DeepEffector: a protein language model-driven deep learning framework for effector prediction in fungi and oomycetes
Plant Physiology · 2026
DOI: 10.1093/plphys/kiag691 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plant Physiology, 2026. Verfasst von Tao Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Life and Health Sciences, Hainan Province Key Laboratory of One Health, Collaborative Innovation Center of Life and Health, Hainan Universi…. Hauptthemen laut MEDLINE: Deep Learning, Oomycetes, Plant Diseases, Fusarium. Die Arbeit nennt 30 Literaturangaben. Gefördert von: Hainan Provincial Natural Science Foundation of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Crop diseases caused by fungal and oomycete pathogens threaten sustainable agricultural production, and the efficient identification of pathogen effectors is essential for understanding virulence mechanisms and developing disease-resistant crops. However, the rapid evolutionary diversification of effectors often obscures conserved motifs, limiting the effectiveness of conventional computational approaches and making experimental prioritization challenging. To address this, we developed DeepEffector, a high-precision predictor for fungal and oomycete effector identification. DeepEffector leverages protein language models (ProtT5 for fungi and esm1b for oomycetes) to generate functional semantic embeddings, integrates G-SMOTE to mitigate class imbalance in the latent feature space, and employs a hybrid multihead self-attention and convolutional neural network (CNN) architecture to capture both global contextual dependencies and local functional patterns. Benchmarking on independent test sets showed that DeepEffector outperformed state-of-the-art tools, providing a reliable high-confidence candidate list to reduce downstream experimental screening. Its practical utility was further evaluated in Fusarium oxysporum f. sp. cubense TR4, the causal agent of destructive banana Fusarium wilt. Four prioritized candidates were experimentally confirmed to be secreted proteins, localized to host-relevant subcellular compartments, and significantly suppress Bax-induced programmed cell death, supporting their potential roles as immune-suppressing effector candidates. DeepEffector is available as a user-friendly web server (https://deepeffector.hainanu.edu.cn/), offering an accessible pipeline to accelerate effector discovery and support crop protection research.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Life and Health Sciences, Hainan Province Key Laboratory of One Health, Collaborative Innovation Center of Life and Health, Hainan University, Haikou, Hainan 570228, China.
- Information Department, Hainan Cancer Hospital, Haikou, Hainan 570228, China.
ORCID-Profile: Qianlin Meng, Danyang Wang, Fangzheng Hu, Rui Zhang, Juanjuan Li, Tianpeng Wang, Hong Li
Förderung
- Hainan Provincial Natural Science Foundation of China
- National Natural Science Foundation of China
Zitieren
APA
Li, T., Meng, Q., Wang, D., Hu, F., Zhang, R., Chi, X., Li, J., Wang, T., & Li, H. (2026). DeepEffector: a protein language model-driven deep learning framework for effector prediction in fungi and oomycetes. Plant Physiology. https://doi.org/10.1093/plphys/kiag691
Vancouver
Li T, Meng Q, Wang D, Hu F, Zhang R, Chi X, et al. DeepEffector: a protein language model-driven deep learning framework for effector prediction in fungi and oomycetes. Plant Physiology. 2026. doi:10.1093/plphys/kiag691
BibTeX
@article{Li2026,
author = {Li, Tao and Meng, Qianlin and Wang, Danyang and Hu, Fangzheng and Zhang, Rui and Chi, Xue and Li, Juanjuan and Wang, Tianpeng and Li, Hong},
title = {DeepEffector: a protein language model-driven deep learning framework for effector prediction in fungi and oomycetes},
journal = {Plant Physiology},
year = {2026},
doi = {10.1093/plphys/kiag691}
}
EUVIMED