RESUMO
Through machine learning, identifying correlations between amino acid sequences of antibodies and their observed characteristics, we developed an internal viscosity prediction model to empower the rapid engineering of therapeutic antibody candidates. For a highly viscous anti-IL-13 monoclonal antibody, we used a structure-based rational design strategy to generate a list of variants that were hypothesized to mitigate viscosity. Our viscosity prediction tool was then used as a screen to cull virtually engineered variants with a probability of high viscosity while advancing those with a probability of low viscosity to production and testing. By combining the rational design engineering strategy with the in silico viscosity prediction screening step, we were able to efficiently improve the highly viscous anti-IL-13 candidate, successfully decreasing the viscosity at 150 mg/mL from 34 cP to 13 cP in a panel of 16 variants.
Assuntos
Anticorpos Monoclonais , Engenharia de Proteínas , Viscosidade , Engenharia de Proteínas/métodos , Anticorpos Monoclonais/química , Anticorpos Monoclonais/imunologia , Aprendizado de Máquina , Sequência de Aminoácidos , HumanosRESUMO
Atopic dermatitis (AD) is a chronic, heterogeneous, inflammatory disease characterized by skin lesions, pruritus, and pain. Patients with moderate-to-severe AD experience chronic symptoms, intensified by unpredictable flares, and often have comorbidities and secondary complications, which can result in significant clinical burden that impacts the patient's overall quality of life. The complex interplay of immune dysregulation and skin barrier disruption drives AD pathogenesis, of which T-cell-dependent inflammation plays a critical role in patients with AD. Despite new targeted therapies, many patients with moderate-to-severe AD fail to achieve or sustain their individual treatment goals and/or may not be suitable for or tolerate these therapies. There remains a need for a novel, efficacious, well-tolerated therapeutic option that can deliver durable benefits across a heterogeneous AD patient population. Expression of OX40 [tumor necrosis factor receptor superfamily, member 4 (TNFRSF4)], a prominent T-cell co-stimulatory molecule, and its ligand [OX40L; tumor necrosis factor superfamily, member 4 (TNFSF4)] is increased in AD. As the OX40 pathway is critical for expansion, differentiation, and survival of effector and memory T cells, its targeting might be a promising therapeutic approach to provide sustained inhibition of pathogenic T cells and associated inflammation and broad disease control. Antibodies against OX40 [rocatinlimab (AMG 451/KHK4083) and telazorlimab (GBR 830)] or OX40L [amlitelimab (KY1005)] have shown promising results in early-phase clinical studies of moderate-to-severe AD, highlighting the importance of OX40 signaling as a new therapeutic target in AD.