Embedding Struktur Sekunder lncRNA Berbasis Variational Autoencoder untuk Klasifikasi Kanker Hati dengan GraphSAGE

Theodora Tantri Trisnawati; Mohammad Isa Irawan

doi:10.37905/euler.v14i2.40387

Embedding Struktur Sekunder lncRNA Berbasis Variational Autoencoder untuk Klasifikasi Kanker Hati dengan GraphSAGE

Theodora Tantri Trisnawati, Mohammad Isa Irawan

Abstract

Identifying liver cancer-associated lncRNAs is a classification problem that can leverage various biological characteristics, such as secondary structure, expression levels, and molecular associations with RNA-binding proteins (RBPs). This study develops a VAE-GraphSAGE framework to integrate this information within a heterogeneous graph. A Variational Autoencoder (VAE) is employed for representation learning to extract lncRNA secondary structure embeddings through a reconstruction process that does not rely on class labels. These embeddings are combined with expression features to form node features, while data on lncRNA similarity, lncRNA-RBP interactions, and protein-protein interactions (PPI) are used to construct the heterogeneous graph. Subsequently, GraphSAGE serves as the classifier, utilizing inter-node relationship information to classify the lncRNAs. The dataset comprises 1,000 lncRNAs (400 positive and 600 negative) and 85 RBPs (as protein nodes), with a training-validation-testing split of 70:15:15. Comparative results indicate that VAE-GraphSAGE achieves the highest recall among the tested models (outperforming AE-GraphSAGE, MLP-GraphSAGE, CNN-GraphSAGE, and ResNet-GraphSAGE); meanwhile, MLP-GraphSAGE yields the highest accuracy, precision, specificity, and F1-score, and CNN-GraphSAGE produces the highest ROC-AUC. Furthermore, using the same VAE embeddings, VAE-GraphSAGE demonstrates superior performance compared to VAE-HGT and VAE-RGCN across the evaluated classification metrics. These results demonstrate that the VAE effectively generates secondary structure representations that facilitate the detection of positive lncRNAs, while GraphSAGE successfully leverages biological relationships within the heterogeneous graph for the classification task.

Keywords

VAE; GraphSAGE; lncRNA; Liver Cancer

Full Text:

PDF

References

International Agency for Research on Cancer (IARC/WHO), “Global cancer observatory (gco): Cancer today,” 2024, url: https://gco.iarc.who.int/en/projects#database.

H. Rumgay et al., “Global burden of primary liver cancer in 2020 and predictions to 2040,” J Hepatol, vol. 77, no. 6, pp. 1598–1606, Dec 2022, doi: 10.1016/j.jhep.2022.08.021.

J.-G. Chen et al., “Liver cancer mortality over six decades in an epidemic area: What we have learned,” PeerJ, vol. 9, p. e10600, 2021, doi: 10.7717/peerj.10600.

R. Qiang, X.-Z. Liu, and J.-C. Xu, “The immune pathogenesis of acute-on-chronic liver failure and the danger hypothesis,” Frontiers in Immunology, vol. 13, 2022, doi: 10.3389/fimmu.2022.935160.

J. Zhou et al., “Guidelines for the diagnosis and treatment of primary liver cancer (2022 edition),” Liver Cancer, vol. 12, no. 5, pp. 405–444, Oct 2023, doi: 10.1159/000530495.

Y. Liu, A. He, B. Liu, Z. Huang, and H. Mei, “Potential role of lncrna h19 as a cancer biomarker in human cancers detection and diagnosis: A pooled analysis based on 1585 subjects,” Biomed Res Int, vol. 2019, p. 9056458, 2019, doi: 10.1155/2019/9056458.

X. Chen, J. Song, X. Wang, D. Sun, Y. Liu, and Y. Jiang, “Lncrna linc00460: Function and mechanism in human cancer,” Thorac Cancer, vol. 13, no. 1, pp. 3–14, Jan 2022, doi: 10.1111/1759-7714.14238.

Y. Zhang, “Lncrna-encoded peptides in cancer,” J Hematol Oncol, vol. 17, no. 1, p. 66, Aug 2024, doi: 10.1186/s13045-024-01591-0.

M. Yang, H. Lu, J. Liu, S. Wu, P. Kim, and X. Zhou, “lncrnafunc: A knowledgebase of lncrna function in human cancer,” Nucleic Acids Res, vol. 50, no. D1, pp. D1295–D1306, Jan 2022, doi: 10.1093/nar/gkab1035.

C. Badowski, B. He, and L. X. Garmire, “Blood-derived lncrnas as biomarkers for cancer diagnosis: The good, the bad and the beauty,” NPJ Precis Oncol, vol. 6, no. 1, p. 40, Jun 2022, doi: 10.1038/s41698-022-00283-7.

L. Min et al., “Exosomal lncrna rp5-977b1 as a novel minimally invasive biomarker for diagnosis and prognosis in non-small cell lung cancer,” Int J Clin Oncol, vol. 27, no. 6, pp. 1013–1024, Jun 2022, doi: 10.1007/s10147-022-02129-5.

Y. Zhang et al., “Lncrna-bc069792 suppresses tumor progression by targeting kcnq4 in breast cancer,” Mol Cancer, vol. 22, no. 1, p. 41, Mar 2023, doi: 10.1186/s12943-023-01747-5.

J. Wang, Q. Jia, S. Jiang, W. Lu, and H. Ning, “Pou6f1 promotes ferroptosis by increasing lncrna-casc2 transcription to regulate socs2/slc7a11 signaling in gastric cancer,” Cell Biol Toxicol, vol. 40, no. 1, p. 3, Jan 2024, doi: 10.1007/s10565-024-09843-y.

Y. Wu and X. Xu, “Long non-coding rna signature in colorectal cancer: Research progression and clinical application,” Cancer Cell Int, vol. 23, no. 1, p. 28, Feb 2023, doi: 10.1186/s12935-023-02867-0.

R. Khalid, H. Naveed, and Z. Khalid, “Computational prediction of disease related lncrnas using machine learning,” Scientific Reports, vol. 13, no. 1, p. 806, Jan 2023, doi: 10.1038/s41598-023-27680-7.

M. Li and C. Liang, “Lncdc: A machine learning-based tool for long non-coding rna detection from rna-seq data,” Scientific Reports, vol. 12, no. 1, p. 19083, Nov 2022, doi: 10.1038/s41598-022-22082-7.

A. Lawarde, M. Khatun, P. Lingasamy, A. Salumets, and V. Modhukur, “Tumor tissue-of-origin classification using mirna-mrna-lncrna interaction networks and machine learning methods,” Frontiers in Bioinformatics, vol. 5, 2025, doi: 10.3389/fbinf.2025.1571476.

Y. Feng and Y. Wang, “Comparison of the classifiers based on mrna, microrna and lncrna expression and dna methylation profiles for the tumor origin detection,” Frontiers in Genetics, vol. 15, 2024, doi: 10.3389/fgene.2024.1383852.

Z. Liu, O. O. Petinrin, M. Toseef, N. Chen, and K.-C. Wong, “Construction of immune infiltration-related lncrna signatures based on machine learning for the prognosis in colon cancer,” Biochem Genet, vol. 62, no. 3, pp. 1925–1952, Jun 2024, doi: 10.1007/s10528-023-10516-4.

Y. Liu et al., “Machine learning combined with multi-omics to identify immune-related lncrna signature as biomarkers for predicting breast cancer prognosis,” Scientific Reports, vol. 15, no. 1, p. 23863, Jul 2025, doi: 10.1038/s41598-025-10186-9.

J. Wang, J. Xing, and J. Wang, “Predicting mirna-disease association based on hybrid graph autoencoder,” in 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2024, pp. 4284–4291, doi: 10.1109/BIBM62325.2024.10821965.

Y. Liu, X. Ren, J. Li, X. Chen, and X. Zhu, “Prediction of circrna-drug sensitivity using random autoencoders and multi-layer heterogeneous graph transformers,” Applied Intelligence, vol. 55, no. 4, p. 238, Dec 2024, doi: 10.1007/s10489-024-05859-3.

S. Ning et al., “Lnc2cancer 3.0: An updated resource for experimentally supported cancer-lncrna and circrna associations with web tools,” 2021, url: https://bio-bigdata.hrbmu.edu.cn/lnc2cancer/.

Z. Bao, Z. Yang, Z. Huang, Y. Zhou, Q. Cui, and D. Dong, “Lncrnadisease v3.0: A comprehensive database of long non-coding rna and circular rna associated with human diseases,” 2023, url: http://www.rnanut.net/lncrnadisease/index.php/home/browse.

GENCODE Project, “Gencode human gene annotation, release 47 (grch38.p14),” 2024, url: https://www.gencodegenes.org/human/.

The Cancer Genome Atlas (TCGA) and GDC Data Portal, “Tcga-lihc: The cancer genome atlas liver hepatocellular carcinoma project,” 2024, url: https://portal.gdc.cancer.gov/projects/TCGA-LIHC.

GTEx Consortium, “The genotype-tissue expression (gtex) portal: Adult bulk tissue expression,” 2023, url: https://gtexportal.org/home/downloads/adult-gtex/bulk_tissue_expression.

ENCODE Project Consortium, “Encode encyclopedia of dna elements: Data portal,” 2024, url: https://www.encodeproject.org/search/.

The UniProt Consortium, “Uniprot id mapping service,” 2024, url: https://www.uniprot.org/idmapping.

EMBL-EBI IntAct Team, “Intact: Molecular interaction database,” 2024, url: https://www.ebi.ac.uk/intact/home.

D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” arXiv preprint arXiv:1312.6114, 2013, url: https://arxiv.org/abs/1312.6114.

W. L. Hamilton, “Graph representation learning,” Synthesis Lectures on Artificial Intelligence and Machine Learning, vol. 14, no. 3, pp. 1–159.

W. L. Hamilton, R. Ying, and J. Leskovec, “Inductive representation learning on large graphs,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, ser. NIPS’17. Red Hook, NY, USA: Curran Associates Inc., 2017, pp. 1025–1035.

DOI: https://doi.org/10.37905/euler.v14i2.40387