The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 6:32 PM PT
The Merck KGaA spinout demonstrated a 20.8-month median overall survival in a 44-patient Phase 1 trial evaluating roginolisib, an oral small-molecule PI3K delta inhibitor, across advanced malignancies including second-line metastatic uveal melanoma.
Roche has committed up to $100 million in upfront and near-term payments, as part of a deal worth up to nearly $1.2 billion including $1.06 billion in future milestones, to license an RNA interference candidate targeting ALK7 from China-based Rona Therapeutics.
Gilead Sciences committed $90 million upfront, comprising $65 million in cash and a $25 million equity investment at a 30% premium, to license three masked T-cell engager therapies engineered using Vir Biotechnology's PRO-XTEN platform.
Zealand Pharma and Flagship Pioneering spinout Generate Biomedicines agreed to collaborate on developing treatments for obesity using generative AI, according to Bloomberg News.
Fairmount Funds led a concurrent private placement of roughly $350 million alongside the merger with the former cell-therapy developer Alaunos Therapeutics.
Enodia Therapeutics has signed a research collaboration and licensing pact worth up to $500 million in upfront cash, milestones, and royalties to develop small-molecule Sec61 inhibitors with Pfizer.
Juvia Group led the Series B round to advance three siRNA programmes into early clinical testing.
Syndax Pharmaceuticals and Incyte have halted development of their CSF-1R-blocking antibody Niktimvo (axatilimab) for idiopathic pulmonary fibrosis after a Phase 2 trial failed to meet its primary endpoint.
Physicians and patient advocates raised alarm after Neurocrine Biosciences' Prader-Willi syndrome drug, Vykat XR, was linked to seven patient deaths and nearly 100 hospitalizations since its approval 18 months ago.
The therapeutic mRNA cancer vaccine BNT113 failed to show a statistically significant improvement in progression-free survival when added to Merck's Keytruda in HPV16-positive head and neck cancer.
Nurix Therapeutics announced in its third-quarter earnings report that it is discontinuing clinical development of zelebrudomide, an oral BTK and cereblon neosubstrate degrader.
Researchers built two neural network tools, xNNDriver and xAEDriver, to prioritize cancer driver genes by connecting mutations to gene essentiality profiles from the Cancer Dependency Map.
A computational framework named SPACER extracts gene-level recruitment rules directly from spatial transcriptomics data to explain how tissues attract specific cell types.
Researchers have developed Scellmate, a computational framework designed to filter contamination and analyze large datasets of single-amplified genomes from single-cell microbial sequencing.
A new open-source simulator called ALBIS generates synthetic spatial transcriptomics datasets from simulated 3D tissues, providing an explicit molecular ground truth for benchmarking spatial analysis algorithms.
Investigators trained a weakly supervised model, named HistoProfile, to predict intratumoral cell densities for CD8, FOXP3, PD-1, and PD-L1 directly from standard hematoxylin and eosin (H&E) pathology images across multiple cancer types.
Researchers combined fragment-based generative molecular design with alchemical absolute binding free-energy calculations to design, prioritize, and synthesize novel small-molecule inhibitors targeting LasB, a virulence enzyme from Pseudomonas aeruginosa.
Computational biologists created proteins designed from scratch (de novo proteins) that switch between two completely different three-dimensional folded states rather than settling into a single static structure.
Researchers developed EcoNet, a deep-learning model using graph attention networks that predicts patient response to immunotherapy by modeling cell-cell signaling circuits inside the tumor microenvironment.
Researchers mapped the binding profiles of 67 RNA-binding proteins in human cells using a ligation-free profiling method termed ecCLIP.
Researchers benchmarked generative design pipelines to create non-oxime reactivators of human acetylcholinesterase, an essential enzyme disabled by organophosphate nerve agents and pesticides.
A computational tool called scMOCHA recovers mitochondrial DNA variants and heteroplasmy directly from standard single-cell RNA sequencing datasets.
Researchers trained an electrical foundation model named PULSE on more than 900 hours of microelectrode array recordings from lab-grown neural tissue and brain organoids.
Researchers built BioMod, a 50-million-parameter single-cell model trained on roughly 73 million human cells using 660 curated pathways and gene programs rather than thousands of individual genes as its basic input tokens.
Large language models used to suggest new ionizable lipid molecules showed no meaningful edge over standard genetic algorithms or random search under matching experimental budgets.