AI X BIO

⚡ Accelerate your molecular clustering with nvMolKit and NVIDIA GPUs Our new guest post on Greg Landrum's RDKit blog breaks down how to achieve over 200x speedups on a local RTX 5080, and well over 1,000x on datacenter GPUs. Read the full breakdown and grab the code 🧵

Across large, multicohort datasets, CardioNets achieved superior performance to ECG-only baselines and diagnostic accuracy comparable to CMR-based models, supporting its potential to expand access to advanced cardiovascular assessment. Full study results: nejm.ai/4166ulW

Our review on AI for protein engineering is out now, about this too-fast-moving field full of hype and overclaim, yet one that is having a real impact on the world and can be described in a coherent manner without histrionics science.org/eprint/666XRGR…

A @nchembio study led by Assoc. Prof. @Michael_A_Erb describes a strategy to deliberately discover “molecular glue” degraders by converting existing protein binders into compounds that recruit the cell’s disposal machinery, selectively degrading ENL and BRD4. More: ow.ly/Fqrr50YoenT

Can AI move beyond chatting to actually making biological discoveries? What if AI could think like a microbiologist? 🧪 📣 Excited to introduce Eubiota: a modular agentic AI framework for autonomous discovery in the gut microbiome. 🧬🤖🦠 👉Explore: eubiota.ai The gut microbiome is complex; manual discovery is slow. 🐌 We built Eubiota to think like a researcher: planning experiments, verifying data, and synthesizing results. It’s an open-source system designed to empower the entire community. 🌐 Eubiota demonstrated its capability across end-to-end discovery tasks, with results validated in the lab: ✅ Identified uvr-ruv DNA repair axis for fitness under inflammatory stress by screening ~2,000 genes🧬 ✅ Designed a microbial consortium therapy to reduce inflammation in mice colitis models.🐁 ✅ Uncovered diet-associated anti-inflammatory metabolites & engineered antibiotic cocktails.💊 Eubiota is the "scientific copilot" the field has been waiting for. Let AI be your partner to accelerate discovery! 🚀 Incredible teamwork with @lupantech and all our co-authors! I'm deeply grateful for the guidance from amazing advisors @james_y_zou, @LabSonnenburg, and brilliant mentors KC Huang, @YejinChoinka. Read more here: 🔗biorxiv.org/content/10.648… Code: github.com/lupantech/Eubi… Try out our system in your browser! 🤖app.eubiota.ai/chat #Eubiota #AI4Science #Gut #Microbiome #AgenticAI

Protein–protein interactions (PPIs) are key to discovering and interpreting new biological functions. We’re excited to introduce 𝑭𝒍𝒂𝒔𝒉𝑷𝑷𝑰: a new application of gLM2 that uses genomic language modeling to predict proteome-wide PPIs in microbial genomes in minutes.

Researchers use #AI and Reverse Vaccinology 2.0 on human blood samples to identify a potential new mpox target, and use the target in a vaccine that elicited mpox-neutralizing antibodies in mice. @ScienceTM scim.ag/4iQkBUy

📣 AI predictions in 2026: @StanfordHAI experts envision 2026 as a year defined by rigor, transparency, and a long-overdue focus on actual utility over speculative promise. Read more: hai.stanford.edu/news/stanford-…

AI agents for science are featured as a “Method to Watch” in @NatureMethods, nature.com/articles/s4159… The piece also highlights our roadmap outlining capabilities, the need for thorough evaluations, and open challenges for AI agents, cell.com/cell/fulltext/…

AI doesn’t just err — it scales errors. On @NEJM_AI Grand Rounds, Dr. Laura Zwaan (@LauraZwaan81) explains why collaboration between humans and machines is the only safeguard. Learn more: nejm.ai/ep36

Editorial by Jack Gallifant, MBBS, and Danielle S. Bitterman, MD: Humanity’s Next Medical Exam: Preparing to Evaluate Superhuman Systems nejm.ai/43FVI7x #ArtificialIntelligence

🚀 GenMol v2 is now live This release updates the SAFE syntax to use angle brackets (< >) for clearer inter-fragment connectivity. This simple tweak brings major boosts to inference tasks like: - 1-step linker design - Scaffold decoration - Superstructure generation Check it out 👇

🚨 What is CodonFM? First large-scale foundation model trained directly at the codon level. With parameter scaling from 80M to 1B, CodonFM brings unprecedented insight to RNA biology by capturing synonymous variation crucial for biomedical research. This is a leap forward for researchers and innovators. #NVIDIAGTC

OpenFold3 is finally out! New fully open-source AF3 reproduction from @open_fold Consortium Try it out on @tamarindbio now! The model is released with training code, similar performance to AlphaFold3 on protein-ligand complexes, best performance ever for RNA structure prediction, and the same functionalities of other AlphaFold3 reproductions.

Join us - only open this week: aka.ms/bioemu-applied Lead a collaboration with drug discoverers. Orchestrate experimental data generation. Deploy BioEmu and other tools to understand biology at scale. #Biology #Bioinformatics #CompBio #MachineLearning

Big news - today we are announcing that @nvidia is working with @EliLillyandCo to launch the world's largest Biopharma AI Factory. Built on over 1000 Blackwell Ultra GPUs, the AI factory will support applications across the entire R&D value chain including drug discovery, clinical development and manufacturing. blogs.nvidia.com/blog/lilly-ai-…

Announcing our new protein design server evedesign.bio: • End-to-end protein design for everyone! • Analyze your generated library interactively and on 3D structures • Export codon-optimized DNA sequences for experimental testing. Developed in collaboration between @deboramarks, @thomas_a_hopf, @SteineggerM, Simon d'Oelsnitz, Chris Sander, Artem Gazizov,@haysunny_hi, Milot Mirdita, Sergio Garcia Busto, Jake Reardon

Last call - open til Oct 30! Are you excited about #MachineLearning and developing new architectures for Molecular Biology? Joint us for the next chapter of BioEmu at @MSFTResearch AI for Science - Berlin DE or Cambridge UK. aka.ms/bioemu-ml

Today we're announcing a second, larger collaboration with @TakedaPharma — deploying our integrated AI + wet-lab platform broadly across their portfolio to design antibodies, multispecifics, and other next-generation biologics. It’s been incredibly fun working with the Takeda team to create new medicines. Looking forward to doing a lot more of that together.

One of our new Gemma open models, Cell2Sentence-Scale, has identified a novel cancer therapy pathway that’s been validated experimentally in living cells. Developed w/ @GoogleDeepMind & @Yale University, it looks deep into how to represent cells & biological information for AI ↓