The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 6:32 PM PT
Cell therapy bioprocessing specialist Ori Biotech has agreed to a $120 million contract to implement its automated production platform for an undisclosed commercial-stage cell therapy.
Researchers at Imperial College London deployed three computational screening models across 6,747 small molecules to identify approved drugs that could be repurposed against the respiratory bacterium Streptococcus pneumoniae.
OpenAI has officially backed a package of bipartisan United States congressional legislation aimed at preventing artificial intelligence systems from assisting in the development of biological weapons.
The Mayo Clinic and Thermo Fisher Scientific have launched Precure LLC, a joint venture built to assemble large-scale datasets combining genomic, proteomic, and longitudinal clinical records.
BioMarin has halted development of its once-daily injected bone-growth peptide, vosoritide, for children with Noonan syndrome, attributing the decision to study feasibility and a changing commercial landscape rather than safety or efficacy.
Obvious Ventures led a $20 million Series A funding round for Mithrl, with backing from Headline, AGI House, and biopharma executives, to advance its biomedical world model and AI orchestration platform.
The OpenAI Foundation has launched a $125 million initiative called Public Data for Health to fund open, standardized scientific and biomedical datasets for machine-learning research.
Johnson & Johnson's oral M1 muscarinic receptor antagonist, JNJ-5120, failed its primary efficacy endpoint in a Phase 2 trial of 107 patients with major depressive disorder, showing no improvement over placebo on a standard depression rating scale at day five.
Novo has ended its metabolic disease collaboration with Ascendis Pharma less than two years after committing up to $285 million in milestones to develop a once-monthly weight-loss therapy.
GSK has agreed to pay up to $750 million in a licensing deal for Chimagen Biosciences' preclinical trispecific T-cell engager, with plans to begin Phase 1 trials in multiple myeloma next year.
Sionna Therapeutics will cut roughly 46% of its workforce to preserve capital after its add-on NBD1 stabilizer SION-719 failed to lower sweat chloride in cystic fibrosis patients already taking Vertex Pharmaceuticals' Trikafta.
The FDA approved Telix Precision Medicine's Pixclara (floretyrosine F-18) for positron emission tomography imaging of gliomas in patients aged one month and older.
Eli Lilly entered a multi-program research partnership with Toronto-based QurCan Therapeutics, offering an upfront payment, equity investment, and up to $237 million in milestones per program to deliver genetic medicines across the blood-brain barrier.
Connect Biopharma reported that its IL-4R alpha antibody rademikibart missed the primary endpoint in a 160-patient Phase 2 trial in individuals with asthma and type 2 inflammation.
The FDA unveiled an expedited investigational new drug pilot under its Operation Trialblazer initiative to speed the transition of drug candidates into early clinical testing.
Vera Therapeutics reported that its dual BAFF and APRIL inhibitor Trutakna met all prespecified endpoints in the pivotal Phase 3 ORIGIN 3 trial for IgA nephropathy, an autoimmune kidney disorder.
Researchers combined solid-state NMR, X-ray crystallography, and machine-learning molecular simulations to resolve protonation states in the active site of Toho-1 beta-lactamase bound to the antibiotic inhibitor avibactam.
A computational framework named E-MAF combines manufacturing process predictions with expert-mimic evolutionary search to design controlled-release drug formulations from target dissolution profiles.
Researchers introduced Dynamo, an open-source Python tool designed to reconstruct, register, and track changes in branching neuronal dendrites and axons across time-lapse imaging series.
Researchers released POME, a self-supervised model that creates low-dimensional numerical representations for messy patient records characterized by mixed data types and missing values.
DiffGSP combines Fick's laws of diffusion with graph signal processing to model and reverse the spread of mRNA molecules between adjacent spots during tissue processing.
Researchers built REN-former by fine-tuning the Geneformer foundation model on single-cell RNA sequencing from 45 kidney patient samples to predict directional cell shifts from acute kidney injury to chronic kidney disease.
A new generative method called high-dimensional adversarial random forests (h-ARF) synthesizes tabular molecular profiles to supplement small biological sample cohorts from hard-to-access tissues.
Using the reinforcement-learning molecular design tools Link-INVENT and AutoMolDesigner, researchers designed Y-11, a small-molecule antibiotic targeting MsbA, an essential transporter protein in Gram-negative bacterial outer-membrane assembly.
A computational study showed that splitting single-cell datasets randomly between training and test sets leaks labels through related clonal sisters, patient backgrounds, or experimental batches.
A hierarchical transformer architecture called HTT combines report-level language embeddings with continuous-time visit intervals to analyze sequential cancer pathology records.