Application and challenges of TCR and BCR sequencing to investigate T- and B-cell clonality in elastase-induced experimental murine abdominal aortic aneurysm.

Background: An abdominal aortic aneurysm (AAA) is a life-threatening cardiovascular disease. Although its pathogenesis is still poorly understood, recent evidence suggests that AAA displays autoimmune disease characteristics. Particularly, T cells responding to AAA-related antigens in the aortic wall may contribute to an initial immune response. Single-cell RNA (scRNA) T cell receptor (TCR) and B cell receptor (BCR) sequencing is a powerful tool for investigating clonality. However, difficulties such as limited numbers of isolated cells must be considered during implementation and data analysis, making biological interpretation challenging. Here, we perform a representative single-cell immune repertoire analysis in experimental murine AAA and show a reliable bioinformatic processing pipeline highlighting opportunities and limitations of this approach. Methods: We performed scRNA TCR and BCR sequencing of isolated lymphocytes from the infrarenal aorta of male C57BL/6J mice 3, 7, 14, and 28 days after AAA induction via elastase perfusion of the aorta. Sham-operated mice at days 3 and 28 and non-operated mice served as controls. Results: Comparison of complementarity-determining region (CDR3) length distribution of 179 B cells and 796 T cells revealed neither differences between AAA and control nor between the disease stages. We found no clonal expansion of B cells in AAA. For T cells, we identified several clones in 11 of 16 AAA samples and one of eight control samples. Immune receptor repertoire comparison indicated that only a few clones were shared between the individual AAA samples. The most frequently used V-genes in the TCR beta chain in AAA were TRBV3, TRBV19, and the splicing variant TRBV12-2 + TRBV13-2. Conclusion: We found no clonal expansion of B cells but evidence for clonal expansion of T cells in elastase-induced AAA in mice. Our findings imply that a more precise characterization of TCR and BCR distribution requires a more extensive number of lymphocytes to prevent undersampling and potentially detect rare clones. Thus, further experiments are necessary to confirm our findings. In summary, this paper examines TCR and BCR sequencing results, identifies limitations and pitfalls, and offers guidance for future studies.

Human thymic putative CD8αα precursors exhibit a biased TCR repertoire in single cell AIRR-seq.

Thymic T cell development comprises T cell receptor (TCR) recombination and assessment of TCR avidity towards self-peptide-MHC complexes presented by antigen-presenting cells. Self-reactivity may lead to negative selection, or to agonist selection and differentiation into unconventional lineages such as regulatory T cells and CD8[Formula: see text] T cells. To explore the effect of the adaptive immune receptor repertoire on thymocyte developmental decisions, we performed single cell adaptive immune receptor repertoire sequencing (scAIRR-seq) of thymocytes from human young paediatric thymi and blood. Thymic PDCD1+ cells, a putative CD8[Formula: see text] T cell precursor population, exhibited several TCR features previously associated with thymic and peripheral ZNF683+ CD8[Formula: see text] T cells, including enrichment of large and positively charged complementarity-determining region 3 (CDR3) amino acids. Thus, the TCR repertoire may partially explain the decision between conventional vs. agonist selected thymocyte differentiation, an aspect of importance for the development of therapies for patients with immune-mediated diseases.

Profiling the baseline performance and limits of machine learning models for adaptive immune receptor repertoire classification.

BACKGROUND: Machine learning (ML) methodology development for the classification of immune states in adaptive immune receptor repertoires (AIRRs) has seen a recent surge of interest. However, so far, there does not exist a systematic evaluation of scenarios where classical ML methods (such as penalized logistic regression) already perform adequately for AIRR classification. This hinders investigative reorientation to those scenarios where method development of more sophisticated ML approaches may be required. RESULTS: To identify those scenarios where a baseline ML method is able to perform well for AIRR classification, we generated a collection of synthetic AIRR benchmark data sets encompassing a wide range of data set architecture-associated and immune state-associated sequence patterns (signal) complexity. We trained ≈1,700 ML models with varying assumptions regarding immune signal on ≈1,000 data sets with a total of ≈250,000 AIRRs containing ≈46 billion TCRß CDR3 amino acid sequences, thereby surpassing the sample sizes of current state-of-the-art AIRR-ML setups by two orders of magnitude. We found that L1-penalized logistic regression achieved high prediction accuracy even when the immune signal occurs only in 1 out of 50,000 AIR sequences. CONCLUSIONS: We provide a reference benchmark to guide new AIRR-ML classification methodology by (i) identifying those scenarios characterized by immune signal and data set complexity, where baseline methods already achieve high prediction accuracy, and (ii) facilitating realistic expectations of the performance of AIRR-ML models given training data set properties and assumptions. Our study serves as a template for defining specialized AIRR benchmark data sets for comprehensive benchmarking of AIRR-ML methods.

In silico proof of principle of machine learning-based antibody design at unconstrained scale.

Generative machine learning (ML) has been postulated to become a major driver in the computational design of antigen-specific monoclonal antibodies (mAb). However, efforts to confirm this hypothesis have been hindered by the infeasibility of testing arbitrarily large numbers of antibody sequences for their most critical design parameters: paratope, epitope, affinity, and developability. To address this challenge, we leveraged a lattice-based antibody-antigen binding simulation framework, which incorporates a wide range of physiological antibody-binding parameters. The simulation framework enables the computation of synthetic antibody-antigen 3D-structures, and it functions as an oracle for unrestricted prospective evaluation and benchmarking of antibody design parameters of ML-generated antibody sequences. We found that a deep generative model, trained exclusively on antibody sequence (one dimensional: 1D) data can be used to design conformational (three dimensional: 3D) epitope-specific antibodies, matching, or exceeding the training dataset in affinity and developability parameter value variety. Furthermore, we established a lower threshold of sequence diversity necessary for high-accuracy generative antibody ML and demonstrated that this lower threshold also holds on experimental real-world data. Finally, we show that transfer learning enables the generation of high-affinity antibody sequences from low-N training data. Our work establishes a priori feasibility and the theoretical foundation of high-throughput ML-based mAb design.

simAIRR: simulation of adaptive immune repertoires with realistic receptor sequence sharing for benchmarking of immune state prediction methods.

BACKGROUND: Machine learning (ML) has gained significant attention for classifying immune states in adaptive immune receptor repertoires (AIRRs) to support the advancement of immunodiagnostics and therapeutics. Simulated data are crucial for the rigorous benchmarking of AIRR-ML methods. Existing approaches to generating synthetic benchmarking datasets result in the generation of naive repertoires missing the key feature of many shared receptor sequences (selected for common antigens) found in antigen-experienced repertoires. RESULTS: We demonstrate that a common approach to generating simulated AIRR benchmark datasets can introduce biases, which may be exploited for undesired shortcut learning by certain ML methods. To mitigate undesirable access to true signals in simulated AIRR datasets, we devised a simulation strategy (simAIRR) that constructs antigen-experienced-like repertoires with a realistic overlap of receptor sequences. simAIRR can be used for constructing AIRR-level benchmarks based on a range of assumptions (or experimental data sources) for what constitutes receptor-level immune signals. This includes the possibility of making or not making any prior assumptions regarding the similarity or commonality of immune state-associated sequences that will be used as true signals. We demonstrate the real-world realism of our proposed simulation approach by showing that basic ML strategies perform similarly on simAIRR-generated and real-world experimental AIRR datasets. CONCLUSIONS: This study sheds light on the potential shortcut learning opportunities for ML methods that can arise with the state-of-the-art way of simulating AIRR datasets. simAIRR is available as a Python package: https://github.com/KanduriC/simAIRR.

Progress and challenges in mass spectrometry-based analysis of antibody repertoires.

Humoral immunity is divided into the cellular B cell and protein-level antibody responses. High-throughput sequencing has advanced our understanding of both these fundamental aspects of B cell immunology as well as aspects pertaining to vaccine and therapeutics biotechnology. Although the protein-level serum and mucosal antibody repertoire make major contributions to humoral protection, the sequence composition and dynamics of antibody repertoires remain underexplored. This limits insight into important immunological and biotechnological parameters such as the number of antigen-specific antibodies, which are for example, relevant for pathogen neutralization, microbiota regulation, severity of autoimmunity, and therapeutic efficacy. High-resolution mass spectrometry (MS) has allowed initial insights into the antibody repertoire. We outline current challenges in MS-based sequence analysis of antibody repertoires and propose strategies for their resolution.

Unconstrained generation of synthetic antibody-antigen structures to guide machine learning methodology for antibody specificity prediction.

Machine learning (ML) is a key technology for accurate prediction of antibody-antigen binding. Two orthogonal problems hinder the application of ML to antibody-specificity prediction and the benchmarking thereof: the lack of a unified ML formalization of immunological antibody-specificity prediction problems and the unavailability of large-scale synthetic datasets to benchmark real-world relevant ML methods and dataset design. Here we developed the Absolut! software suite that enables parameter-based unconstrained generation of synthetic lattice-based three-dimensional antibody-antigen-binding structures with ground-truth access to conformational paratope, epitope and affinity. We formalized common immunological antibody-specificity prediction problems as ML tasks and confirmed that for both sequence- and structure-based tasks, accuracy-based rankings of ML methods trained on experimental data hold for ML methods trained on Absolut!-generated data. The Absolut! framework has the potential to enable real-world relevant development and benchmarking of ML strategies for biotherapeutics design.

Individualized VDJ recombination predisposes the available Ig sequence space.

The process of recombination between variable (V), diversity (D), and joining (J) immunoglobulin (Ig) gene segments determines an individual's naive Ig repertoire and, consequently, (auto)antigen recognition. VDJ recombination follows probabilistic rules that can be modeled statistically. So far, it remains unknown whether VDJ recombination rules differ between individuals. If these rules differed, identical (auto)antigen-specific Ig sequences would be generated with individual-specific probabilities, signifying that the available Ig sequence space is individual specific. We devised a sensitivity-tested distance measure that enables inter-individual comparison of VDJ recombination models. We discovered, accounting for several sources of noise as well as allelic variation in Ig sequencing data, that not only unrelated individuals but also human monozygotic twins and even inbred mice possess statistically distinguishable immunoglobulin recombination models. This suggests that, in addition to genetic, there is also nongenetic modulation of VDJ recombination. We demonstrate that population-wide individualized VDJ recombination can result in orders of magnitude of difference in the probability to generate (auto)antigen-specific Ig sequences. Our findings have implications for immune receptor-based individualized medicine approaches relevant to vaccination, infection, and autoimmunity.

TCR repertoire diversity in Multiple Sclerosis: High-dimensional bioinformatics analysis of sequences from brain, cerebrospinal fluid and peripheral blood.

BACKGROUND: T cells play a key role in the pathogenesis of multiple sclerosis (MS), a chronic, inflammatory, demyelinating disease of the central nervous system (CNS). Although several studies recently investigated the T-cell receptor (TCR) repertoire in cerebrospinal fluid (CSF) of MS patients by high-throughput sequencing (HTS), a deep analysis on repertoire similarities and differences among compartments is still missing. METHODS: We performed comprehensive bioinformatics on high-dimensional TCR Vß sequencing data from published and unpublished MS and healthy donors (HD) studies. We evaluated repertoire polarization, clone distribution, shared CDR3 amino acid sequences (CDR3s-a.a.) across repertoires, clone overlap with public databases, and TCR similarity architecture. FINDINGS: CSF repertoires showed a significantly higher public clones percentage and sequence similarity compared to peripheral blood (PB). On the other hand, we failed to reject the null hypothesis that the repertoire polarization is the same between CSF and PB. One Primary-Progressive MS (PPMS) CSF repertoire differed from the others in terms of TCR similarity architecture. Cluster analysis splits MS from HD. INTERPRETATION: In MS patients, the presence of a physiological barrier, the blood-brain barrier, does not impact clone prevalence and distribution, but impacts public clones, indicating CSF as a more private site. We reported a high Vß sequence similarity in the CSF-TCR architecture in one PPMS. If confirmed it may be an interesting insight into MS progressive inflammatory mechanisms. The clustering of MS repertoires from HD suggests that disease shapes the TCR Vß clonal profile. FUNDING: This study was partly financially supported by the Italian Multiple Sclerosis Foundation (FISM), that contributed to Ballerini-DB data collection (grant #2015 R02).

The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires.

Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. To date, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency, and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (i) reproducing a large-scale study on immune state prediction, (ii) developing, integrating, and applying a novel deep learning method for antigen specificity prediction, and (iii) showcasing streamlined interpretability-focused benchmarking of AIRR ML.