A community resource benchmarking predictions of peptide binding to MHC-I molecules.

Recognition of peptides bound to major histocompatibility complex (MHC) class I molecules by T lymphocytes is an essential part of immune surveillance. Each MHC allele has a characteristic peptide binding preference, which can be captured in prediction algorithms, allowing for the rapid scan of entire pathogen proteomes for peptide likely to bind MHC. Here we make public a large set of 48,828 quantitative peptide-binding affinity measurements relating to 48 different mouse, human, macaque, and chimpanzee MHC class I alleles. We use this data to establish a set of benchmark predictions with one neural network method and two matrix-based prediction methods extensively utilized in our groups. In general, the neural network outperforms the matrix-based predictions mainly due to its ability to generalize even on a small amount of data. We also retrieved predictions from tools publicly available on the internet. While differences in the data used to generate these predictions hamper direct comparisons, we do conclude that tools based on combinatorial peptide libraries perform remarkably well. The transparent prediction evaluation on this dataset provides tool developers with a benchmark for comparison of newly developed prediction methods. In addition, to generate and evaluate our own prediction methods, we have established an easily extensible web-based prediction framework that allows automated side-by-side comparisons of prediction methods implemented by experts. This is an advance over the current practice of tool developers having to generate reference predictions themselves, which can lead to underestimating the performance of prediction methods they are not as familiar with as their own. The overall goal of this effort is to provide a transparent prediction evaluation allowing bioinformaticians to identify promising features of prediction methods and providing guidance to immunologists regarding the reliability of prediction tools.

Curation of complex, context-dependent immunological data.

BACKGROUND: The Immune Epitope Database and Analysis Resource (IEDB) is dedicated to capturing, housing and analyzing complex immune epitope related data http://www.immuneepitope.org. DESCRIPTION: To identify and extract relevant data from the scientific literature in an efficient and accurate manner, novel processes were developed for manual and semi-automated annotation. CONCLUSION: Formalized curation strategies enable the processing of a large volume of context-dependent data, which are now available to the scientific community in an accessible and transparent format. The experiences described herein are applicable to other databases housing complex biological data and requiring a high level of curation expertise.

An ontology for immune epitopes: application to the design of a broad scope database of immune reactivities.

BACKGROUND: Epitopes can be defined as the molecular structures bound by specific receptors, which are recognized during immune responses. The Immune Epitope Database and Analysis Resource (IEDB) project will catalog and organize information regarding antibody and T cell epitopes from infectious pathogens, experimental antigens and self-antigens, with a priority on NIAID Category A-C pathogens (http://www2.niaid.nih.gov/Biodefense/bandc_priority.htm) and emerging/re-emerging infectious diseases. Both intrinsic structural and phylogenetic features, as well as information relating to the interactions of the epitopes with the host's immune system will be catalogued. DESCRIPTION: To effectively represent and communicate the information related to immune epitopes, a formal ontology was developed. The semantics of the epitope domain and related concepts were captured as a hierarchy of classes, which represent the general and specialized relationships between the various concepts. A complete listing of classes and their properties can be found at http://www.immuneepitope.org/ontology/index.html. CONCLUSION: The IEDB's ontology is the first ontology specifically designed to capture both intrinsic chemical and biochemical information relating to immune epitopes with information relating to the interaction of these structures with molecules derived from the host immune system. We anticipate that the development of this type of ontology and associated databases will facilitate rigorous description of data related to immune epitopes, and might ultimately lead to completely new methods for describing and modeling immune responses.