Related Experiment Video
Updated: Jun 28, 2026
LipidUNet-Machine Learning-Based Method of Characterization and Quantification of Lipid Deposits Using iPSC-Derived Retinal Pigment Epithelium
Published on: July 28, 2023
Machine Learning-Based single-cell characterization of lipid metabolic reprogramming in prostate cancer.
Danial Hashemi Karoii1, Ali Qorbanee2, Hossein Azizi3
1Department of Stem Cells and Cancer, College of Biotechnology, Amol University of Special Modern Technologies, Amol, 46158-63111, Iran; Department of Cell and Molecular Biology, School of Biology, College of Science, University of Tehran, Tehran, Iran.
Prostate cancer progression is driven by lipid metabolism reprogramming. Key genes regulating fatty acid and cholesterol metabolism were identified as prognostic biomarkers for personalized therapy.
Area of Science:
- Oncology
- Metabolic Research
- Bioinformatics
Background:
- Prostate cancer (PCa) is a leading cause of cancer death in men globally.
- Lipid metabolism reprogramming is crucial in PCa initiation, progression, and therapeutic resistance.
- Understanding lipid metabolic heterogeneity in PCa is essential for effective treatment strategies.
Purpose of the Study:
- To characterize lipid metabolism-related gene expression in prostate cancer using integrated multi-omics data.
- To identify prognostic biomarkers for prostate cancer progression and therapeutic resistance.
- To explore the role of lipid metabolism reprogramming in PCa heterogeneity.
Main Methods:
- Integration of multi-omics, single-cell RNA sequencing (scRNA-seq), and spatial transcriptomics data.
- Analysis of public datasets (TCGA-PRAD, GSE206962) using R-based bioinformatics pipelines.
- Application of machine learning algorithms (LASSO-Cox regression) to identify prognostic hub genes.
Main Results:
- Significant heterogeneity in lipid metabolic activity was observed across PCa cell populations.
- Key hub genes (HMGCR, MVK, STARD3, FADS1, APOE) identified as central regulators of lipid metabolism.
- A 5-gene prognostic signature demonstrated independent prognostic value for PCa patients.
Conclusions:
- Lipid metabolism reprogramming significantly drives prostate cancer progression and therapeutic resistance.
- Identified lipid metabolism biomarkers offer strong prognostic potential for personalized therapy.
- Targeting lipid biosynthesis and cholesterol pathways presents a promising avenue for improved PCa management.
