Browse
Submit Data
Databases
API
Help

Dataset Information

30 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Predicting HLA class II antigen presentation through integrated deep learning.

ABSTRACT: Accurate prediction of antigen presentation by human leukocyte antigen (HLA) class II molecules would be valuable for vaccine development and cancer immunotherapies. Current computational methods trained on in vitro binding data are limited by insufficient training data and algorithmic constraints. Here we describe MARIA (major histocompatibility complex analysis with recurrent integrated architecture; https://maria.stanford.edu/ ), a multimodal recurrent neural network for predicting the likelihood of antigen presentation from a gene of interest in the context of specific HLA class II alleles. In addition to in vitro binding measurements, MARIA is trained on peptide HLA ligand sequences identified by mass spectrometry, expression levels of antigen genes and protease cleavage signatures. Because it leverages these diverse training data and our improved machine learning framework, MARIA (area under the curve = 0.89-0.92) outperformed existing methods in validation datasets. Across independent cancer neoantigen studies, peptides with high MARIA scores are more likely to elicit strong CD4⁺ T cell responses. MARIA allows identification of immunogenic epitopes in diverse cancers and autoimmune disease.

SUBMITTER: Chen B

PROVIDER: S-EPMC7075463 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

The mechanism of HLA-DM induced peptide exchange in the MHC class II antigen presentation pathway.

Project description:HLA-DM serves a critical function in the loading and editing of peptides on MHC class II (MHCII) molecules. Recent data showed that the interaction cycle between MHCII molecules and HLA-DM is dependent on the occupancy state of the peptide binding groove. Empty MHCII molecules form stable complexes with HLA-DM, which are disrupted by binding of high-affinity peptide. Interestingly, MHCII molecules with fully engaged peptides cannot interact with HLA-DM, and prior dissociation of the peptide N-terminus from the groove is required for HLA-DM binding. There are significant similarities to the peptide loading process for MHC class I molecules, even though it is executed by a distinct set of proteins in a different cellular compartment.

| S-EPMC3288754 | biostudies-literature

Improved Transgenic Mouse Model for Studying HLA Class I Antigen Presentation.

Project description:HLA class I (HLA-I) transgenic mice have proven to be useful models for studying human MHC-related immune responses over the last two decades. However, differences in the processing and presentation machinery between humans and mice may have profound effects on HLA-I restricted antigen presentation. In this study, we generated a novel human TAP-LMP (hTAP-LMP) gene cluster transgenic mouse model carrying an intact human TAP complex and two human immunoproteasome LMP subunits, PSMB8/PSMB9. By crossing the hTAP-LMP strain with different HLA-I transgenic mice, we found that the expression levels of human HLA-I molecules, especially the A3 supertype members (e.g., A11 and A33), were remarkably enhanced in corresponding HLA-I/hTAP-LMP transgenic mice. Moreover, we found that humanized processing and presentation machinery increased antigen presentation of HLA-A11-restricted epitopes and promoted the rapid reduction of hepatitis B virus (HBV) infection in HLA-A11/hTAP-LMP mice. Together, our study highlights that HLA-I/hTAP-LMP mice are an improved model for studying antigen presentation of HLA-I molecules and their related CTL responses.

| S-EPMC5025652 | biostudies-literature

B Cell-Mediated Antigen Presentation through MHC Class II Is Dispensable for Atherosclerosis Progression.

Project description:Depletion of B cells attenuates plaque development and modulates T cell responses in mouse models of atherosclerosis, suggesting that Ag presentation by B cells may promote disease progression. Thus, we set out to determine the role of B cell-mediated MHC class II (MHC II) Ag presentation during atherosclerotic plaque development. We developed murine conditional MHC II deletion and expression systems under control of the B cell-restricted CD19 promoter in an experimental model of atherosclerosis. Mice lacking MHC II expression only on B cells exhibited systemic shifts in germinal center and marginal zone B cell populations, leading to a reduced Ab response compared with littermate control animals. However, all populations were present and normal cholesterol uptake was detected in the plasma following high-fat diet treatment. In a second model, in which conditional expression of MHC II is limited only to B cells, showed similar overall cellularity characteristics compared with mice with complete MHC II deficiency. High-fat diet feeding showed no major changes in atherosclerotic plaque size or plaque cellular content in either conditional deletion or conditional expression approaches, compared with control animals. By testing the necessity and sufficiency of MHC II on B cells in the progression of atherosclerosis, we determine that MHC II on B cells does not directly regulate lesion development in murine models.

| S-EPMC6999615 | biostudies-literature

HLA-II immunopeptidome profiling and deep learning reveal features of antigenicity to inform antigen discovery.

Project description:CD4+ T cell responses are exquisitely antigen specific and directed toward peptide epitopes displayed by human leukocyte antigen class II (HLA-II) on antigen-presenting cells. Underrepresentation of diverse alleles in ligand databases and an incomplete understanding of factors affecting antigen presentation in vivo have limited progress in defining principles of peptide immunogenicity. Here, we employed monoallelic immunopeptidomics to identify 358,024 HLA-II binders, with a particular focus on HLA-DQ and HLA-DP. We uncovered peptide-binding patterns across a spectrum of binding affinities and enrichment of structural antigen features. These aspects underpinned the development of context-aware predictor of T cell antigens (CAPTAn), a deep learning model that predicts peptide antigens based on their affinity to HLA-II and full sequence of their source proteins. CAPTAn was instrumental in discovering prevalent T cell epitopes from bacteria in the human microbiome and a pan-variant epitope from SARS-CoV-2. Together CAPTAn and associated datasets present a resource for antigen discovery and the unraveling genetic associations of HLA alleles with immunopathologies.

| S-EPMC10519123 | biostudies-literature

A cell-based high-throughput screening assay system for inhibitor compounds of antigen presentation by HLA class II molecule.

Project description:A number of autoimmune diseases are associated with the genotypes of human leukocyte antigen class II (HLA), some of which present peptides derived from self-proteins, resulting in clonal expansion of self-reactive T cells. Therefore, selective inhibition of self-peptide loading onto such disease-associated HLA could ameliorate the diseases. To effectively identify such compounds, in this study, we established, for the first time, a cell- and 96-well microplate-based high-throughput screening system for inhibitors of antigen presentation. A panel of DRB1 genes plus DRA*01:01 gene were expressed in HEK293T cells and in 3T3 cells, and their binding with biotinylated known self-antigen peptides was measured by flow cytometry. HLA-DR1 (DRB1*01:01) and DR15 (DRB1*15:01) showed a high affinity with myelin basic protein peptide (MBP83-98). Therefore, in 96-well plate wells, MBP83-99 was allowed to bind to DR1 or DR15 on 3T3 cells in competition with a test compound, and the HLA-bound peptide was detected by streptavidin-conjugated ?-galactosidase, thereby identifying inhibitor compounds for rheumatoid arthritis or multiple sclerosis. Our assay system has a potential for broad applications, including designing peptide vaccines.

| S-EPMC5533769 | biostudies-literature

Antigen identification for HLA class I- and HLA class II-restricted T cell receptors using cytokine-capturing antigen-presenting cells.

Project description:A major limitation to understanding the associations of human leukocyte antigen (HLA) and CD8+ and CD4+ T cell receptor (TCR) genes with disease pathophysiology is the technological barrier of identifying which HLA molecules, epitopes, and TCRs form functional complexes. Here, we present a high-throughput epitope identification system that combines capture of T cell-secreted cytokines by barcoded antigen-presenting cells (APCs), cell sorting, and next-generation sequencing to identify class I- and class II-restricted epitopes starting from highly complex peptide-encoding oligonucleotide pools. We engineered APCs to express anti-cytokine antibodies, a library of DNA-encoded peptides, and multiple HLA class I or II molecules. We demonstrate that these engineered APCs link T cell activation-dependent cytokines with the DNA that encodes the presented peptide. We validated this technology by showing that we could select known targets of viral epitope-, neoepitope-, and autoimmune epitope-specific TCRs, starting from mixtures of peptide-encoding oligonucleotides. Then, starting from 10 TCRβ sequences that are found commonly in humans but lack known targets, we identified seven CD8+ or CD4+ TCR-targeted epitopes encoded by the human cytomegalovirus (CMV) genome. These included known epitopes, as well as a class I and a class II CMV epitope that have not been previously described. Thus, our cytokine capture-based assay makes use of a signal secreted by both CD8+ and CD4+ T cells and allows pooled screening of thousands of encoded peptides to enable epitope discovery for orphan TCRs. Our technology may enable identification of HLA-epitope-TCR complexes relevant to disease control, etiology, or treatment.

| S-EPMC8320540 | biostudies-literature

Predicting adverse drug reactions through interpretable deep learning framework.

Project description:BACKGROUND:Adverse drug reactions (ADRs) are unintended and harmful reactions caused by normal uses of drugs. Predicting and preventing ADRs in the early stage of the drug development pipeline can help to enhance drug safety and reduce financial costs. METHODS:In this paper, we developed machine learning models including a deep learning framework which can simultaneously predict ADRs and identify the molecular substructures associated with those ADRs without defining the substructures a-priori. RESULTS:We evaluated the performance of our model with ten different state-of-the-art fingerprint models and found that neural fingerprints from the deep learning model outperformed all other methods in predicting ADRs. Via feature analysis on drug structures, we identified important molecular substructures that are associated with specific ADRs and assessed their associations via statistical analysis. CONCLUSIONS:The deep learning model with feature analysis, substructure identification, and statistical assessment provides a promising solution for identifying risky components within molecular structures and can potentially help to improve drug safety evaluation.

| S-EPMC6300887 | biostudies-other

Causal ALS genes impact the MHC class II antigen presentation pathway.

Project description:Mutations in RNA/DNA-binding proteins cause amyotrophic lateral sclerosis (ALS), but the underlying disease mechanisms remain unclear. Here, we report that a set of ALS-associated proteins, namely FUS, EWSR1, TAF15, and MATR3, impact the expression of genes encoding the major histocompatibility complex II (MHC II) antigen presentation pathway. Both subunits of the MHC II heterodimer, HLA-DR, are down-regulated in ALS gene knockouts/knockdown in HeLa and human microglial cells, due to loss of the MHC II transcription factor CIITA. Importantly, hematopoietic progenitor cells (HPCs) derived from human embryonic stem cells bearing the FUSR495X mutation and HPCs derived from C9ORF72 ALS patient induced pluripotent stem cells also exhibit disrupted MHC II expression. Given that HPCs give rise to numerous immune cells, our data raise the possibility that loss of the MHC II pathway results in global failure of the immune system to protect motor neurons from damage that leads to ALS.

| S-EPMC10523463 | biostudies-literature

Lack of HLA class II antigen expression in microsatellite unstable colorectal carcinomas is caused by mutations in HLA class II regulatory genes.

Project description:Colorectal cancers (CRCs) develop on the basis of a deficient DNA mismatch repair (MMR) system in about 15% of cases. MMR-deficient CRC lesions show high-level microsatellite instability (MSI-H) and accumulate numerous mutations located at coding microsatellite loci that lead to the generation of immunogenic neopeptides. Consequently, the host's antitumoral immune response is of high importance for the course of the disease in MSI-H CRC patients. Accordingly, immune evasion mediated by impairment of HLA class I antigen presentation is frequently observed in these cancers. In this study, we aimed at a systematic analysis of alterations affecting HLA class II antigen expression in MSI-H CRC. HLA class II antigens are expressed by only two-thirds of MSI-H CRCs. The mechanisms underlying the lack of HLA class II antigens in a subset of MSI-H CRCs remain unknown. We here screened HLA class II regulatory genes for the presence of coding microsatellites and identified mutations of the essential regulator genes RFX5 in 9 (26.9%) out of 34 and CIITA in 1 (2.9%) out of 34 MSI-H CRCs. RFX5 mutations were related to lack of or faint HLA class II antigen expression (p = 0.006, Fisher's exact test). Transfection with wild-type RFX5 was sufficient to restore interferon gamma-inducible HLA class II antigen expression in the RFX5-mutant cell line HDC108. We conclude that somatic mutations of the RFX5 gene represent a novel mechanism of loss of HLA class II antigen expression in tumor cells, potentially contributing to immune evasion in MSI-H CRCs.

| S-EPMC2892639 | biostudies-literature

Human Leukocyte Antigen (HLA) class I and II datasets for sudanese.

Project description:Sudan is located in the heart of Africa and surrounded by eight countries with people of different ethnic origins. Historical records show that the population of the Sudan is a mixture of Arabic, West Asian Arabic and sub-Saharan African elements. The present survey provides data on allele lineages, and haplotype frequencies of Human Leukocyte Antigen (HLA) class I (HLA-A and HLA-B) and class II (HLA-DR and -HLA-DQ) loci in 11 Sudanese populations. The sampled individuals are all local transplant donors who provided informed consent for HLA analyses on their blood samples and were registered at National Cancer Institute, University of Gezira, Wad Medani. The HLA class I and II data reported here can be subjected for future analyses of genetic structure and health in Sudan. These include as reference datasets for identifying the association between HLA and diseases and for designing donor recruitment strategies.

| S-EPMC6545336 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data