iDRBP-EL: Identifying DNA- and RNA- Binding Proteins Based on Hierarchical Ensemble Learning

Ning Wang, Jun Zhang, Bin Liu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)

Abstract

Identification of DNA-binding proteins (DBPs) and RNA-binding proteins (RBPs) from the primary sequences is essential for further exploring protein-nucleic acid interactions. Previous studies have shown that machine-learning-based methods can efficiently identify DBPs or RBPs. However, the information used in these methods is slightly unitary, and most of them only can predict DBPs or RBPs. In this study, we proposed a computational predictor iDRBP-EL to identify DNA- and RNA- binding proteins, and introduced hierarchical ensemble learning to integrate three level information. The method can integrate the information of different features, machine learning algorithms and data into one multi-label model. The ablation experiment showed that the fusion of different information can improve the prediction performance and overcome the cross-prediction problem. Experimental results on the independent datasets showed that iDRBP-EL outperformed all the other competing methods. Moreover, we established a user-friendly webserver iDRBP-EL (http://bliulab.net/iDRBP-EL), which can predict both DBPs and RBPs only based on protein sequences.

Original languageEnglish
Pages (from-to)432-441
Number of pages10
JournalIEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume20
Issue number1
DOIs
Publication statusPublished - 1 Jan 2023

Keywords

  • DNA- and RNA- binding protein prediction
  • hierarchical ensemble learning
  • multi-label learning
  • stacking technology

Fingerprint

Dive into the research topics of 'iDRBP-EL: Identifying DNA- and RNA- Binding Proteins Based on Hierarchical Ensemble Learning'. Together they form a unique fingerprint.

Cite this