Pulse.

a daily field guide to health research that matters

◆ Console

‹ Sun · 26 Jul 2026
Promising but preliminary

Machine learning-guided discovery of withangulatin A as a novel inducer of megakaryocytic differentiation through direct targeting of TYK2 in leukemia.

A natural compound from plants shows promise as a leukemia therapy by triggering cancer cells to mature and stop growing.

Machine learning screening of 113 withanolides from Physalis angulata identified withangulatin A as a potent inducer of megakaryocytic differentiation in non-APL leukemia through direct TYK2 targeting, validated by SPR, CETSA, and DARTS target engagement assays. In vivo studies in a syngeneic mouse model and primary human AML samples confirmed differentiation-inducing activity and prolonged survival, establishing WA as a promising natural product lead for differentiation therapy in non-APL leukemia.

What the study was

Study design
Preclinical (in vitro + in vivo animal model + primary human cells)
Population
K562 and HEL leukemia cell lines; syngeneic leukemia mouse model; primary human non-APL AML samples
Category
Drug Development
Maturity
Exploratory
Journal
Phytomedicine

Why it surfaced

Novel TYK2-targeting natural product discovered by ML-guided screening; validated in primary human cells; addresses differentiation therapy gap in non-APL leukemia where targeted differentiating agents are lacking.

A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.