MZSGO: multimodal zero-shot protein function annotation via evolutionary signals and textual semantics
Bioinformatics · 03.05.2026 · 42 (5)
DOI: 10.1093/bioinformatics/btag168 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 03.04.2026. Verfasst von Boyue Cui und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong 518055, China. Hauptthemen laut MEDLINE: Proteins, Semantics, Molecular Sequence Annotation, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies.
Abstract (Originalsprache)
Motivation Although deep learning has significantly advanced the field of protein function prediction, current approaches are limited by their reliance on a narrow set of modalities. Specifically, they primarily rely on sequence patterns and treat protein domain data and functional labels merely as categorical tags. Consequently, they fail to capitalize on the semantic richness embedded within their textual definitions. These constraints hinder their ability to generalize to novel labels. To tackle this issue, we present MZSGO, a multimodal zero-shot framework that fuses evolutionary signals from protein language models with semantic features derived from large language models (LLMs). By employing an adaptive gated fusion mechanism, MZSGO effectively aligns sequence-based and text-based modalities to enable robust predictions for unseen labels. Results By unifying protein representations and functional annotations, we bridge the semantic gap that limits current approaches. Results indicate that while our model remains competitive on supervised benchmarks, it demonstrates a marked advantage over existing methods in zero-shot tasks. It specifically excels at recognizing previously unseen long-tail and novel Gene Ontology (GO) terms. Availability and implementation The source code and datasets are available at https://github.com/toxic-byte/MZSGO.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong 518055, China.
- Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China.
- Key Laboratory of Biological Bigdata, Ministry of Education, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China.
ORCID-Profile: Yadong Wang, Junyi Li
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies
Zitieren
APA
Cui, B., Li, Y., Chen, S., Wei, J., Wang, X., Wang, Y., & Li, J. (2026). MZSGO: multimodal zero-shot protein function annotation via evolutionary signals and textual semantics. Bioinformatics, 42(5). https://doi.org/10.1093/bioinformatics/btag168
Vancouver
Cui B, Li Y, Chen S, Wei J, Wang X, Wang Y, et al. MZSGO: multimodal zero-shot protein function annotation via evolutionary signals and textual semantics. Bioinformatics. 2026;42(5). doi:10.1093/bioinformatics/btag168
BibTeX
@article{Cui2026,
author = {Cui, Boyue and Li, Yujuan and Chen, Shiqu and Wei, Jiaming and Wang, Xuan and Wang, Yadong and Li, Junyi},
title = {MZSGO: multimodal zero-shot protein function annotation via evolutionary signals and textual semantics},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {5},
doi = {10.1093/bioinformatics/btag168}
}
EUVIMED