Engineered allogeneic T cells decoupling T-cell-receptor and CD3 signalling enhance the antitumour activity of bispecific antibodies.

Bispecific antibodies (biAbs) used in cancer immunotherapies rely on functional autologous T cells, which are often damaged and depleted in patients with haematological malignancies and in other immunocompromised patients. The adoptive transfer of allogeneic T cells from healthy donors can enhance the efficacy of biAbs, but donor T cells binding to host-cell antigens cause an unwanted alloreactive response. Here we show that allogeneic T cells engineered with a T-cell receptor that does not convert antigen binding into cluster of differentiation 3 (CD3) signalling decouples antigen-mediated T-cell activation from T-cell cytotoxicity while preserving the surface expression of the T-cell-receptor-CD3 signalling complex as well as biAb-mediated CD3 signalling and T-cell activation. In mice with CD19+ tumour xenografts, treatment with the engineered human cells in combination with blinatumomab (a clinically approved biAb) led to the recognition and clearance of tumour cells in the absence of detectable alloreactivity. Our findings support the development of immunotherapies combining biAbs and 'off-the-shelf' allogeneic T cells.

TCR clustering by contrastive learning on antigen specificity.

Effective clustering of T-cell receptor (TCR) sequences could be used to predict their antigen-specificities. TCRs with highly dissimilar sequences can bind to the same antigen, thus making their clustering into a common antigen group a central challenge. Here, we develop TouCAN, a method that relies on contrastive learning and pretrained protein language models to perform TCR sequence clustering and antigen-specificity predictions. Following training, TouCAN demonstrates the ability to cluster highly dissimilar TCRs into common antigen groups. Additionally, TouCAN demonstrates TCR clustering performance and antigen-specificity predictions comparable to other leading methods in the field.

Advancing Antibody Engineering through Synthetic Evolution and Machine Learning.

Abs are versatile molecules with the potential to achieve exceptional binding to target Ags, while also possessing biophysical properties suitable for therapeutic drug development. Protein display and directed evolution systems have transformed synthetic Ab discovery, engineering, and optimization, vastly expanding the number of Ab clones able to be experimentally screened for binding. Moreover, the burgeoning integration of high-throughput screening, deep sequencing, and machine learning has further augmented in vitro Ab optimization, promising to accelerate the design process and massively expand the Ab sequence space interrogated. In this Brief Review, we discuss the experimental and computational tools employed in synthetic Ab engineering and optimization. We also explore the therapeutic challenges posed by developing Abs for infectious diseases, and the prospects for leveraging machine learning-guided protein engineering to prospectively design Abs resistant to viral escape.

Meta learning addresses noisy and under-labeled data in machine learning-guided antibody engineering.

Machine learning-guided protein engineering is rapidly progressing; however, collecting high-quality, large datasets remains a bottleneck. Directed evolution and protein engineering studies often require extensive experimental processes to eliminate noise and label protein sequence-function data. Meta learning has proven effective in other fields in learning from noisy data via bi-level optimization given the availability of a small dataset with trusted labels. Here, we leverage meta learning approaches to overcome noisy and under-labeled data and expedite workflows in antibody engineering. We generate yeast display antibody mutagenesis libraries and screen them for target antigen binding followed by deep sequencing. We then create representative learning tasks, including learning from noisy training data, positive and unlabeled learning, and learning out of distribution properties. We demonstrate that meta learning has the potential to reduce experimental screening time and improve the robustness of machine learning models by training with noisy and under-labeled training data.

ePlatypus: an ecosystem for computational analysis of immunogenomics data.

MOTIVATION: The maturation of systems immunology methodologies requires novel and transparent computational frameworks capable of integrating diverse data modalities in a reproducible manner. RESULTS: Here, we present the ePlatypus computational immunology ecosystem for immunogenomics data analysis, with a focus on adaptive immune repertoires and single-cell sequencing. ePlatypus is an open-source web-based platform and provides programming tutorials and an integrative database that helps elucidate signatures of B and T cell clonal selection. Furthermore, the ecosystem links novel and established bioinformatics pipelines relevant for single-cell immune repertoires and other aspects of computational immunology such as predicting ligand-receptor interactions, structural modeling, simulations, machine learning, graph theory, pseudotime, spatial transcriptomics, and phylogenetics. The ePlatypus ecosystem helps extract deeper insight in computational immunology and immunogenomics and promote open science. AVAILABILITY AND IMPLEMENTATION: Platypus code used in this manuscript can be found at github.com/alexyermanos/Platypus.

The Unexpected Benefit of TCR Cross-Reactivity in Cancer Immunotherapy.

The ability of T-cell receptors (TCR) to recognize tumor-associated antigens (TAA) is a key driver of adoptive transfer of tumor-infiltrating lymphocyte (TIL) T cells, which can be a highly effective cancer immunotherapy. While it is common knowledge that TCRs are cross-reactive and can bind multiple different peptide antigens, this is typically considered an unattractive feature and limitation for TCR-based therapies. In a recent publication in Cell, Dolton and colleagues discover that certain TCRs, isolated from TILs used for successful treatment of melanoma, possess beneficial cross-reactivity by recognizing multiple TAA. Moreover, they elucidate the cumulative value of TCR cross-reactivity on cancer cell eradication and its prospective advantages for targeted cancer immunotherapies.

A method for polyclonal antigen-specific T cell-targeted genome editing (TarGET) for adoptive cell transfer applications.

Adoptive cell therapy of donor-derived, antigen-specific T cells expressing native T cell receptors (TCRs) is a powerful strategy to fight viral infections in immunocompromised patients. Determining the fate of T cells following patient infusion hinges on the ability to track them in vivo. While this is possible by genetic labeling of parent cells, the applicability of this approach has been limited by the non-specificity of the edited T cells. Here, we devised a method for CRISPR-targeted genome integration of a barcoded gene into Epstein-Barr virus-antigen-stimulated T cells and demonstrated its use for exclusively identifying expanded virus-specific cell lineages. Our method facilitated the enrichment of antigen-specific T cells, which then mediated improved cytotoxicity against Epstein-Barr virus-transformed target cells. Single-cell and deep sequencing for lineage tracing revealed the expansion profile of specific T cell clones and their corresponding gene expression signature. This approach has the potential to enhance the traceability and the monitoring capabilities during immunotherapeutic T cell regimens.

Deploying synthetic coevolution and machine learning to engineer protein-protein interactions.

Fine-tuning of protein-protein interactions occurs naturally through coevolution, but this process is difficult to recapitulate in the laboratory. We describe a platform for synthetic protein-protein coevolution that can isolate matched pairs of interacting muteins from complex libraries. This large dataset of coevolved complexes drove a systems-level analysis of molecular recognition between Z domain-affibody pairs spanning a wide range of structures, affinities, cross-reactivities, and orthogonalities, and captured a broad spectrum of coevolutionary networks. Furthermore, we harnessed pretrained protein language models to expand, in silico, the amino acid diversity of our coevolution screen, predicting remodeled interfaces beyond the reach of the experimental library. The integration of these approaches provides a means of simulating protein coevolution and generating protein complexes with diverse molecular recognition properties for biotechnology and synthetic biology.

Generation of a single-cell B cell atlas of antibody repertoires and transcriptomes to identify signatures associated with antigen specificity.

Although new genomics-based pipelines have potential to augment antibody discovery, these methods remain in their infancy due to an incomplete understanding of the selection process that governs B cell clonal selection, expansion, and antigen specificity. Furthermore, it remains unknown how factors such as aging and reduction of tolerance influence B cell selection. Here we perform single-cell sequencing of antibody repertoires and transcriptomes of murine B cells following immunizations with a model therapeutic antigen target. We determine the relationship between antibody repertoires, gene expression signatures, and antigen specificity across 100,000 B cells. Recombinant expression and characterization of 227 monoclonal antibodies revealed the existence of clonally expanded and class-switched antigen-specific B cells that were more frequent in young mice. Although integrating multiple repertoire features such as germline gene usage and transcriptional signatures failed to distinguish antigen-specific from nonspecific B cells, other features such as immunoglobulin G (IgG) subtype and sequence composition correlated with antigen specificity.

Nucleotide augmentation for machine learning-guided protein engineering.

Summary: Machine learning-guided protein engineering is a rapidly advancing field. Despite major experimental and computational advances, collecting protein genotype (sequence) and phenotype (function) data remains time- and resource-intensive. As a result, the quality and quantity of training data are often a limiting factor in developing machine learning models. Data augmentation techniques have been successfully applied to the fields of computer vision and natural language processing; however, there is a lack of such augmentation techniques for biological sequence data. Towards this end, we develop nucleotide augmentation (NTA), which leverages natural nucleotide codon degeneracy to augment protein sequence data via synonymous codon substitution. As a proof of concept for protein engineering, we test several online and offline augmentation implementations to train machine learning models with benchmark datasets of protein genotype and phenotype, revealing performance gains on par and surpassing benchmark models using a fraction of the training data. NTA also enables substantial improvements for classification tasks under heavy class imbalance. Availability and implementation: The code used in this study is publicly available at https://github.com/minotm/NTA. Supplementary information: Supplementary data are available at Bioinformatics Advances online.

Persistent virus-specific and clonally expanded antibody-secreting cells respond to induced self-antigen in the CNS.

B cells contribute to the pathogenesis of both cellular- and humoral-mediated central nervous system (CNS) inflammatory diseases through a variety of mechanisms. In such conditions, B cells may enter the CNS parenchyma and contribute to local tissue destruction. It remains unexplored, however, how infection and autoimmunity drive transcriptional phenotypes, repertoire features, and antibody functionality. Here, we profiled B cells from the CNS of murine models of intracranial (i.c.) viral infections and autoimmunity. We identified a population of clonally expanded, antibody-secreting cells (ASCs) that had undergone class-switch recombination and extensive somatic hypermutation following i.c. infection with attenuated lymphocytic choriomeningitis virus (rLCMV). Recombinant expression and characterisation of these antibodies revealed specificity to viral antigens (LCMV glycoprotein GP), correlating with ASC persistence in the brain weeks after resolved infection. Furthermore, these virus-specific ASCs upregulated proliferation and expansion programs in response to the conditional and transient induction of the LCMV GP as a neo-self antigen by astrocytes. This class-switched, clonally expanded, and mutated population persisted and was even more pronounced when peripheral B cells were depleted prior to autoantigen induction in the CNS. In contrast, the most expanded B cell clones in mice with persistent expression of LCMV GP in the CNS did not exhibit neo-self antigen specificity, potentially a consequence of local tolerance induction. Finally, a comparable population of clonally expanded, class-switched, and proliferating ASCs was detected in the cerebrospinal fluid of relapsing multiple sclerosis (RMS) patients. Taken together, our findings support the existence of B cells that populate the CNS and are capable of responding to locally encountered autoantigens.

Quantification of extracellular proteins, protein complexes and mRNAs in single cells by proximity sequencing.

We present proximity sequencing (Prox-seq) for simultaneous measurement of proteins, protein complexes and mRNAs in thousands of single cells. Prox-seq combines proximity ligation assay with single-cell sequencing to measure proteins and their complexes from all pairwise combinations of targeted proteins, providing quadratically scaled multiplexing. We validate Prox-seq and analyze a mixture of T cells and B cells to show that it accurately identifies these cell types and detects well-known protein complexes. Next, by studying human peripheral blood mononuclear cells, we discover that naïve CD8+ T cells display the protein complex CD8-CD9. Finally, we study protein interactions during Toll-like receptor (TLR) signaling in human macrophages. We observe the formation of signal-specific protein complexes, find CD36 co-receptor activity and additive signal integration under lipopolysaccharide (TLR4) and Pam2CSK4 (TLR2) stimulation, and show that quantification of protein complexes identifies signaling inputs received by macrophages. Prox-seq provides access to an untapped measurement modality for single-cell phenotyping and can discover uncharacterized protein interactions in different cell types.

speedingCARs: accelerating the engineering of CAR T cells by signaling domain shuffling and single-cell sequencing.

Chimeric antigen receptors (CARs) consist of an antigen-binding region fused to intracellular signaling domains, enabling customized T cell responses against targets. Despite their major role in T cell activation, effector function and persistence, only a small set of immune signaling domains have been explored. Here we present speedingCARs, an integrated method for engineering CAR T cells via signaling domain shuffling and pooled functional screening. Leveraging the inherent modularity of natural signaling domains, we generate a library of 180 unique CAR variants genomically integrated into primary human T cells by CRISPR-Cas9. In vitro tumor cell co-culture, followed by single-cell RNA sequencing (scRNA-seq) and single-cell CAR sequencing (scCAR-seq), enables high-throughput screening for identifying several variants with tumor killing properties and T cell phenotypes markedly different from standard CARs. Mapping of the CAR scRNA-seq data onto that of tumor infiltrating lymphocytes further helps guide the selection of variants. These results thus help expand the CAR signaling domain combination space, and supports speedingCARs as a tool for the engineering of CARs for potential therapeutic development.

Reference-based comparison of adaptive immune receptor repertoires.

B and T cell receptor (immune) repertoires can represent an individual's immune history. While current repertoire analysis methods aim to discriminate between health and disease states, they are typically based on only a limited number of parameters. Here, we introduce immuneREF: a quantitative multidimensional measure of adaptive immune repertoire (and transcriptome) similarity that allows interpretation of immune repertoire variation by relying on both repertoire features and cross-referencing of simulated and experimental datasets. To quantify immune repertoire similarity landscapes across health and disease, we applied immuneREF to >2,400 datasets from individuals with varying immune states (healthy, [autoimmune] disease, and infection). We discovered, in contrast to the current paradigm, that blood-derived immune repertoires of healthy and diseased individuals are highly similar for certain immune states, suggesting that repertoire changes to immune perturbations are less pronounced than previously thought. In conclusion, immuneREF enables the population-wide study of adaptive immune response similarity across immune states.

High-throughput T cell receptor engineering by functional screening identifies candidates with enhanced potency and specificity.

A major challenge in adoptive T cell immunotherapy is the discovery of natural T cell receptors (TCRs) with high activity and specificity to tumor antigens. Engineering synthetic TCRs for increased tumor antigen recognition is complicated by the risk of introducing cross-reactivity and by the poor correlation that can exist between binding affinity and activity of TCRs in response to antigen (peptide-MHC). Here, we developed TCR-Engine, a method combining genome editing, computational design, and deep sequencing to engineer the functional activity and specificity of TCRs on the surface of a human T cell line at high throughput. We applied TCR-Engine to successfully engineer synthetic TCRs for increased potency and specificity to a clinically relevant tumor-associated antigen (MAGE-A3) and validated their translational potential through multiple in vitro and in vivo assessments of safety and efficacy. Thus, TCR-Engine represents a valuable technology for engineering of safe and potent synthetic TCRs for immunotherapy applications.

Deep mutational learning predicts ACE2 binding and antibody escape to combinatorial mutations in the SARS-CoV-2 receptor-binding domain.

The continual evolution of SARS-CoV-2 and the emergence of variants that show resistance to vaccines and neutralizing antibodies threaten to prolong the COVID-19 pandemic. Selection and emergence of SARS-CoV-2 variants are driven in part by mutations within the viral spike protein and in particular the ACE2 receptor-binding domain (RBD), a primary target site for neutralizing antibodies. Here, we develop deep mutational learning (DML), a machine-learning-guided protein engineering technology, which is used to investigate a massive sequence space of combinatorial mutations, representing billions of RBD variants, by accurately predicting their impact on ACE2 binding and antibody escape. A highly diverse landscape of possible SARS-CoV-2 variants is identified that could emerge from a multitude of evolutionary trajectories. DML may be used for predictive profiling on current and prospective variants, including highly mutated variants such as Omicron, thus guiding the development of therapeutic antibody treatments and vaccines for COVID-19.