Researchers affiliated with UTHealth Houston, competing under the team name Novamab AI, placed among the top five teams in the international AIntibody Challenge, a blinded, prospective benchmark published in Nature Biotechnology.
The study, “A blinded, prospective benchmark of in-silico antibody discovery anchored to experimental affinity and developability,” evaluates artificial intelligence platforms for therapeutic antibody design through laboratory synthesis and experimental characterization.
Unlike retrospective computational benchmarks that evaluate models against historical datasets, the AIntibody Challenge required participating teams to design entirely new antibody sequences. The designs were independently synthesized and experimentally evaluated for binding affinity and developability—key physical and chemical traits required for clinical drug candidates.
Novamab AI fine-tuned a protein language model using experimental preference data to prioritize candidates with demonstrated biological activity and developability, rather than relying solely on theoretical sequence scores.
The international benchmark attracted 166 participants and 527 submissions from leading academic institutions and biotechnology companies worldwide. Novamab AI competed in the sequence-space track, which evaluated 58 submissions from research organizations, and finished among the top five performers. The results provide independent experimental validation that machine learning can identify viable therapeutic candidates before costly laboratory screening.
“The AIntibody Challenge was established to provide the first rigorous prospective evaluation of the ability of artificial intelligence to improve antibody discovery using independent third-party validation,” said Andrew Bradbury, MD, PhD, who led the international AIntibody Challenge. “Built upon a real-world in vitro antibody discovery pipeline, and by comparing AI predictions and designs under blinded experimental conditions, the challenge provided an objective benchmark to judge the effectiveness of AI in antibody discovery that should accelerate the development of more reliable and effective AI approaches in future therapeutic discovery.”
UTHealth Houston co-authors
- Zhiqiang An, PhD, professor and Robert A. Welch Distinguished University Chair in Chemistry at McGovern Medical School at UTHealth Houston, director of the Texas Therapeutics Institute, and vice president of drug discovery at UTHealth Houston
- Xiaoqian Jiang, PhD, professor, chair of the Department of Health Data Science and Artificial Intelligence, and Christopher Sarofim Family Professor in Biomedical Informatics and Bioengineering at McWilliams School of Biomedical Informatics at UTHealth Houston; associate vice president for medical AI at UTHealth Houston
- Yejin Kim, PhD, associate professor of Health Data Science at McWilliams School of Biomedical Informatics
- Yi-Ching Tang, PhD, assistant professor in the Department of Health Data Science and Artificial Intelligence at McWilliams School of Biomedical Informatics
- Xinyan Zhao, PhD, postdoctoral research fellow and technical lead for the Novamab AI platform at McWilliams School of Biomedical Informatics
Collaboration drives innovation
The collaborative framework behind the achievement was praised by John F. Hancock, MB, Bchir, PhD, ScD, senior vice president in Research and Strategy Innovation at UTHealth Houston, senior executive director of The Brown Foundation Institute of Molecular Medicine for the Prevention of Human Diseases, and the John S. Dunn Distinguished University Chair in Physiology and Medicine at McGovern Medical School at UTHealth Houston,
“This accomplishment demonstrates the extraordinary impact that can be achieved when basic scientists and AI researchers work together,” Hancock said. “It reflects UTHealth Houston’s commitment to translating innovative science into technologies that improve health worldwide.”
By coupling advanced machine learning directly with experimental validation pipelines, UTHealth Houston continues to pioneer interdisciplinary strategies that translate computational innovations into tangible therapeutic discoveries.
Source: https://www.uth.edu/news/story/uthealth-houston-researchers-advance-antibody-ai