🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Are biomedical AI models truly as smart as they seem? Yasha Ektefaie rdcu.be/d2D0z Our Nature Machine Intelligence paper introduces SPECTRA, a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity SPECTRA reveals gaps in

Evaluating generalizability of artificial intelligence models for molecular datasets Nature Machine Intelligence 1. Introducing SPECTRA: A novel spectral framework that comprehensively evaluates the generalizability of machine learning models for molecular datasets by analyzing performance

🧬GWAS is fundamental in drug discovery, linking disease to genetic variants. However, studying rare and uncommon diseases with GWAS is hard due to the huge sample sizes required. How can we use AI to help GWAS with small cohorts? In a multi-year collaboration GSK

Medicine thrives on knowledge, yet clinical vocabularies are fragmented. AI struggles to unify this knowledge, creating a gap in precision medicine. Excited to share unified clinical vocabulary embeddings, a project led by stellar Ruthie Johnson Half of healthcare foundation AI

This paper has been a long time coming: We looked at the genomes of historical bacterial samples over a century to look for trends of antibiotic resistance genes, finding multiple instances of them in infections before the age of antibiotics...

What if you could rewind time, tweak a decision, and watch the future unfold differently, one precise edit at a time? That’s exactly what CLEF does for sequences in biology and medicine Michelle M. Li (李敏蕊) Controllable sequence editing: generate precise, time-sensitive

🧪 Introducing POPPER: an AI agent that automates hypothesis validation by sequentially designing and executing falsification experiments with statistical rigor. 🔥POPPER matched PhD-level scientists on complex bio hypothesis validation - while reducing time by 10-fold! 🧵👇

Excited to be a mentor for LOGML Summer School! If you want to come to London and work with me on an exciting project on the intersection of GraphML and medicine --sign up!

🚀 Introducing TxAgent: a first of its kind AI agent for therapeutic reasoning across a universe of 211 tools, with a comparison against DeepSeek-R1 671B NVIDIA AI TxAgent is an AI agent that redefines how AI can reason, retrieve, and integrate biomedical knowledge for precision

⚡️Really thrilled that #textgrad is published in @nature today!⚡️ We present a general method for genAI to self-improve via our new *calculus of text*. We show how this optimizes agents🤖, molecules🧬, code🖥️, treatments💊, non-differentiable systems🤯 + more!

🧬 Meet Lyra, a new paradigm for accessible, powerful modeling of biological sequences. Lyra is a lightweight SSM achieving SOTA performance across DNA, RNA, and protein tasks—yet up to 120,000x smaller than foundation models (ESM, Evo). Bonus: you can train it on your Mac. read

When his son Max was diagnosed with a rare disease, our colleague Thomas turned to Gemini to better understand complex scientific papers — and even make new connections across the research community. His story is a powerful reminder of why we work on AI. ↓

Introducing ATOMICA 💫 A model to universally represent molecular interactions (for proteins, nucleic acids, small molecules, and ions) at an all-atom scale 🧵

🚨 New model alert! 🚨 Can we improve the generalizability of PLMs by teaching them to reason over sequences? Check out Andrew Shen @ ICLR 2025’s tweetorial on Phyla, our new model for multiple sequence reasoning 🧬 Spotlight talk at #ICLR2025 LMRL — don’t miss it! 👇

Had a great time presenting RLDIF yesterday GEMBio Workshop at #ICLR2025! As a bonus got some seed money from a pitch with Aviv Spinner on an exciting new project, more on that later 👀