1
无需活细胞：哈佛大学科学家直接在试管内设计蛋白质，从此氨基酸“字母表”扩展至 34 种
IT之家 8 月 29 日消息，哈佛大学医学院及威斯生物启发工程研究所（Wyss Institute）的 George Church 团队开发出一种名为 AGENTEX 的新工具，将蛋白质设计可使用的“氨基酸字母表”从天然的 20 种扩展至 34 种。 该工具无需改造活细胞基因组，在试管中即可批量构…
2
Team uses AlphaFold AI to redesign gene-editing proteins to make them safer
AlphaFold精准定位基因编辑蛋白易出错部位，用AI设计更安全版本，为基因疗法降低风险
Google's AlphaFold can help ID what parts of a gene editing protein enable mistakes.
3
Claude Science, an AI workbench for scientists
Anthropic推出Claude Science，为科学家打造的AI工作台，集成60+科学领域技能与连接器，支持通用与专业代理协作。
Article URL: https://www.anthropic.com/news/claude-science-ai-workbench Comments URL: https://news.ycombinator.com/item?id=48901923 Points: 1 # Commen…
4
AI生物研发进入“操作系统时代”，许锦波团队MoleculeOS正式开放
许锦波团队推出MoleculeOS，全原子大模型MMFold突破抗体-抗原结构预测，AI从工具升级为生物研发操作系统。
AI变为研发流程的“组织者”
5
Show HN: Open-source GUI for editing 3D molecular structures with diffusion
开源图形界面，轻松编辑3D分子结构，支持扩散模型，重构蛋白质、DNA/RNA片段。
Article URL: https://github.com/DeepFoldProtein/patchr Comments URL: https://news.ycombinator.com/item?id=48835428 Points: 2 # Comments: 0
6
迄今最精最全！我国西湖大学绘制的人体蛋白质“地图”出炉，数据面向全球开放
全球首张人体蛋白质高精地图发布，覆盖上万种蛋白质并开放共享，为癌症研究提供全新坐标。
IT之家 6 月 21 日消息，据科技日报报道，西湖大学医学院郭天南教授团队联合多家科研单位，收集了近 3000 份人体组织样本，覆盖 58 种正常组织、25 种癌症类型，对超过 1.3 万种蛋白质进行定量分析， 成功绘制出迄今分辨率最高、覆盖范围最广的人体蛋白质组空间图谱 。 据介绍，蛋白质是生命…
7
8
How we are computing 'invisible' protein states for AI
用AI揭示蛋白质“隐形”状态，突破传统结构预测的边界
Article URL: https://idps.substack.com/p/a-disordered-protein-wont-hold-still Comments URL: https://news.ycombinator.com/item?id=48554874 Points: 2 # …
9
Circuit Tracing in Autoregressive Protein Language Models
基于论文探索蛋白质语言模型的生成机制，提出电路追踪方法，为理解模型内部原理提供新视角
arXiv:2606.16044v1 Announce Type: new Abstract: Protein language models (pLMs) can generate novel protein sequences with properties beyond those obser…
10
RAGPPI: RAG Benchmark for Protein-Protein Interactions in Drug Discovery
首个专门针对药物发现中蛋白质-蛋白质相互作用的RAG基准，为AI辅助药物设计提供标准化评测框架。
arXiv:2505.23823v2 Announce Type: replace Abstract: Retrieving the biological impacts of protein-protein interactions (PPIs) is essential for target i…
11
Comparative evaluation of training strategies using partially labelled datasets for segmentation of white matter hyperintensities and stroke lesions in FLAIR MRI
白质高信号与卒中病变分割中，如何用部分标注数据优化训练策略？这篇论文系统性对比了多种方法。
arXiv:2601.20503v2 Announce Type: replace Abstract: White matter hyperintensities (WMH) and ischaemic stroke lesions (ISL) are key imaging biomarkers …
12
AI is taking on antibiotic resistance — here’s how
MIT教授因家人经历投身AI研究，用深度学习破解抗生素耐药难题，Nature深度报道展现技术改变医疗的惊人潜力。
Nature, Published online: 08 June 2026; doi:10.1038/d41586-026-01818-9 A suite of artificial-intelligence tools is helping to speed up the process of …
13
GenTract: Generative Global Tractography
生成式全局纤维束追踪新方法，突破局部追踪误差累积瓶颈，有望提升脑白质通路重建精度。
arXiv:2511.13183v2 Announce Type: replace Abstract: Tractography is the process of inferring the trajectories of white-matter pathways in the brain fr…
14
CryoProt: A Protein Pretraining Framework with Cross-Box Interactions on Cryo-EM Density Maps
CryoProt创新地利用冷冻电镜密度图与跨盒交互机制，为蛋白质预训练提供了新思路，值得AI生物研究者关注。
arXiv:2606.00955v1 Announce Type: new Abstract: Despite the growing availability of cryo-electron microscopy (cryo-EM) density maps, effectively lever…
15
De novo design of quasisymmetric two-component protein cages
Nature发表：从头设计准对称双组分蛋白质笼，计算设计策略实现可编程尺寸与冷冻电镜验证。
Nature, Published online: 20 May 2026; doi:10.1038/s41586-026-10464-0 Researchers designed two-component proteins forming quasisymmetric cages via geo…
16
Protein Fold Classification at Scale: Benchmarking and Pretraining
构建大规模非冗余蛋白质折叠分类基准TEDBench，突破尺度瓶颈，助力生物大分子功能解析。
arXiv:2605.18552v1 Announce Type: new Abstract: Classifying protein topology is essential for deciphering biological function, but progress is held ba…
17
Structure-Aware Masking for Protein Representation Learning
突破性结构感知掩码方法，提升蛋白质表征学习效能，为AI制药与蛋白质设计提供新思路
arXiv:2605.16581v1 Announce Type: new Abstract: Masked language modeling (MLM) is the standard objective for training protein language models, typical…
18
Growth charts reveal how the brain’s ‘communication highways’ change throughout life
基于《自然》新论文，揭示人类大脑白质微宏观结构随年龄变化的生长图表，帮你看懂大脑发育与衰老。
Nature, Published online: 13 May 2026; doi:10.1038/d41586-026-01318-w Studies of white matter — the tissue used for communication between brain region…
19
ENSEMBITS: an alphabet of protein conformational ensembles
首个蛋白质构象集合的tokenizer，突破静态结构局限，捕捉动态运动与替代状态。
arXiv:2605.13789v2 Announce Type: replace-cross Abstract: Protein structure tokenizers (PSTs) are workhorses in protein language modeling, function pr…