The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 5:32 PM PT
A multi-agent framework called ExpertTwins anchors language-model agents to inspectable evidence policies and cited publications rather than simple persona prompts.
A team led by Scinetics introduced chain-of-structures, a framework that couples language reasoning with structural generative models to design enzymes directly from reaction specifications.
Researchers deployed autonomous instances of Claude Code to search 1.9 billion protein clusters for reverse transcriptases, identifying a new class of giant-virus enzymes dubbed array-associated RTs.
Researchers built SpatialOmicsLab, an evaluation suite combining 113 analytical tools, 63 reference datasets, and 4,614 task specifications for spatial transcriptomics, alongside an AI agent named ST-Coscientist designed to assemble and run those workflows.
Computational biologists created ddkg.skill, an agent module that compiles natural-language bioinformatics questions into executable Cypher code for the NIH Common Fund Data Distillery Knowledge Graph.
Researchers built MAGI, an open modular agent designed to plan molecular optimization, launch generative tools, and interpret structure-activity relationships across drug discovery campaigns.
An automated research platform named iCloudBiofoundry links AI agents that plan scientific protocols from literature with robotic laboratory hardware that executes experiments autonomously.
Computational biologists paired large language model agents with quantitative systems pharmacology to systematically eliminate flawed hypotheses before designing clinical trials.
Researchers at Anthropic deployed roughly 950 Claude agents to mine genomic databases, identifying an unusual family of array-associated reverse transcriptases found in giant bacterial viruses.
Bioinformaticians built ScProteoAgent, an artificial intelligence agent designed to translate natural-language prompts into reproducible analytical workflows for single-cell proteomics.
NeuronDiscover pairs prediction, intervention, and measurement design to untangle genuine biological responses from numerical modeling errors in computational digital twins of neuronal microenvironments.
Researchers introduced M3OS, a framework that pairs large language models with Monte Carlo graph search to iteratively edit and improve drug-like small molecules.
Researchers built an automated data-extraction pipeline to enrich 74,425 protein-ligand measurements in the public BindingDB database with structured experimental context pulled from original papers.
A team created GEMOT, an AI agent framework designed to infer explicit, modular mathematical equations and hidden biological states from sparse experimental data.
Researchers built an autonomous language-model agent that carries out hit-to-lead molecular optimization by combining literature retrieval, molecular property estimators, docking simulations, and iterative feedback from previously scored analogs.
Anthropic announced that its wet biology lab discovered an enzyme system hidden in bacteriophage DNA that functions similarly to CRISPR by cutting, copying, and pasting genetic material.
Target-adaptive Rescue-Explore-eXploit, or T-REX, uses large language model agents to orchestrate multiple generative models and structure-evaluation tools during protein binder design campaigns.
Researchers built the Virtual Biotech, an ensemble of artificial intelligence agents organized into drug development divisions including target discovery, safety assessment, modality selection, and clinical trials.
A benchmark evaluated three automated coding agents, Biomni, Claude Code, and Codex, on writing a complex Nextflow pipeline for processing epigenomic sequencing data from start to finish.
A Stanford team published an architecture in Science that coordinates specialized computational agents under a virtual chief scientific officer to analyze cross-disciplinary genomic, molecular, and clinical data.
MicroClaw is an artificial intelligence assistant designed to plan and execute automated imaging experiments across multiple microscope platforms using natural language prompts.
A multi-agent framework called scACORN coordinates specialized small language models rather than a single monolithic model to interpret single-cell transcriptomic profiles.
Obvious Ventures led a $20 million Series A funding round for Mithrl, with backing from Headline, AGI House, and biopharma executives, to advance its biomedical world model and AI orchestration platform.