Nature computational science最新文献_第8页

Transferable human mobility network reconstruction with neuroGravity 基于神经重力的可转移人类移动网络重建。

IF 20.3

Nature computational science Pub Date : 2026-06-12 DOI: 10.1038/s43588-026-01003-y

Jinming Yang, Shaoyu Huang, Zongyuan Huang, Yaohui Jin, Xiaokang Yang, Marta C. González, Yanyan Xu

{"title":"Transferable human mobility network reconstruction with neuroGravity","authors":"Jinming Yang, Shaoyu Huang, Zongyuan Huang, Yaohui Jin, Xiaokang Yang, Marta C. González, Yanyan Xu","doi":"10.1038/s43588-026-01003-y","DOIUrl":"10.1038/s43588-026-01003-y","url":null,"abstract":"Accurate modeling of human mobility is critical for tackling urban planning and public health challenges. In undeveloped regions, the absence of comprehensive travel surveys necessitates reconstructing mobility networks from publicly available data. Here we develop neuroGravity, a physics-informed deep learning model that reliably reconstructs mobility flows from limited observations and transfers to unobserved cities. Using only urban facility and population distributions, we find that neuroGravity’s regional representations strongly correlate with socioeconomic and livability status, offering scalable proxies for costly surveys. Furthermore, we uncover that spatial income segregation has a key role in model transferability: mobility networks are most reliably reconstructed when target cities share similar segregation levels with the source. We design an index to quantify this segregation and accurately predict transferability. Finally, we generate mobility flow proxies for over 1,200 cities worldwide, highlighting neuroGravity’s potential to mitigate critical data shortages in resource-limited, underdeveloped areas. This study presents neuroGravity—a model that merges physics with machine learning to reconstruct mobility networks in data-scarce regions. It provides crucial tools for equitable urban planning, revealing income segregation as a core determinant of human flows.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 6","pages":"630-641"},"PeriodicalIF":20.3,"publicationDate":"2026-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148240642","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

Reconstructing urban mobility from the built environment 从建筑环境重构城市交通。

IF 20.3

Nature computational science Pub Date : 2026-06-12 DOI: 10.1038/s43588-026-01005-w

Qi R. Wang

引用次数: 0

MetaSTAARlite: an all-in-one tool for biobank-scale whole-genome sequencing meta-analysis MetaSTAARlite：用于生物库规模全基因组测序荟萃分析的一体化工具。

IF 20.3

Nature computational science Pub Date : 2026-06-03 DOI: 10.1038/s43588-026-00995-x

Yohhan Kumarasinghe, Jacob Williams, Yuxin Yuan, Wenbo Wang, Julie-Alexia Dias, Haoyu Zhang, Zilin Li, Xihao Li

引用次数: 0

Elevating universal interatomic potentials with large-scale off-equilibrium data 利用大规模非平衡数据提高普遍原子间相互作用势。

IF 20.3

Nature computational science Pub Date : 2026-06-02 DOI: 10.1038/s43588-026-00994-y

Jiayu Peng

引用次数: 0

The Open Materials 2024 (OMat24) inorganic materials dataset and models 开放材料2024 （OMat24）无机材料数据集和模型。

IF 20.3

Nature computational science Pub Date : 2026-06-02 DOI: 10.1038/s43588-026-00996-w

Luis Barros-Luque, Muhammed Shuaibi, Xiang Fu, Brandon M. Wood, Misko Dzamba, Meng Gao, Ammar Rizvi, Matt Uyttendaele, C. Lawrence Zitnick, Zachary W. Ulissi

{"title":"The Open Materials 2024 (OMat24) inorganic materials dataset and models","authors":"Luis Barros-Luque, Muhammed Shuaibi, Xiang Fu, Brandon M. Wood, Misko Dzamba, Meng Gao, Ammar Rizvi, Matt Uyttendaele, C. Lawrence Zitnick, Zachary W. Ulissi","doi":"10.1038/s43588-026-00996-w","DOIUrl":"10.1038/s43588-026-00996-w","url":null,"abstract":"The discovery and simulation of inorganic materials is core to diverse applications from climate change to semiconductor manufacturing. Artificial intelligence has the potential to dramatically accelerate materials simulation, discovery and design. Although considerable progress has been made in developing training datasets and machine learning interatomic potential architectures, the state of the art in openly available and reproducible datasets and models has lagged behind proprietary models. Here, to address this issue, we present the Open Materials 2024 (OMat24) dataset, comprising over 110 million density functional theory calculations across diverse chemistries, materials and configurations. Machine learning interatomic potential models trained on OMat24 achieve leading performance on the Matbench-Discovery leaderboard, surpassing previous models with F1 scores above 0.9 for stability and approximately 20 meV per atom accuracy for formation energy. Models trained on OMat24 also exhibit high accuracy in newly developed thermal conductivity and phonon prediction task benchmarks. We show that OMat24’s diversity corrects the consistent softening bias of prior models trained on less diverse datasets, which systematically underpredicted energy, forces and derivative properties such as phonons. The OMat24 dataset has enabled the research community to develop improved model architectures, resulting in a step-change improvement in inorganic material property prediction accuracy. This Resource introduces the Open Materials 2024 (OMat24) dataset, offering more than 110 million diverse density functional theory calculations. AI models trained on OMat24 achieve a high accuracy and can eliminate systematic biases across model architectures.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 6","pages":"642-652"},"PeriodicalIF":20.3,"publicationDate":"2026-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148152493","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

Flow matching for fast, multi-purpose structure-based ligand generation for drug discovery 用于药物发现的快速、多用途的基于结构的配体生成的流量匹配。

IF 20.3

Nature computational science Pub Date : 2026-06-02 DOI: 10.1038/s43588-026-00997-9

引用次数: 0

Protein language models for structural biology 结构生物学的蛋白质语言模型

IF 18.3

Nature computational science Pub Date : 2026-05-28 DOI: 10.1038/s43588-026-00993-z

Chenxiao Xiang, Bin Cheng, Zhenling Peng, Jianyi Yang

引用次数: 0

Supporting early-career researchers in peer review 支持早期职业研究人员进行同行评议

IF 18.3

Nature computational science Pub Date : 2026-05-28 DOI: 10.1038/s43588-026-01001-0

引用次数: 0

FLOWR: flow matching for structure-aware de novo, interaction- and fragment-based ligand generation FLOWR：用于结构感知的从头开始，基于相互作用和片段的配体生成的流动匹配。

IF 20.3

Nature computational science Pub Date : 2026-05-28 DOI: 10.1038/s43588-026-00998-8

Julian Cremer, Ross Irwin, Alessandro Tibo, Jon Paul Janet, Simon Olsson, Djork-Arné Clevert

{"title":"FLOWR: flow matching for structure-aware de novo, interaction- and fragment-based ligand generation","authors":"Julian Cremer, Ross Irwin, Alessandro Tibo, Jon Paul Janet, Simon Olsson, Djork-Arné Clevert","doi":"10.1038/s43588-026-00998-8","DOIUrl":"10.1038/s43588-026-00998-8","url":null,"abstract":"Here we introduce FLOWR, a structure-based framework for the generation and optimization of three-dimensional ligands. FLOWR integrates continuous and categorical flow matching with equivariant optimal transport, enhanced by an efficient protein pocket conditioning. Alongside FLOWR, we present SPINDR, a curated dataset comprising ligand–pocket cocrystal complexes specifically designed to address existing data quality issues. Empirical evaluations demonstrate that FLOWR surpasses current state-of-the-art diffusion- and flow-based methods in terms of PoseBusters-validity, pose accuracy and interaction recovery, while offering an inference speed-up, achieving up to 70-fold faster performance. In addition, we introduce FLOWR.MULTI, a highly accurate multi-purpose model allowing for the targeted sampling of ligands that adhere to predefined interaction profiles and chemical substructures for fragment-based design without the need of retraining or any resampling strategies. Collectively, our results indicate that FLOWR and FLOWR.MULTI represent an advancement in artificial intelligence-driven structure-based drug design, substantially enhancing the reliability and applicability of de novo, interaction- and fragment-based ligand generation in real-world drug discovery settings. FLOWR combines continuous and categorical flow matching with equivariant optimal transport and a separate protein pocket encoder to improve validity, pose accuracy and interaction recovery at substantially faster inference speeds.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 6","pages":"565-574"},"PeriodicalIF":20.3,"publicationDate":"2026-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s43588-026-00998-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148058781","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

AI and the democratization of knowledge work 人工智能和知识工作的民主化。

IF 20.3

Nature computational science Pub Date : 2026-05-27 DOI: 10.1038/s43588-026-00985-z

Madeleine I. G. Daepp, Kiran Tomlinson, Scott Counts, Siddharth Suri

引用次数: 0