🔥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

Designing proteins for multiple, often competing objectives is a major challenge. In our new preprint, we use deep learning + protein language models to design phages with higher activity, defined specificity, and generalizable infectivity—meeting 26 design goals across several

1/ Introducing TxPert: a new model that predicts transcriptional responses across diverse biological contexts It’s designed to generalize across unseen single-gene perturbations, novel combinations of gene perturbations, and even new cell types 🧵

This article analyzes how nonexperts perceive AI-generated medical advice, finding that it is often rated as accurate as — or better than — doctor responses, raising concerns about overreliance and potential harm from incorrect guidance. Full article: nejm.ai/43xKDG0

Virtual Cells: Predict, Explain, Discover by ⁦Recursion⁩ arxiv.org/abs/2505.14613

A deep learning method enables the design of proteins with distinct conformational states, mimicking the dynamic properties of natural signaling proteins #NBThighlight science.org/doi/10.1126/sc…

Some exciting news: ARPA-H's ADAPT Program has funded the proposal from a team combining the expertise of researchers MIT Jameel Clinic for AI & Health and Mass General Brigham to develop game-changing cancer care! 📢Read the full announcement: jclinic.mit.edu/arpah-adapt/

🚨 BREAKING: The U.S. House of Representatives has PASSED the 10-year moratorium on state AI laws. (It now awaits Senate approval.) I've seen a lot of misinformation on the topic; here's what the bill actually says & my comments: This is a budget bill called "H.R.1 - One Big

x.com/i/article/1927…

A new article by José María Gutiérrez, PhD, describes how machine-learning tools were used to design novel protein inhibitors that proved effective against snake-venom toxins in mice. Read the Clinical Implications of Basic Research article “Novel Proteins to Neutralize Venom

Pfizer and AstraZeneca’s FLOWR model generates ligands 70× faster with improved structural accuracy by conditioning on protein pocket shapes. The shift from diffusion to flow-based models like FLOWR shows promising gains in speed and precision for drug discovery.

How can we make genomic foundation models actually useful to biology?! Teach them to REASON!! 🧬 Excited to share BioReason - the first model to successfully integrate DNA foundation models (eg, Evo 2) with LLMs (eg, Qwen3) for biological reasoning! 🔬 What we built: • Novel

Antibody-antigen complex prediction results from all-atom benchmark, FoldBench: (1) AlphaFold3 performs best with a success rate of 47.9% while other models have a failure rate exceeding 60%. (2) Increased sampling improves AF3 performance by 2-3% but not for other models.

SCOOP STAT: The FDA will begin the agency-wide rollout of its AI tool, called "Elsa," tomorrow — weeks ahead of schedule. For the most details yet on the FDA's Claude-based AI tool, plus criticism from FDA employees: statnews.com/2025/06/02/fda…

This article introduces AI-CAC, a deep learning tool that accurately quantifies coronary artery calcium from routine chest CT scans, enabling opportunistic cardiovascular risk assessment across the U.S. VA health system. Read the full article: nejm.ai/42YWX1N

Introducing the world's first reasoning model in biology! 🧬 BioReason enables AI to reason about genomics like a biology expert. A thread 🧵:

🌍 Over 30 governments, private sector, civil society, and research institutions have endorsed the Hamburg Declaration on Responsible #AI for the #SDGs. 🤝💡 Click here to read more 📖: bit.ly/4kmi04H #hsc25

Perspective by Kerstin N. Vokinger, MD, JD, PhD, LLM (Kerstin Noëlle Vokinger), Derek R. Soled, MD, MBA, MSc, and Raja-Elie E. Abdulnour, MD (Raja-Elie Abdulnour): Regulation of AI: Learnings from Medical Education nejm.ai/3YNQ5Se #ArtificialIntelligence

Domain-aware AI agents now reason, act, and learn across entire scientific workflows 👀 Biomni skims papers, selects from 150 + bio tools, writes executable code, and already beats experts from GWAS hits to cloning problems 🔬 Wish I had it during my lab days 😅

We are excited to announce the launch of our new series of talks for early career scientists, including assistant professors, newly appointed principal investigators, and researchers preparing for faculty positions.

Proud to share Recursion's exciting announcement on Boltz-2! Valence Labs, Recursion’s AI research engine, contributed to the foundational research supporting the Massachusetts Institute of Technology (MIT) team led by Regina Barzilay Learn more about Boltz-2 here: rxrx.ai/boltz-2