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.

Progress and challenges for the machine learning-based design of fit-for-purpose monoclonal antibodies.

Although the therapeutic efficacy and commercial success of monoclonal antibodies (mAbs) are tremendous, the design and discovery of new candidates remain a time and cost-intensive endeavor. In this regard, progress in the generation of data describing antigen binding and developability, computational methodology, and artificial intelligence may pave the way for a new era of in silico on-demand immunotherapeutics design and discovery. Here, we argue that the main necessary machine learning (ML) components for an in silico mAb sequence generator are: understanding of the rules of mAb-antigen binding, capacity to modularly combine mAb design parameters, and algorithms for unconstrained parameter-driven in silico mAb sequence synthesis. We review the current progress toward the realization of these necessary components and discuss the challenges that must be overcome to allow the on-demand ML-based discovery and design of fit-for-purpose mAb therapeutic candidates.

Role of Dexamethasone and Methylprednisolone Corticosteroids in Coronavirus Disease 2019 Hospitalized Patients: A Review.

The WHO announced coronavirus disease 2019 (COVID-19) as a pandemic disease globally on March 11, 2020, after it emerged in China. The emergence of COVID-19 has lasted over a year, and despite promising vaccine reports that have been produced, we still have a long way to go until such remedies are accessible to everyone. The immunomodulatory strategy has been kept at the top priority for the research agenda for COVID-19. Corticosteroids have been used to modulate the immune response in a wide range of diseases for the last 70 years. These drugs have been shown to avoid and reduce inflammation in tissues and the bloodstream through non-genomic and genomic effects. Now, the use of corticosteroids increased the chance of survival and relief by combating the viral strong inflammatory impacts and has moved to the forefront in the management of patients seeking supplemental oxygen. The goal of this review is to illuminate dexamethasone and methylprednisolone, i.e., in terms of their chemical and physical properties, role in COVID-19 patients suffering from pneumonia, the proposed mode of action in COVID-19, pharmacokinetics, pharmacodynamics, clinical outcomes in immunocompromised populations with COVID-19, interaction with other drugs, and contradiction to explore the trends and perspectives for future research. Literature was searched from scientific databases such as Science Direct, Wiley, Springer, PubMed, and books for the preparation of this review. The RECOVERY trial, a massive, multidisciplinary, randomized, and open-label trial, is mainly accountable for recommendations over the usage of corticosteroids in COVID-19 patients. The corticosteroids such as dexamethasone and methylprednisolone in the form of medication have anti-inflammatory, analgesic, and anti-allergic characteristics, including the ability to inhibit the immune system. These drugs are also recommended for treating symptoms of multiple ailments such as rheumatic and autoimmune diseases, leukemia, multiple myeloma, and Hodgkin's and non-Hodgkin's lymphoma along with other drugs. Toxicology studies proved them safe usually at low dosage via oral or other routes.

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.

Amelioration of collagen antibody induced arthritis in mice by an antibody directed against the fibronectin type III repeats of tenascin-C: Targeting fibronectin type III repeats of tenascin-C in rheumatoid arthritis.

Tenascin-C (TN-C) levels are elevated in the synovial tissue and fluid, as well as cartilage of rheumatoid arthritis (RA) patients. In addition, the presence of TN-C fragments has also been documented in arthritic cartilage. We have previously shown that a single chain variable fragment antibody (TN64), directed against the fibronectin type III repeats 1-5 (TNfnIII 1-5) of TN-C, effectively inhibits fibrotic pathology. Given that fibrosis results from chronic inflammation, and the fact that increased levels of TN-C in the synovial fluid of patients with RA contributes to synovial inflammation and joint destruction, we aimed to investigate the role of TNfnIII 1-5 region of TN-C in RA pathogenesis. Using either the wild type or variants of the two integrin-binding motifs (RGD and AEIDGIEL) present within the TNfnIII 1-5 polypeptide, we demonstrate that the adhesion and migration of synovial fibroblasts is RGD-dependent. The antibody TN64 is effective in inhibiting migration of cells in response to TnfnIII 1-5, and prevents fibroblast-mediated destruction of cartilage. The TN64 antibody was further tested in collagen antibody induced arthritic (CAIA) mice. Our data shows the efficacy of TN64 in preventing induction of arthritis, with significant downregulation of RA-associated cytokines. This suggests that components of the extracellular matrix such as the TNfnIII 1-5 region of TN-C could be exploited to develop therapies to suppress inflammation seen in RA. The TN64 antibody is one such promising candidate in the development of novel treatments for RA.

Blocking osteopontin-fibronectin interactions reduce extracellular fibronectin deployment and arthritic immunopathology.

Elevated levels of a thrombin-cleaved fragment of osteopontin (OPNT) are seen in synovial fluid (SF) and tissues of rheumatoid arthritis (RA) patients. OPNT binds to integrins on cell surfaces, inducing adhesion, migration and survival of inflammatory cells in the synovial joints, where OPNT binds to fibronectin to link fibroblast-like synoviocytes (FLS) with B cells, stimulating the latter to produce inflammatory cytokines. Our aim was to block OPNT-fibronectin interactions and examine whether this reduces inflammation. A human antibody (phage displayed) library was used to select scFv antibodies cognate to OPNT, and a particular scFv antibody (scFv 31) was evaluated. Adhesion, migration and fibronectin polymerization of FLS cells derived from RA patients were monitored, in cultures incorporating scFv 31. Also, scFv 31 was used in mice with CAIA (collagen antibody-induced arthritis), subjected to clinical and histological assessment, analysis of fibronectin and cartilage damage and induction of pro-inflammatory cytokines. The scFv antibody, scFv 31, appeared to cause significantly reduced migration of synovial fibroblasts, altered cell morphology, changes in actin stress fiber arrangement, and marked reduction in fibronectin. In CAIA mice, scFv 31 appeared to prevent arthritic changes through inhibition of synovial hypertrophy and loss of articular cartilage, decrease in fibronectin polymerization and expression of pro-inflammatory cytokines implicated in arthritis. Osteopontin-fibronectin interaction(s) appear to play a role in the expression of key inflammatory molecules by B cells infiltrating the synovial joint. The scFv antibody, scFv 31, provides a potential therapeutic lead for inhibition of some processes implicated in rheumatoid arthritis.