Leveraging explainable multi-scale features for fine-grained circRNA-miRNA interaction prediction

Abstract Background Circular RNAs (circRNAs) and microRNAs (miRNAs) interactions have essential implications in various biological processes and diseases. Computational science approaches have emerged as powerful tools for studying and predicting these intricate molecular interactions, garnering con...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Peng, Wang Wang, Zongyi Yang, Xiangzheng Fu, Wei Liang, Dongsheng Cao
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Biology
Subjects:
Online Access:https://doi.org/10.1186/s12915-025-02227-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849729000450031616
author Li Peng
Wang Wang
Zongyi Yang
Xiangzheng Fu
Wei Liang
Dongsheng Cao
author_facet Li Peng
Wang Wang
Zongyi Yang
Xiangzheng Fu
Wei Liang
Dongsheng Cao
author_sort Li Peng
collection DOAJ
description Abstract Background Circular RNAs (circRNAs) and microRNAs (miRNAs) interactions have essential implications in various biological processes and diseases. Computational science approaches have emerged as powerful tools for studying and predicting these intricate molecular interactions, garnering considerable attention. Current methods face two significant limitations: the lack of precise interpretable models and insufficient representation of homogeneous and heterogeneous molecules. Results We propose a novel method, MFERL, that addresses both limitations through multi-scale representation learning and an explainable fine-grained model for predicting circRNA-miRNA interactions (CMI). MFERL learns multi-scale representations by aggregating homogeneous node features and interacting with heterogeneous node features, as well as through novel dual-convolution attention mechanisms and contrastive learning to enhance features. Conclusions We utilize a manifold-based method to examine model performance in detail, revealing that MFERL exhibits robust generalization, robustness, and interpretability. Extensive experiments show that MFERL outperforms state-of-the-art models and offers a promising direction for understanding CMI intrinsic mechanisms.
format Article
id doaj-art-df060f4e0f4045b69864fcf044d958f1
institution DOAJ
issn 1741-7007
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Biology
spelling doaj-art-df060f4e0f4045b69864fcf044d958f12025-08-20T03:09:21ZengBMCBMC Biology1741-70072025-05-0123111510.1186/s12915-025-02227-6Leveraging explainable multi-scale features for fine-grained circRNA-miRNA interaction predictionLi Peng0Wang Wang1Zongyi Yang2Xiangzheng Fu3Wei Liang4Dongsheng Cao5School of Computer Science and Engineering, Hunan University of Science and TechnologySchool of Computer Science and Engineering, Hunan University of Science and TechnologySchool of Computer Science and Engineering, Hunan University of Science and TechnologyCollege of Computer Science and Electronic Engineering, Hunan UniversitySchool of Computer Science and Engineering, Hunan University of Science and TechnologyXiangya School of Pharmaceutical Sciences, Central South UniversityAbstract Background Circular RNAs (circRNAs) and microRNAs (miRNAs) interactions have essential implications in various biological processes and diseases. Computational science approaches have emerged as powerful tools for studying and predicting these intricate molecular interactions, garnering considerable attention. Current methods face two significant limitations: the lack of precise interpretable models and insufficient representation of homogeneous and heterogeneous molecules. Results We propose a novel method, MFERL, that addresses both limitations through multi-scale representation learning and an explainable fine-grained model for predicting circRNA-miRNA interactions (CMI). MFERL learns multi-scale representations by aggregating homogeneous node features and interacting with heterogeneous node features, as well as through novel dual-convolution attention mechanisms and contrastive learning to enhance features. Conclusions We utilize a manifold-based method to examine model performance in detail, revealing that MFERL exhibits robust generalization, robustness, and interpretability. Extensive experiments show that MFERL outperforms state-of-the-art models and offers a promising direction for understanding CMI intrinsic mechanisms.https://doi.org/10.1186/s12915-025-02227-6circRNAmiRNAExplainabilityMulti-scale featureRepresentation learning
spellingShingle Li Peng
Wang Wang
Zongyi Yang
Xiangzheng Fu
Wei Liang
Dongsheng Cao
Leveraging explainable multi-scale features for fine-grained circRNA-miRNA interaction prediction
BMC Biology
circRNA
miRNA
Explainability
Multi-scale feature
Representation learning
title Leveraging explainable multi-scale features for fine-grained circRNA-miRNA interaction prediction
title_full Leveraging explainable multi-scale features for fine-grained circRNA-miRNA interaction prediction
title_fullStr Leveraging explainable multi-scale features for fine-grained circRNA-miRNA interaction prediction
title_full_unstemmed Leveraging explainable multi-scale features for fine-grained circRNA-miRNA interaction prediction
title_short Leveraging explainable multi-scale features for fine-grained circRNA-miRNA interaction prediction
title_sort leveraging explainable multi scale features for fine grained circrna mirna interaction prediction
topic circRNA
miRNA
Explainability
Multi-scale feature
Representation learning
url https://doi.org/10.1186/s12915-025-02227-6
work_keys_str_mv AT lipeng leveragingexplainablemultiscalefeaturesforfinegrainedcircrnamirnainteractionprediction
AT wangwang leveragingexplainablemultiscalefeaturesforfinegrainedcircrnamirnainteractionprediction
AT zongyiyang leveragingexplainablemultiscalefeaturesforfinegrainedcircrnamirnainteractionprediction
AT xiangzhengfu leveragingexplainablemultiscalefeaturesforfinegrainedcircrnamirnainteractionprediction
AT weiliang leveragingexplainablemultiscalefeaturesforfinegrainedcircrnamirnainteractionprediction
AT dongshengcao leveragingexplainablemultiscalefeaturesforfinegrainedcircrnamirnainteractionprediction