Lalevee, S. | bioRxiv Science

bioRxiv2025

Predicting TCR antigen specificity at proteome-scale with synthetic immune cells and machine learning

TCR specificity to peptide-HLA antigens is central to immunology, impacting responses in infection, autoimmunity and cancer. Achieving precise recognition while avoiding off-target reactivity is critical for effective immunity and safe therapeutic interventions. Comprehensive, proteome-wide specificity profiling of TCRs is challenging with current methods, which notably lack integrated machine learning for large-scale analysis. Here, we report a synthetic immune cell system coupled with machine learning to enable TCR functional and specificity mapping of peptide-HLA antigens at proteome-scale. Multi-step immunogenomic engineering of synthetic antigen-presenting cells (APCs) was performed to enable stable mono-allelic integration and precise display of peptide antigens and HLA class I from a defined genomic locus, ensuring genomically-encoded antigen presentation. Compatible with a synthetic TCR displaying T cell system, this platform incorporates a fluorescent reporter of cytokine-mediated signaling for real-time activation detection in both synthetic APCs and T cells. We combined this screening with diverse peptide antigen libraries and deep sequencing to train supervised machine learning models. These models were applied to predict TCR specificity to peptide-HLA antigens across the entire human proteome. Experimental validation confirmed novel off-targets for therapeutic TCR candidates, including for a clinically-approved TCR therapeutic. This integrated synthetic immune cell and machine learning approach provides unprecedented proteome-wide peptide-HLA specificity mapping to support the development of safer TCR-based therapies. One sentence summaryWe present a synthetic immune cell platform integrated with machine learning that enables prediction of TCR specificity to peptide-HLA antigens at proteome-scale.

immunology↗

bioRxiv2018

Heterochromatin delays CRISPR-Cas9 mutagenesis but does not influence repair outcome

CRISPR-Cas9 genome editing occurs in the context of chromatin, which is heterogeneous in structure and function across the genome. Chromatin heterogeneity is thought to affect genome editing efficiency, but this has been challenging to quantify due to the presence of confounding variables. Here, we develop a method that exploits the allele-specific chromatin status of imprinted genes in order to address this problem. Because maternal and paternal alleles of imprinted genes have identical DNA sequence and are situated in the same nucleus, allele-specific differences in the frequency and spectrum of Cas9-induced mutations can be attributed unequivocally to epigenetic mechanisms. We found that heterochromatin can impede mutagenesis, but to a degree that depends on other key experimental parameters. Mutagenesis was impeded by up to 7-fold when Cas9 exposure was brief and when intracellular Cas9 expression was low. Surprisingly, the outcome of mutagenic DNA repair was independent of chromatin state, with similar efficiencies of homology directed repair and deletion spectra on maternal and paternal chromosomes. Combined, our data show that heterochromatin imposes a permeable barrier that influences the kinetics, but not the endpoint of CRISPR-Cas9 genome editing, and suggest that therapeutic applications involving low-level Cas9 exposure will be particularly affected by chromatin status.

genetics↗