Here is why you need to understand 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 as an AI Engineer. Simple naive RAG systems are rarely used in real world applications. To provide correct actions to solve the user intent, we are always adding some agency to the RAG system - it is usually just a bit of

Github 👨‍🔧: 🕷️ Undetectable, Lightning-Fast, and Adaptive Web Scraping for Python Helps you build web scrapers in Python that resist website changes and anti-bot measures. It provides adaptive scraping to automatically adjust to website modifications using smart element tracking.

Segment Anything for Microscopy (μSAM) is based on Segment Anything, the vision transformer model for image segmentation, and offers generalist models for light and electron microscopy segmentation tasks. Constantin Pape Anwai Archit Genevieve Buckley Sushmita Nair nature.com/articles/s4159…

Benchmarking the translational potential of spatial gene expression prediction from histology | Nature Communications nature.com/articles/s4146…

🧪 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! 🧵👇

NEW: Google introduces AI co-scientist. It's a multi-agent AI system built with Gemini 2.0 to help accelerate scientific breakthroughs. 2025 is truly the year of multi-agents! Let's break it down:

New online! Beyond the black box with biologically informed neural networks bit.ly/3DhWUUH

NEW content online! A machine learning toolkit for subtyping cancer in existing and new datasets bit.ly/4h9p8it

Introducing the world's best OCR model! mistral.ai/news/mistral-o…

MedSAM is great but not every hospital has GPUs! The high computational demand of MedSAM limits its widespread adoption in resource-constrained clinical settings. To address this issue, we developed a lightweight model to reduce the computational burden. Specifically, we first

The power of 𝗠𝗖𝗣 in 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 Systems. To make it clear, most of the RAG systems running in production today are to some extent Agentic. How the agentic topology is implemented depends on the use case. If you are packing many data sources, most likely there is

Our new paper on Multi-Agent Systems for Healthcare (MASH) just came out today in Nature Biomedical Engineering. with colleagues Dr. Michael Moritz and Dr. Eric Topol

Great joint work with Alejandro Tejada Lapuerta Paul Bertin Stefan Bauer Yoshua Bengio Fabian Theis. Link to the paper: nature.com/articles/s4158…

TXAGENT is an AI agent for therapeutic reasoning, integrating 211 biomedical tools to generate evidence-grounded treatment plans with 92.1% accuracy. It outperforms GPT-4o in multi-step drug reasoning while prioritizing safety and real-time knowledge. arxiv.org/abs/2503.10970

#SingleCell data is often scattered, inconsistently labeled + hard to integrate. CZ #CellxGene aims to standardize + unify this data for easier reuse & integration. 🎯 100M+ unique cells available 🫁 449 tissues 🧩 40 assay types 🤒 Diverse disease states bit.ly/41xPMNA

Diet-microbiome interactions in cancer dlvr.it/TKCtwS

📢 🧬 New preprint! Can we predict which cancer patients will benefit, before treatment begins? Wan Xiang Shen Immunotherapy saves lives but many patients don’t respond to treatment, and we still lack reliable tools to predict who will benefit We introduce COMPASS, foundation

Targeting DNA damage in ageing: towards supercharging DNA repair nature.com/articles/s4157… This new Review discusses approaches to pharmacologically mitigate the adverse effects of DNA damage to prevent mutation-driven cancers and mitigate age-related degenerative diseases