Integration of gene expression and DNA methylation data using MLA-GNN for liver cancer biomarker mining.

The early symptoms of hepatocellular carcinoma patients are often subtle and easily overlooked. By the time patients exhibit noticeable symptoms, the disease has typically progressed to middle or late stages, missing optimal treatment opportunities. Therefore, discovering biomarkers is essential for elucidating their functions for the early diagnosis and prevention. In practical research, challenges such as high-dimensional features, low sample size, and the complexity of gene interactions impact the reliability of biomarker discovery and disease diagnosis when using single-omics approaches. To address these challenges, we thus propose, Multi-level attention graph neural network (MLA-GNN) model for analyzing integrated multi-omics data related to liver cancer. The proposed protocol are using feature selection strategy by removing the noise and redundant information from gene expression and DNA methylation data. Additionally, it employs the Cartesian product method to integrate multi-omics datasets. The study also analyzes gene interactions using WGCNA and identifies potential genes through the MLA-GNN model, offering innovative approaches to resolve these issues. Furthermore, this paper identifies FOXL2 as a promising liver cancer marker through gene ontology and survival analysis. Validation using box plots showed that the expression of the gene FOXL2 was higher in patients with hepatocellular carcinoma than in normal individuals. The drug sensitivity correlation and molecular docking results of FOXL2 with the liver cancer-targeting agent lenvatinib emphasized its potential role in hepatocellular carcinoma treatment and highlighted the importance of FOXL2 in hepatocellular carcinoma treatment.