The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 6:32 PM PT
The FDA cleared Eli Lilly's pirtobrutinib, an oral non-covalent BTK inhibitor branded as Jaypirca, for adults with previously untreated chronic lymphocytic leukemia or small lymphocytic lymphoma lacking a 17p deletion.
Aviceda Therapeutics is closing down after its lead eye-disease asset, the glyco-engineered nanoparticle AVD-104, failed a Phase 2b trial against Astellas' Izervay in geographic atrophy.
FDA Chief Scientist Steven Kozlowski announced that the agency will incorporate aging and longevity research into its upcoming Focus Areas of Regulatory Science report.
The FDA established a new Office of Innovation and Clinical Trial Modernization inside the Center for Drug Evaluation and Research to accelerate novel trial designs.
Summit Therapeutics has formed a clinical collaboration with AstraZeneca and Daiichi Sankyo to evaluate ivonescimab alongside Datroway in a Phase 3 trial for first-line triple-negative breast cancer, with the companies sharing study costs.
Xaira Therapeutics unveiled X-Design, its generative artificial intelligence platform built to design drug-ready antibodies from scratch, along with two early preclinical pipeline candidates.
An FDA advisory committee has voted that the benefits of Grail's Galleri multi-cancer early detection blood test outweigh its risks, bringing the test closer to premarket approval.
Novartis agreed to pay China's Abogen Biosciences $575 million upfront, alongside up to $7.2 billion in milestones that bring the total transaction value to $7.8 billion as reported by Reuters.
Abbott has initiated the U.S. commercial launch of SimpleScreen CRC, an FDA-approved blood test developed and manufactured by Freenome for average-risk adults aged 45 and older.
A computational method called DeCoRE clusters direct RNA sequencing reads to separate multiple coexisting conformations at single-nucleotide resolution.
Researchers built FLIGHTED, a Bayesian statistical method that converts noisy high-throughput assay readouts into probabilistic fitness landscapes before feeding them into machine-learning models.
Researchers combined amino acid alignments with a structural alphabet, using variational autoencoders and evolutionary energy calculations to map protein sequence variations against structural changes.
Researchers built a machine learning model that analyzes glucose metabolism in the brain to predict Alzheimer's-type tau pathology across aging and diverse dementia disorders.
Machine-learning analysis of temporal changes across the cell-surface proteome identified the enzyme ALPP as an adaptive target that pancreatic tumors produce in response to KRAS inhibition.
Researchers introduced AuditPPI, an interpretability framework that converts sparse-autoencoder representations from frozen protein language models into auditable pair fingerprints to evaluate how models predict protein-protein binding.
Researchers have developed mmFEA, a computational framework that estimates relative metabolic reaction rates by combining gene expression or protein abundance with metabolite measurements through Michaelis-Menten enzyme kinetics.
Researchers have built RipplePLM, a computational model that generates natural language descriptions of how single-amino-acid changes disrupt protein behavior.
An analysis of approximately 2 million PubChem bioassays found that more than 99.9% lack standardized ontology tags for assay formats and detection technologies, creating major hurdles for training molecular property models.
Researchers designed an algebraic counting field model to detect cryptic binding pockets, which are hidden drug-binding sites that only become visible when a ligand attaches to a protein.
A systematic benchmark evaluated 4-bit quantization and low-rank adapter fine-tuning, known as QLoRA, across seven protein language models including ESM-2, ProtT5, and Profluent-E1.
CPathOGen uses conditional latent diffusion to generate paired synthetic histology images with independent controls for cell layout, nuclear shape, and tissue stain colors.
Fold'EM combines generative structural priors directly with raw cryo-electron microscopy particle images to infer atomic models, skipping the usual steps of building a 3D density map and fitting a model into it.