Epigenetic clocks and machine learning are being pointed at early cancer detection. We separate what the 2026 evidence shows from what the headlines imply, from breast cancer risk to the NHS-Galleri t...

Protein language models and structure predictors can now design antibodies from scratch. We look at the hit rates, the evidence, the limits and the safety questions.

AI can now write working virus genomes. Who is responsible for checking them? A plain-English tour of AI biosecurity rules in the US, EU, UK and beyond.

Mpox is still circulating, and new clades are mixing. We look at what genomic surveillance has revealed, where machine learning genuinely helps, and where the evidence stops.

AI research assistants can speed up literature searches, but fabricated citations and patchy recall remain real risks. Here is what 2026 studies say about which tools hold up.

OpenAI's DevDay 2026 turned long-running autonomous agents into everyday infrastructure. Here is what that means for the slow, expensive work of automating scientific research, and where the honest li...

A new Nature Medicine study shows on-premise medical AI agents can diagnose at near-cloud accuracy. The bigger story is why the field still can't agree on how to know when to trust them.

AlphaFold has released free, AI-predicted protein complex structures for more than 2,800 human-infecting viruses. Here is what the pandemic preparedness update means for global science.

A new Blue Cross Blue Shield analysis links AI coding and ambient scribe tools to $942 million in added hospital costs. Here is what the evidence actually shows, and where it falls short.

A run of careful benchmarks shows that huge single-cell foundation models often fail to beat plain linear methods. Here is what the reckoning means for AI in biology.

The US Department of War has awarded Flagship Pioneering up to $47 million to build AI platforms that predict viral evolution before outbreaks happen. Here's what the ONTARGET deal means for biosecuri...

As world leaders gather at the UN for a High-Level Meeting on pandemics, a new AI-powered global infrastructure (the Pandemic Preparedness Engine and Global Pathogen Analysis Platform) is quietly bein...

A Nature feature published this week tracks how AI co-scientist platforms from Google DeepMind, FutureHouse and others are already generating validated hypotheses in real labs, and why human judgement...

Alibaba's DAMO Academy has open-sourced RADAR, a Science-published AI that outperformed 23 of 26 radiologists reading abdominal CT scans for 146 conditions, free for any hospital to run.

Stanford's 37,000-agent Virtual Biotech mined 55,984 clinical trials and independently designed a lung cancer drug strategy Merck was already pursuing.

Novo Nordisk just added Anthropic's Claude Science to an AI drug discovery stack that already includes OpenAI. Here's what the deal reveals about AI in healthcare.

A new protein-language-model study claims to out-predict the WHO's flu vaccine picks, reviving a live dispute over whether AI truly beats expert judgement here.

A new Cell study pits 18 leading AI systems against ageing biology data. Small, specialised models beat every frontier system, and the whole toolkit is free to use.

Delphy reformulates Bayesian phylogenetics around explicit mutations and runs in a browser, cutting an H5N1 outbreak analysis from over 21 days to 42 minutes.

Five pharmaceutical companies fine-tuned OpenFold3 on 20,167 private protein–ligand structures without pooling the data. Protein–ligand accuracy jumped from 35.6% to 52.1%. Here is what that means for...

Anthropic's Dario Amodei asked rivals to slow AI development and let outside evaluators inside frontier labs. OpenAI and Google DeepMind agreed within days. Here's what's actually being tested, biowea...

UK Biobank's Research Analysis Platform reopens this September after a data security incident, and a 2026 study shows why AI is quietly eroding old promises of genetic anonymity.

Anthropic's September 2026 threat report reveals Claude was used in five bioweapons-adjacent research attempts, including a chikungunya gain-of-function request. Here's why virologists and AI safety e...

UC Berkeley's GPN-Star, a genomic language model published in Nature, predicts harmful DNA variants better than far larger AI models, and trains in hours not months.

An AI-discovered, AI-designed drug lowered predicted biological age across six independent ageing clocks in a phase 2a trial. What it means, and what it doesn't.

For the first time in an Ebola response, WHO and Flowminder are using anonymised mobile-phone data and modelling to predict where Congo's Bundibugyo outbreak will spread next. An early test called all...

Google DeepMind's AlphaGenome Atlas precomputes the molecular effects of all 9 billion single-letter human DNA changes and offers them free in a browser. What it does, why it matters, and where it fal...

Stanford's SPHERE turns locked biomedical datasets into shareable 'synthetic twins' for AI, and opens an Alzheimer's cohort to prove it. The promise, and the caveats.

OpenEvidence's Darwin is the first medical AI to score 100% on MedQA, yet the company is withholding it over biosecurity risk. The claim, and its caveats.

AI in 2026 is moving past ageing clocks that spit out a single number towards foundation models that reason about biological age, predict disease and nominate targets. Here is what changed and why it ...

German scientists used generative AI to design Synthetic Transfer Vehicles, protein shells that carried RNA into cells more efficiently than the lipid nanoparticles they tested and delivered a CRISPR ...

BiteNetI, a new deep-learning model, out-predicts AlphaFold 3 at finding protein metal-ion binding sites, a blind spot for today's protein language models.

Artificial intelligence is moving from the lab into the working machinery of pandemic preparedness, from spotting risky viruses in genetic data to scanning the world's news for early signals. Here is ...

Scientists mutated every letter of the ΦX174 phage genome and measured the result. Top AI models predicted it only moderately well, a reality check for AI biology.

A Johns Hopkins team built an AI agent that screened 201,064 studies for a suicide-prevention meta-analysis, cutting human workload by 99% at under half a cent per paper. Here is what the preprint act...

Google Research has released the planetary prediction engine, an AI agent that builds geospatial models from a plain-language question. It was tested on a live Ebola outbreak. Here is what the numbers...

The first blinded, wet-lab-validated benchmark for AI antibody design just landed in Nature Biotechnology. Here is what the models got right, and wrong.

A new bioRxiv preprint, Prot-LAMBDA, teaches protein language models explicit 3D geometry and reportedly matches a model five times its size. Why efficiency, not scale, is the real story.

A Nature Medicine study trained AI on 25,712 human tissue slides and found that organs keep separate biological clocks. Some of that signal shows up in a blood sample. What it means, and what it does ...

The EU's science service studied 480 biological AI models and found a gap between scientific brilliance and real-world readiness. Here's what the JRC report says and why it matters.

GenBio AI's AIDO Cell is a 'world model' that simulates a human cell across scales, from DNA to shape. Here's what it does, why it matters, and what still needs proving.

As Congo's Bundibugyo Ebola outbreak hits record size, an AI-assisted model estimates the true toll may be up to triple the confirmed count.

RAND says no single safeguard can stop AI-assisted bioweapons, and lays out nine layered defences. Here is what the report argues, why it lands now, and where it is still guesswork.

A new Science Advances study uses a protein language model to annotate enzyme 'dark matter' in the gut microbiome, mapping metabolism in health and inflammatory bowel disease.

Anthropic published a wet-lab-validated protein binder result on 18 August 2026, then disclosed an 11-month biosecurity classifier gap. The two stories together explain why the world's most capable pr...

A preprint posted on 3 August 2026 teaches robots to read wet-lab protocols and act on them. Benchmarks published weeks earlier show why containment labs are still out of reach.

A Nature Methods paper borrows the alignment method used to tune chatbots and applies it to protein design, producing a heat-stable H5N1 hemagglutinin with only 45 tries.

A new preprint tests whether computational and AI forecasting models could have predicted the 2026 Bundibugyo Ebola epidemic in DR Congo before it became one of the largest on record. Here is what the...

Genentech validated the first AI-discovered neuroscience drug target from its $12B Recursion partnership. A proof point the AI-drug discovery field needed.

The August 2026 American Journal of Bioethics issue confronts AI agents moving into clinical and research operations, and asks an uncomfortable question: what happens when those same agents start doin...