Epitope-anchored contrastive transfer learning for paired CD8+ T cell receptor-antigen recognition (preprint)

Understanding the mechanisms of T-cell antigen recognition that underpin adaptive immune responses is critical for the development of vaccines, immunotherapies, and treatments against autoimmune diseases. Despite extensive research efforts, the accurate identification of T cell receptor (TCR)-antigen binding pairs remains a significant challenge due to the vast diversity and cross-reactivity of TCRs. Here, we propose a deep-learning framework termed Epitope-anchored Contrastive Transfer Learning (EPACT) tailored to paired human CD8+ TCRs from single-cell sequencing data. Harnessing the pre-trained representations and the contrastive co-embedding space, EPACT demonstrates state-of-the-art model generalizability in predicting TCR binding specificity for unseen epitopes and distinct TCR repertoires, offering potential values for practical outcomes in real-world scenarios. The contrastive learning paradigm achieves highly precise predictions for immunodominant epitopes and facilitates interpretable analysis of epitope-specific T cells. The TCR binding strength predicted by EPACT aligns well with the surge in spike-specific immune responses targeting SARS-CoV-2 epitopes after vaccination. We further fine-tune EPACT on TCR-epitope structural data to decipher the residue-level interactions involved in T-cell antigen recognition. EPACT not only exhibits superior capabilities in quantifying inter-chain distance matrices and identifying contact residue pairs but also corroborates the presence of molecular mimicry across multiple tumor-associated antigens. Together, EPACT can serve as a useful AI approach with significant potential in practical applications and contribute toward the development of TCR-based diagnostics and immunotherapies.

Constructing a multiple-layer interactome for SARS-CoV-2 in the context of lung disease: Linking the virus with human genes and co-infecting microbes (preprint)

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic has caused millions of deaths worldwide. Many efforts have focused on unraveling the mechanism of the viral infection to develop effective strategies for treatment and prevention. Previous studies have provided some clarity on the protein-protein interaction linkages occurring during the life cycle of viral infection; however, we lack a complete understanding of the full interactome, comprising human miRNAs and protein-coding genes and co-infecting microbes. To comprehensively determine this, we developed a statistical modeling method using latent Dirichlet allocation (called MLCrosstalk, for multiple-layer crosstalk) to fuse many types of data to construct the full interactome of SARS-CoV-2. Specifically, MLCrosstalk is able to integrate samples with multiple layers of information (e.g., miRNA and microbes), enforce a consistent topic distribution on all data types, and infer individual-level linkages (i.e., differing between patients). We also implement a secondary refinement with network propagation to allow our microbe-gene linkages to address larger network structures (e.g., pathways). Using MLCrosstalk, we generated a list of genes and microbes linked to SARS-CoV-2. Interestingly, we found that two of the identified microbes, Rothia mucilaginosa and Prevotella melaninogenica, show distinct patterns representing synergistic and antagonistic relationships with the virus, respectively. We also identified several SARS-COV-2-associated pathways, including the VEGFA-VEGFR2 and immune response pathways, which may provide potential targets for drug design.

Genetic determination of regional connectivity in modelling the spread of COVID-19 outbreak for improved mitigation strategies (preprint)

Covid-19 has resulted in the death of more than 1,500,000 individuals. Due to the pandemic's severity, thousands of genomes have been sequenced and publicly stored with extensive records, an unprecedented amount of data for an outbreak in a single year. Simultaneously, prediction models offered region-specific and often contradicting results, while states or countries implemented mitigation strategies with little information on success, precision, or agreement with neighboring regions. Even though viral transmissions have been already documented in a historical and geographical context, few studies aimed to model geographic and temporal flow from viral sequence information. Here, using a case study of 7 states, we model the flow of the Covid-19 outbreak with respect to phylogenetic information, viral migration, inter- and intra-regional connectivity, epidemiologic and demographic characteristics. By assessing regional connectivity from genomic variants, we can significantly improve predictions in modeling the viral spread and intensity. Contrary to previous results, our study shows that the vast majority of the first outbreak can be traced to very few lineages, despite the existence of multiple worldwide transmissions. Moreover, our results show that while the distance from hotspots is initially important, connectivity becomes increasingly significant as the virus establishes itself. Similarly, isolated local strategies -such as relying on herd immunity- can negatively impact neighboring states. Our work suggests that we can achieve more efficient unified mitigation strategies with selective interventions.