Structure-based prediction of MHC-peptide association: algorithm comparison and application to cancer vaccine design

Peptide vaccination for cancer immunotherapy requires identification of peptide epitopes derived from antigenic proteins associated with the tumor. Such peptides can bind to MHC proteins (MHC molecules) on the tumor-cell surface, with the potential to initiate a host immune response against the tumor. Computer prediction of peptide epitopes can be based on known motifs for peptide sequences that bind to a certain MHC molecule, on algorithms using experimental data as a training set, or on structure-based approaches. We have developed an algorithm, which we refer to as PePSSI, for flexible structural prediction of peptide binding to MHC molecules. Here, we have applied this algorithm to identify peptide epitopes (of nine amino acids, the common length) from the sequence of the cancer-testis antigen KU-CT-1, based on the potential of these peptides to bind to the human MHC molecule HLA-A2. We compared the PePSSI predictions with those of other algorithms and found that several peptides predicted to be strong HLA-A2 binders by PePSSI were similarly predicted by another structure-based algorithm, PREDEP. The results show how structure-based prediction can identify potential peptide epitopes without known binding motifs and suggest that side chain orientation in binding peptides may be obtained using PePSSI.     

A Bayesian regression approach to the prediction of MHC-II binding affinity

Peptide-major histocompatibility complex (MHC) binding is an important prerequisite event and has immediate consequences to immune response. Those peptides binding to MHC molecules can activate the T-cell immunity, and they are useful for understanding the immune mechanism and developing vaccines for diseases. Recently, researchers are interested in making prediction about binding affinity instead of differentiating the peptides as binder or non-binder. In this paper, we use sparse Bayesian regression algorithm proposed by Tipping [M.E. Tipping, Sparse Bayesian learning and the relevance vector machine. J. Mach. Learn. Res. (2001)] to derive position-specific scoring matrices from allele-related peptides, and develop the models allowing for the prediction of MHC-II binding affinity. We explore the peptide length and peptide flanking residue length's impact on binding affinity, and incorporate these factors into our models to enhance prediction performance. When applied to the datasets from AntiJen database and IEDB database, our method produces better performances than several popular quantitative methods.     

In silico design of knowledge-based Plasmodium falciparum epitope ensemble vaccines

Malaria is a global health burden, and a major cause of mortality and morbidity in Africa. Here we designed a putative malaria epitope ensemble vaccine by selecting an optimal set of pathogen epitopes. From the IEDB database, 584 experimentally-verified CD8+ epitopes and 483 experimentally-verified CD4+ epitopes were collected; 89% of which were found in 8 proteins. Using the PVS server, highly conserved epitopes were identified from variability analysis of multiple alignments of Plasmodium falciparum protein sequences. The allele-dependent binding of epitopes was then assessed using IEDB analysis tools, from which the population protection coverage of single and combined epitopes was estimated. Ten conserved epitopes from four well-studied antigens were found to have a coverage of 97.9% of the world population: 7 CD8+ T cell epitopes (LLMDCSGSI, FLIFFDLFLV, LLACAGLAYK, TPYAGEPAPF, LLACAGLAY, SLKKNSRSL, and NEVVVKEEY) and 3 CD4+ T cell epitopes (MRKLAILSVSSFLFV, KSKYKLATSVLAGLL and GLAYKFVVPGAATPYE). The addition of four heteroclitic peptides − single point mutated epitopes − increased HLA binding affinity and raised the predicted world population coverage above 99%.     

Quantitative prediction of MHC-II peptide binding affinity using relevance vector machine

Peptide-MHC binding is an important prerequisite event and has immediate consequences to immune response. Those peptides binding to MHC molecules can activate the T-cell immunity, and they are useful for understanding the immune mechanism and developing vaccines for diseases. Accurate prediction of the binding between peptides and MHC-II molecules has long been a challenge in bioinformatics. Recently, instead of differentiating peptides as binder or non-binder, researchers are more interested in making predictions directly on peptide binding affinities. In this paper, we investigate the use of relevance vector machine to quantitatively predict the binding affinities between MHC-II molecules and peptides. In our scheme, a new encoding scheme is used to generate the input vectors, and then by using relevance vector machine we develop the prediction models on the basis of binding cores, which are recognized in an iterative self-consistent way. When applied to three MHC-II molecules DRB1*0101, DRB1*0401 and DRB1*1501, our method produces consistently better performance than several popular quantitative methods, in terms of cross-validated squared error, cross-validated correlation coefficient, and area under ROC curve. All evidences indicate that our method is an effective tool for MHC-II binding affinity prediction.     

Analysis of the HLA class I associated peptide repertoire in a hepatocellular carcinoma cell line reveals tumor-specific peptides as putative targets for immunotherapy

HLA class I molecules present peptides on the cell surface to CD8(+) T cells. The repertoire of peptides that associate to class I molecules represents the cellular proteome. Therefore, cells expressing different proteomes could generate different class I-associated peptide repertoires. A large number of peptides have been sequenced from HLA class I alleles, mostly from lymphoid cells. On the other hand, T cell immunotherapy is a goal in the fight against cancer, but the identification of T cell epitopes is a laborious task. Proteomic techniques allow the definition of putative T cell epitopes by the identification of HLA natural ligands in tumor cells. In this study, we have compared the HLA class I-associated peptide repertoire from the hepatocellular carcinoma (HCC) cell line SK-Hep-1 with that previously described from lymphoid cells. The analysis of the peptide pool confirmed that, as expected, the peptides from SK-Hep-1 derive from proteins localized in the same compartments as in lymphoid cells. Within this pool, we have identified 12 HLA class I peptides derived from HCC-related proteins. This confirms that tumor cell lines could be a good source of tumor associated antigens to be used, together with MS, to define putative epitopes for cytotoxic T cells from cancer patients.     

Quantitative online prediction of peptide binding to the major histocompatibility complex

With its implications for vaccine discovery, the accurate prediction of T cell epitopes is one of the key aspirations of computational vaccinology. We have developed a robust multivariate statistical method, based on partial least squares, for the quantitative prediction of peptide binding to major histocompatibility complexes (MHC), the principal checkpoint on the antigen presentation pathway. As a service to the immunobiology community, we have made a Perl implementation of the method available via a World Wide Web server. We call this server MHCPred. Access to the server is freely available from the URL: http://www.jenner.ac.uk/MHCPred. We have exemplified our method with a model for peptides binding to the common human MHC molecule HLA-B*3501.     

Development of predictive selection and placement tests for personnel evaluation

There are a number of similar approaches for developing useful occupational selection and placement tests. The primary concern is that the tests be predictive of occupational requirements. This pape discusses an approach that emphasises the predictive criterion and uses a case study involving the development of occupational physical selection standards to illustrate the salient points. The following steps are discussed: (1) identification of the occupational requirements; (2) identification of the candidate tests; (3) establishment of predictive relationships between tasks representing the occupational requirements and the candidate tests; (4) determination of useful performance standards on a selected test; and (5) validation of the proposed performace standards. For this case study, it is concluded that performance standards on a lifting test could be developed for predicting the performance of two lifting tasks, using this approach.     

Configuring and enhancing measurement systems for damage identification

Engineers often decide to measure structures upon signs of damage to determine its extent and its location. Measurement locations, sensor types and numbers of sensors are selected based on judgment and experience. Rational and systematic methods for evaluating structural performance can help make better decisions. This paper proposes strategies for supporting two measurement tasks related to structural health monitoring - (1) installing an initial measurement system and (2) enhancing measurement systems for subsequent measurements once data interpretation has occurred. The strategies are based on previous research into system identification using multiple models. A global optimization approach is used to design the initial measurement system. Then a greedy strategy is used to select measurement locations with maximum entropy among candidate model predictions. Two bridges are used to illustrate the proposed methodology. First, a railway truss bridge in Zangenberg, Germany, is examined. For illustration purposes, the model space is reduced by assuming only a few types of possible damage in the truss bridge. The approach is then applied to the Schwandbach bridge in Switzerland, where a broad set of damage scenarios is evaluated. For the truss bridge, the approach correctly identifies the damage that represents the behaviour of the structure. For the Schwandbach bridge, the approach is able to significantly reduce the number of candidate models. Values of candidate model parameters are also useful for planning inspection and eventual repair.     

A new encoding technique for peptide classification

Research on peptide classification problems has focused mainly on the study of different encodings and the application of several classification algorithms to achieve improved prediction accuracies. The main drawback of the literature is the lack of an extensive comparison among the available encoding methods on a wide range of classification problems. This paper addresses the fundamental issue of which peptide encoding promises the best results for machine learning classifiers. Two novel encoding methods based on physicochemical properties of the amino acids are proposed and an extensive comparison with several standard encoding methods is performed on three different classification problems (HIV-protease, recognition of T-cell epitopes and prediction of peptides that bind human leukocyte antigens). The experimental results demonstrate the effectiveness of the new encodings and show that the frequently used orthonormal encoding is inferior compared to other methods.     

Application of a multiple-model adaptive filter method to inertial navigation systems

The multiple-model adaptive filter (MMAF) method is applied to the estimation of error states of inertial navigation systems (INS). Monte Carlo simulations are performed to evaluate the sensitivity of several MMAFs to uncertainties in flight condition, where a Doppler radar receiver or Omega receiver is considered as the reference information source. It is shown that the MMAF method is useful not only for a case where the actual system model is included within the candidate models, but also for a case where the actual system model is not included within the candidate models.     

Data mining techniques for improving the reliability of system identification

A system identification methodology that makes use of data mining techniques to improve the reliability of identification is presented in this paper. An important aspect of the methodology is the generation of a population of candidate models. Indications of the reliability of system identification are obtained through an examination of the characteristics of the population. Data mining techniques bring out model characteristics that are important. The methodology has been applied to several engineering systems.     

Discrete-Event Simulation Models of Plasmodium falciparum Malaria

We develop discrete-event simulation models using a single "timeline" variable to represent the Plasmodium falciparum lifecycle in individual hosts and vectors within interacting host and vector populations. Where they are comparable our conclusions regarding the relative importance of vector mortality and the durations of host immunity and parasite development are congruent with those of classic differential-equation models of malaria, epidemiology. However, our results also imply that in regions with intense perennial transmission, the influence of mosquito mortality on malaria prevalence in humans may be rivaled by that of the duration of host infectivity.     

Modelling of HLA-DQ2 and its interaction with gluten peptides to explain molecular recognition in celiac disease

Celiac disease (CD) is sustained by abnormal intestinal mucosal T-cell response to gluten and it is strongly associated with HLA class II molecules encoded by DQA1*0501/DQB1*02 (DQ2) or DQA1*03/DQB1*0302 (DQ8). The in vitro stimulatory activity of gliadin increases after treatment with tissue transglutaminase (tTG) which catalyses the deamidation of specific residues of glutamine to glutamate that can serve as anchors for binding to DQ2 as well as to DQ8 molecules. We modelled the three-dimensional structure of the DQ2 dimer protein, the most frequent in celiac patients, by using a homology modelling strategy, and deposited the model in the Protein Data Bank (PDB). Then, we simulated the interactions of DQ2 with different gluten peptides and the deamidation of specific peptide glutamines in the known p4, p6, p7 and p9 anchor positions, as well as in p1 and p5 positions, and other substitutions for which experimental effects on binding are available by previous experimental studies. By evaluating the energy of interaction and the H-bond interactions, we were able to distinguish what substitutions improve the interaction peptide-DQ2, in agreement with previously published experimental data. By analysing the peptide-DQ2 complex at the atom level, we observed that these glutamate side chains can interact with specific positively charged amino acids of DQ2, absent in other HLA alleles not related to celiac disease. The simulation was also extended to other peptides, related to celiac disease but for which no experimental data exists about the effects of glutamine deamidation. Our results give an interpretation at the molecular level of previously reported binding experimental data and open a new window to gain further insights about peptide recognition in celiac disease.     

Peptide classification using optimal and information theoretic syntactic modeling

We consider the problem of classifying peptides using the information residing in their syntactic representations. This problem, which has been studied for more than a decade, has typically been investigated using distance-based metrics that involve the edit operations required in the peptide comparisons. In this paper, we shall demonstrate that the Optimal and Information Theoretic (OIT) model of Oommen and Kashyap [22] applicable for syntactic pattern recognition can be used to tackle peptide classification problem. We advocate that one can model the differences between compared strings as a mutation model consisting of random substitutions, insertions and deletions obeying the OIT model. Thus, in this paper, we show that the probability measure obtained from the OIT model can be perceived as a sequence similarity metric, using which a support vector machine (SVM)-based peptide classifier can be devised. The classifier, which we have built has been tested for eight different substitution matrices and for two different data sets, namely, the HIV-1 Protease cleavage sites and the T-cell epitopes. The results show that the OIT model performs significantly better than the one which uses a Needleman-Wunsch sequence alignment score, it is less sensitive to the substitution matrix than the other methods compared, and that when combined with a SVM, is among the best peptide classification methods available.     

Conformational and energy evaluations of novel peptides binding to dengue virus envelope protein

Effective novel peptide inhibitors which targeted the domain III of the dengue envelope (E) protein by blocking dengue virus (DENV) entry into target cells, were identified. The binding affinities of these peptides towards E-protein were evaluated by using a combination of docking and explicit solvent molecular dynamics (MD) simulation methods. The interactions of these complexes were further investigated by using the Molecular Mechanics-Poisson Boltzmann Surface Area (MMPBSA) and Molecular Mechanics Generalized Born Surface Area (MMGBSA) methods. Free energy calculations of the peptides interacting with the E-protein demonstrated that van der Waals (vdW) and electrostatic interactions were the main driving forces stabilizing the complexes. Interestingly, calculated binding free energies showed good agreement with the experimental dissociation constant (K_d) values. Our results also demonstrated that specific residues might play a crucial role in the effective binding interactions. Thus, this study has demonstrated that a combination of docking and molecular dynamics simulations can accelerate the identification process of peptides as potential inhibitors of dengue virus entry into host cells.     

Regressor and structure selection in NARX models using a structured ANOVA approach

Regressor selection can be viewed as the first step in the system identification process. The benefits of finding good regressors before estimating complex models are especially clear for nonlinear systems, where the class of possible models is huge. In this article, a structured way of using the tool analysis of variance (ANOVA) is presented and used for NARX model (nonlinear autoregressive model with exogenous input) identification with many candidate regressors.     

Selecting informative data for developing peptide-MHC binding predictors using a query by committee approach

Strategies for selecting informative data points for training prediction algorithms are important, particularly when data points are difficult and costly to obtain. A Query by Committee (QBC) training strategy for selecting new data points uses the disagreement between a committee of different algorithms to suggest new data points, which most rationally complement existing data, that is, they are the most informative data points. In order to evaluate this QBC approach on a real-world problem, we compared strategies for selecting new data points. We trained neural network algorithms to obtain methods to predict the binding affinity of peptides binding to the MHC class I molecule, HLA-A2. We show that the QBC strategy leads to a higher performance than a baseline strategy where new data points are selected at random from a pool of available data. Most peptides bind HLA-A2 with a low affinity, and as expected using a strategy of selecting peptides that are predicted to have high binding affinities also lead to more accurate predictors than the base line strategy. The QBC value is shown to correlate with the measured binding affinity. This demonstrates that the different predictors can easily learn if a peptide will fail to bind, but often conflict in predicting if a peptide binds. Using a carefully constructed computational setup, we demonstrate that selecting peptides with a high QBC performs better than low QBC peptides independently from binding affinity. When predictors are trained on a very limited set of data they cannot be expected to disagree in a meaningful way and we find a data limit below which the QBC strategy fails. Finally, it should be noted that data selection strategies similar to those used here might be of use in other settings in which generation of more data is a costly process.     

Ole e 13 is the unique food allergen in olive: Structure-functional,substrates docking,and molecular allergenicity comparative analysis

Thaumatin-like proteins (TLPs) are enzymes with important functions in pathogens defense and in the response to biotic and abiotic stresses. Last identified olive allergen (Ole e 13) is a TLP, which may also importantly contribute to food allergy and cross-allergenicity to pollen allergen proteins. The goals of this study are the characterization of the structural-functionality of Ole e 13 with a focus in its catalytic mechanism, and its molecular allergenicity by extensive analysis using different molecular computer-aided approaches covering a) functional-regulatory motifs, b) comparative study of linear sequence, 2-D and 3D structural homology modeling, c) molecular docking with two different β-D-glucans, d) conservational and evolutionary analysis, e) catalytic mechanism modeling, and f) IgE-binding, B- and T-cell epitopes identification and comparison to other allergenic TLPs.Sequence comparison, structure-based features, and phylogenetic analysis identified Ole e 13 as a thaumatin-like protein. 3D structural characterization revealed a conserved overall folding among plants TLPs, with mayor differences in the acidic (catalytic) cleft. Molecular docking analysis using two β-(1,3)-glucans allowed to identify fundamental residues involved in the endo-1,3-β-glucanase activity, and defining E84 as one of the conserved residues of the TLPs responsible of the nucleophilic attack to initiate the enzymatic reaction and D107 as proton donor, thus proposing a catalytic mechanism for Ole e 13. Identification of IgE-binding, B- and T-cell epitopes may help designing strategies to improve diagnosis and immunotherapy to food allergy and cross-allergenic pollen TLPs.