Nature Methods最新文献_第9页

Overcoming the preferred-orientation problem in cryo-EM with self-supervised deep learning 利用自我监督深度学习克服低温电子显微镜中的首选方向问题。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-18 DOI: 10.1038/s41592-024-02505-1

Yun-Tao Liu, Hongcheng Fan, Jason J. Hu, Z. Hong Zhou

{"title":"Overcoming the preferred-orientation problem in cryo-EM with self-supervised deep learning","authors":"Yun-Tao Liu, Hongcheng Fan, Jason J. Hu, Z. Hong Zhou","doi":"10.1038/s41592-024-02505-1","DOIUrl":"10.1038/s41592-024-02505-1","url":null,"abstract":"While advances in single-particle cryo-EM have enabled the structural determination of macromolecular complexes at atomic resolution, particle orientation bias (the ‘preferred’ orientation problem) remains a complication for most specimens. Existing solutions have relied on biochemical and physical strategies applied to the specimen and are often complex and challenging. Here, we develop spIsoNet, an end-to-end self-supervised deep learning-based software to address map anisotropy and particle misalignment caused by the preferred-orientation problem. Using preferred-orientation views to recover molecular information in under-sampled views, spIsoNet improves both angular isotropy and particle alignment accuracy during 3D reconstruction. We demonstrate spIsoNet’s ability to generate near-isotropic reconstructions from representative biological systems with limited views, including ribosomes, β-galactosidases and a previously intractable hemagglutinin trimer dataset. spIsoNet can also be generalized to improve map isotropy and particle alignment of preferentially oriented molecules in subtomogram averaging. Therefore, without additional specimen-preparation procedures, spIsoNet provides a general computational solution to the preferred-orientation problem. spIsoNet is an end-to-end self-supervised deep learning-based software to address the reconstruction and misalignment challenge in single-particle cryo-EM caused by the preferred-orientation problem. spIsoNet can also improve map isotropy and particle alignment of preferentially oriented molecules during subtomogram averaging in cryogenic electron tomography.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 1","pages":"113-123"},"PeriodicalIF":36.1,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142668352","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

A foundation model unlocks unified biomedical image analysis 一个基础模型开启了统一的生物医学图像分析。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-18 DOI: 10.1038/s41592-024-02519-9

Yuhao Huang, Haoran Dou, Dong Ni

引用次数: 0

Content-aware motion correction for multi-shot imaging 针对多镜头成像的内容感知运动校正。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-18 DOI: 10.1038/s41592-024-02520-2

Romain F. Laine

引用次数: 0

A foundation model for joint segmentation, detection and recognition of biomedical objects across nine modalities 九种模式生物医学对象联合分割、检测和识别的基础模型。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-18 DOI: 10.1038/s41592-024-02499-w

Theodore Zhao, Yu Gu, Jianwei Yang, Naoto Usuyama, Ho Hin Lee, Sid Kiblawi, Tristan Naumann, Jianfeng Gao, Angela Crabtree, Jacob Abel, Christine Moung-Wen, Brian Piening, Carlo Bifulco, Mu Wei, Hoifung Poon, Sheng Wang

{"title":"A foundation model for joint segmentation, detection and recognition of biomedical objects across nine modalities","authors":"Theodore Zhao, Yu Gu, Jianwei Yang, Naoto Usuyama, Ho Hin Lee, Sid Kiblawi, Tristan Naumann, Jianfeng Gao, Angela Crabtree, Jacob Abel, Christine Moung-Wen, Brian Piening, Carlo Bifulco, Mu Wei, Hoifung Poon, Sheng Wang","doi":"10.1038/s41592-024-02499-w","DOIUrl":"10.1038/s41592-024-02499-w","url":null,"abstract":"Biomedical image analysis is fundamental for biomedical discovery. Holistic image analysis comprises interdependent subtasks such as segmentation, detection and recognition, which are tackled separately by traditional approaches. Here, we propose BiomedParse, a biomedical foundation model that can jointly conduct segmentation, detection and recognition across nine imaging modalities. This joint learning improves the accuracy for individual tasks and enables new applications such as segmenting all relevant objects in an image through a textual description. To train BiomedParse, we created a large dataset comprising over 6 million triples of image, segmentation mask and textual description by leveraging natural language labels or descriptions accompanying existing datasets. We showed that BiomedParse outperformed existing methods on image segmentation across nine imaging modalities, with larger improvement on objects with irregular shapes. We further showed that BiomedParse can simultaneously segment and label all objects in an image. In summary, BiomedParse is an all-in-one tool for biomedical image analysis on all major image modalities, paving the path for efficient and accurate image-based biomedical discovery. BiomedParse is a foundation model for image analysis that uses a joint learning approach to jointly conduct segmentation, detection and recognition and offer state-of-the-art performance across a wide range of datasets and nine modalities.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 1","pages":"166-176"},"PeriodicalIF":36.1,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142668253","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

Nanopore approaches for single-molecule temporal omics: promises and challenges. 纳米孔方法用于单分子时空 omics：前景与挑战。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-18 DOI: 10.1038/s41592-024-02492-3

Meng-Yin Li, Jie Jiang, Jun-Ge Li, Hongyan Niu, Yi-Lun Ying, Ruijun Tian, Yi-Tao Long

{"title":"Nanopore approaches for single-molecule temporal omics: promises and challenges.","authors":"Meng-Yin Li, Jie Jiang, Jun-Ge Li, Hongyan Niu, Yi-Lun Ying, Ruijun Tian, Yi-Tao Long","doi":"10.1038/s41592-024-02492-3","DOIUrl":"10.1038/s41592-024-02492-3","url":null,"abstract":"<p><p>The great molecular heterogeneity within single cells demands omics analysis from a single-molecule perspective. Moreover, considering the perpetual metabolism and communication within cells, it is essential to determine the time-series changes of the molecular library, rather than obtaining data at only one time point. Thus, there is an urgent need to develop a single-molecule strategy for this omics analysis to elucidate the biosystem heterogeneity and temporal dynamics. In this Perspective, we explore the potential application of nanopores for single-molecule temporal omics to characterize individual molecules beyond mass, in both a single-molecule and high-throughput manner. Accordingly, recent advances in nanopores available for single-molecule temporal omics are reviewed from the view of single-molecule mass identification, revealing single-molecule heterogeneity and illustrating temporal evolution. Furthermore, we discuss the primary challenges associated with using nanopores for single-molecule temporal omics in complex biological samples, and present the potential strategies and notes to respond to these challenges.</p>","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":" ","pages":""},"PeriodicalIF":36.1,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142668334","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

Probe set selection for targeted spatial transcriptomics 定向空间转录组学的探针组选择。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-18 DOI: 10.1038/s41592-024-02496-z

Louis B. Kuemmerle, Malte D. Luecken, Alexandra B. Firsova, Lisa Barros de Andrade e Sousa, Lena Straßer, Ilhem Isra Mekki, Francesco Campi, Lukas Heumos, Maiia Shulman, Valentina Beliaeva, Soroor Hediyeh-Zadeh, Anna C. Schaar, Krishnaa T. Mahbubani, Alexandros Sountoulidis, Tamás Balassa, Ferenc Kovacs, Peter Horvath, Marie Piraud, Ali Ertürk, Christos Samakovlis, Fabian J. Theis

{"title":"Probe set selection for targeted spatial transcriptomics","authors":"Louis B. Kuemmerle, Malte D. Luecken, Alexandra B. Firsova, Lisa Barros de Andrade e Sousa, Lena Straßer, Ilhem Isra Mekki, Francesco Campi, Lukas Heumos, Maiia Shulman, Valentina Beliaeva, Soroor Hediyeh-Zadeh, Anna C. Schaar, Krishnaa T. Mahbubani, Alexandros Sountoulidis, Tamás Balassa, Ferenc Kovacs, Peter Horvath, Marie Piraud, Ali Ertürk, Christos Samakovlis, Fabian J. Theis","doi":"10.1038/s41592-024-02496-z","DOIUrl":"10.1038/s41592-024-02496-z","url":null,"abstract":"Targeted spatial transcriptomic methods capture the topology of cell types and states in tissues at single-cell and subcellular resolution by measuring the expression of a predefined set of genes. The selection of an optimal set of probed genes is crucial for capturing the spatial signals present in a tissue. This requires selecting the most informative, yet minimal, set of genes to profile (gene set selection) for which it is possible to build probes (probe design). However, current selections often rely on marker genes, precluding them from detecting continuous spatial signals or new states. We present Spapros, an end-to-end probe set selection pipeline that optimizes both gene set specificity for cell type identification and within-cell type expression variation to resolve spatially distinct populations while considering prior knowledge as well as probe design and expression constraints. We evaluated Spapros and show that it outperforms other selection approaches in both cell type recovery and recovering expression variation beyond cell types. Furthermore, we used Spapros to design a single-cell resolution in situ hybridization on tissues (SCRINSHOT) experiment of adult lung tissue to demonstrate how probes selected with Spapros identify cell types of interest and detect spatial variation even within cell types. Spapros is a probe set selection pipeline for targeted spatial transcriptomics that optimizes for both transcriptional and within-cell type variation.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"21 12","pages":"2260-2270"},"PeriodicalIF":36.1,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41592-024-02496-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142668356","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

Efficient and highly amplified imaging of nucleic acid targets in cellular and histopathological samples with pSABER 利用 pSABER 对细胞和组织病理学样本中的核酸靶标进行高效和高度扩增成像。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-15 DOI: 10.1038/s41592-024-02512-2

Sahar Attar, Valentino E. Browning, Mary Krebs, Yuzhen Liu, Eva K. Nichols, Ashley F. Tsue, David M. Shechner, Jay Shendure, Joshua A. Lieberman, Devin K. Schweppe, Shreeram Akilesh, Brian J. Beliveau

{"title":"Efficient and highly amplified imaging of nucleic acid targets in cellular and histopathological samples with pSABER","authors":"Sahar Attar, Valentino E. Browning, Mary Krebs, Yuzhen Liu, Eva K. Nichols, Ashley F. Tsue, David M. Shechner, Jay Shendure, Joshua A. Lieberman, Devin K. Schweppe, Shreeram Akilesh, Brian J. Beliveau","doi":"10.1038/s41592-024-02512-2","DOIUrl":"10.1038/s41592-024-02512-2","url":null,"abstract":"In situ hybridization (ISH) is a powerful tool for investigating the spatial arrangement of nucleic acid targets in fixed samples. ISH is typically visualized using fluorophores to allow high sensitivity and multiplexing or with colorimetric labels to facilitate covisualization with histopathological stains. Both approaches benefit from signal amplification, which makes target detection effective, rapid and compatible with a broad range of optical systems. Here, we introduce a unified technical platform, termed ‘pSABER’, for the amplification of ISH signals in cell and tissue systems. pSABER decorates the in situ target with concatemeric binding sites for a horseradish peroxidase-conjugated oligonucleotide, enabling the localized deposition of fluorescent or colorimetric substrates. We demonstrate that pSABER effectively labels DNA and RNA targets in cultured cells and FFPE specimens. Furthermore, pSABER can achieve fivefold signal amplification over conventional signal amplification by exchange reaction (SABER) and can be serially multiplexed using solution exchange. Therefore, by linking nucleic acid detection to robust signal amplification capable of diverse readouts, pSABER will have broad utility in research and clinical settings. pSABER combines the power of signal amplification by exchange reaction (SABER) with the deposition of fluorescent or colorimetric substrates by horseradish peroxidase to enable enhanced signals for in situ hybridization in cells and tissues.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 1","pages":"156-165"},"PeriodicalIF":36.1,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142639370","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

Building a molecular reference map of the human embryo 绘制人类胚胎分子参考图。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-14 DOI: 10.1038/s41592-024-02494-1

Rina C. Sakata, Marta N. Shahbazi

引用次数: 0

Deep learning-based models for preimplantation mouse and human embryos based on single-cell RNA sequencing 基于单细胞 RNA 测序的植入前小鼠和人类胚胎深度学习模型。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-14 DOI: 10.1038/s41592-024-02511-3

Martin Proks, Nazmus Salehin, Joshua M. Brickman

{"title":"Deep learning-based models for preimplantation mouse and human embryos based on single-cell RNA sequencing","authors":"Martin Proks, Nazmus Salehin, Joshua M. Brickman","doi":"10.1038/s41592-024-02511-3","DOIUrl":"10.1038/s41592-024-02511-3","url":null,"abstract":"The rapid growth of single-cell transcriptomic technology has produced an increasing number of datasets for both embryonic development and in vitro pluripotent stem cell-derived models. This avalanche of data surrounding pluripotency and the process of lineage specification has meant it has become increasingly difficult to define specific cell types or states in vivo, and compare these with in vitro differentiation. Here we utilize a set of deep learning tools to integrate and classify multiple datasets. This allows the definition of both mouse and human embryo cell types, lineages and states, thereby maximizing the information one can garner from these precious experimental resources. Our approaches are built on recent initiatives for large-scale human organ atlases, but here we focus on material that is difficult to obtain and process, spanning early mouse and human development. Using publicly available data for these stages, we test different deep learning approaches and develop a model to classify cell types in an unbiased fashion at the same time as defining the set of genes used by the model to identify lineages, cell types and states. We used our models trained on in vivo development to classify pluripotent stem cell models for both mouse and human development, showcasing the importance of this resource as a dynamic reference for early embryogenesis. This Resource uses deep learning-based tools to build a dynamic transcriptomic reference for mouse and human preimplantation development.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 1","pages":"207-216"},"PeriodicalIF":36.1,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41592-024-02511-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142624354","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

A comprehensive human embryo reference tool using single-cell RNA-sequencing data 使用单细胞 RNA 测序数据的人类胚胎综合参考工具。

IF 36.1 1区生物学

Nature Methods Pub Date : 2024-11-14 DOI: 10.1038/s41592-024-02493-2

Cheng Zhao, Alvaro Plaza Reyes, John Paul Schell, Jere Weltner, Nicolás M. Ortega, Yi Zheng, Åsa K. Björklund, Laura Baqué-Vidal, Joonas Sokka, Ras Torokovic, Brian Cox, Janet Rossant, Jianping Fu, Sophie Petropoulos, Fredrik Lanner

{"title":"A comprehensive human embryo reference tool using single-cell RNA-sequencing data","authors":"Cheng Zhao, Alvaro Plaza Reyes, John Paul Schell, Jere Weltner, Nicolás M. Ortega, Yi Zheng, Åsa K. Björklund, Laura Baqué-Vidal, Joonas Sokka, Ras Torokovic, Brian Cox, Janet Rossant, Jianping Fu, Sophie Petropoulos, Fredrik Lanner","doi":"10.1038/s41592-024-02493-2","DOIUrl":"10.1038/s41592-024-02493-2","url":null,"abstract":"Stem cell-based embryo models offer unprecedented experimental tools for studying early human development. The usefulness of embryo models hinges on their molecular, cellular and structural fidelities to their in vivo counterparts. To authenticate human embryo models, single-cell RNA sequencing has been utilized for unbiased transcriptional profiling. However, an organized and integrated human single-cell RNA-sequencing dataset, serving as a universal reference for benchmarking human embryo models, remains unavailable. Here we developed such a reference through the integration of six published human datasets covering development from the zygote to the gastrula. Lineage annotations are contrasted and validated with available human and nonhuman primate datasets. Using stabilized Uniform Manifold Approximation and Projection, we constructed an early embryogenesis prediction tool, where query datasets can be projected on the reference and annotated with predicted cell identities. Using this reference tool, we examined published human embryo models, highlighting the risk of misannotation when relevant references are not utilized for benchmarking and authentication. This resource integrates different human embryo datasets to create a transcriptional reference map of human embryonic development from zygote to gastrula.","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 1","pages":"193-206"},"PeriodicalIF":36.1,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41592-024-02493-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142624347","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