Related Experiment Video
Updated: Jun 25, 2026
Detection of Toxin Translocation into the Host Cytosol by Surface Plasmon Resonance
Published on: January 3, 2012
A deep learning method to predict bacterial ADP-ribosyltransferase toxins
Dandan Zheng1, Siyu Zhou1, Lihong Chen1
1NHC Key Laboratory of Systems Biology of Pathogens, National Institute of Pathogen Biology, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 102629, China.
Motivation:
ADP-ribosylation is a critical modification involved in regulating diverse cellular processes, including chromatin structure regulation, RNA transcription, and cell death. Bacterial ADP-ribosyltransferase toxins (bARTTs) serve as potent virulence factors that orchestrate the manipulation of host cell functions to facilitate bacterial pathogenesis. Despite their pivotal role, the bioinformatic identification of novel bARTTs poses a formidable challenge due to limited verified data and the inherent sequence diversity among bARTT members.
Results:
We proposed a deep learning-based model, ARTNet, specifically engineered to predict bARTTs from bacterial genomes. Initially, we introduced an effective data augmentation method to address the issue of data scarcity in training ARTNet. Subsequently, we employed a data optimization strategy by utilizing ART-related domain subsequences instead of the primary full sequences, thereby significantly enhancing the performance of ARTNet. ARTNet achieved a Matthew's correlation coefficient (MCC) of 0.9351 and an F1-score (macro) of 0.9666 on repeated independent test datasets, outperforming three other deep learning models and six traditional machine learning models in terms of time efficiency and accuracy. Furthermore, we empirically demonstrated the ability of ARTNet to predict novel bARTTs across domain superfamilies without sequence similarity. We anticipate that ARTNet will greatly facilitate the screening and identification of novel bARTTs from bacterial genomes.
Availability And Implementation:
ARTNet is publicly accessible at http://www.mgc.ac.cn/ARTNet/. The source code of ARTNet is freely available at https://github.com/zhengdd0422/ARTNet/.
Insights
A new deep learning model, ARTNet, accurately identifies bacterial ADP-ribosyltransferase toxins (bARTTs) in genomes. This tool aids in discovering novel bARTTs, crucial for understanding bacterial virulence and pathogenesis.
Area of Science:
- Biochemistry and Molecular Biology
- Bioinformatics and Computational Biology
- Microbiology
Background:
- ADP-ribosylation regulates key cellular processes like chromatin structure, RNA transcription, and cell death.
- Bacterial ADP-ribosyltransferase toxins (bARTTs) are vital virulence factors enabling bacteria to manipulate host cells for pathogenesis.
- Identifying novel bARTTs is challenging due to limited data and sequence diversity.
Purpose of the Study:
- To develop a deep learning model, ARTNet, for accurate prediction of bARTTs from bacterial genomes.
- To overcome data scarcity and enhance prediction performance through data augmentation and domain subsequence utilization.
Main Methods:
- Developed ARTNet, a deep learning model for bARTT prediction.
- Implemented data augmentation techniques to address limited training data.
- Utilized ART-related domain subsequences for optimized model performance.
Main Results:
- ARTNet achieved high performance with an MCC of 0.9351 and F1-score (macro) of 0.9666 on independent test datasets.
- ARTNet outperformed existing deep learning and traditional machine learning models in accuracy and efficiency.
- Demonstrated ARTNet's capability to predict novel bARTTs across diverse superfamilies, even without sequence similarity.
Conclusions:
- ARTNet is an effective tool for identifying novel bacterial ADP-ribosyltransferase toxins.
- The model significantly advances the screening and discovery of bARTTs in bacterial genomics.
- ARTNet is publicly available, facilitating broader research in bacterial pathogenesis and virulence.
