Researchers Develop Deep Learning Platform to Identify HLA-E Cancer Antigens for Immunotherapy
Researchers developed an integrated platform combining a deep learning model called MHC Attention with high-throughput cell screening and mass spectrometry to discover cancer peptides presented by HLA-E, a molecule expressed widely across human populations and cancer types. The study screened approximately 6,000 peptides, identified stable HLA-E-presented candidates, and used the resulting data to improve the prediction model, ultimately discovering novel cancer antigens from genes including ETV4, WT1, RNF43, and BMP8A. Because HLA-E is minimally polymorphic, therapies targeting these peptides could potentially be applied broadly across diverse patient populations.
A team of researchers has published a preprint on bioRxiv describing MHC Attention, a neural network designed to identify cancer-associated peptides presented by HLA-E, a non-classical MHC molecule that is nearly identical across human populations and widely expressed in cancer cells. Unlike classical HLA molecules, HLA-E's low polymorphism makes it an attractive target for universal cancer immunotherapies that would not need to be tailored to individual patients' immune genetics. The platform addresses a longstanding bottleneck in the field: sparse training data and the technical difficulty of performing HLA-E-specific immunopeptidomics. MHC Attention uses allele-level attention mechanisms to train directly on patient-derived multi-allele peptide datasets, allowing it to disentangle HLA-E-specific binding signals from complex mixtures. A pooled library screen of roughly 6,000 peptides generated new HLA-E-specific training data that improved the model's predictive performance, and the refined algorithm was then used to identify novel cancer antigen candidates, several of which were validated through peptide-HLA-E stability assays or mass spectrometry. The discovered candidates include peptides derived from cancer-relevant genes ETV4, WT1, RNF43, and BMP8A. The authors describe the work as a scalable framework for HLA-E target discovery and have made MHC Attention 2.0 publicly accessible online.
What's missing
As a preprint, this work has not yet undergone formal peer review. The study identifies candidate cancer antigens but does not include functional T-cell immunogenicity data demonstrating that these HLA-E-presented peptides actually elicit cytotoxic immune responses in vivo. The generalizability of the screening library and model to the full diversity of cancer types and patient backgrounds remains to be established in follow-up studies.
What different sources said
- bioRxivCenter
MHC Attention: Identifying HLA-E presented cancer antigens through deep learning and high-throughput screening
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.