Tag
GPT-Rosalind tops biology benchmarks and partners with Amgen, Moderna, and Novo Nordisk — but its restricted access model raises questions about who benefits from AI-accelerated medicine.
Anthropic acquired Coefficient Bio — fewer than 10 employees, eight months old — for $400 million in stock. The play: making Claude the default AI for drug discovery.
Michigan State researchers use machine learning to predict gene effects from chemical structures, identifying compounds that reduced tumors in mice.
Partnering with Anthropic, Ultima Genomics, and PacBio, the startup aims to sequence 100 million species and train AI models that can design therapeutics from a disease prompt.
DeepMind, EMBL-EBI, NVIDIA, and Seoul National University release largest protein interaction dataset, revealing how molecules work together
Machine learning models screened 1.6 million potential drug pairings and identified synergistic combinations that neither drug achieves alone. Lab tests confirmed the predictions work.
A generative AI trained on 23,000 synthesis recipes can suggest how to make materials that have never existed
Isomorphic Labs' new drug design AI doubles AlphaFold 3's accuracy. Scientists call it groundbreaking. There's just one problem: it's completely proprietary.
Google DeepMind and Yale's 27B parameter model identified how silmitasertib plus interferon can boost cancer antigen presentation by 50%
Multiple biotech companies are sprinting to bring the first fully AI-designed antibody drugs to human testing. Here's how they're doing it and what it could mean for medicine.
The first open-source protein structure prediction model to outperform DeepMind's AlphaFold3, now available under Apache 2.0 license.
Penn researchers are using AI to find antibiotic compounds in ancient genomes, from Neanderthals to giant sloths, and testing them against drug-resistant bacteria
Insilico Medicine's rentosertib improved lung function in IPF patients, marking the first clinical validation of AI-driven drug discovery.
University of Missouri releases the world's largest quality-assessed protein structure database to help researchers know when to trust AI predictions.
New protein structure prediction tool from NUS uses physics-based simulations alongside deep learning to predict complex multi-domain proteins 13% more accurately than AlphaFold.
Valar Labs publishes JCO study showing its AI can identify optimal chemotherapy from routine pathology slides, with patients living nearly 3 months longer when matched to predicted treatment.
Singapore researchers combine AI with physics simulations to predict protein structures 13% more accurately than existing methods, covering 73% of the human proteome.
Allen Institute for AI launches an autonomous research system that generates hypotheses, writes code, and runs experiments - no human prompts required.
Google DeepMind spinoff claims its unified AI system can identify hidden binding sites and predict drug interactions faster than physics-based methods
