Highlights d Prediction of antibody-antigen binding is a central question in immunology d A motif vocabulary of paratope-epitope interactions governs antibody specificity d Proof of principle that antibody-antigen binding is predictable d Implications for de novo antibody and (neo-)epitope design

The adaptive immune system is a natural diagnostic and therapeutic. It recognizes threats earlier than clinical symptoms manifest and neutralizes antigen with exquisite specificity. Recognition specificity and broad reactivity is enabled via adaptive B-and T-cell receptors: the immune receptor repertoire. The human immune system, however, is not omnipotent. Our natural defense system sometimes loses the battle to parasites and microbes and even turns against us in the case of cancer and (autoimmune) inflammatory disease. A long-standing dream of immunoengineers has been, therefore, to mechanistically understand how the immune system "sees", "reacts" and "remembers" (auto)antigens. Only very recently, experimental and computational methods have achieved sufficient quantitative resolution to start querying and engineering adaptive immunity with great precision. In specific, these innovations have been applied with the greatest fervency and success in immunotherapy, autoimmunity and vaccine design. The work here highlights advances, challenges and future directions of quantitative approaches which seek to advance the fundamental understanding of immunological phenomena, and reverse engineer the immune system to produce auspicious biopharmaceutical drugs and immunodiagnostics. Our review indicates that the merger of fundamental immunology, computational immunology and (digital) biotechnology minimizes black box engineering, thereby advancing both immunological knowledge and as well immunoengineering methodologies. Introduction 3Advancing immunology through engineering innovations 3Adaptive immune receptors are natural diagnostics and therapeutics 3Engineering the vast immune receptor sequence space requires quantitative approaches 4Current approaches for immune repertoire analysis and immunoengineering 4Computational immunology and immunoinformatics of adaptive immunity 4 B-and T-cell pattern mining using machine and deep learning 6Mathematical modeling of immune receptor recognition 8Computational modeling of immune receptor 3D structure 9Computational modeling of antibody-epitope interaction 10Genomic sequencing of immune repertoires 12Identifying candidate TCRs or antibodies via high-throughput library screens 13Proteomic sequencing and serological profiling of antibody repertoires 14 Future directions for quantitative immunoengineering and immune receptor analysis 15Setting targets on public and private immune receptors 15Efficient modification of immune receptor activity in vitro and in vivo 16De novo design of immune receptor sequences 18Closing the data gap between immune receptor sequence and cognate epitope for immune receptor and epitope engineering 21Challenges in machine learning analysis on immune receptor repertoires 21Relating immune receptor antigen specificity to cellular transcriptomic profile 24 Conclusion 25 Conflicts of Interest 25 Focus Boxes 26Focus Box 1: Brief summary of deep learning and its architectures. 26Focus Box 2: Recognition holes in the immune repertoire 26 Notes and references 30mo...

Antibody recognition of antigen relies on the specific interaction of amino acids at the paratopeepitope interface. A long-standing question in the fields of immunology and structural biology is whether paratope-epitope interaction is predictable. A fundamental premise for the predictability of paratope-epitope binding is the existence of structural units that are universally shared among antibody-antigen binding complexes. Here, we identified structural interaction motifs, which together compose a vocabulary of paratope-epitope binding that is shared among investigated antibody-antigen complexes. The vocabulary (i) is finite with less than 10 4 motifs, (ii) mediates specific and non-redundant interactions between paratope-epitope pairs, (iii) is immunity-specific (distinct from the motif vocabulary used by non-immune protein-protein interactions), and (iv) enables the machine learning prediction of paratope or epitope. The discovery of a vocabulary of paratope-epitope interaction demonstrates the learnability and predictability of paratope-epitope interaction.

Machine learning (ML) is a key technology to enable accurate prediction of antibody-antigen binding, a prerequisite for in silico vaccine and antibody design. Two orthogonal problems hinder the current application of ML to antibody-specificity prediction and the benchmarking thereof: (i) The lack of a unified formalized mapping of immunological antibody specificity prediction problems into ML notation and (ii) the unavailability of large-scale training datasets. Here, we developed the Absolut! software suite that allows the parameter-based unconstrained generation of synthetic lattice-based 3D-antibody-antigen binding structures with ground-truth access to conformational paratope, epitope, and affinity. We show that Absolut!-generated datasets recapitulate critical biological sequence and structural features that render antibody-antigen binding prediction challenging. To demonstrate the immediate, high-throughput, and large-scale applicability of Absolut!, we have created an online database of 1 billion antibody-antigen structures, the extension of which is only constrained by moderate computational resources. We translated immunological antibody specificity prediction problems into ML tasks and used our database to investigate paratope-epitope binding prediction accuracy as a function of structural information encoding, dataset size, and ML method, which is unfeasible with existing experimental data. Furthermore, we found that in silico investigated conditions, predicted to increase antibody specificity prediction accuracy, align with and extend conclusions drawn from experimental antibody-antigen structural data. In summary, the Absolut! framework enables the development and benchmarking of ML strategies for biotherapeutics discovery and design.

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 method for antigen specificity prediction, and (iii) showcasing streamlined interpretability-focused benchmarking of AIRR ML. 1.