BMS-986414 for COVID-19

Abstract Summary Since the emergence of SARS-CoV-2, numerous studies have investigated antibody interactions with viral variants in vitro, and several datasets have been curated to compile available protein structures and experimental measurements. However, existing data remain fragmented, limiting their utility for the development and validation of machine learning models for antibody–antigen interaction prediction. Here, we present CoV-UniBind, a unified database comprising over 75 000 entries of SARS-CoV-2 antibody–antigen sequence, binding, and structural data, integrated and standardized from three public sources and multiple peer-reviewed publications. To demonstrate its utility, we benchmarked multiple protein folding, inverse folding, and language models across tasks relevant to antibody design and vaccine development. We expect CoV-UniBind to facilitate future computational efforts in antibody and vaccine development against SARS-CoV-2. Availability and implementation The curated datasets, model scores and antibody synonyms are free to download at https://huggingface.co/datasets/InstaDeepAI/cov-unibind. Folded structures are available upon request.

ABSTRACT Context To meet the need for effective treatments during the COVID‐19 Public Health Emergency, the U.S. government sought to accelerate the discovery and development of new antiviral treatments—a process that normally took 4–12 years. The government changed many features of the established system, selecting the investigational drugs, sponsoring or conducting the clinical testing, and purchasing and managing the distribution of the successful products. Methods We focused on novel therapeutic agents for COVID‐19 that were funded, clinically tested, and/or received Emergency Use Authorization during the Public Health Emergency from January 2020 to May 2023. The primary sources were the public records of the National Institutes of Health, the U.S. Food and Drug Administration, and the Biomedical Advanced Research and Development Authority. Excluded were vaccines, devices, diagnostic tests, and new indications for approved drugs. Results In less than 24 months, the emergency program developed, tested, approved, and distributed eight new therapeutic products, including six monoclonal antibodies and two new oral antivirals. In addition, 11 other investigational agents were funded or tested under the emergency program but did not receive Emergency Use Authorization. More than 30 million courses of treatment were distributed at a cost of $29 billion or $881 per patient. By the end of the emergency, viral mutations and rapidly growing population immunity rendered the new products ineffective in almost all patients. Conclusions The emergency program was dramatically effective in finding and testing new drug treatments using a variety of clinically relevant endpoints and serving varied patient populations. Planning for future pandemics should include a global network of clinical testing centers that were key to a rapid response. Research is needed to discover more durable antiviral treatments, especially in settings where mutation and population immunity are subject to rapid change.