Related Experiment Video
Updated: Aug 22, 2025
Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases
Published on: May 17, 2019
GLassonet: Identifying Discriminative Gene Sets Among Molecular Subtypes of Breast Cancer
Abstract:
Breast cancer is a heterogeneous disease caused by various alterations in the genome or transcriptome. Molecular subtypes of breast cancer have been reported, but useful biomarkers remain to be identified to uncover underlying biological mechanisms and guide clinical decisions. Towards biomarker discovery, several studies focus on genomic alterations that provide differences, while few works concern transcriptomic characterizations that mediate tumor progression. Rather than using differential expression (DE) or weighted network analysis, we propose a feature selection method, dubbed GLassonet, to identify discriminative biomarkers from transcriptome-wide expression profiles by embedding the relationship graph of high-dimensional expressions into the Lassonet model. GLassonet comprises a nonlinear neural network for identifying cancer subtypes, a skipping fully connected layer for canceling the connections of hidden layers from input features to output categories, and a graph enhancement for preserving the discriminative graph into the selected subspace. First, an iterative optimization algorithm learns model parameters on the TCGA breast cancer dataset to investigate the classification performance. Then, we probe the distribution patterns of GLassonet-selected gene sets across the cancer subtypes and compare them to gene sets outputted from the state-of-the-art. More profoundly, we conduct the overall survival analysis on three GLassonet-selected new marker genes, i.e., SOX10, TPX2, and TUBA1C, to investigate their expression changes and assess their prognostic impacts. Finally, we perform the enrichment analysis to discover the functional associations of the GLassonet-selected genes with GO terms and KEGG pathways. Experimental results show that GLassonet has a powerful ability to select the discriminative genes, which improve cancer subtype classification performance and provide potential biomarkers for cancer personalized therapy.
Insights
We developed GLassonet, a novel method to identify breast cancer biomarkers from gene expression data. This approach improves subtype classification and reveals potential new markers like SOX10, TPX2, and TUBA1C for personalized therapy.
Area of Science:
- Oncology
- Bioinformatics
- Computational Biology
Background:
- Breast cancer is a complex disease with diverse molecular subtypes.
- Identifying reliable biomarkers is crucial for understanding tumor biology and guiding clinical treatment.
- Current methods often focus on genomics or differential gene expression, with limited exploration of transcriptomic relationships for biomarker discovery.
Purpose of the Study:
- To introduce GLassonet, a novel feature selection method for identifying discriminative biomarkers from transcriptome-wide expression profiles.
- To evaluate GLassonet's performance in classifying breast cancer subtypes and uncovering potential therapeutic targets.
- To assess the prognostic value of GLassonet-selected genes through survival analysis.
Main Methods:
- Developed GLassonet, a method integrating a nonlinear neural network, a skipping fully connected layer, and graph enhancement for feature selection.
- Applied an iterative optimization algorithm to the TCGA breast cancer dataset for model training and classification.
- Conducted survival analysis on selected genes (SOX10, TPX2, TUBA1C) and performed enrichment analysis with GO terms and KEGG pathways.
Main Results:
- GLassonet effectively selects discriminative genes, significantly improving breast cancer subtype classification.
- Identified SOX10, TPX2, and TUBA1C as potential novel biomarkers with prognostic implications.
- Selected genes show significant functional associations with known cancer-related pathways.
Conclusions:
- GLassonet is a powerful tool for identifying robust gene expression biomarkers in breast cancer.
- The identified biomarkers offer potential for advancing personalized medicine and targeted cancer therapies.
- This transcriptomic approach enhances our understanding of breast cancer heterogeneity and progression.
