Nature computational science最新文献_第3页

MutexaGPT: an intuition-to-design translator for physics-based enzyme engineering. mutexpt：一个基于物理的酶工程的从直观到设计的翻译器。

IF 20.3

Nature computational science Pub Date : 2026-09-10 DOI: 10.1038/s43588-026-01049-y

Qianzhen Shao, Yinjie Zhong, Sebastian Stull, Xinchun Ran, Ning Ding, Kieran Nehil-Puleo, Ruizhe Yao, Han Xu, Zhongyue J Yang

{"title":"MutexaGPT: an intuition-to-design translator for physics-based enzyme engineering.","authors":"Qianzhen Shao, Yinjie Zhong, Sebastian Stull, Xinchun Ran, Ning Ding, Kieran Nehil-Puleo, Ruizhe Yao, Han Xu, Zhongyue J Yang","doi":"10.1038/s43588-026-01049-y","DOIUrl":"10.1038/s43588-026-01049-y","url":null,"abstract":"Physical intuition about how enzyme structure and dynamics shape function has guided successful engineering efforts, yet a systematic approach is still lacking for translating these qualitative and abstract 'thoughts' into quantitative, actionable principles for enzyme design. Here we introduce MutexaGPT, an open-access, multi-agent large language model platform that translates enzyme engineering intuition to physics-based simulations and thus variant designs. Through a web-interface, MutexaGPT takes plain-English, intuition-driven requests as input and leverages large language model agents to elicit missing information, construct physics-based models, configure and execute high-throughput molecular modeling workflows, and convert the results into actionable design proposals, such as smart mutation libraries. We demonstrate the utility of MutexaGPT in two protein engineering tasks: (1) engineering halide methyltransferase toward bulkier substrates and (2) engineering bidomain amylase for enhanced activity at lower temperature. These results establish MutexaGPT as an intuition-to-design translator that integrates human creativity with high-throughput molecular modeling to democratize physics-guided, intuition-driven enzyme engineering.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":20.3,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

When pathology segmentation learns to listen 当病理分割学会倾听。

IF 20.3

Nature computational science Pub Date : 2026-09-10 DOI: 10.1038/s43588-026-01048-z

Wei Shen

引用次数: 0

Segment anything in pathology images with natural language 用自然语言分割病理图像中的任何东西。

IF 20.3

Nature computational science Pub Date : 2026-09-10 DOI: 10.1038/s43588-026-01042-5

Zhixuan Chen, Junlin Hou, Liqi Lin, Yihui Wang, Yequan Bie, Xi Wang, Yanning Zhou, Danyi Li, Hongxuan Tan, Li Liang, Ronald Cheong Kin Chan, Hao Chen

{"title":"Segment anything in pathology images with natural language","authors":"Zhixuan Chen, Junlin Hou, Liqi Lin, Yihui Wang, Yequan Bie, Xi Wang, Yanning Zhou, Danyi Li, Hongxuan Tan, Li Liang, Ronald Cheong Kin Chan, Hao Chen","doi":"10.1038/s43588-026-01042-5","DOIUrl":"10.1038/s43588-026-01042-5","url":null,"abstract":"Segmenting tissues and cells in pathology images enables quantitative analysis but usually requires task-specific models or repeated spatial prompts. Here we show PathSegmentor, a foundation model that uses natural language descriptions to segment structures across anatomical regions and spatial scales. We assembled PathSeg from 21 public datasets, comprising 275,200 image–mask–label triples organized into a 3-level hierarchy of anatomical region, histological structure and object type. A single PathSegmentor model achieved the highest overall performance across 16 internal datasets and generalized to external public and clinical cohorts. Its text prompts reduced the need to identify every object with points or boxes and remained robust to variations in wording. We further used its predicted structures to explain breast cancer classification models through object-level perturbation and activation maps. These results establish a unified framework for flexible pathology segmentation with potential utility for clinically interpretable image analysis. This Resource introduces PathSegmentor—a foundation model that segments 160 pathological categories via natural language prompts, generalizes across datasets and clinical cohorts, and enables scalable, interpretable pathology image analysis.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 9","pages":"1024-1038"},"PeriodicalIF":20.3,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep learning models enable high-performance, real-time emotion decoding from intracranial brain activity. 深度学习模型能够从颅内大脑活动中实现高性能、实时的情绪解码。

IF 20.3

Nature computational science Pub Date : 2026-09-10 DOI: 10.1038/s43588-026-01055-0

引用次数: 0

Predicting brain morphogenesis via physics-transfer learning. 通过物理迁移学习预测大脑形态发生。

IF 20.3

Nature computational science Pub Date : 2026-09-09 DOI: 10.1038/s43588-026-01040-7

Yingjie Zhao, Yicheng Song, Fan Xu, Zhiping Xu

{"title":"Predicting brain morphogenesis via physics-transfer learning.","authors":"Yingjie Zhao, Yicheng Song, Fan Xu, Zhiping Xu","doi":"10.1038/s43588-026-01040-7","DOIUrl":"10.1038/s43588-026-01040-7","url":null,"abstract":"Brain morphology emerges from the interplay of genetic programming and mechanical forces, yet its fractal-like folding patterns make quantitative analysis and prediction difficult, especially when labeled data are scarce. Here we introduce a theory-grounded physics-transfer learning framework that enables generalization analysis and prediction in complex physical systems by leveraging consistent governing laws across levels of complexity. Specifically, mechanistic insights into the nonlinear elasticity of simple, analytically tractable geometries are embedded into neural networks and successfully transferred to brain models through a sequence of physics-anchored domains, integrating explicit physics constraints into learning theory. Building on the physics-transfer theory, we derive a generalization bound that explains the strong performance in brain feature characterization and morphogenesis prediction. Beyond predictive accuracy, the framework yields reduced-dimensional evolutionary representations that distill the essential physics of brain morphogenesis. Validation against medical imaging data demonstrates the promise of physics-aware digital-twin technologies for understanding, diagnosing and intervening in the developing and diseased brain.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":20.3,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148921567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AI testing is not AI safety 人工智能测试不是人工智能安全。

IF 20.3

Nature computational science Pub Date : 2026-08-28 DOI: 10.1038/s43588-026-01047-0

George Breckenridge, Feng Li

引用次数: 0

When authors are the best judges of their work 当作者是自己作品的最佳评判者时。

IF 20.3

Nature computational science Pub Date : 2026-08-28 DOI: 10.1038/s43588-026-01046-1

Bedoor AlShebli

引用次数: 0

Publisher Correction: Continual integration of single-cell multimodal data with MIRACLE 出版商更正：单细胞多模态数据与MIRACLE的持续集成。

IF 20.3

Nature computational science Pub Date : 2026-08-26 DOI: 10.1038/s43588-026-01053-2

Jiahao Zhou, Jing Wang, Shuofeng Hu, Tongtong Kan, Chao Feng, Xiaohan Qiang, Guohua Dong, Jinhui Shi, Runyan Liu, Xiaochen Bo, Le Ou-Yang, Xiaomin Ying, Zhen He

引用次数: 0

A patient’s longitudinal history reconstructs their unmeasured molecular profile 病人的纵向病史重建了他们未测量的分子谱。

IF 20.3

Nature computational science Pub Date : 2026-08-26 DOI: 10.1038/s43588-026-01024-7

Stephanie Tanis, Samantha Lopez Alvarez, Natalie R. Davidson

引用次数: 0

Enhancing materials discovery with valence-constrained design in generative modeling. 增强材料发现与价约束设计在生成建模。

IF 20.3

Nature computational science Pub Date : 2026-08-26 DOI: 10.1038/s43588-026-01037-2

Mouyang Cheng, Weiliang Luo, Hao Tang, Bowen Yu, Yongqiang Cheng, Weiwei Xie, Ju Li, Heather J Kulik, Mingda Li

{"title":"Enhancing materials discovery with valence-constrained design in generative modeling.","authors":"Mouyang Cheng, Weiliang Luo, Hao Tang, Bowen Yu, Yongqiang Cheng, Weiwei Xie, Ju Li, Heather J Kulik, Mingda Li","doi":"10.1038/s43588-026-01037-2","DOIUrl":"https://doi.org/10.1038/s43588-026-01037-2","url":null,"abstract":"Diffusion-based deep generative models have emerged as powerful tools for inverse materials design. Yet many existing approaches overlook essential chemical constraints, such as oxidation-state balance, which can lead to chemically invalid structures. Here we introduce 'crystal generator with valence-constrained design' (CrysVCD), a modular framework that integrates chemical rules directly into the generative process. CrysVCD first uses a transformer-based elemental language model to generate valence-balanced compositions, followed by a diffusion model to generate crystal structures. The valence constraint enables orders-of-magnitude more efficient chemical valence checking compared with pure data-driven approaches with post-screening. When fine-tuned on stability metrics, CrysVCD achieves 85% metastability (Ehull < 0.1 eV per atom) and 68% phonon stability. Moreover, CrysVCD supports conditional generation of functional materials, enabling discovery of candidates such as high thermal conductivity semiconductors and high dielectric constant (high-κ) materials. Designed as a general-purpose plugin, CrysVCD can be integrated into diverse generative pipelines to promote chemical validity, offering a reliable, scientifically grounded path for materials discovery.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":20.3,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148835391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0