Epitope peptides and immunotherapy

Allergic diseases affect atopic individuals, who synthesize specific Immunoglobulins E (IgE) to environmental allergens, usually proteins or glycoproteins. These allergens include grass and tree pollens, indoor allergens such as house dust mites and animal dander, and various foods. Because allergen-specific IgE antibodies are the main effector molecules in the immune response to allergens, many studies have focused on the identification of IgE-binding epitopes (called B cell epitopes), specific and minimum regions of allergen molecules that binds to IgE. Our initial studies have provided evidence that only four to five amino acid residues are enough to comprise an epitope, since pentapeptide QQQPP in wheat glutenin is minimally required for IgE binding. Afterwards, various kinds of B cell epitope structures have been clarified. Such information contributes greatly not only to the elucidation of the etiology of allergy, but also to the development of strategies for the treatment and prevention of allergy. Allergen-specific T cells also play an important role in allergy and are obvious targets for intervention in the disease. Currently, the principle approach is to modify B cell epitopes to prevent IgE binding while preserving T cell epitopes to retain the capacity for immunotherapy. There is mounting evidence that the administration of peptide(s) containing immunodominant T cell epitopes from an allergen can induce T cell nonresponsiveness (immunotherapy). There have been clinical studies of peptide immunotherapy performed, the most promising being for bee venom sensitivity. Clinical trials of immunotherapy for cat allergen peptide have also received attention. An alternative strategy for the generation of an effective but hypoallergenic preparation for immunotherapy is to modify T cell epitope peptides by, for example, single amino acid substitution. In this article, I will present an overview of epitopes related to allergic disease, particularly stress on allergen specific immunotherapy. In addition, our ongoing study of immunotherapy by 'eating' T cell epitope peptides will be described. Eating T cell epitope peptides as food provides a more practical way of inducing tolerance and a challenge to prevent allergy in daily life, as opposed to therapy by ingesting peptides as medicine.     

A Fully Synthetic Four‐Component Antitumor Vaccine Consisting of a Mucin Glycopeptide Antigen Combined with Three Different T‐Helper‐Cell Epitopes

In a new concept of fully synthetic vaccines, the role of T‐helper cells is emphasized. Here, a synthetic antitumor vaccine consisting of a diglycosylated tumor‐associated MUC1 glycopeptide as the B‐cell epitope was covalently cross‐linked with three different T‐helper‐cell epitopes via squaric acid ligation of two linear (glyco)peptides. In mice this four‐component vaccine administered without external immune‐stimulating promoters elicit titers of MUC1‐specific antibodies that were about eight times higher than those induced by a vaccine containing only one T‐helper‐cell epitope. The promising results indicate that multiple activation of different T‐helper cells is useful for applications in which increased immunogenicity is required. In personalized medicine, in particular, this flexible construction of a vaccine can serve as a role model, for example, when T‐helper‐cell epitopes are needed that match human leukocyte antigens (HLA) in different patients.     

Reduction of the IgE-binding ability and maintenance of immunogenicity of gamma-irradiated Dermatophagoides farinae

House dust mites, Dermatophagoides farinae (DF) and Dermatophagoides pteronyssinus, are major allergens in the most common indoor allergen and are important risk factor for asthma. The modified antigen has been studied to treat allergic disorder. This study was carried out to measure possibility of modified allergen using gamma irradiation to treat allergy such as asthma. DF solutions (2 mg/ml) as target allergen were irradiated with Co-60 at 50 and 100 kGy. Conformational alternation of irradiated DF was observed by sodium dodecyl sulfate polyacrylamide gel electrophoresis (SDS-PAGE). Levels of anti-irradiated DF mouse IgGs (sub-isotypes) against intact DF were measured similar to that of anti-intact DF IgGs. The binding abilities of house dust mite-allergic patients’ IgE were reduced depending on radiation dose, and irradiation could inhibit the binding ability of patients’ IgE more than 40%. This study has shown that the binding ability of IgE was reduced by conformational alteration by irradiation and the irradiated DF had epitopes capable to induce immunogeniciy.     

Characterization and epitope mapping of two monoclonal antibodies against human CD99

CD99 plays a critical role in the diapedesis of monocytes, T cell differentiation, and the transport of MHC molecules. Engagement of CD99 by agonistic monoclonal antibodies has been reported to trigger multifactorial events including T cell activation as well as cell-cell adhesion during hematopoietic cell differentiation. In this study, to identify the functional domains participating in the cellular events, we mapped the epitopes of CD99, which are recognized by two agonistic CD99 monoclonal antibodies, DN16 and YG32. Using recombinant fusion proteins of GST with whole or parts of CD99, we found that both antibodies interact with CD99 molecules independently of sugar moieties. DN16 mAb detected a linear epitope located in the amino terminal region of CD99 while YG32 mAb bound another linear epitope in the center of the extracellular domain. To confirm that the identified epitopes of CD99 are actually recognized by the two mAbs, we showed the presence of physical interaction between the mAbs and the fusion proteins or synthetic peptides containing the corresponding epitopes using surface plasmon resonance analyses. The dissociation constants of DN16 and YG32 mAbs for the antigen were calculated as 1.27 x 10(-7) and 7.08 x 10(-9) M, respectively. These studies will help understand the functional domains and the subsequent signaling mechanism of CD99.     

Potential of peptides selected from random phage-displayed libraries to mimic conformational epitopes: a study on scorpion toxin Cn2 and the neutralizing monoclonal antibody BCF2

Many conformational epitopes cannot be mapped by the use of a phage display approach due to the lack of amino acid similarity with the selected peptides. Exploring the potential of the method, we selected mimotopes of the discontinuous, highly conformational epitope of scorpion neurotoxin Cn2, whose 3D structure is known, using its generic neutralizing monoclonal antibody BCF2. With an exhaustive selection procedure, we isolated from a 12-mer phage library a large collection of mimotopes that reproduce the antigenic and immunogenic specificity of the Cn2-epitope. The selected peptides presented three sequence motifs, the most abundant of which, RD(N)XXGF, appeared in 15 different sequence contexts displayed by 97 out of 206 clones. In the most reactive mimotope, displayed by 24 (25%) clones, the motif was flanked by two Cys residues allowing the adoption of a cyclic conformation. Motifs QL(H,M)L(M) and (S/T)WHLP were selected with less efficiency. Comparison of the motifs with the primary and three-dimensional structure of Cn2 as well as with a model of the Cn2-BCF2(Fv) complex suggests that RD(N)XXGF, which does not share sequence similarity with the epitope, mimics its central structural element, turn 7-11, by using an alternative amino acid combination nevertheless keeping the nature of its interactions with BCF2. The QL(H,M)L(M) is assumed to mimic the hydrophobic part of the epitope. The principles of the conformational mimicry by phage-displayed peptides are discussed.     

非对称流场流分离-超高效液相色谱-串联四极杆飞行时间质谱用于过敏原蛋白表位筛选

应用非对称流场流分离（AF4）技术结合超高效液相色谱-四极杆飞行时间质谱（UPLC-QTOF-MS）对过敏原蛋白表位进行筛选。将选择的过敏原蛋白（虾原肌球蛋白，TM）酶解后经UPLC-QTOF-MS分析，建立蛋白质肽谱。将TM酶解后的肽段与免疫球蛋白E混合孵育30 min，孵育过程中含有抗原表位的特异性肽段与免疫球蛋白E（IgE）结合，未结合的肽段仍留在溶液中。将孵育后的溶液进行AF4分离，已结合的肽段随IgE一起由出口流出，未结合的肽段透过分离通道膜，滤出至废液。收集出口流出的组分进行UPLC-QTOF-MS分析，与蛋白质肽谱匹配，找到特异性肽段，进而检测抗原表位。本研究扩展了非对称流场流分离技术的应用，对过敏原蛋白表位的检测进行了初步探索，为过敏原蛋白表位的研究提供了一种新的研究策略。     

Fully Synthetic Self‐Adjuvanting Thioether‐Conjugated Glycopeptide?Lipopeptide Antitumor Vaccines for the Induction of Complement‐Dependent Cytotoxicity against Tumor Cells

Glycopeptides of tumor‐associated mucin MUC1 are promising target structures for the development of antitumor vaccines. Because these endogenous structures were weakly immunogenic, they were coupled to immune‐response‐stimulating T‐cell epitopes and the Pam₃Cys lipopeptide to induce strong immune responses in mice. A new thioether‐ligation method for the synthesis of two‐ and three‐component vaccines that contain MUC1 glycopeptides as the B‐cell epitopes, a T‐cell epitope peptide, and the Pam₃CSK₄ lipopeptide is described. The resulting fully synthetic vaccines were used for the vaccination of mice, either in a liposome with Freund′s adjuvant or in aqueous PBS buffer. The three‐component vaccines that contained the Tetanus Toxoid P2 T‐cell epitope peptide induced strong immune responses, even when administered just in PBS. By activation of the complement‐dependent cytotoxicity (CDC) complex, the antisera induced the killing of tumor cells.     

Designing an efficient multi-epitope peptide vaccine against Vibrio cholerae via combined immunoinformatics and protein interaction based approaches

Cholera continues to be a major global health concern. Among different Vibrio cholerae strains, only O1 and O139 cause acute diarrheal diseases that are related to epidemic and pandemic outbreaks. The currently available cholera vaccines are mainly lived and attenuated vaccines consisting of V. cholerae virulence factors such as toxin-coregulated pili (TCP), outer membrane proteins (Omps), and nontoxic cholera toxin B subunit (CTB). Nowadays, there is a great interest in designing an efficient epitope vaccine against cholera. Epitope vaccines consisting of immunodominant epitopes and adjuvant molecules enhance the possibility of inciting potent protective immunity. In this study, V. cholerae protective antigens (OmpW, OmpU, TcpA and TcpF) and the CTB, which is broadly used as an immunostimulatory adjuvant, were analyzed using different bioinformatics and immunoinformatics tools. The common regions between promiscuous epitopes, binding to various HLA-II supertype alleles, and B-cell epitopes were defined based upon the aforementioned protective antigens. The ultimately selected epitopes and CTB adjuvant were fused together using proper GPGPG linkers to enhance vaccine immunogenicity. A three-dimensional model of the thus constructed vaccine was generated using I-TASSER. The model was structurally validated using the ProSA-web error-detection software and the Ramachandran plot. The validation results indicated that the initial 3D model needed refinement. Subsequently, a high-quality model obtained after various refinement cycles was used for defining conformational B-cell epitopes. Several linear and conformational B-cell epitopes were determined within the epitope vaccine, suggesting likely antibody triggering features of our designed vaccine. Next, molecular docking was performed between the 3D vaccine model and the tertiary structure of the toll like receptor 2 (TLR2). To gain further insight into the interaction between vaccine and TLR2, molecular dynamics simulation was performed, corroborating stable vaccine-TLR2 binding. In sum, the results suggest that our designed epitope vaccine could incite robust long-term protective immunity against V. cholera.     

Predicting class I major histocompatibility complex (MHC) binders using multivariate statistics: comparison of discriminant analysis and multiple linear regression

The accurate in silico identification of T-cell epitopes is a critical step in the development of peptide-based vaccines, reagents, and diagnostics. It has a direct impact on the success of subsequent experimental work. Epitopes arise as a consequence of complex proteolytic processing within the cell. Prior to being recognized by T cells, an epitope is presented on the cell surface as a complex with a major histocompatibility complex (MHC) protein. A prerequisite therefore for T-cell recognition is that an epitope is also a good MHC binder. Thus, T-cell epitope prediction overlaps strongly with the prediction of MHC binding. In the present study, we compare discriminant analysis and multiple linear regression as algorithmic engines for the definition of quantitative matrices for binding affinity prediction. We apply these methods to peptides which bind the well-studied human MHC allele HLA-A*0201. A matrix which results from combining results of the two methods proved powerfully predictive under cross-validation. The new matrix was also tested on an external set of 160 binders to HLA-A*0201; it was able to recognize 135 (84%) of them.     

Immunogenicity of Foot-and-Mouth Disease Virus Dendrimer Peptides: Need for a T-Cell Epitope and Ability to Elicit Heterotypic Responses

An approach based on a dendrimer display of B- and T-cell epitopes relevant for antibody induction has been shown to be effective as a foot-and-mouth disease (FMD) vaccine. B₂T dendrimers combining two copies of the major FMD virus (FMDV) type O B-cell epitope (capsid proteinVP1 (140–158)) covalently linked to a heterotypic T-cell epitope from non-structural protein 3A (21–35), henceforth B₂T-3A, has previously been shown to elicit high neutralizing antibody (nAb) titers and IFN-γ-producing cells in both mice and pigs. Here, we provide evidence that the B- and T-cell epitopes need to be tethered to a single molecular platform for successful T-cell help, leading to efficient nAb induction in mice. In addition, mice immunized with a non-covalent mixture of B₂T-3A dendrimers containing the B-cell epitopes of FMDV types O and C induced similarly high nAb levels against both serotypes, opening the way for a multivalent vaccine platform against a variety of serologically different FMDVs. These findings are relevant for the design of vaccine strategies based on B- and T-cell epitope combinations.     

Conformational analysis of the ΜΒΡ<Subscript>83–99</Subscript> (Phe<Superscript>91</Superscript>) and ΜΒΡ<Subscript>83–99</Subscript> (Tyr<Superscript>91</Superscript>) peptide analogues and study of their interactions with the HLA-DR2 and human TCR receptors by using Molecular Dynamics

The two new synthetic analogues of the MBP_83–99 epitope substituted at Lys⁹¹ (primary TCR contact) with Phe [MBP_83–99 (Phe⁹¹)] or Tyr [MBP_83–99 (Tyr⁹¹)], have been structurally elucidated using 1D and 2D high resolution NMR studies. The conformational analysis of the two altered peptide ligands (APLs) has been performed and showed that they adopt a linear and extended conformation which is in agreement with the structural requirements of the peptides that interact with the HLA-DR2 and TCR receptors. In addition, Molecular Dynamics (MD) simulations of the two analogues in complex with HLA-DR2 (DRA, DRB1*1501) and TCR were performed. Similarities and differences of the binding motif of the two analogues were observed which provide a possible explanation of their biological activity. Their differences in the binding mode in comparison with the MBP_83–99 epitope may also explain their antagonistic versus agonistic activity. The obtained results clearly indicate that substitutions in crucial amino acids (TCR contacts) in combination with the specific conformational characteristics of the MBP_83–99 immunodominant epitope lead to an alteration of their biological activity. These results make the rational drug design intriguing since the biological activity is very sensitive to the substitution and conformation of the mutated MBP epitopes.     

Convergent chemo-enzymatic synthesis of mannosylated glycopeptides; targeting of putative vaccine candidates to antigen presenting cells

The combination of solid phase peptide synthesis and endo-β-N-acetylglucosaminidase (ENGase) catalysed glycosylation is a powerful convergent synthetic method allowing access to glycopeptides bearing full-length N-glycan structures. Mannose-terminated N-glycan oligosaccharides, produced by either total or semi-synthesis, were converted into oxazoline donor substrates. A peptide from the human cytomegalovirus (CMV) tegument protein pp65 that incorporates a well-characterised T cell epitope, containing N-acetylglucosamine at specific Asn residues, was accessed by solid phase peptide synthesis, and used as an acceptor substrate. High-yielding enzymatic glycosylation afforded glycopeptides bearing defined homogeneous high-mannose N-glycan structures. These high-mannose containing glycopeptides were tested for enhanced targeting to human antigen presenting cells (APCs), putatively mediated via the mannose receptor, and for processing by the APCs for presentation to human CD8+ T cells specific for a 9-mer epitope within the peptide. Binding assays showed increased binding of glycopeptides to APCs compared to the non-glycosylated control. Glycopeptides bearing high-mannose N-glycan structures at a single site outside the T cell epitope were processed and presented by the APCs to allow activation of a T cell clone. However, the addition of a second glycan within the T cell epitope resulted in ablation of T cell activation. We conclude that chemo-enzymatic synthesis of mannosylated glycopeptides enhances uptake by human APCs while preserving the immunogenicity of peptide epitopes within the glycopeptides, provided those epitopes are not themselves glycosylated.     

Two highly similar LAEDDTNAQKT and LTDKIGTEI epitopes in G glycoprotein may be useful for effective epitope based vaccine design against pathogenic Henipavirus

Nipah virus and Hendra virus, two members of the genus Henipavirus, are newly emerging zoonotic pathogens which cause acute respiratory illness and severe encephalitis in human. Lack of the effective antiviral therapy endorses the urgency for the development of vaccine against these deadly viruses. In this study, we employed various computational approaches to identify epitopes which has the potential for vaccine development. By analyzing the immune parameters of the conserved sequences of G glycoprotein using various databases and bioinformatics tools, we identified two potential epitopes which may be used as peptide vaccines. Using different B cell epitope prediction servers, four highly similar B cell epitopes were identified. Immunoinformatics analyses revealed that LAEDDTNAQKT is a highly flexible and accessible B-cell epitope to antibody. Highly similar putative CTL epitopes were analyzed for their binding with the HLA-C 12*03 molecule. Docking simulation assay revealed that LTDKIGTEI has significantly lower binding energy, which bolstered its potential as epitope-based vaccine design. Finally, cytotoxicity analysis has also justified their potential as promising epitope-based vaccine candidate. In sum, our computational analysis indicates that either LAEDDTNAQKT or LTDKIGTEI epitope holds a promise for the development of universal vaccine against all kinds of pathogenic Henipavirus. Further in vivo and in vitro studies are necessary to validate the obtained findings.     

Prediction of T-cell epitopes using biosupport vector machines

The immune system is concerned with the recognition and disposal of foreign or "non self" molecules or cells that enter the body of an immunologically competent individual. The generation of an immune response depends on the interaction of components, namely, the immunogen (nonself or foreign cell or molecule), antibody producing humoral immune system, and sensitized lymphocyte producing cellular immune system. An immunogen possesses surface structures referred to as epitopes; the precise pattern of each epitope enables an individual's immune system to recognize cells or molecules as self or immunogens. During the recognition process, the specific cells known as macrophages identify the epitope structures on the immunogen and save them in the form of short peptides 10-18 amino-acids-long known as immune dominant peptides (IDPs). IDPs are then bound with surface proteins on macrophages known as MHC protein complexes. The macrophages then present this IDP-MHC complex to a T cell that possesses a specific receptor that is specific for the foreign epitope on the IDP bound to MHC complex. This initiates an immune system cascade that results in the disposal of the immunogen. The study and accurate prediction of T-cell epitopes is, thus, very important for designing vaccines against pathogenic diseases. The present study applied the newly developed biosupport vector machine to the T-cell epitope data. This new algorithm introduces a biobasis function into the conventional support vector machines so that the nonnumerical attributes (amino acids) in protein sequences can be recognized without a feature extraction process, which often fails to properly code the biological content in protein sequences. The prediction accuracy of a 10-fold cross validation is 90.31%, compared with 87.86% using support vector machines reported as the best compared with other algorithms in an earlier study.     

Biologically relevant conformational features of linear and cyclic proteolipid protein (PLP) peptide analogues obtained by high-resolution nuclear magnetic resonance and molecular dynamics

Proteolipid protein (PLP) is one of the main proteins of myelin sheath that are destroyed during the progress of multiple sclerosis (MS). The immunodominant PLP_139–151 epitope is known to induce experimental autoimmune encephalomyelitis (EAE, animal model of MS), wherein residues 144 and 147 are recognized by T cell receptor (TCR) during the formation of trimolecular complex with peptide-antigen and major histocompability complex. The conformational behavior of linear and cyclic peptide analogues of PLP, namely PLP_139–151 and cyclic (139–151) (L¹⁴⁴, R¹⁴⁷) PLP_139–151, have been studied in solution by means of nuclear magnetic resonance (NMR) methods in combination with unrestrained molecular dynamics simulations. The results indicate that the side chains of mutated amino acids in the cyclic analogue have different spatial orientation compared with the corresponding side chains of the linear analogue, which can lead to reduced affinity to TCR. NMR experiments combined with theoretical calculations pave the way for the design and synthesis of potent restricted peptides of immunodominant PLP_139–151 epitope as well as non peptide mimetics that rises as an ultimate goal.     

Cholic acid as template for multivalent peptide assembly

Cholic acid, an amphiphilic steroid containing several selectively addressable functionalities, was exploited as a rigid template for multivalent peptide assembly. Thus, cholic acid-based templates suitable for chemoselective peptide ligation were synthesized, in which maleimide or bromoacetyl moieties were selectively introduced at the 3alpha, 7alpha, 12alpha-positions of cholic acid with varied length of linkers. Three peptides were chosen and tested for the chemoselective ligation. These include the HIV-1 peptide inhibitor DP178, the universal T-helper epitope derived from tetanus toxoid (830-844), and the minimum epitope sequence of the HIV-neutralizing antibody 2F5. It was found that the maleimide-functionalized templates are highly efficient for the ligation of all the peptides, while bromoacetyl templates led to low yield of ligation. Circular dichroism (CD) spectroscopic studies of the multivalent peptides (10a and 11a) containing three strands of peptide DP178 indicate that the template-assembled peptides form three alpha-helix bundles with significantly enhanced alpha-helix contents than the single peptide. The results suggest that cholic acid is a valuable template for constructing alpha-helix bundles that may be useful as mimics of conformational epitopes for vaccine development.     

"Affinity-proteomics": direct protein identification from biological material using mass spectrometric epitope mapping

We describe here a new approach for the identification of affinity-bound proteins by proteolytic generation and mass spectrometric analysis of their antibody bound epitope peptides (epitope excision). The cardiac muscle protein troponin T was chosen as a protein antigen because of its diagnostic importance in myocardial infarct, and its previously characterised epitope structure. Two monoclonal antibodies (IgG1-1B10 and IgG1-11.7) raised against intact human troponin T were found to be completely cross reactive with bovine heart troponin T. A combination of immuno-affinity isolation, partial proteolytic degradation (epitope excision), mass spectrometric peptide mapping, and database analysis was used for the direct identification of Tn T from bovine heart cell lysate. Selective binding of the protein was achieved by addition of bovine heart cell lysate to the Sepharose-immobilised monoclonal antibodies, followed by removal of supernatant material containing unbound protein. While still bound to the affinity matrix the protein was partially degraded thereby generating a set of affinity-bound, overlapping peptide fragments comprising the epitope. Following dissociation from the antibody the epitope peptides were analysed by matrix assisted laser desorption-ionisation (MALDI) and electrospray-ionisation (ESI) mass spectrometry. The peptide masses identified by mass spectrometry were used to perform an automated database search, combined with a search for a common "epitope motif". This procedure resulted in the unequivocal identification of the protein from biological material with only a minimum number of peptide masses, and requiring only limited mass-determination accuracy. The dramatic increase of selectivity for identification of the protein by combining the antigen-antibody specificity with the redundancy of peptide sequences renders this "affinity-proteomics" approach a powerful tool for mass spectrometric identification of proteins from biological material.     

A General Synthetic Approach for Designing Epitope Targeted Macrocyclic Peptide Ligands

We describe a general synthetic strategy for developing high‐affinity peptide binders against specific epitopes of challenging protein biomarkers. The epitope of interest is synthesized as a polypeptide, with a detection biotin tag and a strategically placed azide (or alkyne) presenting amino acid. This synthetic epitope (SynEp) is incubated with a library of complementary alkyne or azide presenting peptides. Library elements that bind the SynEp in the correct orientation undergo the Huisgen cycloaddition, and are covalently linked to the SynEp. Hit peptides are tested against the full‐length protein to identify the best binder. We describe development of epitope‐targeted linear or macrocycle peptide ligands against 12 different diagnostic or therapeutic analytes. The general epitope targeting capability for these low molecular weight synthetic ligands enables a range of therapeutic and diagnostic applications, similar to those of monoclonal antibodies.     

MIMOTOPES,CONTINUOUS PARATOPES AND HYDROPATHIC COMPLEMENTARITY: NOVEL APPROXIMATIONS IN THE DESCRIPTION OF IMMUNOCHEMICAL SPECIFICITY

Most antigenic sites of proteins, known as discontinuous epitopes, are made up of residues on different loops that are brought together by the folding of the polypeptide chain. The individual loops are sometimes able, on their own, to bind to the antibody and they are then known as continuous epitopes. The binding sites of antibodies, known as paratopes, are built up from residues on six hypervariable loops known as complementarity determining regions (CDRs). Peptides corresponding to individual CDR loops are often able to bind the antigen and such peptides may be viewed as continuous paratopes. Using random combinatorial peptide libraries, it is possible to obtain peptides that bind to an antiprotein antibody without showing any sequence similarity with any part of the protein. Such epitope mimics are called mimotopes provided they are able also to elicit antibodies that react with the original antigen. The binding activity of mimotopes may partly be due to the phenomenon of hydropathic complementarity between epitope and paratope peptides. Although these concepts are vague in their structural connotation, they are useful for describing the immunological activity of linear peptides.     

Prediction of T-cell epitopes based on least squares support vector machines and amino acid properties

T-lymphocyte (T-cell) is a very important component in human immune system. It possesses a receptor (TCR) that is specific for the foreign epitopes which are in a form of short peptides bound to the major histocompatibility complex (MHC). When T-cell receives the message about the peptides bound to MHC, it makes the immune system active and results in the disposal of the immunogen. The antigenic determinants recognized and bound by the T-cell receptor is known as T-cell epitope. The accurate prediction of T-cell epitopes is crucial for vaccine development and clinical immunology. For the first time we developed new models using least squares support vector machine (LSSVM) and amino acid properties for T-cell epitopes prediction. A dataset including 203 short peptides (167 non-epitopes and 36 epitopes) was used as the input dataset and it was randomly divided into a training set and a test set. The models based on LSSVM and amino acid properties were evaluated using leave-one-out cross-validation method and the predictive ability of the test set, and obtained the results of 0.9875 and 0.9734 under the ROC curves, respectively. This result is more satisfactory than that were reported before. Especially, the accuracy of true positive gets a marked enhancement.