iDRNA-ITF
iDRNA-ITF identifies DNA- and RNA-binding residues in protein sequences to characterize protein–nucleic acid interactions.
Key Features:
- Induction and Transfer Framework: Uses an induction and transfer framework that enhances residue representation by incorporating functional properties.
- Feature Extraction Network: Employs a nucleic acid-binding residue feature extraction network to induce properties of residues involved in DNA and RNA binding.
- Integrated Prediction Networks: Applies separate but integrated networks for predicting DNA-binding and RNA-binding residues, transferring extracted features into final predictions.
- State-of-the-Art Performance: Experimental validation across four distinct test sets demonstrates superior performance relative to existing sequence-based methods.
Scientific Applications:
- Protein function analysis: Mapping DNA- and RNA-binding residues to interpret roles in gene regulation, transcriptional control, and RNA processing.
- Mechanistic studies of protein–nucleic acid interaction: Identifying binding sites to support molecular-level characterization of protein–nucleic acid interfaces.
- Drug discovery and therapeutic design: Informing design of therapeutics that target specific protein–nucleic acid interactions relevant to genetic disorders and disease mechanisms.
Methodology:
Sequence-based approach enhanced by machine learning techniques, integrating functional properties into residue representation using an induction and transfer framework, a nucleic acid-binding residue feature extraction network, and separate integrated networks for DNA- and RNA-binding residue prediction.
Topics
Details
- Cost:
- Free of charge
- Tool Type:
- web application
- Operating Systems:
- Mac, Linux, Windows
- Added:
- 9/7/2022
- Last Updated:
- 11/24/2024
Operations
Publications
Wang N, Yan K, Zhang J, Liu B. iDRNA-ITF: identifying DNA- and RNA-binding residues in proteins based on induction and transfer framework. Briefings in Bioinformatics. 2022;23(4). doi:10.1093/bib/bbac236. PMID:35709747.
DOI: 10.1093/bib/bbac236
PMID: 35709747
Funding: - Beijing Natural Science Foundation: JQ19019
- National Natural Science Foundation of China: 62102030