PLM-effector: unleashing the potential of protein language models for bacterial secreted protein prediction
Briefings in Bioinformatics · 01.03.2026 · 27 (2)
DOI: 10.1093/bib/bbag143 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 06.04.2026. Verfasst von Dandan Zheng und 3 weiteren Autor:innen. Beteiligte Einrichtung: NHC Key Laboratory of Systems Biology of Pathogens, National Institute of Pathogen Biology, Chinese Academy of Medical Sciences & Peking Union Medica…. Hauptthemen laut MEDLINE: Bacterial Proteins, Bacterial Secretion Systems, Computational Biology, Deep Learning. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Bacterial secreted proteins, particularly effectors delivered by specialized secretion systems, are key mediators of virulence and host–pathogen interactions. However, accurate computational identification remains challenging, as many existing methods rely heavily on sequence similarity or handcrafted features, and often focus on a single secretion system. Recent studies have reported that some bacterial effectors may be associated with more than one secretion system, highlighting the complexity of secretion system annotation and motivating the development of system-aware computational prediction approaches. Here, we present PLM-Effector, a hybrid deep learning framework that integrates modern protein language models (PLMs) with multiple neural architectures via a two-layer ensemble stacking strategy. By extracting complementary features from N- and C-terminal regions, PLM-Effector enables secretion-type-aware prediction across five major bacterial secretion systems (T1SS–T4SS and T6SS), with each system modeled independently. Systematic benchmarking shows that embeddings from protein-specific PLMs (ESM-1b, ESM2_t33, ProtT5) are more discriminative than those from general-purpose language models (e.g. BERT, BioBERT). Leveraging these representations, PLM-Effector achieves superior performance on an independent test set, with macro F1-scores of 0.9848, 0.8649, 0.9899, 0.9620, and 0.9728 for secreted proteins of T1SS–T4SS and T6SS, respectively, outperforming existing tools and homology-based baselines. Implemented as an accessible web server (http://www.mgc.ac.cn/PLM-Effector/) with source code and datasets available (https://github.com/zhengdd0422/PLM-Effector/), PLM-Effector provides a reproducible and user-friendly platform for both small-scale and genome-wide secreted protein discovery, facilitating advances in the study of bacterial pathogenesis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- NHC Key Laboratory of Systems Biology of Pathogens, National Institute of Pathogen Biology, Chinese Academy of Medical Sciences & Peking Union Medical College, No. 16 Tianrong Street, Daxing District, Beijing 102629, P.…
- School of Computing and Information Systems, Singapore Management University, 80 Stamford Road, Singapore 178902, Singapore.
ORCID-Profile: Dandan Zheng
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zheng, D., Chen, L., Pang, G., & Yang, J. (2026). PLM-effector: unleashing the potential of protein language models for bacterial secreted protein prediction. Briefings in Bioinformatics, 27(2). https://doi.org/10.1093/bib/bbag143
Vancouver
Zheng D, Chen L, Pang G, Yang J. PLM-effector: unleashing the potential of protein language models for bacterial secreted protein prediction. Briefings in Bioinformatics. 2026;27(2). doi:10.1093/bib/bbag143
BibTeX
@article{Zheng2026,
author = {Zheng, Dandan and Chen, Lihong and Pang, Guansong and Yang, Jian},
title = {PLM-effector: unleashing the potential of protein language models for bacterial secreted protein prediction},
journal = {Briefings in Bioinformatics},
year = {2026},
volume = {27},
number = {2},
doi = {10.1093/bib/bbag143}
}
EUVIMED