Nature computational science最新文献_第4页

SciToolAgent: a knowledge-graph-driven scientific agent for multitool integration. SciToolAgent：知识图驱动的科学代理，用于多工具集成。

IF 18.3

Nature computational science Pub Date : 2025-08-20 DOI: 10.1038/s43588-025-00849-y

Keyan Ding, Jing Yu, Junjie Huang, Yuchen Yang, Qiang Zhang, Huajun Chen

{"title":"SciToolAgent: a knowledge-graph-driven scientific agent for multitool integration.","authors":"Keyan Ding, Jing Yu, Junjie Huang, Yuchen Yang, Qiang Zhang, Huajun Chen","doi":"10.1038/s43588-025-00849-y","DOIUrl":"https://doi.org/10.1038/s43588-025-00849-y","url":null,"abstract":"Scientific research increasingly relies on specialized computational tools, yet effectively utilizing these tools requires substantial domain expertise. While large language models show promise in tool automation, they struggle to seamlessly integrate and orchestrate multiple tools for complex scientific workflows. Here we present SciToolAgent, a large language model-powered agent that automates hundreds of scientific tools across biology, chemistry and materials science. At its core, SciToolAgent leverages a scientific tool knowledge graph that enables intelligent tool selection and execution through graph-based retrieval-augmented generation. The agent also incorporates a comprehensive safety-checking module to ensure responsible and ethical tool usage. Extensive evaluations on a curated benchmark demonstrate that SciToolAgent outperforms existing approaches. Case studies in protein engineering, chemical reactivity prediction, chemical synthesis and metal-organic framework screening further demonstrate SciToolAgent's capability to automate complex scientific workflows, making advanced research tools accessible to both experts and nonexperts.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":18.3,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981676","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

Engineering morphogenesis of cell clusters with differentiable programming. 可微规划细胞簇的工程形态发生。

IF 18.3

Nature computational science Pub Date : 2025-08-13 DOI: 10.1038/s43588-025-00851-4

Ramya Deshpande, Francesco Mottes, Ariana-Dalia Vlad, Michael P Brenner, Alma Dal Co

引用次数: 0

Probing the limitations of multimodal language models for chemistry and materials research. 探讨多模态语言模型在化学和材料研究中的局限性。

IF 18.3

Nature computational science Pub Date : 2025-08-11 DOI: 10.1038/s43588-025-00836-3

Nawaf Alampara, Mara Schilling-Wilhelmi, Martiño Ríos-García, Indrajeet Mandal, Pranav Khetarpal, Hargun Singh Grover, N M Anoop Krishnan, Kevin Maik Jablonka

{"title":"Probing the limitations of multimodal language models for chemistry and materials research.","authors":"Nawaf Alampara, Mara Schilling-Wilhelmi, Martiño Ríos-García, Indrajeet Mandal, Pranav Khetarpal, Hargun Singh Grover, N M Anoop Krishnan, Kevin Maik Jablonka","doi":"10.1038/s43588-025-00836-3","DOIUrl":"10.1038/s43588-025-00836-3","url":null,"abstract":"Recent advancements in artificial intelligence have sparked interest in scientific assistants that could support researchers across the full spectrum of scientific workflows, from literature review to experimental design and data analysis. A key capability for such systems is the ability to process and reason about scientific information in both visual and textual forms-from interpreting spectroscopic data to understanding laboratory set-ups. Here we introduce MaCBench, a comprehensive benchmark for evaluating how vision language models handle real-world chemistry and materials science tasks across three core aspects: data extraction, experimental execution and results interpretation. Through a systematic evaluation of leading models, we find that although these systems show promising capabilities in basic perception tasks-achieving near-perfect performance in equipment identification and standardized data extraction-they exhibit fundamental limitations in spatial reasoning, cross-modal information synthesis and multi-step logical inference. Our insights have implications beyond chemistry and materials science, suggesting that developing reliable multimodal AI scientific assistants may require advances in curating suitable training data and approaches to training those models.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":18.3,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144823355","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

Arti-‘fickle’ intelligence: using LLMs as a tool for inference in the political and social sciences “善变”的智慧：利用法学硕士作为政治和社会科学推理的工具。

IF 18.3

Nature computational science Pub Date : 2025-08-08 DOI: 10.1038/s43588-025-00843-4

Lisa P. Argyle, Ethan C. Busby, Joshua R. Gubler, Bryce Hepner, Alex Lyman, David Wingate

引用次数: 0

Experimenting on AI can (sometimes) teach us about ourselves 对人工智能进行实验（有时）可以让我们了解自己。

IF 18.3

Nature computational science Pub Date : 2025-08-07 DOI: 10.1038/s43588-025-00838-1

Austin van Loon, Zoe Heidenry

引用次数: 0

A comprehensive mapping of zeolite–template chemical space 沸石模板化学空间的综合制图。

IF 18.3

Nature computational science Pub Date : 2025-08-07 DOI: 10.1038/s43588-025-00842-5

Mingrou Xie, Daniel Schwalbe-Koda, Yolanda Marcela Semanate-Esquivel, Estefanía Bello-Jurado, Alexander Hoffman, Omar Santiago-Reyes, Cecilia Paris, Manuel Moliner, Rafael Gómez-Bombarelli

{"title":"A comprehensive mapping of zeolite–template chemical space","authors":"Mingrou Xie, Daniel Schwalbe-Koda, Yolanda Marcela Semanate-Esquivel, Estefanía Bello-Jurado, Alexander Hoffman, Omar Santiago-Reyes, Cecilia Paris, Manuel Moliner, Rafael Gómez-Bombarelli","doi":"10.1038/s43588-025-00842-5","DOIUrl":"10.1038/s43588-025-00842-5","url":null,"abstract":"Zeolites are industrially important catalysts and adsorbents, typically synthesized using specific molecules known as organic structure-directing agents (OSDAs). The templating effect of the OSDAs is pivotal in determining the zeolite polymorph formed and its physicochemical properties. However, de novo design of selective OSDAs is challenging because of the diversity and size of the zeolite–OSDA chemical space. Here we present ZeoBind, a computational workflow powered by machine learning that enables an exhaustive exploration of the OSDA space. We design predictive tasks that capture zeolite–molecule matching, train predictive models for these tasks on hundreds of thousands of datapoints and curate a library of 2.3 million synthetically accessible, hypothetical OSDA-like molecules enumerated from commercially available precursors. We use ZeoBind to screen nearly 500 million zeolite–molecule pairs and identified and experimentally validated two new OSDAs that template zeolites with novel compositions. The scale of the OSDA library, along with the open-access tools and data, has the potential to accelerate OSDA design for zeolite synthesis. ZeoBind is developed for high-throughput molecule screening in zeolite synthesis. Here 2.3 million organic structure-directing agents are enumerated and predictive models for binding affinity are developed; the screening is experimentally validated for two zeolites.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 8","pages":"661-674"},"PeriodicalIF":18.3,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144801128","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

Diving deep into zeolite space 深入沸石空间。

IF 18.3

Nature computational science Pub Date : 2025-08-07 DOI: 10.1038/s43588-025-00831-8

David Balcells

引用次数: 0

Virtual brain twins for stimulation in epilepsy 虚拟脑双胞胎刺激癫痫。

IF 18.3

Nature computational science Pub Date : 2025-08-05 DOI: 10.1038/s43588-025-00841-6

Huifang E. Wang, Borana Dollomaja, Paul Triebkorn, Gian Marco Duma, Adam Williamson, Julia Makhalova, Jean-Didier Lemarechal, Fabrice Bartolomei, Viktor Jirsa

{"title":"Virtual brain twins for stimulation in epilepsy","authors":"Huifang E. Wang, Borana Dollomaja, Paul Triebkorn, Gian Marco Duma, Adam Williamson, Julia Makhalova, Jean-Didier Lemarechal, Fabrice Bartolomei, Viktor Jirsa","doi":"10.1038/s43588-025-00841-6","DOIUrl":"10.1038/s43588-025-00841-6","url":null,"abstract":"Estimating the epileptogenic zone network (EZN) is an important part of the diagnosis of drug-resistant focal epilepsy and has a pivotal role in treatment and intervention. Virtual brain twins provide a modeling method for personalized diagnosis and treatment. They integrate patient-specific brain topography with structural connectivity from anatomical neuroimaging such as magnetic resonance imaging, and dynamic activity from functional recordings such as electroencephalography (EEG) and stereo-EEG (SEEG). Seizures show rich spatial and temporal features in functional recordings, which can be exploited to estimate the EZN. Stimulation-induced seizures can provide important and complementary information. Here we consider invasive SEEG stimulation and non-invasive temporal interference stimulation as a complementary approach. This paper offers a high-resolution virtual brain twin framework for EZN diagnosis based on stimulation-induced seizures. It provides an important methodological and conceptual basis to make the transition from invasive to non-invasive diagnosis and treatment of drug-resistant focal epilepsy. A high-resolution virtual brain twin approach is proposed using stimulation-induced seizures to estimate the epileptogenic network, offering a step toward non-invasive diagnosis and treatment of drug-resistant focal epilepsy.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 9","pages":"754-768"},"PeriodicalIF":18.3,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s43588-025-00841-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144790951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient modeling of ionic and electronic interactions by a resistive memory-based reservoir graph neural network. 基于电阻记忆的储层图神经网络对离子和电子相互作用的有效建模。

IF 18.3

Nature computational science Pub Date : 2025-08-01 DOI: 10.1038/s43588-025-00844-3

Meng Xu, Shaocong Wang, Yangu He, Yi Li, Woyu Zhang, Ming Yang, Xiaojuan Qi, Zhongrui Wang, Ming Xu, Dashan Shang, Qi Liu, Xiangshui Miao, Ming Liu

{"title":"Efficient modeling of ionic and electronic interactions by a resistive memory-based reservoir graph neural network.","authors":"Meng Xu, Shaocong Wang, Yangu He, Yi Li, Woyu Zhang, Ming Yang, Xiaojuan Qi, Zhongrui Wang, Ming Xu, Dashan Shang, Qi Liu, Xiangshui Miao, Ming Liu","doi":"10.1038/s43588-025-00844-3","DOIUrl":"https://doi.org/10.1038/s43588-025-00844-3","url":null,"abstract":"Current quantum chemistry and materials science are dominated by first-principles methodologies such as density functional theory. However, these approaches face substantial computational costs as system scales up. In addition, the von Neumann bottleneck of digital computers imposes energy efficiency limitations. Here we propose a software-hardware co-design: the resistive memory-based reservoir graph neural network for efficient modeling of ionic and electronic interactions. Software-wise, the reservoir graph neural network is evaluated for computational tasks, including atomic force, Hamiltonian and wavefunction prediction, achieving comparable accuracy while reducing computational costs by approximately 104-, 106- and 103-fold, respectively, compared with traditional first-principles methods. Moreover, it reduces training costs by approximately 90% due to reservoir computing. Hardware-wise, validated on a 40-nm 256-kb in-memory computing macro, our co-design achieves improvements in area-normalized inference speed by approximately 2.5-, 2.5- and 2.7-fold, and inference energy efficiency by approximately 2.7, 1.9 and 4.4 times, compared with state-of-the-art digital hardware, respectively.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":18.3,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144765877","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

Threats to scientific software from over-reliance on AI code assistants 过度依赖人工智能代码助手对科学软件的威胁。

IF 18.3

Nature computational science Pub Date : 2025-07-25 DOI: 10.1038/s43588-025-00845-2

Gabrielle O’Brien

引用次数: 0