BetaDescribe: Providing rich descriptions from protein sequences
Proceedings of the National Academy of Sciences · 07.07.2026 · 123 (27)
DOI: 10.1073/pnas.2537345123 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 29.06.2026. Verfasst von Edo Dotan und 5 weiteren Autor:innen. Beteiligte Einrichtung: The Henry and Marilyn Taub Faculty of Computer Science, Technion-Israel Institute of Technology, Haifa 3200003, Israel. Hauptthemen laut MEDLINE: Proteins, Computational Biology, Sequence Analysis, Protein. Die Arbeit nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Israel Science Foundation (ISF).
Abstract (Originalsprache)
Deciphering protein function is fundamental to advancements in medicine and biotechnology. However, conventional experimental characterization remains resource-intensive. Public large language models (LLMs), though proficient in natural language processing, often fail to accurately interpret and predict the functional and structural properties of proteins, limiting their utility in bioinformatics. To address this gap, we introduce BetaDescribe, designed to generate detailed and rich textual descriptions of proteins, including their function, catalytic activity, involvement in specific metabolic pathways, subcellular localizations, and the presence of specific domains. The trained BetaDescribe model receives protein sequences as input and outputs a textual description of these properties. BetaDescribe starting point was the LLAMA2 model, which was trained on trillions of tokens. Our model was next trained on datasets containing both biological and English text, which allowed the incorporation of biological knowledge. In addition to the description generator, BetaDescribe comprises multiple validator models and a judge, which together enable accurate ranking of alternative generated descriptions. We demonstrate the utility of BetaDescribe by providing descriptions for proteins that share little to no sequence similarity to proteins with functional descriptions in public datasets. Using in silico mutagenesis, we further show that BetaDescribe relies on functionally important regions, as part of its prediction, suggesting that the model identifies regions of importance for the protein functionality without needing homologous sequence. BetaDescribe offers a powerful tool to explore protein functionality, augmenting existing approaches such as annotation transfer based on sequence or structure similarity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- The Henry and Marilyn Taub Faculty of Computer Science, Technion-Israel Institute of Technology, Haifa 3200003, Israel.
- The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University, Tel Aviv 69978, Israel.
- Kempner Institute, Harvard University, Cambridge, MA 02134.
ORCID-Profile: Marcelo Ehrlich, Eran Bacharach, Tal Pupko, Yonatan Belinkov
Förderung
- Israel Science Foundation (ISF)
Zitieren
APA
Dotan, E., Lyubman, I., Ehrlich, M., Bacharach, E., Pupko, T., & Belinkov, Y. (2026). BetaDescribe: Providing rich descriptions from protein sequences. Proceedings of the National Academy of Sciences, 123(27). https://doi.org/10.1073/pnas.2537345123
Vancouver
Dotan E, Lyubman I, Ehrlich M, Bacharach E, Pupko T, Belinkov Y. BetaDescribe: Providing rich descriptions from protein sequences. Proceedings of the National Academy of Sciences. 2026;123(27). doi:10.1073/pnas.2537345123
BibTeX
@article{Dotan2026,
author = {Dotan, Edo and Lyubman, Iris and Ehrlich, Marcelo and Bacharach, Eran and Pupko, Tal and Belinkov, Yonatan},
title = {BetaDescribe: Providing rich descriptions from protein sequences},
journal = {Proceedings of the National Academy of Sciences},
year = {2026},
volume = {123},
number = {27},
doi = {10.1073/pnas.2537345123}
}
EUVIMED