The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 6:32 PM PT
Lakefront Biotherapeutics, formerly Galapagos, has sold its early-stage CAR-T cell therapy assets to newly formed Belgian biotech Armed Cell Therapeutics for €8 million upfront and up to $230 million in regulatory and commercial milestones.
Bain Capital Life Sciences, Forbion, and Novo Holdings co-led the Series C financing, backed by new investors Janus Henderson, SV Health Investors, and Jefferson Life Sciences alongside Alphabet-backed GV and Syncona.
Compass Pathways plans to complete a rolling FDA submission this quarter for COMP360, a synthetic psilocybin therapy for treatment-resistant depression, ahead of a potential launch early next year.
Iambic Therapeutics priced its initial public offering at $16 per share to raise $150 million, selling roughly 9.4 million shares ahead of trading on the Nasdaq under ticker IAM.
The FDA cleared ImmunityBio's Anktiva, an IL-15 superagonist immunotherapy, for patients with papillary-only non-muscle invasive bladder cancer.
Colossal Biosciences announced GenoMorph, a computational platform designed to pick out target genetic edits for de-extinction projects constrained by scarce ancient DNA.
Ultragenyx has monetized two rare pediatric disease priority review vouchers for a combined $413 million following two summer gene therapy approvals from the FDA.
The Food and Drug Administration launched its Rare Disease Framework Initiative to tailor trial requirements and evidence standards to small patient groups.
In an early Phase 1/2 trial, Verastem Oncology reported an overall response rate of 41% among 22 patients with advanced pancreatic ductal adenocarcinoma treated with its daily pill VS-7375.
Verdiva Bio has terminated a Phase 2 trial testing its once-weekly oral GLP-1 peptide, VRB-101, as a maintenance treatment for patients switching off injectable weight-loss drugs.
Biomea Fusion reported early trial results for BMF-650, its oral small-molecule GLP-1 receptor agonist, showing mean weight reductions between 1.5% and 3.2% across four cohorts at Day 29.
ARO-MAPT, an experimental RNA interference medicine delivered by simple injection under the skin, lowered tau protein levels by up to 85% in healthy volunteers.
GSK plans to cut up to 1,217 roles across R&D, manufacturing, and support functions in Belgium, the site of its global vaccines division.
Agilent Technologies agreed to pay $240 million in cash upfront, plus up to $30 million in milestone payments, to acquire the digital pathology software developer Proscia.
An artificial intelligence system quantified human brown adipose tissue activity across clinical scans, revealing strong associations between active brown fat, improved metabolic profiles, and reduced rates of psychiatric illness.
SpatialZoomer uses spectral graph theory to analyze spatial transcriptomics data simultaneously at individual cell resolution and across broad tissue domains.
Researchers have released MassNet, an AI-ready training dataset containing 1.5 billion tandem mass spectrometry spectra across 35 species, stored in a tensor format designed for deep learning.
LoL-align matches 3D protein structures by iteratively optimizing a local log-odds score based on inter-residue distances.
A computational model called SVC treats subcellular RNA transcript locations as image patches, using surrounding molecules to predict where individual genes localize within single cells.
Researchers introduced DNA-LLM2Vec, a staged conversion framework that equips directional, generative DNA language models with two-way sequence context.
Researchers developed a local computational pipeline that evaluates whether candidate industrial enzymes will express well in common host microbes such as Escherichia coli and yeast.
Foundation models trained on general molecular chemistry successfully predict key properties of complex sugars, including immunogenicity and protein-glycan interactions.
Researchers used AI-predicted structural models of an antibody-antigen complex to design point mutations that increased the binding affinity of a synthetic single-domain antibody eightfold against interleukin-12.
A biophysical generative algorithm designed functional intrinsically disordered regions from scratch for the developmental transcription factor RUNX2.
Researchers redesigned the photosynthetic enzyme fructose-1,6-bisphosphatase from the green alga Chlamydomonas reinhardtii, swapping more than 13% of its amino acids based on distant evolutionary sequences.
Neuroscientists developed LightSuite, an open-source image-processing framework that automates large-scale 3D anatomical alignment and single-cell detection across the central nervous system.
A computational drug-repurposing pipeline pairs multi-tissue RNA sequencing from treated rodents with a harmonized library of over 900 human disease expression profiles.
Computational biologists built a random forest classifier to predict cancer resistance mechanisms against synthetic lethal therapies using protein interaction networks, gene expression, and cellular essentiality profiles.
Investigators developed Borzoi-SE, a genomic transformer framework that detects super-enhancers, large regulatory DNA clusters that drive cell identity, directly from long-range sequence across 90 human lineages.
A reinforcement learning framework called Multi-turn Feedback Guided optimization trains large language models to iteratively redesign molecules based on feedback from prior modification steps.
Researchers built CellChain, an evaluation benchmark spanning 590 biological cases and 2,360 matched conditions across gene dependency, cytokine signaling, and drug sensitivity.
Researchers demonstrated a black-box attack on the genomic language model Evo 2 7B that extracts memorized DNA sequences without access to model gradients, token probabilities, or training data.
Researchers introduced STAMP, a molecular representation format that explicitly separates chemical fragments, their attachment sites, and the overall molecular skeleton.
Researchers introduced an optimization and Bayesian inference framework that penalizes parameter sets violating thermodynamic detailed balance, rather than strictly reparameterizing complex reaction networks.
CloneOT uses lineage tracing to learn custom cost functions for neural optimal transport, predicting how individual cancer clones change after therapeutic perturbation.
Researchers trained machine-learning surrogates on wide parameter ranges to evaluate which patient factors drive simulated pharmacokinetic and pharmacodynamic drug trials across multiple virtual cohorts.