←
NVIDIA Healthcare1,647 posts
NVIDIA Healthcare avatar

NVIDIA Healthcare

@NVIDIAHealth

The official handle for #NVIDIAHealthcare. Helping the scientific and developer community advance research, diagnostics, and patient care with #AI.

◷ Joined October 2020▧ 432 Photos and videos
Genesis Molecular AI avatar
⟳ NVIDIA Healthcare retweeted
Genesis Molecular AI@genesismolai·Nov 16

NVIDIA just announced cuPotential at #SC26 — we helped test and refine it. Paired with Pearl, our cofolding model, it makes physics-based MD refinement ~4x faster in our drug discovery workflow. See the demo at the NVIDIA booth. @NVIDIAHealth @NVIDIA blogs.nvidia.com/blog/cuda-x…

Terray Therapeutics avatar
⟳ NVIDIA Healthcare retweeted
Terray Therapeutics@Terray_Tx·Nov 16

Our collaboration with @nvidia continues to expand the frontier for Terray. With early access to cuPotential, a new CUDA-X library that speeds up molecular dynamics simulations, we realized 50% efficiency gains compared to the baseline. This allows us to generate adaptive synthetic training data on the fly at lower cost, continuously improving the accuracy of TerraBind, EMMI’s universal potency model. Thank you to our amazing collaborators at NVIDIA for their partnership. @NVIDIAHealth Read more about our work: terraytx.ai/news-and-researc…

0:12
NVIDIA HPC Developer avatar
⟳ NVIDIA Healthcare retweeted
NVIDIA HPC Developer@NVIDIAHPCDev·19h

Scientists spend a lot of time waiting for simulations and data analysis to finish. New at #SC26, we announced CUDA-X libraries to help speed up that work across astrophysics, materials science and biology, and give AI agents tools to help researchers along the way. See what’s new → nvda.ws/4iXYKen

Post attachment
ToposBio avatar
⟳ NVIDIA Healthcare retweeted
ToposBio@ToposBio·Nov 16

Proteins move. Drug discovery moves with them. With @nvidia and @NVIDIAHealth cuPotential in our OpenMM workflows, we're running ~2-3× more molecular dynamics. Up to ~7× with our own optimizations: more physics to train our generative models on. More detail on our blog: toposbio.ai/blog/nvidia-cupo…

1:06
NVIDIA Healthcare avatar
NVIDIA Healthcare@NVIDIAHealth·Nov 16

On Wednesday, @proteneer is giving a talk: Fast, Accurate Molecular Dynamics for AI-Driven Drug Discovery. It's a 15-minute presentation followed by 5 minutes of Q&A. 🗓️ Wed, Nov 18, 4:30 PM CT 📍 Slurm Booth #1711, McCormick Place

NVIDIA Healthcare avatar
NVIDIA Healthcare@NVIDIAHealth·Nov 16

See cuPotential running at our demo, Accelerating Molecular Dynamics with NVIDIA cuPotential. 📍 NVIDIA Booth #3011 McCormick Place West, Exhibit Halls F1-2

NVIDIA Healthcare avatar
NVIDIA Healthcare@NVIDIAHealth·Nov 16

🆕 cuPotential A CUDA-X library for computing nonbonded interactions in molecular dynamics. The OpenMM plugin replaces the nonbonded force, integrator, and barostat. In NPT benchmarks on systems from 24K to 400K atoms, it ran over 3x faster than OpenMM on RTX PRO 6000 Blackwell and about 2x faster on B200, H100, A100, L40S, A10, L4, and T4. Accuracy holds up too, with a few hundred times less energy drift than default PME. 💻 Github nvda.ws/3WIwogJ 📄 Technical Blog nvda.ws/4AyIpDX 📍 Find us at #SC26 👇

Post attachment
NVIDIA Healthcare avatar
NVIDIA Healthcare@NVIDIAHealth·Nov 13

We used three models: - KERMT: our graph-based molecular property model, multi-task fine-tuned across all four CYP isoforms - Uni-Mol2: a 3D structure-aware backbone, ensembled with KERMT - NVIDIA Nemotron: post-trained to call the predictors as tools (2/3)

NVIDIA Healthcare avatar
NVIDIA Healthcare@NVIDIAHealth·Nov 13

🏆 NVIDIA BioNeMo team, NV-deCYPher, placed 3rd on both tracks of the OpenADMET Blind Challenge predicting CYP inhibition: Tier 1 on time-dependent inhibition, Tier 2 on direct inhibition. CYP inhibition causes drug-drug interactions often found late in the drug development pipeline. Predicting it early lets teams design around the liability. @SrimukhP @modernscientist @saint__ai (1/3)

Ben Pouladian avatar
⟳ NVIDIA Healthcare retweeted
Ben Pouladian@benitoz·Nov 8

Timeline cleanse I’ve been writing about this: the next inflection is the lab. I lost both my parents to cancer and my father in law to Alzheimer’s Jensen lays out the vision here. Connect AI agents to instruments and robots, run experiments, and feed the results back into models. I’ve seen a piece of this firsthand at Terray, where I’m an investor. The moat is the measurement. More experiments. More data. More tokens. 🧬🤖 We need faster cures

0:46
NVIDIA GTC avatar
⟳ NVIDIA Healthcare retweeted
NVIDIA GTC@NVIDIAGTC·Nov 6

Scientific discovery takes the spotlight at #NVIDIAGTC in Washington, D.C. Hear from scientists, policymakers, and industry leaders on advances in drug development, quantum computing, and federal health. Explore the sessions → nvda.ws/3WoiaBC

0:05
biohub avatar
⟳ NVIDIA Healthcare retweeted
biohub@biohub·Nov 5

Folding large biomolecular complexes takes models that can handle longer sequences without running out of compute and memory. Join Biohub, @nvidia, and @AnthropicAI on Nov 18 at 1pm PT for a webinar on long-context structure prediction with ESMFold2. Register: biohub.zoom.us/webinar/regis…

Post attachment
CellType avatar
⟳ NVIDIA Healthcare retweeted
CellType@celltypeinc·Nov 4

Can LLMs simulate biology? We tested frontier models on real lab experiments: predict how cells respond to drugs, gene knockdowns, and immune signals. Even the best get only part of the response right. Lots of room to improve. Introducing BioSimBench, built on @NVIDIAAI. 🧵

1:20
NVIDIA Healthcare avatar
NVIDIA Healthcare@NVIDIAHealth·Nov 4

NVIDIA Parabricks DeepVariant and DeepSomatic are now available in the Sarek pipeline on @nf_core. 🧬 This adds to the growing library of GPU accelerated alignment and variant calling tools available in Sarek. Try it 👉 nvda.ws/4imyJX5

Post attachment