Machine learning predictions of MHC-II specificities reveal alternative binding mode of class II epitopes

Racle, J.; Guillaume, P.; Schmidt, J.; Michaux, J.; Larabi, A.; Lau, K.; Perez, M. A. S.; Croce, G.; Genolet, R.; Coukos, G.; Zoete, V.; Pojer, F.; Bassani-Sternberg, M.; Harari, A.; Gfeller, D.

doi:10.1101/2022.06.26.497561

bioRxiv · 10.1101/2022.06.26.497561

Machine learning predictions of MHC-II specificities reveal alternative binding mode of class II epitopes

Racle, J.·Guillaume, P.·Schmidt, J.·Michaux, J.·Larabi, A.·Lau, K.·Perez, M. A. S.·Croce, G.·Genolet, R.·Coukos, G.·Zoete, V.·Pojer, F.·Bassani-Sternberg, M.·Harari, A.·Gfeller, D.

View original source ↗Export metadata ↓

Abstract

CD4+ T cells orchestrate the adaptive immune response against pathogens and cancer by recognizing epitopes presented on MHC-II molecules. The high polymorphism of MHC-II genes represents an important hurdle towards accurate prediction and identification of CD4+ T-cell epitopes in different individuals and different species. Here we collected and curated a dataset of 627,013 unique MHC-II ligands identified by mass spectrometry. This enabled us to precisely determine the binding motifs of 88 MHC-II alleles across human, mouse, cattle and chicken. Analysis of these binding specificities combined with X-ray crystallography refined our understanding of the molecular determinants of MHC-II motifs and revealed a widespread reverse binding mode in MHC-II ligands. We then developed a machine learning framework to accurately predict binding specificities and ligands of any MHC-II allele. This tool improves and expands predictions of CD4+ T-cell epitopes, and enabled us to discover and characterize several viral and bacterial epitopes following the aforementioned reverse binding mode.

Source connections

Published article ↗

Explore related subjects

immunology Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Racle, J., Guillaume, P., Schmidt, J., Michaux, J., Larabi, A., Lau, K., Perez, M. A. S., Croce, G., Genolet, R., Coukos, G., Zoete, V., Pojer, F., Bassani-Sternberg, M., Harari, A., Gfeller, D.. 2022-06-29. Machine learning predictions of MHC-II specificities reveal alternative binding mode of class II epitopes. https://doi.org/10.1101/2022.06.26.497561

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

De novo design of CR2 binder as vaccine scaffold

Efficient B cell activation during vaccine-induced humoral immunity relies on both B cell receptor (BCR) antigen recognition and synergistic signaling from co-receptors. Complement receptor 2 (CR2), the primary BCR co-receptor on B cells, lowers the activation threshold and amplifies downstream kinase signaling by orders of magnitude when engaged by complement fragment C3d decorated antigens. Targeting CR2 therefore represents a rational vaccine enhancement strategy, yet native C3d suffers from low affinity, poor stability, and manufacturing challenges. Here, we report the de novo design of a highly stable, high-affinity CR2 binder using deep learning driving protein design methods. Biophysical characterization, high-resolution cryoEM structural determination, and functional assays in vitro and in vivo confirm that the designed binder matches computational design models and specifically engages CR2 to boost B cell activation. When fused to antigen as a vaccine scaffold, the trimeric CR2 binder elicits robust humoral immune responses comparable to nanoparticle vaccines, while retaining the simplicity of single-chain protein production. Our work establishes a modular CR2 targeting vaccine scaffold platform with broad translational potential for next-generation protein vaccines.

immunology↗

bioRxiv2026

Chronic opioid-associated immune dysregulation among people living with HIV

Objectives: Persistent immune dysregulation contributes to chronic disease among people living with HIV (PWH), even after viral suppression with antiretroviral therapy (ART). Although chronic opioid exposure is associated with adverse clinical outcomes, its impact on immune homeostasis during ART remains incompletely understood. We investigated whether opioid use disorder (OUD) is associated with persistent systemic and cellular immune dysregulation despite ART-mediated reductions in HIV viral load (VL). Methods: Peripheral blood was collected longitudinally from PWH with OUD (PWH/OUD+) and detectable HIV VL during 6 months of optimized ART (months 0, 3, and 6). A reference cohort of PWH without OUD (PWH/OUD-) and suppressed HIV VL provided a single blood sample. Immune profiling included plasma inflammatory biomarkers, multiplex cytokine analyses, spectral flow cytometry, and assessment of monocyte cytokine responses following lipopolysaccharide (LPS) stimulation. Mixed-effects models adjusted for HIV VL and VL-stratified analyses were performed. Results: PWH/OUD+ exhibited persistent immune dysregulation despite reductions in HIV VL. Plasma sCD163, sCD14, fractalkine, and I-TAC remained elevated, whereas TGF-{beta}1 was reduced. OUD was associated with expansion of CD16 monocytes and altered expression of CCR2, CD38, and CD11b. CD4 and CD8 T cells, NK cells, and B cells also exhibited persistent alterations in markers of activation, metabolism, and trafficking. Monocytes from PWH/OUD+ displayed attenuated cytokine responses following LPS stimulation. Conclusions: OUD is associated with persistent systemic and cellular immune dysfunction in PWH despite ART-mediated viral suppression, supporting opioid exposure as an independent contributor to chronic immune dysregulation that may promote inflammation, immune dysfunction, and long-term HIV-associated comorbidities. Keywords: HIV, Opioid-use disorder, innate immunity, cytokine

immunology↗

bioRxiv2026

The mitochondrial RNA extrusion-induced innate immunity is regulated by N6-methyladenosine machinery

Mitochondrial RNA (mtRNA) released into the cytosol functions as a damage associated molecular pattern that activates pattern-recognition receptor (PRR)-mediated inflammation, yet its release mechanisms and cytoplasmic fate remain poorly understood. Here we report that chemical Abt-373-treatment and Vesicular stomatitis virus (VSV) infection induce mtRNA extrusion through Bax/Bak and VDAC1 channels, accompanied by mtDNA release. Extruded mtRNA in A549 cells activates multiple cytosolic PRRs, including RIG-I, MDA5, TLR3/7/8, and PKR, each contributing differentially to the innate immune signaling. Analysis of GEO datasets and methylated RNA immunoprecipitation (MeRIP) assays further reveals that mtRNA carries methyladenosine (m6A) modification. m6A machinery proteins are involved in the cytoplasmic retention time of mtRNA and its interaction with RIG-I, thereby modulating mtRNA-induced innate immunity. Thus, our work establishes in vitro models of mtRNA extrusion, and highlights m6A-dependent modulation as a potential therapeutic target for mtRNA-driven inflammation.

immunology↗