Nature Methods最新文献

英文中文

MultiCell: geometric learning in multicellular development. 多细胞：多细胞发育中的几何学习。

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-15 DOI: 10.1038/s41592-025-02983-x

Haiqian Yang, George Roy, Anh Q Nguyen, Dapeng Bi, Tomer Stern, Markus J Buehler, Ming Guo

During developmental processes such as embryogenesis, how a group of cells self-organizes into specific structures is a central question in biology. However, it remains a major challenge to understand and predict the behavior of every cell within the living tissue over time during such intricate processes. Here we present MultiCell, a geometric deep learning method that can accurately capture the highly convoluted interactions among cells. We demonstrate that multicellular data can be represented with both granular and foam-like physical pictures through a unified graph data structure, considering both cellular interactions and cell junction networks. Using this method, we achieve interpretable four-dimensional morphological sequence alignment and predict single-cell behaviors before they occur at single-cell resolution during Drosophila embryogenesis. Furthermore, using neural activation map and model ablation studies, we demonstrate that cell geometry and cell junction networks are essential features for predicting cell behaviors during morphogenesis. This method sets the stage for data-driven quantitative studies of dynamic multicellular developmental processes at single-cell precision, offering a proof-of-concept pathway toward a unified morphodynamic atlas.

在胚胎发生等发育过程中，一群细胞如何自我组织成特定的结构是生物学中的一个核心问题。然而，在如此复杂的过程中，理解和预测活组织内每个细胞随时间的行为仍然是一个重大挑战。在这里，我们提出了MultiCell，一种几何深度学习方法，可以准确地捕捉细胞之间高度复杂的相互作用。我们证明，考虑到细胞相互作用和细胞连接网络，通过统一的图形数据结构，多细胞数据可以用颗粒状和泡沫状的物理图像来表示。利用这种方法，我们实现了可解释的四维形态序列比对，并预测了果蝇胚胎发生过程中单细胞分辨率前的单细胞行为。此外，通过神经激活图和模型消融研究，我们证明了细胞几何和细胞连接网络是预测形态发生过程中细胞行为的基本特征。该方法为单细胞精度的动态多细胞发育过程的数据驱动定量研究奠定了基础，为统一的形态动力学图谱提供了概念验证途径。

{"title":"MultiCell: geometric learning in multicellular development.","authors":"Haiqian Yang, George Roy, Anh Q Nguyen, Dapeng Bi, Tomer Stern, Markus J Buehler, Ming Guo","doi":"10.1038/s41592-025-02983-x","DOIUrl":"10.1038/s41592-025-02983-x","url":null,"abstract":"<p><p>During developmental processes such as embryogenesis, how a group of cells self-organizes into specific structures is a central question in biology. However, it remains a major challenge to understand and predict the behavior of every cell within the living tissue over time during such intricate processes. Here we present MultiCell, a geometric deep learning method that can accurately capture the highly convoluted interactions among cells. We demonstrate that multicellular data can be represented with both granular and foam-like physical pictures through a unified graph data structure, considering both cellular interactions and cell junction networks. Using this method, we achieve interpretable four-dimensional morphological sequence alignment and predict single-cell behaviors before they occur at single-cell resolution during Drosophila embryogenesis. Furthermore, using neural activation map and model ablation studies, we demonstrate that cell geometry and cell junction networks are essential features for predicting cell behaviors during morphogenesis. This method sets the stage for data-driven quantitative studies of dynamic multicellular developmental processes at single-cell precision, offering a proof-of-concept pathway toward a unified morphodynamic atlas.</p>","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":" ","pages":""},"PeriodicalIF":32.1,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145763348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Systematic scRNA-seq screens profile neural organoid response to morphogens 系统scRNA-seq筛选分析神经类器官对形态因子的反应。

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-15 DOI: 10.1038/s41592-025-02927-5

Fátima Sanchís-Calleja, Nadezhda Azbukina, Akanksha Jain, Zhisong He, Ryoko Okamoto, Charlotte Rusimbi, Pedro Rifes, Gaurav Singh Rathore, Malgorzata Santel, Jasper Janssens, Makiko Seimiya, Benedikt Eisinger, Jonas Simon Fleck, Agnete Kirkeby, J. Gray Camp, Barbara Treutlein

Morphogens direct neuroepithelial fates toward discrete regional identities in vivo. Neural organoids provide models for studying neural regionalization through morphogen exposure; however, we lack a comprehensive survey of how the developing human neuroepithelium responds to morphogen cues. Here we produce a detailed survey of morphogen-induced effects on the regional specification of human neural organoids using multiplexed single-cell transcriptomic screens. We find that the timing, concentration and combination of morphogens strongly influence organoid cell-type and regional composition, and that cell line and neural induction method impact the response to a given morphogen condition. We apply concentration gradients in microfluidic chips or increasing static concentrations in multi-well plates and observe different patterning dynamics in each scenario. Altogether, we provide a detailed resource on neural lineage specification that, in combination with deep learning models, can enable the prediction of differentiation outcomes in human stem-cell-based systems. This Resource provides a detailed atlas of morphogen-induced responses in human neural organoids.

形态原在体内将神经上皮细胞的命运导向离散的区域特征。神经类器官通过形态素暴露为研究神经区域化提供了模型；然而，我们缺乏对发育中的人类神经上皮如何响应形态发生线索的全面调查。在这里，我们使用多路单细胞转录组筛选对形态诱导对人类神经类器官区域规格的影响进行了详细的调查。我们发现，形成因子的时间、浓度和组合强烈影响类器官细胞类型和区域组成，细胞系和神经诱导方法影响对给定形态因子条件的反应。我们在微流控芯片中应用浓度梯度或在多孔板中增加静态浓度，并在每种情况下观察到不同的模式动力学。总之，我们提供了神经谱系规范的详细资源，结合深度学习模型，可以预测人类干细胞系统的分化结果。

{"title":"Systematic scRNA-seq screens profile neural organoid response to morphogens","authors":"Fátima Sanchís-Calleja, Nadezhda Azbukina, Akanksha Jain, Zhisong He, Ryoko Okamoto, Charlotte Rusimbi, Pedro Rifes, Gaurav Singh Rathore, Malgorzata Santel, Jasper Janssens, Makiko Seimiya, Benedikt Eisinger, Jonas Simon Fleck, Agnete Kirkeby, J. Gray Camp, Barbara Treutlein","doi":"10.1038/s41592-025-02927-5","DOIUrl":"10.1038/s41592-025-02927-5","url":null,"abstract":"Morphogens direct neuroepithelial fates toward discrete regional identities in vivo. Neural organoids provide models for studying neural regionalization through morphogen exposure; however, we lack a comprehensive survey of how the developing human neuroepithelium responds to morphogen cues. Here we produce a detailed survey of morphogen-induced effects on the regional specification of human neural organoids using multiplexed single-cell transcriptomic screens. We find that the timing, concentration and combination of morphogens strongly influence organoid cell-type and regional composition, and that cell line and neural induction method impact the response to a given morphogen condition. We apply concentration gradients in microfluidic chips or increasing static concentrations in multi-well plates and observe different patterning dynamics in each scenario. Altogether, we provide a detailed resource on neural lineage specification that, in combination with deep learning models, can enable the prediction of differentiation outcomes in human stem-cell-based systems. This Resource provides a detailed atlas of morphogen-induced responses in human neural organoids.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 2","pages":"465-478"},"PeriodicalIF":32.1,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41592-025-02927-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145763331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Carta offers a computational approach to inference of differentiation maps from cell lineages. Carta提供了一种从细胞谱系推断分化图的计算方法。

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-15 DOI: 10.1038/s41592-025-02904-y

引用次数: 0

Computational strategies for cross-species knowledge transfer 跨物种知识转移的计算策略。

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-12 DOI: 10.1038/s41592-025-02931-9

Hao Yuan, Christopher A. Mancuso, Kayla Johnson, Ingo Braasch, Arjun Krishnan

Research organisms provide invaluable insights into human biology and diseases, serving as essential tools for functional experiments, disease modeling and drug testing. However, evolutionary divergence between humans and research organisms hinders effective knowledge transfer across species. Here, we review state-of-the-art methods for computationally transferring knowledge across species, primarily focusing on methods that use transcriptome data and/or molecular networks. Our Perspective addresses four key areas: (1) transferring disease and gene annotation knowledge across species, (2) identifying functionally equivalent molecular components, (3) inferring equivalent perturbed genes or gene sets and (4) identifying equivalent cell types. We conclude with an outlook on future directions and several key challenges that remain in cross-species knowledge transfer, including introducing the concept of ‘agnology’ to describe functional equivalence of biological entities, regardless of their evolutionary origins. This concept is becoming pervasive in integrative data-driven models in which evolutionary origins of functions can remain unresolved. This Perspective reviews computational methods for cross-species knowledge transfer and introduces ‘agnology’, a data-driven concept of functional equivalence independent of evolutionary origin.

研究生物体为人类生物学和疾病提供了宝贵的见解，是功能实验、疾病建模和药物测试的基本工具。然而，人类和研究生物之间的进化差异阻碍了物种间有效的知识转移。在这里，我们回顾了最先进的跨物种计算转移知识的方法，主要集中在使用转录组数据和/或分子网络的方法。我们的观点涉及四个关键领域：(1)跨物种转移疾病和基因注释知识；(2)鉴定功能等效的分子成分；(3)推断等效的扰动基因或基因集；(4)鉴定等效的细胞类型。最后，我们展望了跨物种知识转移的未来方向和几个关键挑战，包括引入“agnology”概念来描述生物实体的功能等效，无论其进化起源如何。这个概念在综合数据驱动的模型中越来越普遍，在这些模型中，功能的进化起源仍然无法解决。

{"title":"Computational strategies for cross-species knowledge transfer","authors":"Hao Yuan, Christopher A. Mancuso, Kayla Johnson, Ingo Braasch, Arjun Krishnan","doi":"10.1038/s41592-025-02931-9","DOIUrl":"10.1038/s41592-025-02931-9","url":null,"abstract":"Research organisms provide invaluable insights into human biology and diseases, serving as essential tools for functional experiments, disease modeling and drug testing. However, evolutionary divergence between humans and research organisms hinders effective knowledge transfer across species. Here, we review state-of-the-art methods for computationally transferring knowledge across species, primarily focusing on methods that use transcriptome data and/or molecular networks. Our Perspective addresses four key areas: (1) transferring disease and gene annotation knowledge across species, (2) identifying functionally equivalent molecular components, (3) inferring equivalent perturbed genes or gene sets and (4) identifying equivalent cell types. We conclude with an outlook on future directions and several key challenges that remain in cross-species knowledge transfer, including introducing the concept of ‘agnology’ to describe functional equivalence of biological entities, regardless of their evolutionary origins. This concept is becoming pervasive in integrative data-driven models in which evolutionary origins of functions can remain unresolved. This Perspective reviews computational methods for cross-species knowledge transfer and introduces ‘agnology’, a data-driven concept of functional equivalence independent of evolutionary origin.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 2","pages":"312-327"},"PeriodicalIF":32.1,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145743179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bio-friendly and high-precision super-resolution imaging through self-supervised reconstruction structured illumination microscopy 利用自监督重构结构照明显微镜进行生物友好、高精度的超分辨率成像。

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-12 DOI: 10.1038/s41592-025-02966-y

Jiahao Liu, Xue Dong, Huaide Lu, Tao Liu, Wei Liu, Xinyao Hu, Quan Meng, Amin Jiang, Tao Jiang, Xiaohan Geng, Haosen Liu, Jun Cheng, Edmund Y. Lam, Yan-Jun Liu, Shan Tan, Dong Li

Deep-learning-based structured illumination microscopy (SIM) has demonstrated substantial potential in long-term super-resolution imaging of biostructures, enabling the study of subcellular dynamics and interactions in live cells. However, the acquisition of ground-truth (GT) data for training poses inherent challenges, limiting its universal applicability. Current approaches without using GT training data compromise reconstruction fidelity and resolution, and the lack of physical priors in end-to-end networks further limits these qualities. Here we developed self-supervised reconstruction (SSR)-SIM by combining statistical analysis of reconstruction artifacts with structured light modulation priors to eliminate the need for GT and improve reconstruction precision. We validated SSR-SIM on common biological datasets and demonstrated that SSR-SIM enabled long-term recording of dynamic events, including cytoskeletal remodeling in cell adhesion, mitochondrial cristae remodeling, interactions between viral glycoprotein and endoplasmic reticulum, endocytic recycling of transferrin receptors, vaccinia-virus-induced actin comet remodeling, and mitochondrial intercellular transfer through tunneling nanotubes. Self-supervised reconstruction structured illumination microscopy (SSR-SIM) is a reconstruction approach for SIM that improves image reconstruction by including light modulation priors and information on reconstruction artifacts, while simultaneously eliminating the need for ground-truth images. The improvements allow long-term imaging of sensitive cellular processes.

基于深度学习的结构照明显微镜（SIM）在生物结构的长期超分辨率成像方面已经显示出巨大的潜力，能够研究活细胞中的亚细胞动力学和相互作用。然而，获取用于训练的ground-truth （GT）数据存在固有的挑战，限制了其普遍适用性。目前没有使用GT训练数据的方法会影响重建的保真度和分辨率，并且在端到端网络中缺乏物理先验进一步限制了这些质量。本文通过将重建伪影的统计分析与结构光调制先验相结合，开发了自监督重建(SSR)-SIM，从而消除了对GT的需求，提高了重建精度。我们在常见的生物学数据集上验证了SSR-SIM，并证明SSR-SIM能够长期记录动态事件，包括细胞粘附中的细胞骨架重塑、线粒体嵴重塑、病毒糖蛋白与内质网的相互作用、转铁蛋白受体的内吞循环、牛痘病毒诱导的肌动蛋白彗星重塑以及通过隧道纳米管的线粒体细胞间转移。

{"title":"Bio-friendly and high-precision super-resolution imaging through self-supervised reconstruction structured illumination microscopy","authors":"Jiahao Liu, Xue Dong, Huaide Lu, Tao Liu, Wei Liu, Xinyao Hu, Quan Meng, Amin Jiang, Tao Jiang, Xiaohan Geng, Haosen Liu, Jun Cheng, Edmund Y. Lam, Yan-Jun Liu, Shan Tan, Dong Li","doi":"10.1038/s41592-025-02966-y","DOIUrl":"10.1038/s41592-025-02966-y","url":null,"abstract":"Deep-learning-based structured illumination microscopy (SIM) has demonstrated substantial potential in long-term super-resolution imaging of biostructures, enabling the study of subcellular dynamics and interactions in live cells. However, the acquisition of ground-truth (GT) data for training poses inherent challenges, limiting its universal applicability. Current approaches without using GT training data compromise reconstruction fidelity and resolution, and the lack of physical priors in end-to-end networks further limits these qualities. Here we developed self-supervised reconstruction (SSR)-SIM by combining statistical analysis of reconstruction artifacts with structured light modulation priors to eliminate the need for GT and improve reconstruction precision. We validated SSR-SIM on common biological datasets and demonstrated that SSR-SIM enabled long-term recording of dynamic events, including cytoskeletal remodeling in cell adhesion, mitochondrial cristae remodeling, interactions between viral glycoprotein and endoplasmic reticulum, endocytic recycling of transferrin receptors, vaccinia-virus-induced actin comet remodeling, and mitochondrial intercellular transfer through tunneling nanotubes. Self-supervised reconstruction structured illumination microscopy (SSR-SIM) is a reconstruction approach for SIM that improves image reconstruction by including light modulation priors and information on reconstruction artifacts, while simultaneously eliminating the need for ground-truth images. The improvements allow long-term imaging of sensitive cellular processes.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 2","pages":"395-404"},"PeriodicalIF":32.1,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145743172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Benchmarking algorithms for generalizable single-cell perturbation response prediction 广义单细胞扰动响应预测的基准算法。

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-11 DOI: 10.1038/s41592-025-02980-0

Zhiting Wei, Yiheng Wang, Yicheng Gao, Shuguang Wang, Ping Li, Duanmiao Si, Yuli Gao, Siqi Wu, Danlu Li, Kejing Dong, Xingbo Yang, Chen Tang, Shaliu Fu, Xiaohan Chen, Wannian Li, Yuzhou You, Chen Zhang, Aibin Liang, Guohui Chuai, Qi Liu

Single-cell perturbation technologies enable systematic investigation of gene functions and regulatory networks with single-cell resolution. However, performing large-scale and combinatorial perturbation screens poses notable challenges due to their exponentially increased complexity. Computational methods, including foundation models, have been developed to predict perturbation effects. Yet despite claims of promising performance, concerns remain about their true efficacy, particularly when evaluated across diverse and previously unseen cellular contexts and perturbation scenarios. Here, we present a comprehensive benchmark of 27 methods for single-cell perturbation response prediction, evaluated across 29 datasets using 6 complementary performance metrics. By evaluating them under multiple scenarios, we systematically assess their generalizability, including that of emerging foundation models. Our results provide practical guidance for method selection and underscore the need for cellular context embedding approaches to enhance the generalizability of perturbation effect prediction in single-cell research. This analysis performs comprehensive comparisons of 27 single-cell perturbation response prediction methods using 29 datasets under different test scenarios and against multiple evaluation metrics.

单细胞摄动技术能够系统地研究基因功能和单细胞分辨率的调控网络。然而，由于其指数增长的复杂性，执行大规模和组合摄动筛选带来了显着的挑战。计算方法，包括基础模型，已经发展到预测扰动效应。然而，尽管声称具有良好的性能，但对其真正功效的担忧仍然存在，特别是在不同的和以前看不见的细胞环境和扰动情况下进行评估时。在这里，我们提出了27种单细胞扰动响应预测方法的综合基准，使用6个互补的性能指标对29个数据集进行了评估。通过在多个场景下对它们进行评估，我们系统地评估了它们的泛化性，包括新兴的基础模型。我们的结果为方法选择提供了实用的指导，并强调需要细胞上下文嵌入方法来增强单细胞研究中扰动效应预测的泛化性。

{"title":"Benchmarking algorithms for generalizable single-cell perturbation response prediction","authors":"Zhiting Wei, Yiheng Wang, Yicheng Gao, Shuguang Wang, Ping Li, Duanmiao Si, Yuli Gao, Siqi Wu, Danlu Li, Kejing Dong, Xingbo Yang, Chen Tang, Shaliu Fu, Xiaohan Chen, Wannian Li, Yuzhou You, Chen Zhang, Aibin Liang, Guohui Chuai, Qi Liu","doi":"10.1038/s41592-025-02980-0","DOIUrl":"10.1038/s41592-025-02980-0","url":null,"abstract":"Single-cell perturbation technologies enable systematic investigation of gene functions and regulatory networks with single-cell resolution. However, performing large-scale and combinatorial perturbation screens poses notable challenges due to their exponentially increased complexity. Computational methods, including foundation models, have been developed to predict perturbation effects. Yet despite claims of promising performance, concerns remain about their true efficacy, particularly when evaluated across diverse and previously unseen cellular contexts and perturbation scenarios. Here, we present a comprehensive benchmark of 27 methods for single-cell perturbation response prediction, evaluated across 29 datasets using 6 complementary performance metrics. By evaluating them under multiple scenarios, we systematically assess their generalizability, including that of emerging foundation models. Our results provide practical guidance for method selection and underscore the need for cellular context embedding approaches to enhance the generalizability of perturbation effect prediction in single-cell research. This analysis performs comprehensive comparisons of 27 single-cell perturbation response prediction methods using 29 datasets under different test scenarios and against multiple evaluation metrics.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 2","pages":"451-464"},"PeriodicalIF":32.1,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145743224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Scikit-bio: a fundamental Python library for biological omic data analysis 用于生物组学数据分析的基本Python库。

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-11 DOI: 10.1038/s41592-025-02981-z

Matthew Aton, Daniel McDonald, Jorge Cañardo Alastuey, Raeed Azom, Paarth Batra, Valentyn Bezshapkin, Evan Bolyen, Alexander Cagle, J. Gregory Caporaso, Justine W. Debelius, Kestrel Gorlick, Nirmitha Hamsanipally, Lars Hunger, Aryan Keluskar, Disen Liao, Yang Young Lu, Jose A. Navas-Molina, Anders Pitman, Jai Ram Rideout, Anton Sazonov, Bharath Sathappan, Karen Schwarzberg Lipson, Igor Sfiligoi, Chris Tapo, Yoshiki Vázquez-Baeza, Zijun Wu, Zhenjiang Zech Xu, Mingsong Sam Ye, Jianshu Zhao, Rob Knight, James T. Morton, Qiyun Zhu

引用次数: 0

Novae: a graph-based foundation model for spatial transcriptomics data Novae：一个基于图的空间转录组学数据基础模型

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-10 DOI: 10.1038/s41592-025-02899-6

Quentin Blampey, Hakim Benkirane, Nadège Bercovici, Kevin Mulder, Grégoire Gessain, Florent Ginhoux, Fabrice André, Paul-Henry Cournède

Spatial transcriptomics is advancing molecular biology by providing high-resolution insights into gene expression within the spatial context of tissues. This context is essential for identifying spatial domains, enabling the understanding of microenvironment organizations and their implications for tissue function and disease progression. To improve current model limitations on multiple slides, we have designed Novae ( https://github.com/MICS-Lab/novae ), a graph-based foundation model that extracts representations of cells within their spatial contexts. Our model was trained on a large dataset of nearly 30 million cells across 18 tissues, allowing Novae to perform zero-shot domain inference across multiple gene panels, tissues and technologies. Unlike other models, it also natively corrects batch effects and constructs a nested hierarchy of spatial domains. Furthermore, Novae supports various downstream tasks, including spatially variable gene or pathway analysis and spatial domain trajectory analysis. Overall, Novae provides a robust and versatile tool for advancing spatial transcriptomics and its applications in biomedical research. Novae, a self-supervised graph attention network, is a foundation model excelling at a diverse spectrum of spatial transcriptomics modeling and analysis tasks.

空间转录组学通过在组织的空间背景下提供高分辨率的基因表达见解，正在推进分子生物学。这一背景对于识别空间域至关重要，有助于理解微环境组织及其对组织功能和疾病进展的影响。为了改善目前在多张幻灯片上的模型限制，我们设计了Novae (https://github.com/MICS-Lab/novae)，这是一个基于图形的基础模型，可以在空间环境中提取细胞的表示。我们的模型是在18个组织中近3000万个细胞的大型数据集上进行训练的，这使得Novae能够跨多个基因面板、组织和技术执行零射击域推断。与其他模型不同的是，它还可以本地校正批处理效果并构建嵌套的空间域层次结构。此外，Novae还支持各种下游任务，包括空间可变基因或通路分析和空间域轨迹分析。总的来说，Novae为推进空间转录组学及其在生物医学研究中的应用提供了一个强大而通用的工具。Novae是一个自监督图注意网络，是一个擅长于多种空间转录组学建模和分析任务的基础模型。

{"title":"Novae: a graph-based foundation model for spatial transcriptomics data","authors":"Quentin Blampey, Hakim Benkirane, Nadège Bercovici, Kevin Mulder, Grégoire Gessain, Florent Ginhoux, Fabrice André, Paul-Henry Cournède","doi":"10.1038/s41592-025-02899-6","DOIUrl":"10.1038/s41592-025-02899-6","url":null,"abstract":"Spatial transcriptomics is advancing molecular biology by providing high-resolution insights into gene expression within the spatial context of tissues. This context is essential for identifying spatial domains, enabling the understanding of microenvironment organizations and their implications for tissue function and disease progression. To improve current model limitations on multiple slides, we have designed Novae ( https://github.com/MICS-Lab/novae ), a graph-based foundation model that extracts representations of cells within their spatial contexts. Our model was trained on a large dataset of nearly 30 million cells across 18 tissues, allowing Novae to perform zero-shot domain inference across multiple gene panels, tissues and technologies. Unlike other models, it also natively corrects batch effects and constructs a nested hierarchy of spatial domains. Furthermore, Novae supports various downstream tasks, including spatially variable gene or pathway analysis and spatial domain trajectory analysis. Overall, Novae provides a robust and versatile tool for advancing spatial transcriptomics and its applications in biomedical research. Novae, a self-supervised graph attention network, is a foundation model excelling at a diverse spectrum of spatial transcriptomics modeling and analysis tasks.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 12","pages":"2539-2550"},"PeriodicalIF":32.1,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145719853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Systematic evaluation of computational tools for multitype RNA modification detection using nanopore direct RNA sequencing 使用纳米孔直接RNA测序进行多类型RNA修饰检测的计算工具的系统评估。

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-10 DOI: 10.1038/s41592-025-02974-y

Tingting Luo, Moping Xu, Miao Wang, Faying Chen, Jiejun Shi

Nanopore direct RNA sequencing offers a versatile approach for detecting multiple types of RNA modifications at a single-base resolution. In this study, we systematically evaluate 86 computational tools for detecting six RNA modifications (m6A, Ψ, m5C, A-to-I editing, m7G and m1A) using direct RNA sequencing data from both RNA002 and RNA004 chemistries. We demonstrate that retraining tools with a combination of in vitro transcription and real biological samples notably enhances both accuracy and generalizability over their original implementations, especially for Ψ, m5C and A-to-I. Evaluations on real biological samples reveal that while m6A detection tools generally achieve high accuracy, non-m6A tools struggle with precision–recall balance, quantification accuracy and biological validity. Our findings highlight the importance of incorporating diverse training data and stress the need for tools capable of reliably distinguishing between modification types at single-base resolution. These insights provide a foundation for advancing RNA modification detection. This analysis benchmarked computational tools for RNA modification detection using nanopore direct RNA sequencing and showed that retraining with mixed in vitro transcription and real data improves performance.

纳米孔直接RNA测序提供了一种通用的方法来检测多种类型的RNA修饰在单碱基分辨率。在这项研究中，我们系统地评估了86种计算工具，用于检测六种RNA修饰（m6A， Ψ， m5C， A-to-I编辑，m7G和m1A），使用来自RNA002和RNA004化学的直接RNA测序数据。我们证明，结合体外转录和真实生物样本的再训练工具显著提高了其原始实现的准确性和通用性，特别是Ψ， m5C和a -to- i。对真实生物样品的评估表明，虽然m6A检测工具通常具有较高的准确性，但非m6A检测工具在精密度-召回率平衡、定量准确性和生物效度方面存在困难。我们的研究结果强调了合并不同训练数据的重要性，并强调需要能够在单碱基分辨率下可靠地区分修改类型的工具。这些见解为推进RNA修饰检测提供了基础。

{"title":"Systematic evaluation of computational tools for multitype RNA modification detection using nanopore direct RNA sequencing","authors":"Tingting Luo, Moping Xu, Miao Wang, Faying Chen, Jiejun Shi","doi":"10.1038/s41592-025-02974-y","DOIUrl":"10.1038/s41592-025-02974-y","url":null,"abstract":"Nanopore direct RNA sequencing offers a versatile approach for detecting multiple types of RNA modifications at a single-base resolution. In this study, we systematically evaluate 86 computational tools for detecting six RNA modifications (m6A, Ψ, m5C, A-to-I editing, m7G and m1A) using direct RNA sequencing data from both RNA002 and RNA004 chemistries. We demonstrate that retraining tools with a combination of in vitro transcription and real biological samples notably enhances both accuracy and generalizability over their original implementations, especially for Ψ, m5C and A-to-I. Evaluations on real biological samples reveal that while m6A detection tools generally achieve high accuracy, non-m6A tools struggle with precision–recall balance, quantification accuracy and biological validity. Our findings highlight the importance of incorporating diverse training data and stress the need for tools capable of reliably distinguishing between modification types at single-base resolution. These insights provide a foundation for advancing RNA modification detection. This analysis benchmarked computational tools for RNA modification detection using nanopore direct RNA sequencing and showed that retraining with mixed in vitro transcription and real data improves performance.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 2","pages":"438-450"},"PeriodicalIF":32.1,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145724208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FACED 2.0 enables large-scale voltage and calcium imaging in vivo. face2.0可实现体内大规模电压和钙成像。

IF 32.1 1区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Nature Methods

Pub Date : 2025-12-09 DOI: 10.1038/s41592-025-02925-7

Jian Zhong, Ryan G Natan, Qinrong Zhang, Justin S J Wong, Christoph Miehl, Krishnashish Bose, Xiaoyu Lu, François St-Pierre, Su Guo, Brent Doiron, Kevin K Tsia, Na Ji

Monitoring neuronal activity at large scale and high spatiotemporal resolution is crucial for understanding information processing within the brain. Here we optimized a kilohertz-frame-rate two-photon fluorescence microscope with an all-optical megahertz line-scan rate to achieve ultrafast imaging across large areas and volumes at subcellular resolution. Applying this technique to in vivo voltage and calcium imaging, we demonstrated simultaneous recording of voltage activity over 200 neurons and calcium activity over 14,000 neurons from the mouse visual cortex, as well as volumetric calcium imaging of the larval zebrafish brain.

在大尺度和高时空分辨率下监测神经元活动对于理解大脑内部的信息处理至关重要。在这里，我们优化了一种千赫兹帧率双光子荧光显微镜，具有全光兆赫线扫描速率，以实现亚细胞分辨率的大面积和体积的超快成像。将该技术应用于体内电压和钙成像，我们展示了同时记录小鼠视觉皮层200多个神经元的电压活动和14000多个神经元的钙活动，以及斑马鱼幼虫大脑的体积钙成像。

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Nature Methods

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀