Machine Learning Detects Anti-DENV Signatures in Antibody Repertoire Sequences

Machine learning for precision diagnostics of autoimmunity

Early and accurate diagnosis is crucial to prevent disease development and define therapeutic strategies. Due to predominantly unspecific symptoms, diagnosis of autoimmune diseases (AID) is notoriously challenging. Clinical decision support systems (CDSS) are a promising method with the potential to enhance and expedite precise diagnostics by physicians. However, due to the difficulties of integrating and encoding multi-omics data with clinical values, as well as a lack of standardization, such systems are often limited to certain data types. Accordingly, even sophisticated data models fall short when making accurate disease diagnoses and presenting data analyses in a user-friendly form. Therefore, the integration of various data types is not only an opportunity but also a competitive advantage for research and industry. We have developed an integration pipeline to enable the use of machine learning for patient classification based on multi-omics data in combination with clinical values and laboratory results. The application of our framework resulted in up to 96% prediction accuracy of autoimmune diseases with machine learning models. Our results deliver insights into autoimmune disease research and have the potential to be adapted for applications across disease conditions.

Immunisation of chickens with inactivated and/or infectious H9N2 avian influenza virus leads to differential immune B-cell repertoire development

Avian influenza viruses (AIVs) are a major economic burden to the poultry industry and pose serious zoonotic risks, with human infections being reported every year. To date, the vaccination of birds remains the most important method for the prevention and control of AIV outbreaks. Most national vaccination strategies against AIV infection use whole virus-inactivated vaccines, which predominantly trigger a systemic antibody-mediated immune response. There are currently no studies that have examined the antibody repertoire of birds that were infected with and/or vaccinated against AIV. To this end, we evaluate the changes in the H9N2-specific IgM and IgY repertoires in chickens subjected to vaccination(s) and/or infectious challenge. We show that a large proportion of the IgM and IgY clones were shared across multiple individuals, and these public clonal responses are dependent on both the immunisation status of the birds and the specific tissue that was examined. Furthermore, the analysis revealed specific clonal expansions that are restricted to particular H9N2 immunisation regimes. These results indicate that both the nature and number of immunisations are important drivers of the antibody responses and repertoire profiles in chickens following H9N2 antigenic stimulation. We discuss how the repertoire biology of avian B-cell responses may affect the success of AIV vaccination in chickens, in particular the implications of public versus private clonal selection.

High throughput long-read sequencing of circulating lymphocytes of the evolutionarily distant sea lamprey reveals diversity and common elements of the variable lymphocyte receptor B (VLRB) repertoire

The leucine-rich repeat-based variable lymphocyte receptor B (VLRB) antibody system of jawless vertebrates is capable of generating an antibody repertoire equal to or exceeding the diversity of antibody repertoires of jawed vertebrates. Unlike immunoglobulin-based immune repertoires, the VLRB repertoire diversity is characterized by variable lengths of VLRB encoding transcripts, rendering conventional immunoreceptor repertoire sequencing approaches unsuitable for VLRB repertoire sequencing. Here we demonstrate that long-read single-molecule real-time (SMRT) sequencing (PacBio) approaches permit the efficient large-scale assessment of the VLRB repertoire. We present a computational pipeline for sequence data processing and provide the first repertoire-based analysis of VLRB protein characteristics including properties of its subunits and regions of diversity within each structural leucine-rich repeat subunit. Our study provides a template to explore changes in the VLRB repertoire during immune responses and to establish large scale VLRB repertoire databases for computational approaches aimed at isolating monoclonal VLRB reagents for biomedical research and clinical applications.

Machine-learning-assisted high-throughput identification of potent and stable neutralizing antibodies against all four dengue virus serotypes

Several computational methods have been developed to identify neutralizing antibodies (NAbs) covering four dengue virus serotypes (DENV-1 to DENV-4); however, limitations of the dataset and the resulting performance remain. Here, we developed a new computational framework to predict potent and stable NAbs against DENV-1 to DENV-4 using only antibody (CDR-H3) and epitope sequences as input. Specifically, our proposed computational framework employed sequence-based ML and molecular dynamic simulation (MD) methods to achieve more accurate identification. First, we built a novel dataset (n = 1108) by compiling the interactions of CDR-H3 and epitope sequences with the half maximum inhibitory concentration (IC50) values, which represent neutralizing activities. Second, we achieved an accurately predictive ML model that showed high AUC values of 0.879 and 0.885 by tenfold cross-validation and independent tests, respectively. Finally, our computational framework could be applied to filter approximately 2.5 million unseen antibodies into two final candidates that showed strong and stable binding to all four serotypes. In addition, the most potent and stable candidate (1B3B9_V21) was evaluated for its development potential as a therapeutic agent by molecular docking and MD simulations. This study provides an antibody computational approach to facilitate the high-throughput identification of NAbs and accelerate the development of therapeutic antibodies.

Predicting class switch recombination in B-cells from antibody repertoire data

Statistical and machine learning methods have proved useful in many areas of immunology. In this paper, we address for the first time the problem of predicting the occurrence of class switch recombination (CSR) in B-cells, a problem of interest in understanding antibody response under immunological challenges. We propose a framework to analyze antibody repertoire data, based on clonal (CG) group representation in a way that allows us to predict CSR events using CG level features as input. We assess and compare the performance of several predicting models (logistic regression, LASSO logistic regression, random forest, and support vector machine) in carrying out this task. The proposed approach can obtain an unweighted average recall of71 % $71\%$ with models based on variable region descriptors and measures of CG diversity during an immune challenge and, most notably, before an immune challenge.

The dengue-specific immune response and antibody identification with machine learning

Dengue virus poses a serious threat to global health and there is no specific therapeutic for it. Broadly neutralizing antibodies recognizing all serotypes may be an effective treatment. High-throughput adaptive immune receptor repertoire sequencing (AIRR-seq) and bioinformatic analysis enable in-depth understanding of the B-cell immune response. Here, we investigate the dengue antibody response with these technologies and apply machine learning to identify rare and underrepresented broadly neutralizing antibody sequences. Dengue immunization elicited the following signatures on the antibody repertoire: (i) an increase of CDR3 and germline gene diversity; (ii) a change in the antibody repertoire architecture by eliciting power-law network distributions and CDR3 enrichment in polar amino acids; (iii) an increase in the expression of JNK/Fos transcription factors and ribosomal proteins. Furthermore, we demonstrate the applicability of computational methods and machine learning to AIRR-seq datasets for neutralizing antibody candidate sequence identification. Antibody expression and functional assays have validated the obtained results.

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.

Predicting antibody binders and generating synthetic antibodies using deep learning

The antibody drug field has continually sought improvements to methods for candidate discovery and engineering. Historically, most such methods have been laboratory-based, but informatics methods have recently started to make an impact. Deep learning, a subfield of machine learning, is rapidly gaining prominence in the biomedical research. Recent advances in microfluidics technologies and next-generation sequencing have not only revolutionized therapeutic antibody discovery, but also contributed to a vast amount of antibody repertoire sequencing data, providing opportunities for deep learning-based applications. Previously, we used microfluidics, yeast display, and deep sequencing to generate a panel of binder and non-binder antibody sequences to the cancer immunotherapy targets PD-1 and CTLA-4. Here we encoded the antibody light and heavy chain complementarity-determining regions (CDR3s) into antibody images, then built and trained convolutional neural network models to classify binders and non-binders. To improve model interpretability, we performed in silico mutagenesis to identify CDR3 residues that were important for binder classification. We further built generative deep learning models using generative adversarial network models to produce synthetic antibodies against PD-1 and CTLA-4. Our models generated variable length CDR3 sequences that resemble real sequences. Overall, our study demonstrates that deep learning methods can be leveraged to mine and learn patterns in antibody sequences, offering insights into antibody engineering, optimization, and discovery.

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.