Collaborations in artificial intelligence (AI)-driven drug development are spreading across Korea's pharmaceutical and biotech industry. The strategy aims to accelerate development and reduce failure rates by integrating AI from the candidate discovery stage.
HK inno.N announced Thursday that it has teamed up with AI drug discovery firm Atommerce to jointly research and develop next-generation obesity treatments, according to industry sources on the 27th. The goal is to discover non-incretin drug candidates that can overcome the limitations of existing GLP-1 (incretin) class therapies.
The collaboration will utilize Atommerce's AI-based drug design platform "CANDY." HK inno.N will handle the synthesis and biological evaluation of candidate substances to verify efficacy and safety, while Atommerce will be responsible for AI-based molecular design and screening.
CANDY is a platform based on molecular dynamics that can predict not only the binding stability between proteins and candidate substances but also the pharmacological responses that occur after binding. It has drawn attention for its ability to filter out unsuitable substances at an early research stage, thereby lowering the probability of development failure and improving cost efficiency.
The current obesity treatment market is led by GLP-1 class drugs, but limitations such as gastrointestinal side effects and muscle loss have been noted. HK inno.N's strategy is to use CANDY to discover new substances in the non-incretin class and secure differentiated competitiveness.
Such AI-driven drug development collaborations are spreading across the industry. Olix earlier partnered with AI firm Galux to jointly develop an siRNA delivery platform. By combining Galux's AI-based protein design technology with Olix's siRNA platform, the partnership aims to develop next-generation therapeutics that can be delivered to various tissues, including the central nervous system.
ISU Abxis has also teamed up with Galux to establish an AI-based protein drug development collaboration system. The company plans to combine its antibody therapeutics development experience with the AI design platform to simultaneously improve the precision and speed of candidate discovery.
The industry views these moves as the spread of "AI alliances." Strategies are shifting toward resolving bottlenecks in the early exploration stage through collaborations with AI platform companies. In particular, using AI at the candidate discovery stage can shorten research periods that once took years and reduce failure rates, improving the cost-heavy structure of drug development, according to industry observers.
"AI has moved beyond being a simple auxiliary tool and is establishing itself as a key variable that determines the speed and success probability of drug development," an industry official said. "How effectively companies utilize AI platforms will become the standard that differentiates corporate competitiveness going forward."
