Pub Date : 2025-12-02DOI: 10.1038/s41592-025-02911-z
Shihang Luo (, ), Xian’ao Zhao (, ), Yuanyuan Li (, ), Chunyan Fan (, ), Ruina Liu (, ), Ran Gong (, ), Weixing Li (, ), Nana Ma (, ), Zhenghong Yang (, ), Tao Xu (, ), Wei Ji (, ), Lusheng Gu (, )
Three-dimensional (3D) nanoscale imaging reveals the detailed morphology of subcellular structures; however, conventional single-molecule localization microscopy is constrained by limited axial resolution. Here we introduce ROSE-3D, an interferometric localization approach that enables isotropic 3D super-resolution imaging with uniform performance across the entire depth of field. Compared with conventional astigmatism-based methods, ROSE-3D improves lateral localization precision by 2–6 times and axial precision by 3.5–8 times over a depth of field of approximately 1.2 μm. Leveraging its multicolor and whole-cell imaging capabilities, ROSE-3D resolves, in situ, the nanoscale organization of nuclear lamins and the assemblies of mitochondrial fission-related protein DRP1. These results establish ROSE-3D as a powerful tool for interrogating nanoscale cellular architecture. ROSE-3D is a single-molecule localization microscopy approach that achieves high isotropic resolution via interferometric localization. The approach is capable of whole-cell and multicolor imaging.
{"title":"Molecular-scale isotropic 3D super-resolution microscopy via interference localization","authors":"Shihang Luo \u0000 (, ), Xian’ao Zhao \u0000 (, ), Yuanyuan Li \u0000 (, ), Chunyan Fan \u0000 (, ), Ruina Liu \u0000 (, ), Ran Gong \u0000 (, ), Weixing Li \u0000 (, ), Nana Ma \u0000 (, ), Zhenghong Yang \u0000 (, ), Tao Xu \u0000 (, ), Wei Ji \u0000 (, ), Lusheng Gu \u0000 (, )","doi":"10.1038/s41592-025-02911-z","DOIUrl":"10.1038/s41592-025-02911-z","url":null,"abstract":"Three-dimensional (3D) nanoscale imaging reveals the detailed morphology of subcellular structures; however, conventional single-molecule localization microscopy is constrained by limited axial resolution. Here we introduce ROSE-3D, an interferometric localization approach that enables isotropic 3D super-resolution imaging with uniform performance across the entire depth of field. Compared with conventional astigmatism-based methods, ROSE-3D improves lateral localization precision by 2–6 times and axial precision by 3.5–8 times over a depth of field of approximately 1.2 μm. Leveraging its multicolor and whole-cell imaging capabilities, ROSE-3D resolves, in situ, the nanoscale organization of nuclear lamins and the assemblies of mitochondrial fission-related protein DRP1. These results establish ROSE-3D as a powerful tool for interrogating nanoscale cellular architecture. ROSE-3D is a single-molecule localization microscopy approach that achieves high isotropic resolution via interferometric localization. The approach is capable of whole-cell and multicolor imaging.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 1","pages":"183-192"},"PeriodicalIF":32.1,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145661543","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}
Pub Date : 2025-12-02DOI: 10.1038/s41592-025-02972-0
Gerard G. Lambert, Emmanuel L. Crespo, Jeremy Murphy, Kevin L. Turner, Emily Gershowitz, Michaela Cunningham, Daniela Boassa, Selena Luong, Dmitrijs Celinskis, Justine J. Allen, Stephanie Venn, Yunlu Zhu, Mürsel Karadas, Jiakun Chen, Roberta Marisca, Hannah Gelnaw, Daniel K. Nguyen, Junru Hu, Brittany N. Sprecher, Maya O. Tree, Richard Orcutt, Daniel Heydari, Aidan B. Bell, Albertina Torreblanca-Zanca, Ali Hakimi, Tim Czopka, Shy Shoham, Katherine I. Nagel, David Schoppik, Arturo Andrade, Diane Lipscombe, Christopher I. Moore, Ute Hochgeschwender, Nathan C. Shaner
Monitoring intracellular calcium is central to understanding cell signaling across nearly all cell types and organisms. Fluorescent genetically encoded calcium indicators (GECIs) remain the standard tools for in vivo calcium imaging, but require intense excitation light, leading to photobleaching, background autofluorescence and phototoxicity. Bioluminescent GECIs, which generate light enzymatically, eliminate these artifacts but have been constrained by low dynamic range and suboptimal calcium affinities. Here we show that CaBLAM (‘calcium bioluminescence activity monitor’), an engineered bioluminescent calcium indicator, achieves an order-of-magnitude improvement in signal contrast and a tunable affinity matched to physiological cytosolic calcium. CaBLAM enables single-cell and subcellular activity imaging at video frame rates in cultured neurons and sustained imaging over hours in awake, behaving animals. These capabilities establish CaBLAM as a robust and general alternative to fluorescent GECIs, extending calcium imaging to regimes where excitation light is undesirable or infeasible. CaBLAM is a bioluminescent genetically encoded calcium indicator that delivers high-contrast signals as shown in cell culture, in the in vivo mouse brain and in zebrafish larvae.
{"title":"CaBLAM: a high-contrast bioluminescent Ca2+ indicator derived from an engineered Oplophorus gracilirostris luciferase","authors":"Gerard G. Lambert, Emmanuel L. Crespo, Jeremy Murphy, Kevin L. Turner, Emily Gershowitz, Michaela Cunningham, Daniela Boassa, Selena Luong, Dmitrijs Celinskis, Justine J. Allen, Stephanie Venn, Yunlu Zhu, Mürsel Karadas, Jiakun Chen, Roberta Marisca, Hannah Gelnaw, Daniel K. Nguyen, Junru Hu, Brittany N. Sprecher, Maya O. Tree, Richard Orcutt, Daniel Heydari, Aidan B. Bell, Albertina Torreblanca-Zanca, Ali Hakimi, Tim Czopka, Shy Shoham, Katherine I. Nagel, David Schoppik, Arturo Andrade, Diane Lipscombe, Christopher I. Moore, Ute Hochgeschwender, Nathan C. Shaner","doi":"10.1038/s41592-025-02972-0","DOIUrl":"10.1038/s41592-025-02972-0","url":null,"abstract":"Monitoring intracellular calcium is central to understanding cell signaling across nearly all cell types and organisms. Fluorescent genetically encoded calcium indicators (GECIs) remain the standard tools for in vivo calcium imaging, but require intense excitation light, leading to photobleaching, background autofluorescence and phototoxicity. Bioluminescent GECIs, which generate light enzymatically, eliminate these artifacts but have been constrained by low dynamic range and suboptimal calcium affinities. Here we show that CaBLAM (‘calcium bioluminescence activity monitor’), an engineered bioluminescent calcium indicator, achieves an order-of-magnitude improvement in signal contrast and a tunable affinity matched to physiological cytosolic calcium. CaBLAM enables single-cell and subcellular activity imaging at video frame rates in cultured neurons and sustained imaging over hours in awake, behaving animals. These capabilities establish CaBLAM as a robust and general alternative to fluorescent GECIs, extending calcium imaging to regimes where excitation light is undesirable or infeasible. CaBLAM is a bioluminescent genetically encoded calcium indicator that delivers high-contrast signals as shown in cell culture, in the in vivo mouse brain and in zebrafish larvae.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 1","pages":"205-215"},"PeriodicalIF":32.1,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41592-025-02972-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145661586","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}
Pub Date : 2025-12-02DOI: 10.1038/s41592-025-02944-4
Roman Kiselev, Ryan A. Brady, Arnab Modak, F. Aaron Cruz-Navarrete, Jose L. Alejo, Daniel S. Terry, Roger B. Altman, Wesley B. Asher, Jonathan A. Javitch, Scott C. Blanchard
Single-molecule imaging techniques have provided unprecedented insights into functional changes in composition and conformation across diverse biological systems. As with other biophysical methods, single-molecule fluorescence and Förster resonance energy transfer investigations are typically limited to examination of one sample at a time. Consequently, experimental throughput is restricted, and experimental variances are introduced that can obscure functional distinctions in closely related systems. Here, to address these limitations, we introduce parallel rapid exchange single-molecule fluorescence and single-molecule Förster resonance energy transfer to enable simultaneous steady-state and pre-steady-state interrogations of diverse systems. Using this approach, we elucidate the timing of distinct conformational events underpinning β-arrestin1 activation, unmask antibiotic-induced impacts on messenger RNA decoding fidelity and demonstrate that endogenously encoded ribosomal RNA sequence variation modulates antibiotic sensitivity. This generalizable and scalable method promises to broaden the scope and reproducibility of quantitative single-molecule interrogations of biomolecular function. Parallelized single-molecule fluorescence and single-molecule FRET experiments enable quantitative biophysics investigations of molecular function from multiple samples in a single experiment.
{"title":"Parallel stopped-flow interrogation of diverse biological systems at the single-molecule scale","authors":"Roman Kiselev, Ryan A. Brady, Arnab Modak, F. Aaron Cruz-Navarrete, Jose L. Alejo, Daniel S. Terry, Roger B. Altman, Wesley B. Asher, Jonathan A. Javitch, Scott C. Blanchard","doi":"10.1038/s41592-025-02944-4","DOIUrl":"10.1038/s41592-025-02944-4","url":null,"abstract":"Single-molecule imaging techniques have provided unprecedented insights into functional changes in composition and conformation across diverse biological systems. As with other biophysical methods, single-molecule fluorescence and Förster resonance energy transfer investigations are typically limited to examination of one sample at a time. Consequently, experimental throughput is restricted, and experimental variances are introduced that can obscure functional distinctions in closely related systems. Here, to address these limitations, we introduce parallel rapid exchange single-molecule fluorescence and single-molecule Förster resonance energy transfer to enable simultaneous steady-state and pre-steady-state interrogations of diverse systems. Using this approach, we elucidate the timing of distinct conformational events underpinning β-arrestin1 activation, unmask antibiotic-induced impacts on messenger RNA decoding fidelity and demonstrate that endogenously encoded ribosomal RNA sequence variation modulates antibiotic sensitivity. This generalizable and scalable method promises to broaden the scope and reproducibility of quantitative single-molecule interrogations of biomolecular function. Parallelized single-molecule fluorescence and single-molecule FRET experiments enable quantitative biophysics investigations of molecular function from multiple samples in a single experiment.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 1","pages":"78-87"},"PeriodicalIF":32.1,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41592-025-02944-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145661501","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}
Pub Date : 2025-12-01DOI: 10.1038/s41592-025-02918-6
Sumeer Ahmad Khan, Xabier Martínez-de-Morentin, Abdel Rahman Alsabbagh, Alberto Maillo, Vincenzo Lagani, David Gomez-Cabrero, Robert Lehmann, Jesper Tegner
Transformer-based models are rapidly becoming foundational tools for analyzing and integrating multiscale biological data. This Perspective examines recent advances in transformer architectures, tracing their evolution from unimodal and augmented unimodal models to large-scale multimodal foundation models operating across genomic sequences, single-cell transcriptomics and spatial data. We categorize these models into three tiers and evaluate their capabilities for structural learning, representation transfer and tasks such as cell annotation, prediction and imputation. While discussing tokenization, interpretability and scalability challenges, we highlight emerging approaches that leverage masked modeling, contrastive learning and large language models. To support broader adoption, we provide practical guidance through code-based primers, using public datasets and open-source implementations. Finally, we propose designing a modular ‘Super Transformer’ architecture using cross-attention mechanisms to integrate heterogeneous modalities. This Perspective serves as a resource and roadmap for leveraging transformer models in multiscale, multimodal genomics. This Perspective overviews recent and emerging developments in building and using multimodal foundation models based on transformers for analyzing various types of genomics data.
{"title":"Multimodal foundation transformer models for multiscale genomics","authors":"Sumeer Ahmad Khan, Xabier Martínez-de-Morentin, Abdel Rahman Alsabbagh, Alberto Maillo, Vincenzo Lagani, David Gomez-Cabrero, Robert Lehmann, Jesper Tegner","doi":"10.1038/s41592-025-02918-6","DOIUrl":"10.1038/s41592-025-02918-6","url":null,"abstract":"Transformer-based models are rapidly becoming foundational tools for analyzing and integrating multiscale biological data. This Perspective examines recent advances in transformer architectures, tracing their evolution from unimodal and augmented unimodal models to large-scale multimodal foundation models operating across genomic sequences, single-cell transcriptomics and spatial data. We categorize these models into three tiers and evaluate their capabilities for structural learning, representation transfer and tasks such as cell annotation, prediction and imputation. While discussing tokenization, interpretability and scalability challenges, we highlight emerging approaches that leverage masked modeling, contrastive learning and large language models. To support broader adoption, we provide practical guidance through code-based primers, using public datasets and open-source implementations. Finally, we propose designing a modular ‘Super Transformer’ architecture using cross-attention mechanisms to integrate heterogeneous modalities. This Perspective serves as a resource and roadmap for leveraging transformer models in multiscale, multimodal genomics. This Perspective overviews recent and emerging developments in building and using multimodal foundation models based on transformers for analyzing various types of genomics data.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 2","pages":"299-311"},"PeriodicalIF":32.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145654571","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}
Pub Date : 2025-12-01DOI: 10.1038/s41592-025-02940-8
The plant cell wall makes the preparation of high-quality cells for single-cell RNA sequencing challenging. To tackle this issue, we developed FX-Cell, a method that enables the enzymatic digestion of the cell wall at high temperatures to result in high-quality single plant cells for transcriptome analysis.
{"title":"Next-generation method for preparing plant cells for single-cell RNA sequencing","authors":"","doi":"10.1038/s41592-025-02940-8","DOIUrl":"10.1038/s41592-025-02940-8","url":null,"abstract":"The plant cell wall makes the preparation of high-quality cells for single-cell RNA sequencing challenging. To tackle this issue, we developed FX-Cell, a method that enables the enzymatic digestion of the cell wall at high temperatures to result in high-quality single plant cells for transcriptome analysis.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 12","pages":"2506-2507"},"PeriodicalIF":32.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145654483","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}
Pub Date : 2025-12-01DOI: 10.1038/s41592-025-02917-7
We introduce the Cryo-EM Image Evaluation Foundation (Cryo-IEF) model, which has been pretrained on 65 million particle images in an unsupervised manner. Cryo-IEF excels in diverse cryogenic electron microscopy data-processing tasks; it automates the complex workflow and makes this technology more accessible and robust.
{"title":"Artificial intelligence foundation model automates cryo-EM structure determination","authors":"","doi":"10.1038/s41592-025-02917-7","DOIUrl":"10.1038/s41592-025-02917-7","url":null,"abstract":"We introduce the Cryo-EM Image Evaluation Foundation (Cryo-IEF) model, which has been pretrained on 65 million particle images in an unsupervised manner. Cryo-IEF excels in diverse cryogenic electron microscopy data-processing tasks; it automates the complex workflow and makes this technology more accessible and robust.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 1","pages":"26-27"},"PeriodicalIF":32.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145653357","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}
Pub Date : 2025-11-28DOI: 10.1038/s41592-025-02928-4
Lindsey N. Young, Alice Sherrard, Huabin Zhou, Farhaz Shaikh, Joshua Hutchings, Margot Riggi, Mythreyi Narasimhan, W. Alexander Flaherty, Eric J. Bennett, Michael K. Rosen, Antonio J. Giraldez, Elizabeth Villa
In situ cryo-electron microscopy (cryo-EM) enables the direct interrogation of structure–function relationships by resolving macromolecular structures in their native cellular environment. Recent progress in sample preparation, imaging and data processing has enabled the identification and determination of large biomolecular complexes. However, the majority of proteins are of a size that still eludes identification in cellular cryo-EM data, and most proteins exist in low copy numbers. Therefore, novel tools are needed for cryo-EM to identify macromolecules across multiple size scales (from microns to nanometers). Here we introduce nanogold probes for detecting specific proteins using correlative light and electron microscopy, cryo-electron tomography (cryo-ET) and resin-embedded electron microscopy. These nanogold probes can be introduced into live cells, in a manner that preserves intact molecular networks and cell viability. We use this ExoSloNano system to identify both cytoplasmic and nuclear proteins by room-temperature electron microscopy, and resolve associated structures by cryo-ET. By providing high-efficiency protein labeling in live cells and molecular specificity within cryo-ET tomograms, ExoSloNano expands the proteome available to electron microscopy. The ExoSloNano system facilitates nanogold probe-based labeling of specific proteins of a wide range of sizes in live cells for cryo-electron tomography and correlative light and electron microscopy studies.
{"title":"ExoSloNano: multimodal nanogold labels for identification of macromolecules in live cells and cryo-electron tomograms","authors":"Lindsey N. Young, Alice Sherrard, Huabin Zhou, Farhaz Shaikh, Joshua Hutchings, Margot Riggi, Mythreyi Narasimhan, W. Alexander Flaherty, Eric J. Bennett, Michael K. Rosen, Antonio J. Giraldez, Elizabeth Villa","doi":"10.1038/s41592-025-02928-4","DOIUrl":"10.1038/s41592-025-02928-4","url":null,"abstract":"In situ cryo-electron microscopy (cryo-EM) enables the direct interrogation of structure–function relationships by resolving macromolecular structures in their native cellular environment. Recent progress in sample preparation, imaging and data processing has enabled the identification and determination of large biomolecular complexes. However, the majority of proteins are of a size that still eludes identification in cellular cryo-EM data, and most proteins exist in low copy numbers. Therefore, novel tools are needed for cryo-EM to identify macromolecules across multiple size scales (from microns to nanometers). Here we introduce nanogold probes for detecting specific proteins using correlative light and electron microscopy, cryo-electron tomography (cryo-ET) and resin-embedded electron microscopy. These nanogold probes can be introduced into live cells, in a manner that preserves intact molecular networks and cell viability. We use this ExoSloNano system to identify both cytoplasmic and nuclear proteins by room-temperature electron microscopy, and resolve associated structures by cryo-ET. By providing high-efficiency protein labeling in live cells and molecular specificity within cryo-ET tomograms, ExoSloNano expands the proteome available to electron microscopy. The ExoSloNano system facilitates nanogold probe-based labeling of specific proteins of a wide range of sizes in live cells for cryo-electron tomography and correlative light and electron microscopy studies.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 1","pages":"131-142"},"PeriodicalIF":32.1,"publicationDate":"2025-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41592-025-02928-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145636298","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}
Pub Date : 2025-11-28DOI: 10.1038/s41592-025-02967-x
Yu Zhu, Aidas Aglinskas, Stefano Anzellotti
Functional magnetic resonance imaging (fMRI) allows noninvasive measurement of neural activity with high spatial resolution. However, fMRI data are affected by noise. Here we introduce and evaluate a denoising method (DeepCor) that utilizes deep generative models to disentangle and remove noise. The method is applicable to data from single participants. DeepCor outperforms other state-of-the-art denoising approaches on a variety of simulated datasets. In real fMRI data, DeepCor enhances BOLD signal responses to face stimuli, outperforming CompCor by 215%. DeepCor is a deep-learning-based denoising approach for task-based and resting-state fMRI data that can be used even for single participants.
{"title":"DeepCor: denoising fMRI data with contrastive autoencoders","authors":"Yu Zhu, Aidas Aglinskas, Stefano Anzellotti","doi":"10.1038/s41592-025-02967-x","DOIUrl":"10.1038/s41592-025-02967-x","url":null,"abstract":"Functional magnetic resonance imaging (fMRI) allows noninvasive measurement of neural activity with high spatial resolution. However, fMRI data are affected by noise. Here we introduce and evaluate a denoising method (DeepCor) that utilizes deep generative models to disentangle and remove noise. The method is applicable to data from single participants. DeepCor outperforms other state-of-the-art denoising approaches on a variety of simulated datasets. In real fMRI data, DeepCor enhances BOLD signal responses to face stimuli, outperforming CompCor by 215%. DeepCor is a deep-learning-based denoising approach for task-based and resting-state fMRI data that can be used even for single participants.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 2","pages":"334-337"},"PeriodicalIF":32.1,"publicationDate":"2025-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145636359","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}
T cell receptors (TCRs) play a vital role in immune recognition by binding specific epitopes. Accurate prediction of TCR–epitope interactions is fundamental for advancing immunology research. Although numerous computational methods have been developed, a comprehensive evaluation of their performance remains lacking. Here we assessed 50 state-of-the-art TCR–epitope prediction models using 21 datasets covering 762 epitopes and hundreds of thousands binding TCRs. Our analysis revealed that the source of negative TCRs substantially impacts model accuracy, with external negatives potentially introducing uncontrolled confounders. Model performance generally improved with more TCRs per epitope, highlighting the importance of large and diverse datasets. Models incorporating multiple features typically outperformed those using only complementarity-determining region 3β information, yet all struggle to generalize to unseen epitopes. The use of independent test sets proved crucial for unbiased assessment on both seen and unseen epitopes. These insights will guide the development of more accurate and generalizable TCR–epitope prediction models for real-world applications. This Analysis benchmarks 50 state-of-the-art TCR–epitope binding prediction methods and evaluates key factors that influence predictive performance.
{"title":"Assessment of computational methods in predicting TCR–epitope binding recognition","authors":"Yanping Lu, Yuyan Wang, Meng Xu, Bingbing Xie, Yumeng Yang, Haodong Xu, Shengbao Suo","doi":"10.1038/s41592-025-02910-0","DOIUrl":"10.1038/s41592-025-02910-0","url":null,"abstract":"T cell receptors (TCRs) play a vital role in immune recognition by binding specific epitopes. Accurate prediction of TCR–epitope interactions is fundamental for advancing immunology research. Although numerous computational methods have been developed, a comprehensive evaluation of their performance remains lacking. Here we assessed 50 state-of-the-art TCR–epitope prediction models using 21 datasets covering 762 epitopes and hundreds of thousands binding TCRs. Our analysis revealed that the source of negative TCRs substantially impacts model accuracy, with external negatives potentially introducing uncontrolled confounders. Model performance generally improved with more TCRs per epitope, highlighting the importance of large and diverse datasets. Models incorporating multiple features typically outperformed those using only complementarity-determining region 3β information, yet all struggle to generalize to unseen epitopes. The use of independent test sets proved crucial for unbiased assessment on both seen and unseen epitopes. These insights will guide the development of more accurate and generalizable TCR–epitope prediction models for real-world applications. This Analysis benchmarks 50 state-of-the-art TCR–epitope binding prediction methods and evaluates key factors that influence predictive performance.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 1","pages":"248-259"},"PeriodicalIF":32.1,"publicationDate":"2025-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41592-025-02910-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145636330","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}
Pub Date : 2025-11-27DOI: 10.1038/s41592-025-02916-8
Yang Yan, Shiqi Fan, Fajie Yuan, Huaizong Shen
Cryogenic electron microscopy (cryo-EM) has become a premier technique for determining high-resolution structures of biological macromolecules. However, its broad application is constrained by the demand for specialized expertise. Here, to address this limitation, we introduce the Cryo-EM Image Evaluation Foundation (Cryo-IEF) model, a versatile tool pre-trained on ~65 million cryo-EM particle images through unsupervised learning. Cryo-IEF performs diverse cryo-EM processing tasks, including particle classification by structure, pose-based clustering and image quality assessment. Building on this foundation, we developed CryoWizard, a fully automated single-particle cryo-EM processing pipeline enabled by fine-tuned Cryo-IEF for efficient particle quality ranking. CryoWizard resolves high-resolution structures across samples of varied properties and effectively mitigates the prevalent challenge of preferred orientation in cryo-EM. Cryo-IEF is a pre-trained foundation model for performing diverse image-processing tasks in single-particle cryo-EM. CryoWizard, enabled by Cryo-IEF, is a fully automated cryo-EM processing pipeline.
{"title":"A comprehensive foundation model for cryo-EM image processing","authors":"Yang Yan, Shiqi Fan, Fajie Yuan, Huaizong Shen","doi":"10.1038/s41592-025-02916-8","DOIUrl":"10.1038/s41592-025-02916-8","url":null,"abstract":"Cryogenic electron microscopy (cryo-EM) has become a premier technique for determining high-resolution structures of biological macromolecules. However, its broad application is constrained by the demand for specialized expertise. Here, to address this limitation, we introduce the Cryo-EM Image Evaluation Foundation (Cryo-IEF) model, a versatile tool pre-trained on ~65 million cryo-EM particle images through unsupervised learning. Cryo-IEF performs diverse cryo-EM processing tasks, including particle classification by structure, pose-based clustering and image quality assessment. Building on this foundation, we developed CryoWizard, a fully automated single-particle cryo-EM processing pipeline enabled by fine-tuned Cryo-IEF for efficient particle quality ranking. CryoWizard resolves high-resolution structures across samples of varied properties and effectively mitigates the prevalent challenge of preferred orientation in cryo-EM. Cryo-IEF is a pre-trained foundation model for performing diverse image-processing tasks in single-particle cryo-EM. CryoWizard, enabled by Cryo-IEF, is a fully automated cryo-EM processing pipeline.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"23 1","pages":"88-95"},"PeriodicalIF":32.1,"publicationDate":"2025-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145636344","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：