AI4Life Open Calls and Public Challenges: why, how, and what we have learned
Published in bioRxiv, 2026
Recommended citation: Galinova, V., Seifi, M., Serrano Solano, B., Lidayova, K., Dalle Nogare, D., Corbat, A. A., Talks, J., Giacomello, E., Gomez-de-Mariscal, E., Ferreira, M. G., Fuster-Barceló, C., Battagliotti, J. M., García-López-de-Haro, C., Salmon, B., Croft, M., Yie, S. Y., Rey-Paniagua, G., Hu, X., Cho, S., Sheth, A., Porwal, C., Li, X., AI4Life Consortium, Henriques, R., Li, X., Krull, A., Klemm, A., Muñoz Barrutia, A., Kreshuk, A., Ouyang, W., Jug, F., & Deschamps, J. (2026). AI4Life Open Calls and Public Challenges: why, how, and what we have learned. bioRxiv. https://doi.org/10.64898/2026.07.21.739486 https://www.biorxiv.org/content/10.64898/2026.07.21.739486v1.abstract
AI4Life Open Calls and Public Challenges: why, how, and what we have learned
Submitted to: bioRxiv
Posted: July 22, 2026
Authors: Vera Galinova, Mehdi Seifi, Beatriz Serrano Solano, Kristina Lidayova, Damian Dalle Nogare, Agustin Andres Corbat, Joshua Talks, Edoardo Giacomello, Estibaliz Gomez-de-Mariscal, Mariana G. Ferreira, Caterina Fuster-Barceló, Juan Manuel Battagliotti, Carlos García-López-de-Haro, Benjamin Salmon, Melisande Croft, Si Young Yie, Guillermo Rey-Paniagua, Xiaotian Hu, Sungjun Cho, Aagam Sheth, Chhayansh Porwal, Xiaomeng Li, AI4Life Consortium, Ricardo Henriques, Xinyang Li, Alexander Krull, Anna Klemm, Arrate Muñoz Barrutia, Anna Kreshuk, Wei Ouyang, Florian Jug, Joran Deschamps
Abstract
This preprint summarizes the lessons learned from the AI4Life Open Calls and Public Challenges carried out between 2023 and 2025.
Across three Open Calls and three Public Challenges, the initiative supported 22 bioimage analysis projects from 151 applications and engaged 225 challenge participants, with a strong focus on FAIR deep learning for the life sciences.
The paper highlights a recurring gap between available methods and practical adoption: even carefully selected AI-ready projects often still require substantial work on data, annotations, and workflow integration before deep learning can be applied effectively.
Its main conclusion is that, for scientific AI in biology, the limiting factor is not the availability of models but the shared data, annotations, and infrastructure needed to make those models useful in practice.