Epistemic blind spots in protein function prediction: uncertainty, homology bias and failure modes in deep learning models
Frontiers in Bioinformatics · 20.11.2026 · 6
DOI: 10.3389/fbinf.2026.2010708 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Bioinformatics, online erschienen am 20.11.2026. Verfasst von Leonardo Ledesma-Dominguez und 3 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Protein function prediction has advanced from homology-based annotation transfer to deep learning, protein language models, and multimodal foundation models. Yet improved benchmark performance does not resolve a more basic problem: these systems learn from biological knowledge that is incomplete, heterogeneous in evidential support, and strongly structured by evolutionary relationships. We organize this problem as two sequentially dependent epistemological levels. The first concerns biological knowledge: what functional states become observable, with what evidential support and evolutionary structure. The second concerns what models can legitimately infer from that supervision, including representation sufficiency, uncertainty, generalization, and the scope of a universal computational blueprint for protein function inference. Because limitations at the first level enter the learning problem before model fitting, benchmark performance and model uncertainty cannot by themselves establish certainty about latent biological function. Trustworthy protein AI therefore requires explicit attention to applicability domains, distribution shift, uncertainty, and the limits of inference from available biological knowledge.
Zitieren
APA
Ledesma-Dominguez, L., Carbajal-Degante, E., Perez-Rueda, E., & Cortes-Espinosa, R. (2026). Epistemic blind spots in protein function prediction: uncertainty, homology bias and failure modes in deep learning models. Frontiers in Bioinformatics, 6. https://doi.org/10.3389/fbinf.2026.2010708
Vancouver
Ledesma-Dominguez L, Carbajal-Degante E, Perez-Rueda E, Cortes-Espinosa R. Epistemic blind spots in protein function prediction: uncertainty, homology bias and failure modes in deep learning models. Frontiers in Bioinformatics. 2026;6. doi:10.3389/fbinf.2026.2010708
BibTeX
@article{LedesmaDominguez2026,
author = {Ledesma-Dominguez, Leonardo and Carbajal-Degante, Erik and Perez-Rueda, Ernesto and Cortes-Espinosa, Ricardo},
title = {Epistemic blind spots in protein function prediction: uncertainty, homology bias and failure modes in deep learning models},
journal = {Frontiers in Bioinformatics},
year = {2026},
volume = {6},
doi = {10.3389/fbinf.2026.2010708}
}
EUVIMED