The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 6:32 PM PT
The Medicines and Healthcare products Regulatory Agency will continually monitor artificial intelligence-based medical devices throughout their lifecycle, replacing the current one-time approval model.
GE HealthCare has agreed to acquire radiopharmaceutical company Sofie Biosciences for $945 million.
Nuvig Therapeutics has halted a Phase 2 trial of its lead fusion protein, NVG-2089, in chronic inflammatory demyelinating polyradiculoneuropathy, a rare nerve disorder.
Dutch venture capital firm Forbion gathered €2.3 billion across Forbion Growth Opportunities IV and Forbion Ventures Fund VIII to back up to 30 biotechnology startups.
The biotech's brain-penetrant oral EGFR inhibitor firmonertinib failed to significantly improve progression-free survival against platinum-based chemotherapy as a first-line treatment for non-small cell lung cancer with exon 20 insertion mutations.
The biotech adjusted its Phase 2 protocol to evaluate its CD105 inhibitor ENV-105 combined with Astellas and Pfizer's Xtandi against monotherapy immediately after patients show rising PSA levels.
The funding comprises a Series A round joined by OTB Ventures, In-Q-Tel, Recode Ventures, and other backers, alongside up to $20 million in non-dilutive grants from Slovakia and the European Union.
Researchers built NA-CDQuant, a computational framework that deconvolves complex circular dichroism spectra to determine the structural shapes of nucleic acids in solution.
CardamomOT combines optimal transport mathematics with a mechanistic model of gene expression to infer gene regulatory networks and reconstruct unmeasured protein trajectories across single-cell RNA sequencing time series.
Researchers built variational inference-based microniche analysis, or VIMA, a deep learning statistical method that detects disease-linked tissue structures directly from spatial molecular data.
Researchers built NuCaliby, a structure-conditioned generative model that designs protein amino-acid sequences together with their corresponding DNA and mRNA nucleotide sequences.
Nagini3D combines deep learning models with active surface algorithms to segment multiple objects directly across volumetric fluorescence microscopy images.
Researchers built MAGI, an open modular agent designed to plan molecular optimization, launch generative tools, and interpret structure-activity relationships across drug discovery campaigns.
Researchers built a scoring system called semantic precision score using the biomedical language model BioLORD to weed out overly broad answers, such as general terms like antibiotics or pharmaceutical preparations, from knowledge graphs querying potential treatments for 200 diseases.
Researchers modeled the tertiary structure of the complete CPLANE complex and its largest subunit, JBTS17, using deep learning protein-folding tools.
Deep learning representations of induced pluripotent stem cell-derived neurons from three familial Parkinson's disease cases mirrored independent measurements of cell death, according to a bioRxiv preprint.
Researchers developed CatFunc, a lightweight protein language model pipeline that classifies how AAA proteins convert ATP chemical energy into mechanical force directly from sequence data.
Researchers have developed peptide-retargeted phosphatases, synthetic fusion proteins that link computationally designed peptide binders to a serine/threonine phosphatase subunit to selectively remove phosphate groups from specific cellular targets.
Bioengineers developed the Catalytic Guidance Engine, an iterative design framework that detunes geometric constraints during diffusion sampling to build complex catalytic sites into de novo proteins.
Computational biologists introduced Kodiak, a discrete representation learning architecture that uses balanced codebook assignments to map complex scientific images into a reusable visual vocabulary.
Researchers introduced two learned discrete latent vocabularies to train autoregressive transformers on protein sequence and structure, replacing conventional residue tokens and coordinates.