Nanyang Biologics Unveils AI-Powered Drug Discovery Platform, Patented Therapeutic Candidates.

Nanyang Biologics offers a comprehensive drug discovery platform integrating traditional medicine with state-of-the-art technologies. Its flagship product, NB-A002, is a DNA Damage Response therapeutic targeting ILF2, inducing synthetic lethality in certain cancers. The company's Drug-Target Interaction Graph Neural Network (DTIGN) AI model enables faster identification of promising drug candidates and reduces R&D costs. NYB collaborates with Nanyang Technological University Singapore to revolutionize drug discovery using AI and natural compounds.

Ginkgo Bioworks (NYSE: DNA) has announced a strategic partnership with Apheris to launch the Antibody Developability Consortium, aiming to accelerate the application of artificial intelligence (AI) in biologics drug discovery. The initiative includes the AbDev AI Competition, which seeks to establish standards for antibody developability modeling.

The Antibody Developability Consortium, led by Ginkgo Datapoints in partnership with Apheris, addresses one of the most significant challenges in biologics development: predicting and optimizing antibody properties early in research and development (R&D) to ensure downstream clinical and commercial success. Ginkgo Datapoints will contribute its AI/ML and high-throughput experimental capabilities, while Apheris provides federated computing infrastructure for secure collaboration on sensitive data.

Robin Röhm, CEO and cofounder of Apheris, stated, "The future of AI in drug discovery depends on creating environments where companies can collaborate without compromising their most valuable data. We are successfully doing this with the AI Structural Biology (AISB) consortium and now with this new consortium with Ginkgo, we’re bringing federated learning directly into antibody R&D, making critical datasets usable in ways that were never before possible."

The consortium combines centralized dataset generation with federated model training, blending high-quality diverse datasets generated by Ginkgo with secure access to distributed partner datasets through Apheris' federated computing technology. The consortium is currently enrolling member companies with initial datasets and models for multiple antibody formats expected in 2026.

In parallel, Ginkgo is launching the first-ever AbDev AI Competition, designed to measure the current state of antibody developability modeling and create widely accepted standards for performance and evaluation. The competition, hosted on the Hugging Face platform, runs until early November, with winners to be announced with up to $60,000 in prize values.

Peter Tessier, professor of pharmaceutical sciences and chemical engineering at the University of Michigan and paid advisor to Ginkgo Datapoints, noted, "One of the biggest barriers in antibody AI has been the lack of large, high-quality datasets on developability. Consortia and competitions like these are a crucial step toward closing that gap—creating the shared data and benchmarks we need to advance predictive models across the field."

These efforts build on Ginkgo Datapoints' recent collaboration with Tangible Scientific and Inductive Bio to advance small molecule drug discovery through AI-driven, lab-in-the-loop workflows. The initiatives underscore Ginkgo’s commitment to scaling its biologics capabilities and providing the data infrastructure needed to accelerate R&D across major drug classes, creating value for partners and the broader ecosystem.