Tag
An interactive educational article that builds a tiny simulated creature ('spark') with a minimal neural circuit to show how simple excitatory and inhibitory neuron wiring can produce complex behaviors like steering toward and stopping at a light source.
一支几乎没有生物学背景的五人投资团队利用 Claude 协调 300 多个 AI 智能体，在 64 小时内设计了 318,484 种蛋白质，其中 17 种经独立实验室验证可结合危险的蝎子神经毒素。
Arc Institute 的 Science Fellow 周景天及其团队在新预印本中介绍 Bolero，这是一个以细胞状态为条件、仅从 DNA 预测染色质可及性与基因表达的模型，解释了相同 DNA 在不同细胞中的差异解读。
IRIS 是一种利用扰动筛选与迁移学习重建跨细胞类型细胞信号传导历史的新方法，发表于 Nature Methods。
提出了GOLD框架，通过GeoVAE将RNA离散序列与连续侧链角度投影到统一潜在流形上进行协同扩散，并引入训练无关的梯度引导采样机制，实现结构感知的RNA逆折叠，达到最先进性能。
MIT researchers led by Pulin Li developed IRIS, a neural network model that detects unique gene-activity 'fingerprints' left by cellular signaling pathways, allowing them to reconstruct a cell's signaling history across many cell types using transfer learning. Published in Nature Methods, the approach could accelerate stem cell engineering, organoid development, and disease research.
This paper presents a family of conditional generative models over phylogenetic trees trained with a discrete diffusion framework, enabling simulation-based inference under complex evolutionary models. The approach recovers MCMC posteriors more accurately than prior methods like Phyloformer and outperforms the conventional method IQ-Tree on realistic data.
研究人员利用AI蛋白质设计工具，替换锌蛋白酶和半胱氨酸蛋白酶的催化核心之外的全部结构，设计出可定制切割特定蛋白质的新型蛋白酶，并成功展示了其切断与神经系统疾病相关蛋白的能力。
The paper introduces Finsler Flow Matching (FFM), a framework that learns continuous stochastic dynamics from discrete Markov transition graphs using Finsler geometry to encode directional and diffusive structure, improving single-cell trajectory inference over existing generative approaches.
Biohub宣布启动Virtual Biology Initiative，这是一项为期五年、总额18亿美元的全球合作计划，旨在构建可预测的人体细胞模型；Biohub承诺投入5亿美元，DeepMind、Isomorphic Labs、Meta、美国政府及NVIDIA等均参与其中。
Google DeepMind and collaborators present AlphaProtein Novo, a machine-learning pipeline for generative de novo enzyme design that produces new-to-nature enzymes with state-of-the-art activity on benchmark reactions, including enzymes for synthesizing piperidine and degrading the environmental toxin DEHP.
ToposBio announced Topos-2, a next-generation model generating the full range of protein shapes across the order-disorder spectrum, plus a preview of Topos-Bind, a generative binding model built and run on Modal, aiming to drug previously undruggable targets.
Researchers at Maynooth University have developed the fastest and most complex DNA computer to date, capable of executing complex math calculations without wires or continuous power.
TorchCraft is a unified binder design framework that inverts all-atom structure predictors like AlphaFold3 to optimize sequences for minibinders, VHHs, cyclic peptides, and ligand-binding proteins, with experimental validation across multiple formats.
This paper introduces TP-DATE, a simulation-free framework for dynamic Gromov-Wasserstein optimal transport, which enhances spatial structure preservation and continuous dynamics reconstruction in spatial transcriptomics data.
A paper published in Cell Press describes how an AI agent was used to create a uniformly processed resource of over 502 million cells from publicly available data.
Arc Institute is hiring experts in disease biology, computational biology, functional genomics, and NGS for its Tech Centers and Core Labs, with various roles based in Palo Alto.
LabAgent is an AI agent system designed to customize research hubs for scientific discoveries, enabling reproducible and continuous laboratory work across various biological domains and outperforming commercial generalist agents.
The article introduces Autopoietic Game Theory, a computational model demonstrating that coupling social interactions with replication costs in evolving agentic systems can favor the emergence of cooperation, using Z80 machine code simulations.
A post discussing the mapped neurons of a fruit fly's brain, which has garnered significant attention.