Securing Commercialization Rights Just Nine Months After Project Launch
Industry Sees "Positive Signal" in Early Results
Taking on the High-Difficulty Challenge of AI-Designed Antibody Drugs

Samsung Bioepis has begun evaluating the potential of antibody drugs designed by artificial intelligence (AI). Instead of immediately acquiring candidate substances, the company is adopting an option contract that allows it to select only those antibodies designed and verified by domestic AI that demonstrate strong performance. This marks the company’s official entry into the emerging field of “AI antibody design,” which is still in its early stages globally.


Samsung Bioepis Launches Antibody Drug Initiative with Nobel Lineage Domestic AI View original image

According to the industry on July 10, Samsung Bioepis signed an AI-based antibody drug co-development and technology transfer option agreement with Proteina, an AI drug development specialist company, the previous day. For reasons related to its patent strategy, Proteina has decided not to disclose the specific contract amount until 2047. This research is considered highly significant as it represents the first test of expanding AI drug development from small molecules to antibodies. Until now, most achievements in AI drug development have focused on relatively simple small molecule compounds. For example, the first AI-designed drug to enter clinical trials, developed by British company Exscientia in 2020, and Insilico Medicine’s phase 2 clinical results for a pulmonary fibrosis treatment published in Nature Medicine in June last year, were both based on small molecules. In contrast, the design and optimization of antibodies, which are larger and more complex, present greater challenges; as a result, AI-driven drug development in this area is still considered uncharted territory where notable breakthroughs have yet to be achieved. A Samsung Bioepis representative explained, “Rather than limiting ourselves to a particular modality (drug type), we are broadly exploring the full range of antibody drugs—including monoclonal antibodies, bispecific antibodies, and antibody-drug conjugates (ADCs)—to identify the best candidates.”


The industry views this option contract as a signal that business potential has been identified at an early stage, going beyond joint research. When the national government project was launched in October last year, Samsung Bioepis, Proteina, and the Seoul National University research team were simply engaged in a government-funded joint research relationship without any separate business contract. However, just nine months after the project’s initiation, Samsung Bioepis moved to secure future commercialization rights (options) for antibody candidates that may be discovered. An industry source stated, “The fact that commercial terms such as upfront payments, milestones, and royalties have already been set at this stage can be seen as a positive assessment of the early research results.” The number and timing of option exercises by Samsung Bioepis will be determined through internal evaluation before the project concludes at the end of 2027.


This initiative is underpinned by world-class domestic AI technology. The project, a government-funded initiative with a total budget of about 46.9 billion won, is led by Proteina, with Samsung Bioepis and Professor Baek Min-kyung’s Seoul National University research team participating as joint research institutions. Professor Baek is regarded as a global authority in the field of AI-based antibody design, having been the first author of the paper that developed the protein structure prediction and design AI “RoseTTAFold” together with Professor David Baker of the University of Washington, who won the Nobel Prize in Chemistry in 2024.



Each institution will divide responsibilities for antibody design, verification, and development to increase the efficiency of candidate discovery. Professor Baek’s team will use computers to design antibodies from scratch (de novo) with desired functions, while Proteina will use its proprietary platform “SPID” to quantitatively evaluate seven indicators such as binding affinity, productivity, and thermal stability. The goal is to analyze over 10,000 antibodies per week and reduce the candidate verification period from several months to about two weeks. Samsung Bioepis will then be responsible for cell line development and submission of the clinical phase 1 investigational new drug (IND) application for the selected candidates.


This content was produced with the assistance of AI translation services.

© The Asia Business Daily. All rights reserved. Unauthorized AI training and use prohibited.

Today’s Briefing