Nature computational science最新文献_第7页

Leveraging large language models for pandemic preparedness 利用大型语言模型防备大流行病。

IF 18.3

Nature computational science Pub Date : 2025-06-06 DOI: 10.1038/s43588-025-00805-w

Narendra M. Dixit

引用次数: 0

Advancing real-time infectious disease forecasting using large language models 使用大型语言模型推进实时传染病预测。

IF 18.3

Nature computational science Pub Date : 2025-06-06 DOI: 10.1038/s43588-025-00798-6

Hongru Du, Yang Zhao, Jianan Zhao, Shaochong Xu, Xihong Lin, Yiran Chen, Lauren M. Gardner, Hao ‘Frank’ Yang

{"title":"Advancing real-time infectious disease forecasting using large language models","authors":"Hongru Du, Yang Zhao, Jianan Zhao, Shaochong Xu, Xihong Lin, Yiran Chen, Lauren M. Gardner, Hao ‘Frank’ Yang","doi":"10.1038/s43588-025-00798-6","DOIUrl":"10.1038/s43588-025-00798-6","url":null,"abstract":"Forecasting the short-term spread of an ongoing disease outbreak poses a challenge owing to the complexity of contributing factors, some of which can be characterized through interlinked, multi-modality variables, and the intersection of public policy and human behavior. Here we introduce PandemicLLM, a framework with multi-modal large language models (LLMs) that reformulates real-time forecasting of disease spread as a text-reasoning problem, with the ability to incorporate real-time, complex, non-numerical information. This approach, through an artificial intelligence–human cooperative prompt design and time-series representation learning, encodes multi-modal data for LLMs. The model is applied to the COVID-19 pandemic, and trained to utilize textual public health policies, genomic surveillance, spatial and epidemiological time-series data, and is tested across all 50 states of the United States for a duration of 19 months. PandemicLLM opens avenues for incorporating various pandemic-related data in heterogeneous formats and shows performance benefits over existing models. PandemicLLM adapts the large language model to predict disease trends by converting diverse disease-relevant data into text. It responds to new variants in real time, offering robust, interpretable forecasts for effective public health responses.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 6","pages":"467-480"},"PeriodicalIF":18.3,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144251194","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

A committor-based method to uniformly sample rare reactive events 一种基于提交者的方法，用于统一采样罕见的反应事件。

IF 18.3

Nature computational science Pub Date : 2025-06-06 DOI: 10.1038/s43588-025-00825-6

引用次数: 0

Unified deep learning framework for many-body quantum chemistry via Green’s functions 基于格林函数的多体量子化学统一深度学习框架。

IF 18.3

Nature computational science Pub Date : 2025-06-04 DOI: 10.1038/s43588-025-00810-z

Christian Venturella, Jiachen Li, Christopher Hillenbrand, Ximena Leyva Peralta, Jessica Liu, Tianyu Zhu

{"title":"Unified deep learning framework for many-body quantum chemistry via Green’s functions","authors":"Christian Venturella, Jiachen Li, Christopher Hillenbrand, Ximena Leyva Peralta, Jessica Liu, Tianyu Zhu","doi":"10.1038/s43588-025-00810-z","DOIUrl":"10.1038/s43588-025-00810-z","url":null,"abstract":"Quantum many-body methods provide a systematic route to computing electronic properties of molecules and materials, but high computational costs restrict their use in large-scale applications. Owing to the complexity in many-electron wavefunctions, machine learning models capable of capturing fundamental many-body physics remain limited. Here we present a deep learning framework targeting the many-body Green’s function, which unifies predictions of electronic properties in ground and excited states, while offering physical insights into many-electron correlation effects. By learning the many-body perturbation theory or coupled-cluster self-energy from mean-field features, our graph neural network achieves competitive performance in predicting one- and two-particle excitations and quantities derivable from a one-particle density matrix. We demonstrate its high data efficiency and good transferability across chemical species, system sizes, molecular conformations and correlation strengths in bond breaking, through multiple molecular and nanomaterial benchmarks. This work opens up opportunities for utilizing machine learning to solve many-electron problems. A data-efficient deep learning model developed to predict ground-state and photophysical properties of molecules and nanomaterials by learning many-body Green’s functions achieves an accuracy surpassing the state-of-the-art density functional theory calculations.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 6","pages":"502-513"},"PeriodicalIF":18.3,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144227879","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

How molecular changes impact brain states and whole-brain activity: a multiscale approach 分子变化如何影响大脑状态和全脑活动：多尺度方法。

IF 18.3

Nature computational science Pub Date : 2025-06-02 DOI: 10.1038/s43588-025-00813-w

引用次数: 0

A computational approach to evaluate how molecular mechanisms impact large-scale brain activity 一种评估分子机制如何影响大规模大脑活动的计算方法。

IF 18.3

Nature computational science Pub Date : 2025-05-28 DOI: 10.1038/s43588-025-00796-8

Maria Sacha, Federico Tesler, Rodrigo Cofre, Alain Destexhe

{"title":"A computational approach to evaluate how molecular mechanisms impact large-scale brain activity","authors":"Maria Sacha, Federico Tesler, Rodrigo Cofre, Alain Destexhe","doi":"10.1038/s43588-025-00796-8","DOIUrl":"10.1038/s43588-025-00796-8","url":null,"abstract":"Assessing the impact of pharmaceutical compounds on brain activity is a critical issue in contemporary neuroscience. Currently, no systematic approach exists for evaluating these effects in whole-brain models, which typically focus on macroscopic phenomena, while pharmaceutical interventions operate at the molecular scale. Here we address this issue by presenting a computational approach for brain simulations using biophysically grounded mean-field models that integrate membrane conductances and synaptic receptors, showcased in the example of anesthesia. We show that anesthetics targeting GABAA and NMDA receptors can switch brain activity to generalized slow-wave patterns, as observed experimentally in deep anesthesia. To validate our models, we demonstrate that these slow-wave states exhibit reduced responsiveness to external stimuli and functional connectivity constrained by anatomical connectivity, mirroring experimental findings in anesthetized states across species. Our approach, founded on mean-field models that incorporate molecular realism, provides a robust framework for understanding how molecular-level drug actions impact whole-brain dynamics. A computational framework is introduced to study how molecular changes impact brain activity, using biophysically grounded mean-field models to evaluate how drugs acting on synaptic receptors lead to emergent changes in large-scale brain activity.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 5","pages":"405-417"},"PeriodicalIF":18.3,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12119344/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144175970","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

Algorithms for reliable decision-making need causal reasoning 可靠决策的算法需要因果推理。

IF 18.3

Nature computational science Pub Date : 2025-05-27 DOI: 10.1038/s43588-025-00814-9

Christoph Kern, Unai Fischer-Abaigar, Jonas Schweisthal, Dennis Frauen, Rayid Ghani, Stefan Feuerriegel, Mihaela van der Schaar, Frauke Kreuter

引用次数: 0

Interpretable niche-based cell‒cell communication inference using multi-view graph neural networks 利用多视图图神经网络可解释的基于小生境的细胞-细胞通信推理。

IF 18.3

Nature computational science Pub Date : 2025-05-27 DOI: 10.1038/s43588-025-00809-6

Juntian Qi, Zhengchao Luo, Chuan-Yun Li, Jinzhuo Wang, Wanqiu Ding

{"title":"Interpretable niche-based cell‒cell communication inference using multi-view graph neural networks","authors":"Juntian Qi, Zhengchao Luo, Chuan-Yun Li, Jinzhuo Wang, Wanqiu Ding","doi":"10.1038/s43588-025-00809-6","DOIUrl":"10.1038/s43588-025-00809-6","url":null,"abstract":"Cell‒cell communication (CCC) is a fundamental biological process for the harmonious functioning of biological systems. Increasing evidence indicates that cells of the same type or cluster may exhibit different interaction patterns under varying niches, yet most prevailing methods perform CCC inference at the cell type or cluster level while disregarding niche heterogeneity. Here we introduce the Spatial Transcriptomics-based cell‒cell Communication And Subtype Exploration (STCase) tool, which can describe CCC events at the single-cell/spot level based on spatial transcriptomics (ST). STCase includes an interpretable multi-view graph neural network via CCC-aware attention to identify niches for each cell type and uncover niche-specific CCC events. We show that STCase outperforms state-of-the-art approaches and accurately captures reported immune-related CCC events in human bronchial glands. We also identify three distinct niches of oral squamous cell carcinoma that may be obscured by agglomerative methods, and discover niche-specific CCC events that could influence tumor prognosis. An interpretable tool called STCase is introduced to leverage a multi-view graph neural network based on cell‒cell communication (CCC)-aware attention to uncover functional niche-specific CCC events based on spatial transcriptomics data.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 6","pages":"444-455"},"PeriodicalIF":18.3,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144163304","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 disruption endures 当破坏持续时。

IF 18.3

Nature computational science Pub Date : 2025-05-27 DOI: 10.1038/s43588-025-00812-x

Russell J. Funk, Xiangting Wu

引用次数: 0

Probabilistic photonic computing for AI 人工智能的概率光子计算。

IF 18.3

Nature computational science Pub Date : 2025-05-23 DOI: 10.1038/s43588-025-00800-1

Frank Brückerhoff-Plückelmann, Anna P. Ovvyan, Akhil Varri, Hendrik Borras, Bernhard Klein, Lennart Meyer, C. David Wright, Harish Bhaskaran, Ghazi Sarwat Syed, Abu Sebastian, Holger Fröning, Wolfram Pernice

{"title":"Probabilistic photonic computing for AI","authors":"Frank Brückerhoff-Plückelmann, Anna P. Ovvyan, Akhil Varri, Hendrik Borras, Bernhard Klein, Lennart Meyer, C. David Wright, Harish Bhaskaran, Ghazi Sarwat Syed, Abu Sebastian, Holger Fröning, Wolfram Pernice","doi":"10.1038/s43588-025-00800-1","DOIUrl":"10.1038/s43588-025-00800-1","url":null,"abstract":"Probabilistic computing excels in approximating combinatorial problems and modeling uncertainty. However, using conventional deterministic hardware for probabilistic models is challenging: (pseudo) random number generation introduces computational overhead and additional data shuffling. Therefore, there is a pressing need for different probabilistic computing architectures that achieve low latencies with reasonable energy consumption. Physical computing offers a promising solution, as these systems do not rely on an abstract deterministic representation of data but directly encode the information in physical quantities, enabling inherent probabilistic architectures utilizing entropy sources. Photonic computing is a prominent variant of physical computing due to the large available bandwidth, several orthogonal degrees of freedom for data encoding and optimal properties for in-memory computing and parallel data transfer. Here, we highlight key developments in physical photonic computing and photonic random number generation. We further provide insights into the realization of probabilistic photonic processors and their impact on artificial intelligence systems and future challenges. Physical computing, particularly photonic computing, offers a promising alternative by directly encoding data in physical quantities, enabling efficient probabilistic computing. This Perspective discusses the challenges and opportunities in photonic probabilistic computing and its applications in artificial intelligence.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 5","pages":"377-387"},"PeriodicalIF":18.3,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144133377","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