Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 2 min ago
Peer-reviewedCC BY 4.0PLOS Computational Biology

GeoEPred: A multimodal structure-aware geometric deep learning framework for Gram-negative bacterial secreted effector prediction with sequence semantics

  • Shouzhen Song1
  • Hua Shi2
  • Hongfeng Wu3
  • Dachen Liu4
  • Yihang Lin5
  • Nor Ashidi Mat Isa
  • Quan Zou
  • Leyi Wei
5 affiliations
  1. 1School of Opto-electronic and Communication Engineering, Xiamen University of Technology, Xiamen, Fujian, China
  2. 2School of Electrical and Electronic Engineering, Engineering Campus, Universiti Sains Malaysia, Nibong Tebal, Pulau Pinang, Malaysia
  3. 3Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, Zhejiang, China
  4. 4Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, Sichuan, China
  5. 5Faculty of Applied Sciences, Macao Polytechnic University, Macao, China
Read full textPDFDOICite

Abstract

Accurate prediction of effector proteins secreted by Gram-negative bacteria is important for elucidating bacterial pathogenic mechanisms and developing precise anti-infective strategies. Although existing methods have benefited from the strong sequence feature extraction capacity of pretrained protein language models, reliance on linear sequence information alone often fails to fully capture the three-dimensional conformational signals required for virulence functions. Meanwhile, conventional structure-based methods are limited by the scarcity of experimentally resolved protein structures. To address these challenges, we propose GeoEPred, a multimodal deep learning framework designed for the synergistic modeling of protein sequence and structure to identify Gram-negative bacterial effector proteins. Specifically, the model integrates sequence-contextual embeddings from a pretrained protein language model with three-dimensional structural representations predicted by ESMFold. A feature projection network refines fine-grained sequence signals associated with effector functions, while geometric vector perceptrons characterize inter-residue orientations, distances, and local spatial topology to capture potential structural conformational motifs. To further enable effective cross-modal fusion, we design a cross-modal alignment and feature-tokenized self-attention module. This module enhances consistency between the sequence-semantic and structural-geometric spaces through contrastive learning and models associations between linear functional motifs and spatial conformational patterns at a fine-grained token level. Extensive evaluations on multiple benchmark datasets show that GeoEPred achieves better predictive performance than existing leading models in T3SE, T4SE, and T6SE prediction tasks, while maintaining stable performance in remote homolog recognition scenarios. Moreover, the modular and extensible architecture of GeoEPred demonstrates strong generalization ability and substantial application potential for genome-scale effector protein discovery. Author summary: Secreted effector proteins are central virulence factors used by many Gram-negative bacterial pathogens to execute infection strategies. Their functions are governed not only by secretion signals and short linear motifs in the amino acid sequence, but also by three-dimensional folds, local domains, and surface geometric patterns. However, current predictors mainly exploit sequence-contextual features, limiting their ability to model the correspondence between linear sequence signals and spatial conformational motifs, and thereby constraining accuracy and interpretability. Here, we present GeoEPred, a multimodal deep learning framework for secreted effector protein identification. GeoEPred couples sequence-semantic embeddings from a pretrained protein language model with structural representations learned by geometric vector perceptrons. A cross-modal alignment and interaction module uses contrastive learning to improve functional consistency between sequence and structure modalities, while feature-token attention captures fine-grained links between key linear and conformational motifs. Across benchmark datasets covering multiple effector types, GeoEPred outperforms existing state-of-the-art methods and provides interpretable evidence from sequence fragments, structural regions, and cross-modal associations, supporting functional annotation, pathogenic mechanism analysis, and experimental validation.

Related

  1. Prediction of Residue-Level Base Preference for DNA-Binding Proteins Using a Multimodal Learning Framework
    Siyuan Li, Wenyan He, Mengru Zhang +7
    JACS AuPeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossrefEurope PMCPMC
  2. KAT-Net: a hyperbolic routing framework for joint lysine acylation site prediction with shared sequence–structure representations
    Briefings in bioinformaticsPeer-reviewedCC BY-NCFull textMolecular biology & gene regulationEurope PMC
  3. TAPERSS-MoCa: A Physics-Based Monte Carlo Framework for 3D RNA Structure Prediction from Sequence
    Mariam Ibrahim, Ivan Issac Riveros, Nanayakkara P.N.R. Kumarachchi +1
    ChemRxivPreprintCC BYFull textMolecular biology & gene regulationChemRxiv
  4. Lipid–Metal-Organic Framework Colloidosomes for Multimodal Encapsulation and Pollutant Capture
    Computational and structural biotechnology journalPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  5. Joint enzyme–reaction retrieval and catalytic optima prediction via multimodal fusion
    Yueyi Cai, Feng Yang, Juan Liu
    BioinformaticsPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationCrossrefPMC

Cite

BibTeXRIS
BibTeX
@article{song2026geoepred,
  title = {{GeoEPred: A multimodal structure-aware geometric deep learning framework for Gram-negative bacterial secreted effector prediction with sequence semantics}},
  author = {Shouzhen Song and Hua Shi and Hongfeng Wu and Dachen Liu and Yihang Lin and Nor Ashidi Mat Isa and Quan Zou and Leyi Wei},
  journal = {PLOS Computational Biology},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pcbi.1014344},
  url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014344},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - GeoEPred: A multimodal structure-aware geometric deep learning framework for Gram-negative bacterial secreted effector prediction with sequence semantics
AU  - Shouzhen Song
AU  - Hua Shi
AU  - Hongfeng Wu
AU  - Dachen Liu
AU  - Yihang Lin
AU  - Nor Ashidi Mat Isa
AU  - Quan Zou
AU  - Leyi Wei
PY  - 2026
DA  - 2026/09/30
JO  - PLOS Computational Biology
DO  - 10.1371/journal.pcbi.1014344
UR  - https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014344
AB  - Accurate prediction of effector proteins secreted by Gram-negative bacteria is important for elucidating bacterial pathogenic mechanisms and developing precise anti-infective strategies. Although existing methods have benefited from the strong sequence feature extraction capacity of pretrained protein language models, reliance on linear sequence information alone often fails to fully capture the three-dimensional conformational signals required for virulence functions. Meanwhile, conventional structure-based methods are limited by the scarcity of experimentally resolved protein structures. To address these challenges, we propose GeoEPred, a multimodal deep learning framework designed for the synergistic modeling of protein sequence and structure to identify Gram-negative bacterial effector proteins. Specifically, the model integrates sequence-contextual embeddings from a pretrained protein language model with three-dimensional structural representations predicted by ESMFold. A feature projection network refines fine-grained sequence signals associated with effector functions, while geometric vector perceptrons characterize inter-residue orientations, distances, and local spatial topology to capture potential structural conformational motifs. To further enable effective cross-modal fusion, we design a cross-modal alignment and feature-tokenized self-attention module. This module enhances consistency between the sequence-semantic and structural-geometric spaces through contrastive learning and models associations between linear functional motifs and spatial conformational patterns at a fine-grained token level. Extensive evaluations on multiple benchmark datasets show that GeoEPred achieves better predictive performance than existing leading models in T3SE, T4SE, and T6SE prediction tasks, while maintaining stable performance in remote homolog recognition scenarios. Moreover, the modular and extensible architecture of GeoEPred demonstrates strong generalization ability and substantial application potential for genome-scale effector protein discovery. Author summary: Secreted effector proteins are central virulence factors used by many Gram-negative bacterial pathogens to execute infection strategies. Their functions are governed not only by secretion signals and short linear motifs in the amino acid sequence, but also by three-dimensional folds, local domains, and surface geometric patterns. However, current predictors mainly exploit sequence-contextual features, limiting their ability to model the correspondence between linear sequence signals and spatial conformational motifs, and thereby constraining accuracy and interpretability. Here, we present GeoEPred, a multimodal deep learning framework for secreted effector protein identification. GeoEPred couples sequence-semantic embeddings from a pretrained protein language model with structural representations learned by geometric vector perceptrons. A cross-modal alignment and interaction module uses contrastive learning to improve functional consistency between sequence and structure modalities, while feature-token attention captures fine-grained links between key linear and conformational motifs. Across benchmark datasets covering multiple effector types, GeoEPred outperforms existing state-of-the-art methods and provides interpretable evidence from sequence fragments, structural regions, and cross-modal associations, supporting functional annotation, pathogenic mechanism analysis, and experimental validation.
SN  - 1553-7358
ER  -