Related Experiment Video
Updated: Jun 11, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
685
Identifying nucleotide-binding leucine-rich repeat receptor and pathogen effector pairing using transfer-learning and
Baixue Qiao1,2, Shuda Wang1,2, Mingjun Hou1
1Key Laboratory of Saline-Alkali Vegetation Ecology Restoration, Ministry of Education (Northeast Forestry University), Harbin 150001, China.
Bioinformatics (Oxford, England)
|September 27, 2024
Summary
A new deep learning algorithm, ProNEP, efficiently identifies nucleotide-binding leucine-rich repeat (NLR) and effector (CNE) pairs. This advances crop breeding by overcoming scarce CNE data, enabling high-throughput prediction for numerous NLRs.
Area of Science:
- Plant immunology
- Bioinformatics
- Genomics
Background:
- Nucleotide-binding leucine-rich repeat (NLR) proteins are crucial immune receptors in plants, widely used in crop breeding for pathogen defense.
- The effectiveness of NLRs depends on their correspondence with effectors (CNEs), but existing CNE data is extremely limited.
- A vast number of NLRs (91,291) are known, yet only 387 CNEs are identified, hindering practical applications.
Purpose of the Study:
- To develop a high-throughput computational method for predicting NLR-effector pairs (CNEs).
- To address the scarcity of experimental CNE data and unlock the potential of NLRs in crop improvement.
Main Methods:
- Proposed ProNEP, a deep learning algorithm conceptualizing CNE prediction as a protein-protein interaction (PPI) task.
- Integrated transfer learning with a bilinear attention network within ProNEP for accurate interaction prediction.
- Applied ProNEP to predict potential CNEs for a large dataset of 91,291 NLRs.
Main Results:
- ProNEP demonstrated superior performance compared to existing state-of-the-art PPI prediction models.
- Successfully identified numerous potential CNEs for the extensive NLR dataset.
- The study highlights the potential of ProNEP for large-scale CNE prediction.
Conclusions:
- ProNEP offers an efficient, high-throughput solution for identifying NLR-effector pairs, overcoming data limitations.
- This tool is expected to significantly advance plant biology, immunology, and breeding by facilitating CNE prediction in new species.
- The availability of ProNEP (http://nerrd.cn/#/prediction) and its code (https://github.com/QiaoYJYJ/ProNEP) promotes wider adoption and research.
