Towards in silico prediction of immunogenic epitopes

Flower, Darren R.

doi:10.1016/j.it.2003.10.006

Cited by 105 publications

(67 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the years, multiple algorithms have been developed to identify individual T cell epitopes within a protein (for review, see [28]). Early algorithms that relied on the identification of biochemical 'hot-spots' along a protein sequence were shown to be wholly unreliable [29].…”

Section: Discussionmentioning

confidence: 99%

Synthetic multi‐epitope peptides identified in silico induce protective immunity against multiple influenza serotypes

Stoloff

Caparrós-Wanderley

2007

Eur J Immunol

View full text Add to dashboard Cite

Influenza causes yearly epidemics of mild disease and, occasionally, pandemics with millions of fatalities. Currently, no vaccine is effective against all influenza strains. Analysis of influenza sequences from animal and human isolates using CLUSTALW and a novel proprietary epitope prediction algorithm identified six conserved T cell‐reactive regions in several proteins. Immunisation of transgenic mice with a preparation of these six regions as chemically synthesised peptides (FLU‐v) induced a specific HLA‐A*0201‐mediated CD8+ T cell response. This T cell population also reacted against human cells infected with three non‐related influenza strains, confirming that the identified regions contain epitopes naturally presented by infected human cells and conserved amongst non‐related viruses. Moreover, FLU‐v immunisation significantly increased survival of transgenic mice against lethal challenge with influenza. Overall, FLU‐v represents a promising influenza vaccine candidate, obviating the need for yearly vaccinations and allowing the stockpiling and initiation of a worldwide vaccination program in advance of a pandemic outbreak.

show abstract

Section: Discussionmentioning

confidence: 99%

Synthetic multi‐epitope peptides identified in silico induce protective immunity against multiple influenza serotypes

Stoloff

Caparrós-Wanderley

2007

Eur J Immunol

View full text Add to dashboard Cite

show abstract

“…Previously proposed learning approaches for protein-peptide binding prediction, address the binding prediction problem using traditional margin based binary classifiers: for each protein a classifier is trained to distinguish binding peptides from non-binding peptides [6,4,16] (for a review see [9]). Recently, we proposed PepDist: a novel approach for predicting binding affinity based on learning peptide-peptide distance functions 1 [28].…”

Section: Learning Peptide-peptide Distance Functionsmentioning

confidence: 99%

Identifying HLA supertypes by learning distance functions

Hertz

Yanover²

2007

Bioinformatics

View full text Add to dashboard Cite

The development of epitope-based vaccines crucially relies on the ability to classify Human Leukocyte Antigen (HLA) molecules into sets that have similar peptide binding specificities, termed supertypes. In their seminal work, Sette and Sidney [21] defined 9 HLA class I supertypes, and claimed that these provide an almost perfect coverage of the entire repertoire of HLA class I molecules.HLA alleles are highly polymorphic and polygenic and therefore experimentally classifying each of these molecules to supertypes is at present an impossible task. Recently, a number of computational methods have been proposed for this task. These methods are based on defining protein similarity measures, derived from analysis of binding peptides or from analysis of the proteins themselves [13,7]. In this paper we define both peptide derived and protein derived similarity measures, which are based on learning distance functions. The peptide driven measure is defined using a peptide-peptide distance function, which is learnt using information about known binding and non-binding peptides [28]. The protein similarity measure is defined using a protein-protein distance function, which is learnt using information about alleles previously classified into supertypes by [21]. We compare the classification obtained by these two complimentary methods to previously suggested classification methods. In general, our results are in excellent agreement with the classifications suggested by Sette and Sidney [21] and with those reported in [13].There are two important advantages of our proposed distancebased approach. First, it makes use of two different and important immunological sources of information -HLA alleles and peptides that are known to bind or not bind to these alleles. Second, since each of our distance measures is trained using a different source of information, their combination can provide a more confident classification of alleles into supertypes.

show abstract

“…Many different computational approaches have been suggested for the proteinpeptide binding prediction problem (see [11] for a recent review). These methods can be roughly divided into three categories:…”

Section: Related Workmentioning

confidence: 99%

Predicting Protein-Peptide Binding Affinity by Learning Peptide-Peptide Distance Functions

Yanover

Hertz

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Many important cellular response mechanisms are activated when a peptide binds to an appropriate receptor. In the immune system, the recognition of pathogen peptides begins when they bind to cell membrane Major Histocompatibility Complexes (MHCs). MHC proteins then carry these peptides to the cell surface in order to allow the activation of cytotoxic T-cells. The MHC binding cleft is highly polymorphic and therefore protein-peptide binding is highly specific. Developing computational methods for predicting protein-peptide binding is important for vaccine design and treatment of diseases like cancer. Previous learning approaches address the binding prediction problem using traditional margin based binary classifiers. In this paper we propose a novel approach for predicting binding affinity. Our approach is based on learning a peptide-peptide distance function. Moreover, we learn a single peptide-peptide distance function over an entire family of proteins (e.g MHC class I). This distance function can be used to compute the affinity of a novel peptide to any of the proteins in the given family. In order to learn these peptide-peptide distance functions, we formalize the problem as a semi-supervised learning problem with partial information in the form of equivalence constraints. Specifically we propose to use DistBoost [1, 2], which is a semi-supervised distance learning algorithm. We compare our method to various state-of-the-art binding prediction algorithms on MHC class I and MHC class II datasets. In almost all cases, our method outperforms all of its competitors. One of the major advantages of our novel approach is that it can also learn an affinity function over proteins for which only small amounts of labeled peptides exist. In these cases, DistBoost's performance gain, when compared to other computational methods, is even more pronounced.

show abstract

Towards in silico prediction of immunogenic epitopes

Cited by 105 publications

References 61 publications

Synthetic multi‐epitope peptides identified in silico induce protective immunity against multiple influenza serotypes

Synthetic multi‐epitope peptides identified in silico induce protective immunity against multiple influenza serotypes

Identifying HLA supertypes by learning distance functions

Predicting Protein-Peptide Binding Affinity by Learning Peptide-Peptide Distance Functions

Contact Info

Product

Resources

About