This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: 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 data sets, 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, Ph.D., 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." M. Frank Erasmus et al, A blinded, prospective benchmark of in silico antibody discovery anchored to experimental affinity and developability, Nature Biotechnology (2026).
DOI: 10.1038/s41587-026-03238-6 Journal information: Nature Biotechnology MA in English, copy editor since 2021 with experience in higher education and health content. Dedicated to trustworthy science news. Full profile → Bachelor's in mathematical biology, Master's in creative writing.
Well-traveled with unique perspectives on science and language.
Extract — continue reading at the source.
