Deep learning predictions of TCR-epitope interactions reveal epitope-specific chains in dual alpha T cells.

T cells have the ability to eliminate infected and cancer cells and play an essential role in cancer immunotherapy. T cell activation is elicited by the binding of the T cell receptor (TCR) to epitopes displayed on MHC molecules, and the TCR specificity is determined by the sequence of its α and ß chains. Here, we collect and curate a dataset of 17,715 αßTCRs interacting with dozens of class I and class II epitopes. We use this curated data to develop MixTCRpred, an epitope-specific TCR-epitope interaction predictor. MixTCRpred accurately predicts TCRs recognizing several viral and cancer epitopes. MixTCRpred further provides a useful quality control tool for multiplexed single-cell TCR sequencing assays of epitope-specific T cells and pinpoints a substantial fraction of putative contaminants in public databases. Analysis of epitope-specific dual α T cells demonstrates that MixTCRpred can identify α chains mediating epitope recognition. Applying MixTCRpred to TCR repertoires from COVID-19 patients reveals enrichment of clonotypes predicted to bind an immunodominant SARS-CoV-2 epitope. Overall, MixTCRpred provides a robust tool to predict TCRs interacting with specific epitopes and interpret TCR-sequencing data from both bulk and epitope-specific T cells.

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

CD4+ T cells orchestrate the adaptive immune response against pathogens and cancer by recognizing epitopes presented on class II major histocompatibility complex (MHC-II) molecules. The high polymorphism of MHC-II genes represents an important hurdle toward accurate prediction and identification of CD4+ T cell epitopes. 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 humans, mice, cattle, and chickens. 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 HLA-DP 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 enables us to discover viral and bacterial epitopes following the aforementioned reverse-binding mode.

Improved predictions of antigen presentation and TCR recognition with MixMHCpred2.2 and PRIME2.0 reveal potent SARS-CoV-2 CD8+ T-cell epitopes.

The recognition of pathogen or cancer-specific epitopes by CD8+ T cells is crucial for the clearance of infections and the response to cancer immunotherapy. This process requires epitopes to be presented on class I human leukocyte antigen (HLA-I) molecules and recognized by the T-cell receptor (TCR). Machine learning models capturing these two aspects of immune recognition are key to improve epitope predictions. Here, we assembled a high-quality dataset of naturally presented HLA-I ligands and experimentally verified neo-epitopes. We then integrated these data in a refined computational framework to predict antigen presentation (MixMHCpred2.2) and TCR recognition (PRIME2.0). The depth of our training data and the algorithmic developments resulted in improved predictions of HLA-I ligands and neo-epitopes. Prospectively applying our tools to SARS-CoV-2 proteins revealed several epitopes. TCR sequencing identified a monoclonal response in effector/memory CD8+ T cells against one of these epitopes and cross-reactivity with the homologous peptides from other coronaviruses.

Both APRIL and antibody-fragment-based CAR T cells for myeloma induce BCMA downmodulation by trogocytosis and internalization.

BACKGROUND: Chimeric antigen receptor (CAR) T cell therapy targeting B cell maturation antigen (BCMA) on multiple myeloma (MM) produces fast but not long-lasting responses. Reasons for treatment failure are poorly understood. CARs simultaneously targeting two antigens may represent an alternative. Here, we (1) designed and characterized novel A proliferation inducing ligand (APRIL) based dual-antigen targeting CARs, and (2) investigated mechanisms of resistance to CAR T cells with three different BCMA-binding moieties (APRIL, single-chain-variable-fragment, heavy-chain-only). METHODS: Three new APRIL-CARs were designed and characterized. Human APRIL-CAR T cells were evaluated for their cytotoxic function in vitro and in vivo, for their polyfunctionality, immune synapse formation, memory, exhaustion phenotype and tonic signaling activity. To investigate resistance mechanisms, we analyzed BCMA levels and cellular localization and quantified CAR T cell-target cell interactions by live microscopy. Impact on pathway activation and tumor cell proliferation was assessed in vitro and in vivo. RESULTS: APRIL-CAR T cells in a trimeric ligand binding conformation conferred fast but not sustained antitumor responses in vivo in mouse xenograft models. In vitro trimer-BBζ CAR T cells were more polyfunctional and formed stronger immune synapses than monomer-BBζ CAR T cells. After CAR T cell-myeloma cell contact, BCMA was rapidly downmodulated on target cells with all evaluated binding moieties. CAR T cells acquired BCMA by trogocytosis, and BCMA on MM cells was rapidly internalized. Since BCMA can be re-expressed during progression and persisting CAR T cells may not protect patients from relapse, we investigated whether non-functional CAR T cells play a role in tumor progression. While CAR T cell-MM cell interactions activated BCMA pathway, we did not find enhanced tumor growth in vitro or in vivo. CONCLUSION: Antitumor responses with APRIL-CAR T cells were fast but not sustained. Rapid BCMA downmodulation occurred independently of whether an APRIL or antibody-based binding moiety was used. BCMA internalization mostly contributed to this effect, but trogocytosis by CAR T cells was also observed. Our study sheds light on the mechanisms underlying CAR T cell failure in MM when targeting BCMA and can inform the development of improved treatment strategies.

Deciphering polymorphism in 61,157 Escherichia coli genomes via epistatic sequence landscapes.

Characterizing the effect of mutations is key to understand the evolution of protein sequences and to separate neutral amino-acid changes from deleterious ones. Epistatic interactions between residues can lead to a context dependence of mutation effects. Context dependence constrains the amino-acid changes that can contribute to polymorphism in the short term, and the ones that can accumulate between species in the long term. We use computational approaches to accurately predict the polymorphisms segregating in a panel of 61,157 Escherichia coli genomes from the analysis of distant homologues. By comparing a context-aware Direct-Coupling Analysis modelling to a non-epistatic approach, we show that the genetic context strongly constrains the tolerable amino acids in 30% to 50% of amino-acid sites. The study of more distant species suggests the gradual build-up of genetic context over long evolutionary timescales by the accumulation of small epistatic contributions.

Epistatic models predict mutable sites in SARS-CoV-2 proteins and epitopes.

The emergence of new variants of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a major concern given their potential impact on the transmissibility and pathogenicity of the virus as well as the efficacy of therapeutic interventions. Here, we predict the mutability of all positions in SARS-CoV-2 protein domains to forecast the appearance of unseen variants. Using sequence data from other coronaviruses, preexisting to SARS-CoV-2, we build statistical models that not only capture amino acid conservation but also more complex patterns resulting from epistasis. We show that these models are notably superior to conservation profiles in estimating the already observable SARS-CoV-2 variability. In the receptor binding domain of the spike protein, we observe that the predicted mutability correlates well with experimental measures of protein stability and that both are reliable mutability predictors (receiver operating characteristic areas under the curve ∼0.8). Most interestingly, we observe an increasing agreement between our model and the observed variability as more data become available over time, proving the anticipatory capacity of our model. When combined with data concerning the immune response, our approach identifies positions where current variants of concern are highly overrepresented. These results could assist studies on viral evolution and future viral outbreaks and, in particular, guide the exploration and anticipation of potentially harmful future SARS-CoV-2 variants.

FilterDCA: Interpretable supervised contact prediction using inter-domain coevolution.

Predicting three-dimensional protein structure and assembling protein complexes using sequence information belongs to the most prominent tasks in computational biology. Recently substantial progress has been obtained in the case of single proteins using a combination of unsupervised coevolutionary sequence analysis with structurally supervised deep learning. While reaching impressive accuracies in predicting residue-residue contacts, deep learning has a number of disadvantages. The need for large structural training sets limits the applicability to multi-protein complexes; and their deep architecture makes the interpretability of the convolutional neural networks intrinsically hard. Here we introduce FilterDCA, a simpler supervised predictor for inter-domain and inter-protein contacts. It is based on the fact that contact maps of proteins show typical contact patterns, which results from secondary structure and are reflected by patterns in coevolutionary analysis. We explicitly integrate averaged contacts patterns with coevolutionary scores derived by Direct Coupling Analysis, improving performance over standard coevolutionary analysis, while remaining fully transparent and interpretable. The FilterDCA code is available at http://gitlab.lcqb.upmc.fr/muscat/FilterDCA.

A multi-scale coevolutionary approach to predict interactions between protein domains.

Interacting proteins and protein domains coevolve on multiple scales, from their correlated presence across species, to correlations in amino-acid usage. Genomic databases provide rapidly growing data for variability in genomic protein content and in protein sequences, calling for computational predictions of unknown interactions. We first introduce the concept of direct phyletic couplings, based on global statistical models of phylogenetic profiles. They strongly increase the accuracy of predicting pairs of related protein domains beyond simpler correlation-based approaches like phylogenetic profiling (80% vs. 30-50% positives out of the 1000 highest-scoring pairs). Combined with the direct coupling analysis of inter-protein residue-residue coevolution, we provide multi-scale evidence for direct but unknown interaction between protein families. An in-depth discussion shows these to be biologically sensible and directly experimentally testable. Negative phyletic couplings highlight alternative solutions for the same functionality, including documented cases of convergent evolution. Thereby our work proves the strong potential of global statistical modeling approaches to genome-wide coevolutionary analysis, far beyond the established use for individual protein complexes and domain-domain interactions.