pan-MHC and cross-Species Prediction of T Cell Receptor-Antigen Binding

Han, Y.; Yang, Y.; Tian, Y.; Fattah, F. J.; Itzstein, M. S. v.; Zhang, M.; Kang, X.; Yang, D. M.; Liu, J.; Xue, Y.; Liang, C.; Raman, I.; Zhu, C.; Xiao, O.; Hu, Y.; Dowell, J. E.; Homsi, J.; Rashdan, S.; Yang, S.; Gwin, M. E.; Hsiehchen, D.; Gloria-McCutchen, Y.; Pan, K.; Wu, F.; Gibbons, D.; Wang, X.; Yee, C.; Huang, J.; Reuben, A.; Cheng, C.; Zhang, J.; Gerber, D. E.; Wang, T.

doi:10.1101/2023.12.01.569599

Home/Archive/bioRxiv

bioRxiv · 10.1101/2023.12.01.569599

pan-MHC and cross-Species Prediction of T Cell Receptor-Antigen Binding

View original source ↗Export metadata ↓

Abstract

Profiling the binding of T cell receptors (TCRs) of T cells to antigenic peptides presented by MHC proteins is one of the most important unsolved problems in modern immunology. Experimental methods to probe TCR-antigen interactions are slow, labor-intensive, costly, and yield moderate throughput. To address this problem, we developed pMTnet-omni, an Artificial Intelligence (AI) system based on hybrid protein sequence and structure information, to predict the pairing of TCRs of {beta} T cells with peptide-MHC complexes (pMHCs). pMTnet-omni is capable of handling peptides presented by both class I and II pMHCs, and capable of handling both human and mouse TCR-pMHC pairs, through information sharing enabled this hybrid design. pMTnet-omni achieves a high overall Area Under the Curve of Receiver Operator Characteristics (AUROC) of 0.888, which surpasses competing tools by a large margin. We showed that pMTnet-omni can distinguish binding affinity of TCRs with similar sequences. Across a range of datasets from various biological contexts, pMTnet-omni characterized the longitudinal evolution and spatial heterogeneity of TCR-pMHC interactions and their functional impact. We successfully developed a biomarker based on pMTnet-omni for predicting immune-related adverse events of immune checkpoint inhibitor (ICI) treatment in a cohort of 57 ICI-treated patients. pMTnet-omni represents a major advance towards developing a clinically usable AI system for TCR-pMHC pairing prediction that can aid the design and implementation of TCR-based immunotherapeutics.

Explore related subjects

immunology Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Han, Y., Yang, Y., Tian, Y., Fattah, F. J., Itzstein, M. S. v., Zhang, M., Kang, X., Yang, D. M., Liu, J., Xue, Y., Liang, C., Raman, I., Zhu, C., Xiao, O., Hu, Y., Dowell, J. E., Homsi, J., Rashdan, S., Yang, S., Gwin, M. E., Hsiehchen, D., Gloria-McCutchen, Y., Pan, K., Wu, F., Gibbons, D., Wang, X., Yee, C., Huang, J., Reuben, A., Cheng, C., Zhang, J., Gerber, D. E., Wang, T.. 2023-12-04. pan-MHC and cross-Species Prediction of T Cell Receptor-Antigen Binding. https://doi.org/10.1101/2023.12.01.569599

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

KEEP EXPLORING

Related preprints

bioRxiv2026

ACE-engineered human iPSC-derived neutrophils enhance host defense against multidrug-resistant bacterial infections

Severe neutropenia predisposes patients to life-threatening infections, while donor-dependent granulocyte transfusions are limited by availability and variable cell quality. Here, we engineered human induced pluripotent stem cells (iPSCs) to constitutively or inducibly express angiotensin-converting enzyme (ACE) and differentiated them into functional ACE-engineered neutrophils (ACE-iNeu). ACE expression enhanced granulocytic maturation, reactive oxygen species generation, inflammatory cytokine production, and antimicrobial signaling. ACE-iNeu exhibited enhanced bactericidal activity against methicillin-resistant Staphylococcus aureus and multidrug-resistant Pseudomonas aeruginosa. Following adoptive transfer into neutropenic mice, ACE-iNeu significantly reduced circulating and tissue bacterial burdens. Integrated metabolomic and transcriptomic analyses revealed ACE-associated alterations in adenine nucleotide abundance and developmental and inflammatory pathways. Together, these findings establish ACE engineering as a strategy to enhance the production and antimicrobial function of human iPSC-derived neutrophils and support further preclinical development of engineered granulocyte therapies for severe drug-resistant infections.

immunology↗

bioRxiv2026

Tetravalent dengue mRNA vaccination orchestrates balanced four-serotype immunity with durable memory and protection in mice.

An effective dengue vaccine must establish durable immunity across four dengue virus (DENV) serotypes, evade antibody-dependent enhancement (ADE), and overcome immune imprinting from prior exposure. Here, we developed TetprM-E mRNA-LNP, a tetravalent vaccine comprising LNP-formulated nucleoside-modified mRNAs encoding DENV1-4 precursor membrane-envelope (prM-E) antigens, and evaluated its immunogenicity, durability, protection and breath across serotype-specific immune backgrounds. Three immunization strategies elicited neutralizing titers greater than 1:1500 against each serotype. Passive transfer of immune sera conferred 100% survival and reduced viremia after lethal DENV2 challenge in immunocompromised mice. Vaccination induced DENV envelope (env)-specific CD8+T cells and CD4-dependent germinal-center responses. DENV env-binding antibodies persisted for 34 weeks alongside DENV env-specific memory B cells. Vaccine-elicited sera showed no measurable in vitro ADE. Although monovalent priming initially biased antibody responses, TetprM-E mRNA-LNP vaccination broadened neutralization across DENV1-4 regardless of priming serotype. Together, TetprM-E mRNA-LNP elicits broad, durable, and protective immunity despite serologic constraints from pre-existing immunity.

immunology↗

bioRxiv2026

The antagonism of sex chromosomes and sex hormones dictates outcomes in Th17 cell-mediated central nervous system autoimmunity.

Biological sex traits are shaped by the combined effects of both sex hormones and chromosomes. How these factors interact in sex-related autoimmune diseases, such as multiple sclerosis (MS), has been a subject of intense recent interest. Here, using the Four Core Genotype (FCG) mouse model, in which these two variables can be disentangled, we describe an antagonism between sex hormones and chromosomes that potently influences outcomes in T helper 17 (Th17)-driven progressive central nervous system (CNS) autoimmunity. Male gonadal hormones dampen disease severity, irrespective of sex chromosome complement, by promoting a Wnt/{beta}-catenin signaling program associated with a homeostatic, non-pathogenic Th17 phenotype. By contrast, XY chromosomal complement exacerbates Th17 pathogenicity in a recipient sex-dependent manner; we identify the X-linked molecule SUV39H1 as an inhibitor of inflammatory Th17 cell function. Unexpectedly, we found that hormonally and chromosomally female FCG Th17 cells induced far more severe disease than WT female counterparts despite being genetically identical, pointing to a parental imprinting effect in dictating Th17 cell pathogenicity. These latter investigations uncovered Runx2, a transcription factor previously linked to developmental programs, as a novel negative regulator of the pathogenicity of Th17 cells. Together, our findings establish biological sex as a multilayered regulator of Th17 pathogenicity, revealing distinct and sometimes opposing contributions of hormones, chromosomes, and parental inheritance.

immunology↗