The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 6:32 PM PT
Eli Lilly reported that its dual-drug combination eloraTZP delivered 23.3% average weight loss at 48 weeks in a trial of 367 adults with both type 2 diabetes and obesity or overweight.
Merck announced that its antibody tulisokibart met the primary and secondary endpoints in a 149-patient Phase 2b trial for moderate to severe hidradenitis suppurativa, an inflammatory skin condition.
Primary endpoint Phase 2 data published in The Lancet Diabetes & Endocrinology showed Zealand Pharma and Roche's amylin analog, petrelintide, produced 9.8% mean weight loss at Week 28 on a 5 mg dose compared to 1.7% on placebo.
Researchers at Boston Children's Hospital and the Broad Institute identified the BACH2-NRF2 pathway as an independent regulator of fetal hemoglobin expression, according to a study published in Nature.
Lux Capital and Natural Capital co-led a $251 million Series D round for Varda Space Industries, with participation from Founders Fund, Khosla Ventures, and General Catalyst.
The FDA has accepted Roche's regulatory application to review fenebrutinib, an oral Bruton's tyrosine kinase inhibitor, across two major forms of multiple sclerosis.
The European Commission revoked its marketing authorization for Hansoh Pharma's Aumseqa (aumolertinib), an oral third-generation EGFR inhibitor for non-small cell lung cancer, after a legal challenge by AstraZeneca.
Pierre Fabre Laboratories has resubmitted its biologics license application for Ebvallo, an allogeneic T-cell therapy targeting a complication of Epstein-Barr virus infections that the FDA rejected twice over manufacturing problems.
GSK will pay Wave Life Sciences $12 million upfront to take ownership of a liver-targeted small interfering RNA (siRNA) candidate emerging from their 2022 research partnership.
In a 159-patient Phase 2 trial, the company's experimental antibody rademikibart cut new moderate-to-severe lung attacks by 85% and reduced overall treatment failure by 81% over 28 days compared to placebo.
In a 72-patient Phase 2 trial in discoid lupus, the low dose of the monoclonal antibody daxdilimab delivered a 6-point reduction against placebo on the skin-severity index at Week 24, while a higher dose achieved a 5.7-point reduction.
Eli Lilly presented full results from the 1,152-patient Triumph-2 Phase 3 trial testing retatrutide, an injectable triple agonist targeting GIP, GLP-1, and glucagon receptors, in adults with obesity and Type 2 diabetes.
Researchers introduced GenAI-Net, a generative framework that automates the design of chemical reaction networks by pairing reaction proposal with simulation against user-specified dynamical goals.
Researchers combined high-throughput yeast display screening with AlphaFold3 structural modeling to discover single-domain antibodies that neutralize neurotoxins from multiple snake species.
A new live-cell imaging workflow combines single-shot stimulated emission depletion microscopy with a neural network to track lipid movement across the endoplasmic reticulum, lipid droplets, and mitochondria simultaneously.
Researchers introduced GeoEPred, a geometric deep learning model that identifies effector proteins secreted by Gram-negative bacteria by fusing linear sequence embeddings with predicted three-dimensional structures.
Google researchers introduced SynthIDBio, a set of methods that embeds detectable digital watermarks directly into AI-generated protein sequences and molecular structures.
Researchers have developed CytoVI, a probabilistic deep generative model that integrates single-cell protein measurements across flow cytometry, mass cytometry, and CITE-seq.
Researchers built Mendel, an AI foundation model trained from scratch on human whole-genome sequences using a training objective focused on differences between individual genomes rather than invariant sequence.
CycloCross uses a cycle-consistent adversarial network (CycleGAN) architecture to translate single-cell RNA sequencing data between species without requiring strict one-to-one gene matches.
Researchers built CHACAM, a supervised attention model that combines single-cell gene expression with known ligand-receptor pairs and physical cell contact maps to annotate early roundworm embryo cells.
Researchers built PeTriPPI2, a computational framework that predicts whether two proteins interact by pairing sequence embeddings from ESM-2 with structural features from PeTriBERT.
OmniVCBench introduces 6,077 question-and-answer pairs based on published figures to evaluate whether multimodal AI models can interpret wet-lab data and formulate biological hypotheses.
Researchers designed ZEST, a tokenization scheme that uses conserved regions from multiple sequence alignments to compress protein sequences into multi-residue tokens averaging four amino acids in length.
Researchers introduced CrystAF, an all-atom flow-matching model paired with the UMA interatomic potential, to evaluate the best stage to inject physics into generative models predicting molecular crystals.