AI-assisted screening identifies TFEB activators for adipose remodeling in mice
Published in Artificial Intelligence, Drugs development & discovery, Immunology, Journals.
Published October 28, 2026.
An October 27 study in Communications Biology combines mechanistic experiments with AI-assisted image screening to investigate healthier remodeling of adipose tissue. Zeng and colleagues focused on TFEB, a transcription factor involved in cellular regulation.
In mice fed a high-fat diet, deleting Tfeb in myeloid cells worsened oxygen deprivation, fibrosis and insulin resistance. Additional analyses implicated TFEB-driven VEGFA expression in macrophages as a contributor to blood-vessel adaptation during fat-tissue expansion.
The researchers built an image-analysis screening platform to measure TFEB movement into the nucleus. It identified tetrandrine and pacritinib as TFEB activators. In obese mice, these compounds improved adipose vascularization, reduced fibrosis and improved insulin sensitivity; tetrandrine acted through an mTOR-independent mechanism.
This is preclinical evidence, not proof of an effective obesity treatment in people. Myeloid gene deletion is broader than adipose-macrophage-specific manipulation, so attributing every systemic effect to those cells requires caution. Further work must establish tissue specificity, safety and clinical benefit before therapeutic conclusions follow.
Source: Zeng et al., Communications Biology, October 27, 2026. DOI: 10.1038/s42003-026-11253-1.