TY - JOUR
T1 - Stacked Graph Attention Network With Temporal Modeling for lncRNA-miRNA Association Network
AU - Saxena, Shivani
AU - Rizvi, Ahsan Z.
PY - 2025
Y1 - 2025
N2 - Long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) play critical roles in regulating biological processes and disease mechanisms through their interactions, known as lncRNA-miRNA associations (LMAs). Accurate prediction of LMAs is essential for understanding disease progression, yet existing computational methods often exhibit inadequate feature integration, limited generalizability, and insufficient modeling of complex interactions. This study introduces the Stacked Graph Attention Network with Temporal Modeling (SGAT-TM), a novel framework that integrates statistical, graph-structural, and sequence-derived features of lncRNAs and miRNAs. SGAT-TM utilizes a multilayer Graph Attention Network (GAT), enhanced by self-attention, a multilayer perceptron (MLP), and a Gated Recurrent Unit (GRU) to capture LMA patterns, preserve long-range dependencies, and produce robust representations. Evaluation on benchmark datasets demonstrates that SGAT-TM outperforms state-of-the-art methods in predictive accuracy, robustness, and generalizability. SGAT-TM enhances LMA network analysis and provides significant insights into lncRNA-miRNA associations in biological and disease contexts.
AB - Long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) play critical roles in regulating biological processes and disease mechanisms through their interactions, known as lncRNA-miRNA associations (LMAs). Accurate prediction of LMAs is essential for understanding disease progression, yet existing computational methods often exhibit inadequate feature integration, limited generalizability, and insufficient modeling of complex interactions. This study introduces the Stacked Graph Attention Network with Temporal Modeling (SGAT-TM), a novel framework that integrates statistical, graph-structural, and sequence-derived features of lncRNAs and miRNAs. SGAT-TM utilizes a multilayer Graph Attention Network (GAT), enhanced by self-attention, a multilayer perceptron (MLP), and a Gated Recurrent Unit (GRU) to capture LMA patterns, preserve long-range dependencies, and produce robust representations. Evaluation on benchmark datasets demonstrates that SGAT-TM outperforms state-of-the-art methods in predictive accuracy, robustness, and generalizability. SGAT-TM enhances LMA network analysis and provides significant insights into lncRNA-miRNA associations in biological and disease contexts.
KW - Accuracy
KW - Biological information theory
KW - Biological system modeling
KW - Computational modeling
KW - Data models
KW - Deep learning
KW - Diseases
KW - Long non-coding RNAs
KW - Predictive models
KW - RNA
KW - Regulation
KW - graph attention networks
KW - graph neural networks
KW - lncRNA-miRNA association network
KW - microRNAs
KW - Accuracy
KW - Biological information theory
KW - Biological system modeling
KW - Computational modeling
KW - Data models
KW - Deep learning
KW - Diseases
KW - Long non-coding RNAs
KW - Predictive models
KW - RNA
KW - Regulation
KW - graph attention networks
KW - graph neural networks
KW - lncRNA-miRNA association network
KW - microRNAs
UR - https://res.slu.se/id/publ/144449
U2 - 10.1109/TCBBIO.2025.3587877
DO - 10.1109/TCBBIO.2025.3587877
M3 - Journal article
C2 - 40811279
SN - 2998-4165
VL - 22
SP - 2216
EP - 2229
JO - IEEE Transactions on Computational Biology and Bioinformatics
JF - IEEE Transactions on Computational Biology and Bioinformatics
IS - 5
ER -