Recent advances in multimodal-driven protein AI
Biophysics Reviews · 01.03.2026 · 7 (1)
DOI: 10.1063/5.0273453 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biophysics Reviews, online erschienen am 24.03.2026. Verfasst von Yuhang Yang und 4 weiteren Autor:innen. Die Arbeit nennt 119 Literaturangaben. Gefördert von: National Major Science and Technology Projects of China.
Abstract (Originalsprache)
The AI revolution in natural-language and image processing has catalyzed new concepts and research paradigms in protein science. Researchers in protein science have first developed protein language models via self-supervised pre-training on large-scale protein sequences and have subsequently integrated multiple data sources or modalities into a single model to leverage vast data and the complementary information across modalities. These sources include, but are not limited to, protein sequences, structures, dynamics derived from molecular-dynamics simulations, functional annotations from resources such as the Gene Ontology, experimental data, and even natural-language descriptions. Such integration boosts performance, enables cross-talking between distinct data modalities, and endows models with new capabilities. In this review, we discuss recent studies that fuse diverse modalities, including foundation models designed for downstream tasks and representative works that integrate heterogeneous data for specific applications.
Förderung
- National Major Science and Technology Projects of China
Zitieren
APA
Yang, Y., Huang, H., Zhang, J., Li, W., & Wang, W. (2026). Recent advances in multimodal-driven protein AI. Biophysics Reviews, 7(1). https://doi.org/10.1063/5.0273453
Vancouver
Yang Y, Huang H, Zhang J, Li W, Wang W. Recent advances in multimodal-driven protein AI. Biophysics Reviews. 2026;7(1). doi:10.1063/5.0273453
BibTeX
@article{Yang2026,
author = {Yang, Yuhang and Huang, Hengyan and Zhang, Jian and Li, Wenfei and Wang, Wei},
title = {Recent advances in multimodal-driven protein AI},
journal = {Biophysics Reviews},
year = {2026},
volume = {7},
number = {1},
doi = {10.1063/5.0273453}
}
EUVIMED