of MHC class II-binding peptides based on sequential learning
TLDR
The SL-based prediction method is proposed, which chooses the modified sequential learning ahead masking (SLAM) model combined with incremental learning (FIL- SLAM) to predict MHC II-binding peptides.
NN-align. An artificial neural network-based alignment algorithm for MHC class II peptide binding prediction
TLDR
A novel artificial neural network-based method, NN-align, that allows for simultaneous identification of the MHC class II binding core and binding affinity and is competitive with the state-of-the-art M HC class II peptide binding prediction algorithms.
Predicting Class-II MHC Binding Peptide Using Global Representation of Peptides
  • Y. Niu
  • Computer Science, Biology
    2011 International Conference on Intelligent Computation and Bio-Medical Instrumentation
  • 2011
TLDR
This paper proposes a method that can utilize whole peptides to predict MHC-II binding affinity by using sequence-derived structure and physicochemical properties, and yields satisfying performance over existing methods by using full-length representation of the peptides.
Prediction Rule Generation of MHC Class I Binding Peptides Using ANN and GA
TLDR
Experimental results show that the method could generate new rules for MHC class I binding peptides prediction and includes rule extraction from a trained neural network and then enhancing the extracted rules by genetic evolution.
Generating Rules for Predicting MHC Class I Binding Peptide using ANN and Knowledge-based GA
TLDR
This paper demonstrates that a machine learning approach can be successfully applied to extract rules to predict MHC class I binding peptides and introduces a new method using a feed-forward neural network and genetic algorithm that outperforms other methods in both quantity and quality of the prediction rules.
Prediction of MHC II-binding peptides using rough set-based rule sets ensemble
TLDR
The Rule Sets ENsemble (RSEN) algorithm, which takes advantage of diverse attribute and attribute value reduction algorithms based on rough set (RS) theory, is proposed as the initial trial to acquire understandable rules along with enhancement of prediction performance.
A Bayesian regression approach to the prediction of MHC-II binding affinity
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 39 REFERENCES
Prediction of binding to MHC class I molecules.
Scheme for ranking potential HLA-A2 binding peptides based on independent binding of individual peptide side-chains.
TLDR
It is concluded that the side-chains of most nonamer peptides to the first approximation bind independently of one another to the HLA-A2 molecule.
Strategies for identifying and predicting islet autoantigen T-cell epitopes in insulin-dependent diabetes mellitus.
TLDR
A strategy to predict T-cell epitopes and applied it to tyrosine phosphatase IA-2, an autoantigen in IDDM, and HLA-DR4 showed high negative predictive values, indicating that this strategy of combining experimental results with computer modelling should lead to a significant reduction in the amount of blood and the number of peptides required to define T- cell epitopes in humans.
Application of Genetic Search in Derivation of Matrix Models of Peptide Binding to MHC Molecules
TLDR
A simulation study was performed to determine the minimum number of peptide samples required to derive matrices, given the pre-defined accuracy of the matrix model, and matrices for peptide binding to the human class I MHC molecules, HLA-B35 and -A24 were derived.
Prediction of major histocompatibility complex binding regions of protein antigens by sequence pattern analysis.
  • A. Sette, S. Buus, +5 authors H. Grey
  • Biology
    Proceedings of the National Academy of Sciences of the United States of America
  • 1989
TLDR
Two procedures devised to predict specifically the capacity of peptide molecules to interact with MHC class II molecules (IAd and IEd) are described and suggest that definition of such sequence "motifs" could be of general use in predicting potentially immunogenic peptide regions within proteins.
Prominent roles of secondary anchor residues in peptide binding to HLA-A24 human class I molecules.
TLDR
It was noted that certain crucial secondary interactions appear to be remarkably similar in the case of A24 and other HLA-A molecules previously analyzed, which may reflect contributions to binding affinity of relatively invariant residues located within the polymorphic pockets of the HLA binding groove.
Promiscuous and allele-specific anchors in HLA-DR-binding peptides
Structure of peptides associated with class I and class II MHC molecules.
TLDR
This review summarizes information and describes how it accounts for both the specificity and degeneracy of peptide binding and considers how the origin and structural features of peptides that have been isolated from MHC molecules have provided insight into the pathways through which the peptides are produced.
Specificity and promiscuity among naturally processed peptides bound to HLA-DR alleles
TLDR
Most of the peptides derived from endogenous proteins that intersect the endocytic/class II pathway, even though class II molecules are thought to function mainly in the presentation of exogenous foreign peptide antigens, were derived from major histocompatibility complex-related molecules.
Fine tuning of peptide binding to HLA-B*3501 molecules by nonanchor residues.
TLDR
It was demonstrated that high affinity peptide binding requires more than one favorable position of positions 3, 4, and 7, and it was found that bulky aromatic residues and basic residues with a positively charged side chain at position 8 decreased the binding affinity.
...
1
2
3
4
...