Systems
The funny thing about revolutions (and yes, the transition to AI-driven drug discovery certainly qualifies) is how they unfold gradually, right under our noses. If you had blinked sometime around, say, 2019, you might have missed the moment when major pharma firms stopped treating AI as an intriguing experiment. Instead,
MIT
At last week’s MIT AI Conference, a panel of scientists and industry leaders gathered to tackle a deceptively simple question: how do we build artificial intelligence that clinicians can trust? More specifically, how to we get to AI precise enough to handle life-or-death decisions yet transparent enough for a
Systems
At the bleeding edge of drug discovery, researchers are facing a new kind of bottleneck. Models balloon to trillions of parameters, datasets surge into exabyte territory, and suddenly the GPU-driven datacenter begins to wobble under the load. Inside pharma labs, research hospitals, and genomics shops, computational scientists increasingly find themselves
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
Data
Xaira just dropped X-Atlas/Orion—the largest genome-wide Perturb-seq dataset ever, covering 8 million cells. It's public, powerful, and poised to reshape how AI predicts biology. Launching a biotech startup is often about making promises. These are promises to investors, to science, to medicine. But when you start
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&
The backend of biotech. AI, datacenters, and the systems powering the future of life sciences
Recursion Pharma's stack is bioIT future spelled out clearly from automated labs through edge GPU compute streaming Kafka Kubernetes orchestration and cloud TPUs The architecture isn't just efficient it's inevitable. It’s almost a cliché now to say biology has become a data science
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
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
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
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
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
Inside the strange, silent future of terahertz wireless infrastructure There’s a thing that happens in aging datacenters—not always visible, but felt. You open the floor tile, expecting clean airflow, and instead find a bundled, brittle, half-labeled horror of fiber and copper, snaking in knots like something alive and
Why the next frontier in compute might leave your infrastructure behind In the beginning, there was brute force. You fed the GPUs data—any data, all data—and they ground it into insight with raw, burn-the-planet math. Bigger models meant bigger training runs meant bigger clusters. And the datacenter, that