Tag
A new preprint from Arc Institute reports that Evo 2 can design enhancers that label specific neuronal subtypes in live mouse brains, using fewer than 100 example sequences as prompts, advancing programmable gene expression for biology and therapeutic engineering.
New work shows that genome language models like Evo 2 can perform in-context learning from a few examples, generating proteins, de novo antibodies, CRISPR-Cas9 loci, mitochondrial genomes, and even complete bacteriophages, with iterative chain-of-thought-style prompting for harder design goals.
BenchBench-Cloning 介绍了一个包含 65 项分子克隆任务的基准，用于评估大语言模型在端到端实验规划与协议开发方面的能力，结果显示即使是前沿模型（最高 GPT-6 Astra 仅 30.6%）仍难以完成完整有效的克隆方案。
MIT Technology Review hosts a subscriber-only live roundtable with Stanford PhD candidate Samuel King, one of its Innovators Under 35, about using generative AI to design viral genetic blueprints.
YC S21 startup Sensible Biotechnologies raised a $47M Series A to scale its platform for engineering living cells to manufacture mRNA, aiming to meet the higher dose and purity demands of next-generation mRNA medicines like in vivo CAR-T and gene editing.
Google DeepMind announced SynthID Bio, a watermarking technology that embeds verifiable signatures into AI-designed proteins while preserving their biological function, verified in wet-lab tests and built into AlphaFold 3's diffusion network.
AI-designed synthetic protein assemblies enable gene therapy delivery systems far superior to natural capsids, as reported in a Nature paper.
Scientists have accidentally created a synthetic cell factory, which could advance biotechnology and medical applications.
Researchers have found a way to operate two separate genetic codes simultaneously, avoiding the need to re-engineer every gene in an organism's genome and potentially accelerating synthetic biology work.
Scientists have used AI to design novel bacteriophages, raising concerns about biosecurity and the pace of regulation for AI-enabled biotechnology.
A tweet about the AASF 2026 life sciences panel discussion, noting that life sciences are shifting from observation to targeted manipulation of genes, proteins, and cellular states.
Researchers at Stanford and the Arc Institute used AI models Evo 1 and Evo 2 to design hundreds of novel bacteriophage genomes, 16 of which produced fully functional viruses capable of infecting E. coli. The breakthrough opens new avenues for combating antibiotic resistance but raises biosecurity concerns.
US researchers used generative AI models Evo1 and Evo2 to design complete virus genomes for the first time, creating 16 novel bacteriophages that can kill E. coli. The breakthrough could enable new disease treatments but raises urgent safety and security concerns.
AI has created the first synthetic viruses, a significant breakthrough in synthetic biology that raises biosecurity concerns.
A research paper highlights a major AI-driven breakthrough in synthetic biology and green chemistry, as reported by Nature Communications.
SynBio Studio es un IDE para biología sintética que permite a los científicos programar circuitos genéticos, mapear plásmidos en tiempo real y simular su cinética antes de realizar experimentos en laboratorio.
Synbio Studio es un software que permite diseñar y simular células y proteínas digitalmente, reemplazando costosos y lentos experimentos de laboratorio.
Researchers at the University of Minnesota developed SpudCells, artificial cells that can undergo a few rounds of cell division by importing materials from the environment, using components from viruses and purified translation machinery.
A team led by Kate Adamala at the University of Minnesota has built a completely new cell, SpudCell, from non-living chemical components. It can grow, divide, and evolve—a milestone breakthrough in synthetic biology.
Scientists at the University of Minnesota have created SpudCells, synthetic cells that feed, grow, reproduce, and compete, marking a major advance in synthetic biology. The work is described in a 190-page preprint under journal review.