The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 6:32 PM PT
A patent court in the Netherlands ordered Merck to halt manufacturing and sales of its subcutaneous formulation of pembrolizumab, an anti-PD-1 antibody marketed as Keytruda, across eight European countries including France, Italy, and the Netherlands.
China's drug agency approved a Phase 1/3 trial and the FDA cleared a Phase 1/2 trial for NouvSight001, an off-the-shelf cell therapy for the inherited blinding condition retinitis pigmentosa.
The California-based life sciences investment firm has raised its debut regional vehicle, the TCGX Asia Life Sciences Fund I, to back drug developers across Asia at multiple development stages.
Henri B. Kagan and Kenso Soai were awarded the 2026 Nobel Prize in Chemistry for discovering how to drive chemical reactions to favor one mirror-image structure over another, a property known as homochirality.
The San Diego biotech plans to offer 9.4 million shares at $15 to $17 each, targeting roughly $135 million in net proceeds to fund clinical trials through 2028.
London-based specialty pharmaceutical company Theramex has agreed to pay up to $250 million to license a non-surgical therapy for cervical precancerous lesions from Shanghai-based Asieris Pharmaceuticals.
Life sciences equipment giant Danaher plans to launch its first autonomous research lab run by AI by early 2027, according to Reuters reporting.
The FDA has granted an expanded indication for remibrutinib, an oral Bruton's tyrosine kinase (BTK) inhibitor marketed as Rhapsido, to treat both of the two most common forms of chronic urticaria.
The Chan Zuckerberg Biohub has unveiled an expanded $1.8 billion Virtual Biology Initiative in collaboration with Meta, Google DeepMind, Isomorphic Labs, the Department of Energy, and the National Institutes of Health.
Ultragenyx has agreed to sell an FDA Rare Pediatric Disease Priority Review Voucher to an undisclosed buyer for $210 million in cash.
The board of Cadrenal Therapeutics is reviewing strategic options that include licensing its assets, partnering, or selling the company entirely.
The oral GPR6 inverse agonist, evaluated as an add-on to levodopa in 341 patients experiencing motor fluctuations, met its primary goal by cutting daily OFF time by 0.61 hours versus placebo at 12 weeks.
Researchers at Sungkyunkwan University are developing a hybrid digital twin that couples physical bioprocess equations with explainable machine learning to run bioreactors autonomously.
The Advanced Research Projects Agency for Health awarded Bexorg up to $28.3 million, reported by Endpoints News as $28 million, over a three-phase, 36-month contract.
The Advanced Research Projects Agency for Health introduced Surpass, a program using predictive computational modeling, shared trial infrastructure, common controls, and real-time analysis to modernize clinical trials.
The Hague court found Merck's under-the-skin formulation of Keytruda infringes Halozyme's European patent covering modified hyaluronidase enzymes used for rapid high-volume drug delivery.
Nextech Invest and Norwest co-led the round, joined by Sanofi Ventures, Digitalis Ventures, Invus, BB Biotech, the T1D Fund, and BOLD Longevity Growth.
In the Phase 1/2 portion of the Lighthouse trial, six of nine patients with X-linked retinoschisis who received the Phase 3 dose of ATSN-201 met the microperimetry response criteria, compared with zero of three untreated controls.
Caribou Biosciences will close and discontinue its clinical pipeline after failing to secure capital for a Phase 3 study of its lead allogeneic CAR-T therapy, vispa-cel.
MimiVax reported that its cancer vaccine, SurVaxM, narrowly missed its primary overall survival endpoint in a Phase 2b trial for glioblastoma.
Researchers used the structure-informed protein language model ESM-IF1 to pick mutation sites in tobacco Rubisco, the primary enzyme plants use to fix carbon dioxide.
Researchers released a standalone desktop application for intelligent Differential Mobility Spectrometry, a deep learning tool that automates parameter tuning for distinguishing nearly identical lipid molecules.
A deep-learning model trained on time-lapse video of single blood-forming stem cells predicted which cells could engraft long-term with 98.5% average precision.
Computational biologists created ddkg.skill, an agent module that compiles natural-language bioinformatics questions into executable Cypher code for the NIH Common Fund Data Distillery Knowledge Graph.
A machine-learning framework augments protein language model representations with structural priors and evolutionary co-variation features derived from an AlphaFold-style trunk.
Comparative analysis of four field strains of Colletotrichum graminicola against a reference assembly revealed extensive chromosomal rearrangements, duplications, and non-conserved minichromosomes.
Researchers combined machine learning with directed evolution to engineer adeno-associated virus (AAV) capsids optimized for exosomal encapsulation, a method used to protect gene therapy delivery vehicles from immune recognition.
Researchers designed Neural Petri Flow, an architecture that embeds physical valence and atom-conservation laws as fixed mathematical layers while using neural networks only to predict reaction propensities.
Researchers showed that assay-specific fitness variations align within a compact, linear subspace of mutation representation changes produced by protein language models.