Deep learning reveals FLAD1-mediated mitochondrial metabolic reprogramming in hypoxic tumors

Area of Science:

• Oncology
• Metabolic Engineering
• Computational Biology

Background:

• Hypoxia is a key characteristic of solid tumors, promoting cancer progression and posing therapeutic challenges.
• Tumor metabolic reprogramming under hypoxia creates vulnerabilities exploitable for cancer therapy.

Purpose of the Study:

• To systematically compare metabolic network differences between hypoxic and normoxic tumor cells.
• To develop a deep learning model (DepFormer) for identifying hypoxia-dependent metabolic genes.
• To identify FLAD1 as a potential therapeutic target in hypoxic tumors.

Main Methods:

• Comparative analysis of metabolic networks in hypoxic vs. normoxic cells.
• Development and application of DepFormer, a transformer-based deep learning model.
• Functional validation of FLAD1's role in tumor cell adaptation to hypoxia.

Main Results:

• Oxidative phosphorylation identified as a significantly hypoxia-dependent pathway.
• FLAD1 predicted as a key hypoxia-dependent metabolic gene, with locus amplification and upregulation in tumors.
• FLAD1 depletion impairs mitochondrial complex II, causing metabolic imbalance and hindering hypoxia adaptation.
• A FLAD1 inhibitor selectively targets hypoxic tumor cell growth.

Conclusions:

• DepFormer is an effective framework for predicting state-specific metabolic dependencies.
• FLAD1 represents a metabolic vulnerability and a novel therapeutic target for hypoxic tumors.