Brittany Trang, Ph.D., covers AI in health and medicine: Does it actually work? Who benefits, or might be harmed? She writes the weekly AI Prognosis newsletter. Follow her on Threads, Mastodon, and Bluesky. You can reach Brittany on Signal at btrang.01.

Want to stay on top of the science and politics driving biotech today? Sign up to get our biotech newsletter in your inbox.

The tumors possibly connected to pediatric gene therapies make me sad. Babies. 

The need-to-know this morning

• Vir Biotechnology said monthly injections of two experimental medicines reduced hepatitis D virus to undetectable levels in 44% of patients compared to none of the patients who received delayed treatment with the same regimen. The result achieved the primary goal of a Phase 3 study. 
• Zura Bio said its experimental antibody tibulizumab failed to improve the symptoms of hidradenitis suppurativa, an inflammatory skin condition, compared to a placebo in a mid-stage study. 
• Roivant said Lisraya generated $31 million in sales in the five weeks since it was approved to treat dermatomyositis.
• Argenx is acquiring privately held Unnatural Products, a medicinal chemistry company that specializes in the discovery of protein-based drugs. 

Why two heart trials should puncture AI drug discovery enthusiasm

Before anyone promises that AI will cure every disease, consider what happened the last time a shiny new tool was supposed to make drug development more predictable. At the American Heart Association meeting, two big trials came up empty.