iProtDNA-SMOTE: Enhancing protein-DNA binding sites prediction through imbalanced graph neural networks
Open Access
- 13 May 2025
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (5) , e0320817
Abstract
Protein-DNA interactions play a crucial role in cellular biology, essential for maintaining life processes and regulating cellular functions. We propose a method called iProtDNA-SMOTE, which utilizes non-equilibrium graph neural networks along with pre-trained protein language models to predict DNA binding residues. This approach effectively addresses the class imbalance issue in predicting protein-DNA binding sites by leveraging unbalanced graph data, thus enhancing model’s generalization and specificity. We trained the model on two datasets, TR646 and TR573, and conducted a series of experiments to evaluate its performance. The model achieved AUC values of 0.850, 0.896, and 0.858 on the independent test datasets TE46, TE129, and TE181, respectively. These results indicate that iProtDNA-SMOTE outperforms existing methods in terms of accuracy and generalization for predicting DNA binding sites, offering reliable and effective predictions to minimize errors. The model has been thoroughly validated for its ability to predict protein-DNA binding sites with high reliability and precision. For the convenience of the scientific community, the benchmark datasets and codes are publicly available at https://github.com/primrosehry/iProtDNA-SMOTE.Keywords
Funding Information
- National Natural Science Foundation of China (62162032)
- National Natural Science Foundation of China (32260154)
- Education Department of Jiangxi Province (GJJ2201040)
- Education Department of Jiangxi Province (GJJ2201004)
This publication has 43 references indexed in Scilit:
- Graph Neural Network with curriculum learning for imbalanced node classificationNeurocomputing, 2024
- Mit Protein Transformer: Identification Mitochondrial Proteins with Transformer Model2023
- A GO catalogue of human DNA-binding transcription factorsBiochimica et Biophysica Acta (BBA) - Gene Regulatory Mechanisms, 2021
- iSS-CNN: Identifying splicing sites using convolution neural networkChemometrics and Intelligent Laboratory Systems, 2019
- DNAPred: Accurate Identification of DNA-Binding Sites from Protein Sequence by Ensembled Hyperplane-Distance-Based Support Vector MachinesJournal of Chemical Information and Modeling, 2019
- MUFOLD‐SS: New deep inception‐inside‐inception networks for protein secondary structure predictionProteins: Structure, Function, and Bioinformatics, 2018
- Effects of radiation damage in studies of protein-DNA complexes by cryo-EMMicron, 2017
- Sequence-based prediction of protein-binding sites in DNA: Comparative study of two SVM modelsComputer Methods and Programs in Biomedicine, 2014
- ChIP-Seq Data Analysis: Identification of Protein–DNA Binding Sites with SISSRs Peak-Finder2011
- Protein microarray technologyDrug Discovery Today, 2002