If you're building AI models for drug discovery, you should check out the newly open-source #BioNeMo Framework:

code: github.com/NVIDIA/bione...
paper: arxiv.org/abs/2411.10548
docs: docs.nvidia.com/bionemo-fram...
explainer: t.co/7MOamSChGN

bionemo-framework

A framework for building and adapting AI models in drug discovery at scale.

https://github.com/NVIDIA/bionemo-framework

NVIDIA boosts BioNeMo models with efficient MoE training

Read more:
https://quantumzeitgeist.com/nvidia-bionemo-demonstration-boosts-efficient/

Nvidia has just open-sourced BioNeMo, a framework for bioinformatics researchers doing machine learning research. Looks like it currently supports (hopefully not only) molecule generation, structure prediction, ligand binding, and representation learning.

nvidia.github.io/bionemo-fram...

BioNemo es de Nvidia, que está demandada por infracción de derechos de autor, también lo puedes leer en el manifiesto enlazado.

NVIDIA; biyoloji, kimya, genomik ve ilaç keşfi alanlarındaki yaşam bilimleri iş akışlarına özel araçlar kazandırmak amacıyla BioNeMo Agent Toolkit yazılım paketini tanıttı.

www.airehber.com.tr/timeline/y8x...

#nvidia #bionemo #biotech #science

🤖 NVIDIA's BioNeMo Agent Toolkit boosts biomolecular modeling accuracy

NVIDIA's BioNeMo Agent Toolkit has increased task completion in biomolecular modeling from 57.1% to 100% by packaging biomolecular models as callable...

#ComputationalBiology #GenerativeAI #DeepLearning #AI #AIPulse

NVIDIA、Transformer Engineを活用した生物系MoEモデルの効率的学習手法を公開

https://localmodelwatch.tsuchitsuchi.com/2026/09/25/nvidia-efficient-moe-training-bionemo/

New video: a brief introduction to NVIDIA's BioNeMo, OpenAI's GPT-Rosalind, and Anthropic's Claude Science. While they all sell "AI-powered drug discovery", they are in fact very different products.
youtu.be/NQvWXcYszMI
#artificialintelligence #bioinformatics #drugdiscovery

It has also been exciting to see Protein-Complexa used in emerging agentic biology workflows—from work at Anthropic and Muni Bio to Levin Harness and the BioNeMo Agent Toolkit (and many others!)

SOTA open models can become infrastructure for accelerating science! 4/n

PyTorch workflows in NVIDIA BioNeMo Inference Runtime cover Boltz-2, OpenFold2, and OpenFold3, with optimized kernels and CUDA Graphs where applicable.

https://developer.nvidia.com/blog/high-throughput-structure-prediction-with-bionemo-inference-runtime/?ncid=so-twit-687376&linkId=100000438747365

arxiv.org/abs/2411.10548

Built on the NVIDIA Vera Rubin architecture and the BioNeMo platform, the lab will utilize manufacturing lines to optimize global supply chains before a single molecule is produced.

#AI #NVIDIA #EliLilly #BioNeMo #VeraRubin #DrugDiscovery #Biotech #NexTrend

Anthropic Claude Science now integrates the BioNeMo Agent Toolkit, allowing researchers to type plain-text requests and execute hardware-accelerated genomics and proteomics workflows. #nvidia #anthropic #claude #science #lifesciences #hpc #ai #technology

NVIDIA BioNeMo Agent Toolkit Brings Accelerated AI to Life Sciences Researchers in Claude Science

blogs.nvidia.com/blog/claude-...

Homology retrieval grounds ML systems to produce reliable predictions. MMseqs2 is already used in Boltz1/2, BioEmu, MSA-Pairformer, Chai-1, BioNeMo, Proteinx, etc. MMseqs2-GPU can enable these and next-gen models to integrate fast homology retrieval for end-to-end GPU inference. 3/n

🤖 NVIDIA's BioNeMo boosts AI scientists' biomolecular task efficiency

NVIDIA's BioNeMo toolkit has doubled AI scientists' token efficiency and increased task completion rates to 100% in biomolecular research. This...

#Genomics #ComputationalBiology #GenerativeAI #AI #AIPulse

The best hope we at NVIDIA have to help dent progress in machine learning biology is to enable everyone to do it as efficiently as possible.

We released BioNeMo Framework open-source to share our learnings with the community, and learn from everyone here about what we need to build for you to scale