AI Built Antibodies Against a Variant That Has Not Emerged Yet
A Stanford and Arc Institute preprint uses AI to design antibodies that tackle several SARS-CoV-2 variants at once, and to rescue one against a lab-engineered escape variant. What it shows, and what it does not.
Editor's picks
See allA Protein-Ligand Language Model Hit 9 of 9 Drug Targets. How Solid Is It?
Bonbon, a protein-ligand language model trained on 3.2 trillion tokens, reports new inhibitors for nine drug targets. Here is what the preprint shows, and what to check.
AI for Tropical Diseases: 9 in 10 Studies Carry High Risk of Bias
Europe Delays, America Argues: Where AI Rules Stand for Science
DeepMind's AlphaGenome 2 Finds Disease Variants Cell by Cell
93% of Delhi Residents Had Zika Antibodies. The Real Story Is Subtler
AI
See allVirology
See allRecent posts
See allOpen RNA AI Model Rivals AlphaFold 3 at RNA Structure Prediction
A structure-guided RNA foundation model, structRFM, was published in Nature on 4 November 2026 with open data, weights and code. We explain what it does, how it compares with AlphaFold 3, and where the evidence is thin.
AI-Designed Bird Flu Vaccine Beat the Stockpile Jab. Here's the Catch
A computer-designed mRNA bird flu vaccine outperformed WHO-based candidates in mice and ferrets. Here is what the Cell Reports Medicine study shows, and what it cannot yet tell us.
Your Government Wants to Tell You Your Biological Age. Can It?
Abu Dhabi is putting an AI biological age score on a government app. Its own standard says such clocks still need validation.
Shuffle the Test Set and Protein AI's Best Scores Collapse
New benchmarking work reports that protein language model scores fall sharply once homologous sequences are kept out of the test set. The problem is well documented.
AI Agents Just Ran a DNA Lab for 11,000 Steps With Almost No Humans
AutoDNA, published in Nature, orchestrates 20-plus instrument types across 11,000 steps of DNA work. The interesting part is the architecture, not the robots.
Western Ethics Wrote AI's Medical Rulebook. Yoruba Philosophy Answers Back
A new Developing World Bioethics paper applies six Yoruba moral principles to AI and big-data health research, and proposes concrete governance machinery.
AI in Healthcare
See allAI Can Call Drug Resistance in Hours. Should Labs Trust It Yet?
AI diagnostics can now predict antibiotic and antiviral resistance from a pathogen genome with striking accuracy. We examine the 2026 evidence, and why Europe's own susceptibility testing committee says it is not ready for the clinic.