Nature MethodsPub Date : 2025-05-01Epub Date: 2025-04-03DOI: 10.1038/s41592-025-02636-z
Bo Chen, Xingyi Cheng, Pan Li, Yangli-Ao Geng, Jing Gong, Shen Li, Zhilei Bei, Xu Tan, Boyan Wang, Xin Zeng, Chiming Liu, Aohan Zeng, Yuxiao Dong, Jie Tang, Le Song
{"title":"xTrimoPGLM: unified 100-billion-parameter pretrained transformer for deciphering the language of proteins.","authors":"Bo Chen, Xingyi Cheng, Pan Li, Yangli-Ao Geng, Jing Gong, Shen Li, Zhilei Bei, Xu Tan, Boyan Wang, Xin Zeng, Chiming Liu, Aohan Zeng, Yuxiao Dong, Jie Tang, Le Song","doi":"10.1038/s41592-025-02636-z","DOIUrl":"10.1038/s41592-025-02636-z","url":null,"abstract":"<p><p>Protein language models have shown remarkable success in learning biological information from protein sequences. However, most existing models are limited by either autoencoding or autoregressive pretraining objectives, which makes them struggle to handle protein understanding and generation tasks concurrently. We propose a unified protein language model, xTrimoPGLM, to address these two types of tasks simultaneously through an innovative pretraining framework. Our key technical contribution is an exploration of the compatibility and the potential for joint optimization of the two types of objectives, which has led to a strategy for training xTrimoPGLM at an unprecedented scale of 100 billion parameters and 1 trillion training tokens. Our extensive experiments reveal that (1) xTrimoPGLM substantially outperforms other advanced baselines in 18 protein understanding benchmarks across four categories. The model also facilitates an atomic-resolution view of protein structures, leading to an advanced three-dimensional structural prediction model that surpasses existing language model-based tools. (2) xTrimoPGLM not only can generate de novo protein sequences following the principles of natural ones, but also can perform programmable generation after supervised fine-tuning on curated sequences. These results highlight the substantial capability and versatility of xTrimoPGLM in understanding and generating protein sequences, contributing to the evolving landscape of foundation models in protein science. Trained weight for the xTrimoPGLM model, and downstream datasets are available at https://huggingface.co/biomap-research .</p>","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":" ","pages":"1028-1039"},"PeriodicalIF":36.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143780656","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}
Nature MethodsPub Date : 2025-05-01Epub Date: 2025-04-09DOI: 10.1038/s41592-024-02426-z
Sven Dorkenwald, Casey M Schneider-Mizell, Derrick Brittain, Akhilesh Halageri, Chris Jordan, Nico Kemnitz, Manual A Castro, William Silversmith, Jeremy Maitin-Shephard, Jakob Troidl, Hanspeter Pfister, Valentin Gillet, Daniel Xenes, J Alexander Bae, Agnes L Bodor, JoAnn Buchanan, Daniel J Bumbarger, Leila Elabbady, Zhen Jia, Daniel Kapner, Sam Kinn, Kisuk Lee, Kai Li, Ran Lu, Thomas Macrina, Gayathri Mahalingam, Eric Mitchell, Shanka Subhra Mondal, Shang Mu, Barak Nehoran, Sergiy Popovych, Marc Takeno, Russel Torres, Nicholas L Turner, William Wong, Jingpeng Wu, Wenjing Yin, Szi-Chieh Yu, R Clay Reid, Nuno Maçarico da Costa, H Sebastian Seung, Forrest Collman
{"title":"CAVE: Connectome Annotation Versioning Engine.","authors":"Sven Dorkenwald, Casey M Schneider-Mizell, Derrick Brittain, Akhilesh Halageri, Chris Jordan, Nico Kemnitz, Manual A Castro, William Silversmith, Jeremy Maitin-Shephard, Jakob Troidl, Hanspeter Pfister, Valentin Gillet, Daniel Xenes, J Alexander Bae, Agnes L Bodor, JoAnn Buchanan, Daniel J Bumbarger, Leila Elabbady, Zhen Jia, Daniel Kapner, Sam Kinn, Kisuk Lee, Kai Li, Ran Lu, Thomas Macrina, Gayathri Mahalingam, Eric Mitchell, Shanka Subhra Mondal, Shang Mu, Barak Nehoran, Sergiy Popovych, Marc Takeno, Russel Torres, Nicholas L Turner, William Wong, Jingpeng Wu, Wenjing Yin, Szi-Chieh Yu, R Clay Reid, Nuno Maçarico da Costa, H Sebastian Seung, Forrest Collman","doi":"10.1038/s41592-024-02426-z","DOIUrl":"10.1038/s41592-024-02426-z","url":null,"abstract":"<p><p>Advances in electron microscopy, image segmentation and computational infrastructure have given rise to large-scale and richly annotated connectomic datasets, which are increasingly shared across communities. To enable collaboration, users need to be able to concurrently create annotations and correct errors in the automated segmentation by proofreading. In large datasets, every proofreading edit relabels cell identities of millions of voxels and thousands of annotations like synapses. For analysis, users require immediate and reproducible access to this changing and expanding data landscape. Here we present the Connectome Annotation Versioning Engine (CAVE), a computational infrastructure that provides scalable solutions for proofreading and flexible annotation support for fast analysis queries at arbitrary time points. Deployed as a suite of web services, CAVE empowers distributed communities to perform reproducible connectome analysis in up to petascale datasets (~1 mm<sup>3</sup>) while proofreading and annotating is ongoing.</p>","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 5","pages":"1112-1120"},"PeriodicalIF":36.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12074985/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143972063","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}
Nature MethodsPub Date : 2025-05-01DOI: 10.1038/s41592-025-02670-x
Jacqueline F Rivera, Haoyang Huang, Weiguang Weng, Heesung Sohn, Allison E Girasole, Shun Li, Madeline A Albanese, Melissa Qin, Can Tao, Molly E Klug, Sadhna Rao, Ronald Paletzki, Bruce E Herring, Scott E Kanoski, Li I Zhang, Charles R Gerfen, Bernardo L Sabatini, Don B Arnold
{"title":"ATLAS: a rationally designed anterograde transsynaptic tracer.","authors":"Jacqueline F Rivera, Haoyang Huang, Weiguang Weng, Heesung Sohn, Allison E Girasole, Shun Li, Madeline A Albanese, Melissa Qin, Can Tao, Molly E Klug, Sadhna Rao, Ronald Paletzki, Bruce E Herring, Scott E Kanoski, Li I Zhang, Charles R Gerfen, Bernardo L Sabatini, Don B Arnold","doi":"10.1038/s41592-025-02670-x","DOIUrl":"10.1038/s41592-025-02670-x","url":null,"abstract":"<p><p>Genetically modified rabies virus can map neural circuits retrogradely from genetically determined cells. However, similar tools for anterograde tracing are not available. Here, we describe a method for anterograde transsynaptic tracing from genetically determined neurons based on a rationally designed protein, ATLAS. Expression of ATLAS in neurons causes presynaptic release of a payload composed of an antibody-like protein, AMPA.FingR, which binds to the N terminus of GluA1, and a recombinase. In the synaptic cleft, AMPA.FingR binds to GluA1, causing the payload to be endocytosed into postsynaptic cells and delivered to the nucleus, where it triggers expression of a recombinase-dependent reporter. In mice, ATLAS mediates monosynaptic transneuronal tracing from random or genetically determined cells that is strictly anterograde, synaptic and nontoxic. Moreover, ATLAS-mediated tracing shows activity dependence, suggesting that it can label active circuits underlying specific behaviors. Finally, ATLAS is composed of modular components that can be independently replaced or modified.</p>","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 5","pages":"1101-1111"},"PeriodicalIF":36.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12074993/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144033091","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}
Nature MethodsPub Date : 2025-05-01DOI: 10.1038/s41592-025-02666-7
{"title":"Coupling the 3D epigenome to the transcriptome in single cells.","authors":"","doi":"10.1038/s41592-025-02666-7","DOIUrl":"https://doi.org/10.1038/s41592-025-02666-7","url":null,"abstract":"","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 5","pages":"906-907"},"PeriodicalIF":36.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143990931","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}
Nature MethodsPub Date : 2025-05-01Epub Date: 2025-04-10DOI: 10.1038/s41592-025-02656-9
Fred Zhangzhi Peng, Chentong Wang, Tong Chen, Benjamin Schussheim, Sophia Vincoff, Pranam Chatterjee
{"title":"PTM-Mamba: a PTM-aware protein language model with bidirectional gated Mamba blocks.","authors":"Fred Zhangzhi Peng, Chentong Wang, Tong Chen, Benjamin Schussheim, Sophia Vincoff, Pranam Chatterjee","doi":"10.1038/s41592-025-02656-9","DOIUrl":"10.1038/s41592-025-02656-9","url":null,"abstract":"<p><p>Current protein language models (LMs) accurately encode protein properties but have yet to represent post-translational modifications (PTMs), which are crucial for proteomic diversity and influence protein structure, function and interactions. To address this gap, we develop PTM-Mamba, a PTM-aware protein LM that integrates PTM tokens using bidirectional Mamba blocks fused with ESM-2 protein LM embeddings via a newly developed gating mechanism. PTM-Mamba uniquely models both wild-type and PTM sequences, enabling downstream tasks such as disease association and druggability prediction, PTM effect prediction on protein-protein interactions and zero-shot PTM discovery. In total, our work establishes PTM-Mamba as a foundational tool for PTM-aware protein modeling and design.</p>","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 5","pages":"945-949"},"PeriodicalIF":36.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12074982/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144036415","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}
Nature MethodsPub Date : 2025-05-01Epub Date: 2025-04-11DOI: 10.1038/s41592-025-02648-9
Alexandre Pellan Cheng, Adam J Widman, Anushri Arora, Itai Rusinek, Aaron Sossin, Srinivas Rajagopalan, Nicholas Midler, William F Hooper, Rebecca M Murray, Daniel Halmos, Theophile Langanay, Hoyin Chu, Giorgio Inghirami, Catherine Potenski, Soren Germer, Melissa Marton, Dina Manaa, Adrienne Helland, Rob Furatero, Jaime McClintock, Lara Winterkorn, Zoe Steinsnyder, Yohyoh Wang, Asrar I Alimohamed, Murtaza S Malbari, Ashish Saxena, Margaret K Callahan, Dennie T Frederick, Lavinia Spain, Michael Sigouros, Jyothi Manohar, Abigail King, David Wilkes, John Otilano, Olivier Elemento, Juan Miguel Mosquera, Ariel Jaimovich, Doron Lipson, Samra Turajlic, Michael C Zody, Nasser K Altorki, Jedd D Wolchok, Michael A Postow, Nicolas Robine, Bishoy M Faltas, Genevieve Boland, Dan A Landau
{"title":"Error-corrected flow-based sequencing at whole-genome scale and its application to circulating cell-free DNA profiling.","authors":"Alexandre Pellan Cheng, Adam J Widman, Anushri Arora, Itai Rusinek, Aaron Sossin, Srinivas Rajagopalan, Nicholas Midler, William F Hooper, Rebecca M Murray, Daniel Halmos, Theophile Langanay, Hoyin Chu, Giorgio Inghirami, Catherine Potenski, Soren Germer, Melissa Marton, Dina Manaa, Adrienne Helland, Rob Furatero, Jaime McClintock, Lara Winterkorn, Zoe Steinsnyder, Yohyoh Wang, Asrar I Alimohamed, Murtaza S Malbari, Ashish Saxena, Margaret K Callahan, Dennie T Frederick, Lavinia Spain, Michael Sigouros, Jyothi Manohar, Abigail King, David Wilkes, John Otilano, Olivier Elemento, Juan Miguel Mosquera, Ariel Jaimovich, Doron Lipson, Samra Turajlic, Michael C Zody, Nasser K Altorki, Jedd D Wolchok, Michael A Postow, Nicolas Robine, Bishoy M Faltas, Genevieve Boland, Dan A Landau","doi":"10.1038/s41592-025-02648-9","DOIUrl":"10.1038/s41592-025-02648-9","url":null,"abstract":"<p><p>Differentiating sequencing errors from true variants is a central genomics challenge, calling for error suppression strategies that balance costs and sensitivity. For example, circulating cell-free DNA (ccfDNA) sequencing for cancer monitoring is limited by sparsity of circulating tumor DNA, abundance of genomic material in samples and preanalytical error rates. Whole-genome sequencing (WGS) can overcome the low abundance of ccfDNA by integrating signals across the mutation landscape, but higher costs limit its wide adoption. Here, we applied deep (~120×) lower-cost WGS (Ultima Genomics) for tumor-informed circulating tumor DNA detection within the part-per-million range. We further leveraged lower-cost sequencing by developing duplex error-corrected WGS of ccfDNA, achieving 7.7 × 10<sup>-7</sup> error rates, allowing us to assess disease burden in individuals with melanoma and urothelial cancer without matched tumor sequencing. This error-corrected WGS approach will have broad applicability across genomics, allowing for accurate calling of low-abundance variants at efficient cost and enabling deeper mapping of somatic mosaicism as an emerging central aspect of aging and disease.</p>","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 5","pages":"973-981"},"PeriodicalIF":36.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12077166/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143971644","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}
Nature MethodsPub Date : 2025-05-01DOI: 10.1038/s41592-025-02715-1
Nina Vogt
{"title":"Unraveling the black box in neural signal analysis.","authors":"Nina Vogt","doi":"10.1038/s41592-025-02715-1","DOIUrl":"https://doi.org/10.1038/s41592-025-02715-1","url":null,"abstract":"","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 5","pages":"894"},"PeriodicalIF":36.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144025088","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}
Nature MethodsPub Date : 2025-05-01DOI: 10.1038/s41592-025-02671-w
{"title":"Tracing neural circuits in the anterograde direction.","authors":"","doi":"10.1038/s41592-025-02671-w","DOIUrl":"https://doi.org/10.1038/s41592-025-02671-w","url":null,"abstract":"","PeriodicalId":18981,"journal":{"name":"Nature Methods","volume":"22 5","pages":"910-911"},"PeriodicalIF":36.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144008562","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}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
