Data
In the endlessly recursive world of drug development, where billions are burned chasing molecules that never make it to market, the idea of conjuring promising compounds from nothing has always been more hope than method. Until this week. SandboxAQ, a company born out of Alphabet and now backed by Nvidia
News
The biotech industry, never short on acronyms or ambition, has been flirting with artificial intelligence for years. Models have already been shaping protocol designs, accelerated site selection, and sifted through trial data faster than any human team could hope to match. But until recently, these systems operated in a kind
AI
Fauna Bio is betting evolution already cracked biology’s toughest problems. Their new AI engine, Fauna Brain, turns nature’s wildest genetic secrets into therapeutic targets in minutes and costs pennies. Fauna Bio isn’t your typical Silicon Valley biotech startup. Instead of chasing incremental tweaks to familiar targets, they&
AI
BioIT isn’t starved for data. It’s choking on chaos. No shared formats. No clean metadata. No real interoperability. If we don’t fix that, AI stays blind. The scene is not particularly dramatic, unless you’re the kind of person who thinks databases can scream. We’re in
AI
BioNeMo isn’t open, cheap, or fully explainable. It runs best on NVIDIA hardware and wraps biology in black-box APIs. Still, it’s quietly becoming the stack real pipelines depend on. If you’ve ever tried to run AlphaFold at scale or fine-tune a protein language model without burning six
AI
If you want to see what an antibody language model trained only on humans can actually do, GLIMPSE-1 is your proof. No mouse scaffolds or synthetic libraries. And no structural hallucinations either. Just native human sequence data, paired heavy-light chains, and a model trained to learn the logic evolution already
News
AstraZeneca is placing a $110 million direct bet on CSPC Pharmaceuticals AI platform in Shijiazhuang. It’s not about factories or sales, it’s about code. CSPC, which few in the West have heard of and which has only a small trace on the web, will power discovery with a
Protein Design
Most of what passes for protein design these days is better described as substitution. You take a known backbone, swap in plausible residues based on energy or evolutionary alignment, and run it through simulation until the numbers settle into something stable. It works, in a way, but it’s more