LncRNAs are crucial in gene regulation and associated with diseases and biological processes. Predicting their subcellular localization accurately remains a challenge due to sequence complexity and data imbalance. We propose a graph neural network method based on LncRNA sequence features, emphasizing enhanced prediction accuracy through optimized graph structure and attention mechanisms. Our approach addresses data imbalance by introducing a weighted graph attention mechanism and a corrective network for improved generalization with fewer samples. This study introduces a potential method for LncRNA subcellular localization prediction, highlighting GNN applicability in bioinformatics tasks. These innovations contribute to biological data analysis and understanding LncRNA function, with practical applications in experimental validation.

Xi Deng. Application of Graph Attention Networks in LncRNA Subcellular Localization Prediction. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 3: 68-72. https://doi.org/10.25236/AJCIS.2024.070310.

[1] T. Zhang, P.W. Tan, L.Q. Wang, N.N. Jin, Y.N. Li, L. Zhang, H. Yang, Z.Y. Hu, L. N. Zhang, C.Y. Hu, C.H. Li, K. Qian, C.J. Zhang, Y. Huang, K.N. Li, H. Lin, D. Wang, RNALocate: a resource for RNA subcellular localizations, Nucleic Acids Res. 45 (2017) 135–138.

[2] Velickovic P, Cucurull G, Casanova A, et al. Graph attention networks[J]. stat, 2017, 1050: 20.

[3] Cui Y, Jia M, Lin T Y, et al. Class-balanced loss based on effective number of samples[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 9268-9277.

[4] Cao Z, Pan X, Yang Y, et al. The lncLocator: a subcellular localization predictor for long non-coding RNAs based on a stacked ensemble classifier[J]. Bioinformatics, 2018, 34(13): 2185-2194.

[5] Zeng M, Wu Y, Lu C, et al. DeepLncLoc: a deep learning framework for long non-coding RNA subcellular localization prediction based on subsequence embedding[J]. Briefings in Bioinformatics, 2022, 23(1): bbab360.