Nature Biomedical Engineering最新文献_第9页

Synthetic data boosts medical foundation models 合成数据增强了医学基础模型

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2025-04-08 DOI: 10.1038/s41551-025-01375-y

Bin Sheng, Pearse A. Keane, Yih-Chung Tham, Tien Yin Wong

引用次数: 0

Coordinated AI agents for advancing healthcare 协调人工智能代理，促进医疗保健发展

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2025-04-01 DOI: 10.1038/s41551-025-01363-2

Michael Moritz, Eric Topol, Pranav Rajpurkar

引用次数: 0

A framework for integrating artificial intelligence for clinical care with continuous therapeutic monitoring. 将人工智能用于临床护理与持续治疗监测相结合的框架。

IF 26.8 1区医学

Nature Biomedical Engineering Pub Date : 2025-04-01 Epub Date: 2023-11-06 DOI: 10.1038/s41551-023-01115-0

Emma Chen, Shvetank Prakash, Vijay Janapa Reddi, David Kim, Pranav Rajpurkar

引用次数: 0

A vision-language foundation model for the generation of realistic chest X-ray images. 用于生成逼真胸部 X 光图像的视觉语言基础模型。

IF 26.8 1区医学

Nature Biomedical Engineering Pub Date : 2025-04-01 Epub Date: 2024-08-26 DOI: 10.1038/s41551-024-01246-y

Christian Bluethgen, Pierre Chambon, Jean-Benoit Delbrouck, Rogier van der Sluijs, Małgorzata Połacin, Juan Manuel Zambrano Chaves, Tanishq Mathew Abraham, Shivanshu Purohit, Curtis P Langlotz, Akshay S Chaudhari

{"title":"A vision-language foundation model for the generation of realistic chest X-ray images.","authors":"Christian Bluethgen, Pierre Chambon, Jean-Benoit Delbrouck, Rogier van der Sluijs, Małgorzata Połacin, Juan Manuel Zambrano Chaves, Tanishq Mathew Abraham, Shivanshu Purohit, Curtis P Langlotz, Akshay S Chaudhari","doi":"10.1038/s41551-024-01246-y","DOIUrl":"10.1038/s41551-024-01246-y","url":null,"abstract":"The paucity of high-quality medical imaging datasets could be mitigated by machine learning models that generate compositionally diverse images that faithfully represent medical concepts and pathologies. However, large vision-language models are trained on natural images, and the diversity distribution of the generated images substantially differs from that of medical images. Moreover, medical language involves specific and semantically rich vocabulary. Here we describe a domain-adaptation strategy for large vision-language models that overcomes distributional shifts. Specifically, by leveraging publicly available datasets of chest X-ray images and the corresponding radiology reports, we adapted a latent diffusion model pre-trained on pairs of natural images and text descriptors to generate diverse and visually plausible synthetic chest X-ray images (as confirmed by board-certified radiologists) whose appearance can be controlled with free-form medical text prompts. The domain-adaptation strategy for the text-conditioned synthesis of medical images can be used to augment training datasets and is a viable alternative to the sharing of real medical images for model training and fine-tuning.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":" ","pages":"494-506"},"PeriodicalIF":26.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11861387/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142073376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Techniques for supercharging academic writing with generative AI. 利用生成式人工智能提高学术写作水平的技术。

IF 26.8 1区医学

Nature Biomedical Engineering Pub Date : 2025-04-01 DOI: 10.1038/s41551-024-01185-8

Zhicheng Lin

引用次数: 0

Generation of tolerogenic antigen-presenting cells in vivo via the delivery of mRNA encoding PDL1 within lipid nanoparticles 通过在脂质纳米颗粒内传递编码PDL1的mRNA，在体内产生耐受性抗原提呈细胞

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2025-03-28 DOI: 10.1038/s41551-025-01373-0

Yang Liu, Qian Liu, Baowen Zhang, Shanshan Chen, Yanqiong Shen, Zhibin Li, Jiachen Zhang, Yi Yang, Min Li, Yucai Wang

{"title":"Generation of tolerogenic antigen-presenting cells in vivo via the delivery of mRNA encoding PDL1 within lipid nanoparticles","authors":"Yang Liu, Qian Liu, Baowen Zhang, Shanshan Chen, Yanqiong Shen, Zhibin Li, Jiachen Zhang, Yi Yang, Min Li, Yucai Wang","doi":"10.1038/s41551-025-01373-0","DOIUrl":"https://doi.org/10.1038/s41551-025-01373-0","url":null,"abstract":"Tolerogenic antigen-presenting cells (APCs) are promising as therapeutics for suppressing T cell activation in autoimmune diseases. However, the isolation and ex vivo manipulation of autologous APCs is costly, and the process is customized for each patient. Here we show that tolerogenic APCs can be generated in vivo by delivering, via lipid nanoparticles, messenger RNA coding for the inhibitory protein programmed death ligand 1. We optimized a lipid-nanoparticle formulation to minimize its immunogenicity by reducing the molar ratio of nitrogen atoms on the ionizable lipid and the phosphate groups on the encapsulated mRNA. In mouse models of rheumatoid arthritis and ulcerative colitis, subcutaneous delivery of nanoparticles encapsulating mRNA encoding programmed death ligand 1 reduced the fraction of activated T cells, promoted the induction of regulatory T cells and effectively prevented disease progression. The method may allow for the engineering of APCs that target specific autoantigens or that integrate additional inhibitory molecules.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"95 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143723123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Osteopontin attenuates the foreign-body response to silicone implants 骨桥蛋白减轻了硅胶植入物对异物的反应

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2025-03-24 DOI: 10.1038/s41551-025-01361-4

Michelle F. Griffin, Jennifer B. Parker, Ruth Tevlin, Norah E. Liang, Caleb Valencia, Annah Morgan, Maxwell Kuhnert, Mauricio Downer, Emily L. Meany, Jason L. Guo, Dominic Henn, Renato S. Navarro, Kerry Shefren, Dung Nguyen, Geoffrey C. Gurtner, Sarah C. Heilshorn, Charles K. F. Chan, Michael Januszyk, Eric A. Appel, Arash Momeni, Derrick C. Wan, Michael T. Longaker

{"title":"Osteopontin attenuates the foreign-body response to silicone implants","authors":"Michelle F. Griffin, Jennifer B. Parker, Ruth Tevlin, Norah E. Liang, Caleb Valencia, Annah Morgan, Maxwell Kuhnert, Mauricio Downer, Emily L. Meany, Jason L. Guo, Dominic Henn, Renato S. Navarro, Kerry Shefren, Dung Nguyen, Geoffrey C. Gurtner, Sarah C. Heilshorn, Charles K. F. Chan, Michael Januszyk, Eric A. Appel, Arash Momeni, Derrick C. Wan, Michael T. Longaker","doi":"10.1038/s41551-025-01361-4","DOIUrl":"https://doi.org/10.1038/s41551-025-01361-4","url":null,"abstract":"The inflammatory process resulting in the fibrotic encapsulation of implants has been well studied. However, how acellular dermal matrix (ADM) used in breast reconstruction elicits an attenuated foreign-body response (FBR) remains unclear. Here, by leveraging single-cell RNA-sequencing and proteomic data from pairs of fibrotically encapsulated specimens (bare silicone and silicone wrapped with ADM) collected from individuals undergoing breast reconstruction, we show that high levels of the extracellular-matrix protein osteopontin are associated with the use of ADM as a silicone wrapping. In mice with osteopontin knocked out, FBR attenuation by ADM-coated implants was abrogated. In wild-type mice, the sustained release of recombinant osteopontin from a hydrogel placed adjacent to a silicone implant attenuated the FBR in the absence of ADM. Our findings suggest strategies for the further minimization of the FBR.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"21 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143677652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cas12a-knock-in mice for multiplexed genome editing, disease modelling and immune-cell engineering cas12a敲入小鼠用于多重基因组编辑、疾病建模和免疫细胞工程

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2025-03-20 DOI: 10.1038/s41551-025-01371-2

Kaiyuan Tang, Liqun Zhou, Xiaolong Tian, Shao-Yu Fang, Erica Vandenbulcke, Andrew Du, Johanna Shen, Hanbing Cao, Jerry Zhou, Krista Chen, Hyunu R. Kim, Zhicheng Luo, Shan Xin, Shawn H. Lin, Daniel Park, Luojia Yang, Yueqi Zhang, Kazushi Suzuki, Medha Majety, Xinyu Ling, Stanley Z. Lam, Ryan D. Chow, Ping Ren, Bo Tao, Keyi Li, Adan Codina, Xiaoyun Dai, Xingbo Shang, Suxia Bai, Timothy Nottoli, Andre Levchenko, Carmen J. Booth, Chen Liu, Rong Fan, Matthew B. Dong, Xiaoyu Zhou, Sidi Chen

{"title":"Cas12a-knock-in mice for multiplexed genome editing, disease modelling and immune-cell engineering","authors":"Kaiyuan Tang, Liqun Zhou, Xiaolong Tian, Shao-Yu Fang, Erica Vandenbulcke, Andrew Du, Johanna Shen, Hanbing Cao, Jerry Zhou, Krista Chen, Hyunu R. Kim, Zhicheng Luo, Shan Xin, Shawn H. Lin, Daniel Park, Luojia Yang, Yueqi Zhang, Kazushi Suzuki, Medha Majety, Xinyu Ling, Stanley Z. Lam, Ryan D. Chow, Ping Ren, Bo Tao, Keyi Li, Adan Codina, Xiaoyun Dai, Xingbo Shang, Suxia Bai, Timothy Nottoli, Andre Levchenko, Carmen J. Booth, Chen Liu, Rong Fan, Matthew B. Dong, Xiaoyu Zhou, Sidi Chen","doi":"10.1038/s41551-025-01371-2","DOIUrl":"https://doi.org/10.1038/s41551-025-01371-2","url":null,"abstract":"The pleiotropic effects of human disease and the complex nature of gene-interaction networks require knock-in mice allowing for multiplexed gene perturbations. Here we describe a series of knock-in mice with a C57BL/6 background and with the conditional or constitutive expression of LbCas12a or of high-fidelity enhanced AsCas12a, which were inserted at the Rosa26 locus. The constitutive expression of Cas12a in the mice did not lead to discernible pathology and enabled efficient multiplexed genome engineering. We used the mice for the retrovirus-based immune-cell engineering of CD4+ and CD8+ T cells, B cells and bone-marrow-derived dendritic cells, for autochthonous cancer modelling through the delivery of multiple CRISPR RNAs as a single array using adeno-associated viruses, and for the targeted genome editing of liver tissue using lipid nanoparticles. We also describe a system for simultaneous dual-gene activation and knockout (DAKO). The Cas12a-knock-in mice and the viral and non-viral delivery vehicles provide a versatile toolkit for ex vivo and in vivo applications in genome editing, disease modelling and immune-cell engineering, and for the deconvolution of complex gene interactions.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"18 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143660364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Non-viral intron knock-ins for targeted gene integration into human T cells and for T-cell selection 非病毒内含子敲入基因整合到人类T细胞和T细胞选择

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2025-03-07 DOI: 10.1038/s41551-025-01372-1

Theodore L. Roth, Johnathan Lu, Alison McClellan, Courtney Kernick, Oliver Takacsi-Nagy, Ansuman T. Satpathy

{"title":"Non-viral intron knock-ins for targeted gene integration into human T cells and for T-cell selection","authors":"Theodore L. Roth, Johnathan Lu, Alison McClellan, Courtney Kernick, Oliver Takacsi-Nagy, Ansuman T. Satpathy","doi":"10.1038/s41551-025-01372-1","DOIUrl":"https://doi.org/10.1038/s41551-025-01372-1","url":null,"abstract":"Current methods for the precise integration of DNA sequences into the genome of human T cells predominantly target exonic regions, which limits the choice of integration site and requires complex cell-selection strategies. Here we show that non-viral intron knock-ins for incorporating synthetic exons into endogenous introns enable efficient gene targeting and selective gene knockout in successfully edited cells. In primary human T cells, the knock-in of a chimaeric antigen receptor (CAR) into the T-cell receptor alpha constant locus facilitated the purification of more than 90% CAR+ T cells via the negative selection of T-cell-receptor-negative cells. The method is scalable, applicable across intronic sites, as we show for introns within four distinct endogenous surface-receptor genes, and supports the integration of large synthetic exons (longer than 5 kb), of alternative splicing architectures that preserve endogenous gene expression, and of synthetic promoters allowing for endogenous or user-defined gene regulation. Non-viral intron knock-ins expand the range of targetable genomic sites and provide a simplified and high-throughput strategy for selecting edited primary human T cells.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"229 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143569638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A deep-learning model for quantifying circulating tumour DNA from the density distribution of DNA-fragment lengths 从DNA片段长度的密度分布定量循环肿瘤DNA的深度学习模型

IF 26.8 1区医学

Nature Biomedical Engineering Pub Date : 2025-03-07 DOI: 10.1038/s41551-025-01370-3

Guanhua Zhu, Chowdhury Rafeed Rahman, Victor Getty, Denis Odinokov, Probhonjon Baruah, Hanaé Carrié, Avril Joy Lim, Yu Amanda Guo, Zhong Wee Poh, Ngak Leng Sim, Ahmed Abdelmoneim, Yutong Cai, Lakshmi Narayanan Lakshmanan, Danliang Ho, Saranya Thangaraju, Polly Poon, Yi Ting Lau, Anna Gan, Sarah Ng, Si-Lin Koo, Dawn Q. Chong, Brenda Tay, Tira J. Tan, Yoon Sim Yap, Aik Yong Chok, Matthew Chau Hsien Ng, Patrick Tan, Daniel Tan, Limsoon Wong, Pui Mun Wong, Iain Beehuat Tan, Anders Jacobsen Skanderup

{"title":"A deep-learning model for quantifying circulating tumour DNA from the density distribution of DNA-fragment lengths","authors":"Guanhua Zhu, Chowdhury Rafeed Rahman, Victor Getty, Denis Odinokov, Probhonjon Baruah, Hanaé Carrié, Avril Joy Lim, Yu Amanda Guo, Zhong Wee Poh, Ngak Leng Sim, Ahmed Abdelmoneim, Yutong Cai, Lakshmi Narayanan Lakshmanan, Danliang Ho, Saranya Thangaraju, Polly Poon, Yi Ting Lau, Anna Gan, Sarah Ng, Si-Lin Koo, Dawn Q. Chong, Brenda Tay, Tira J. Tan, Yoon Sim Yap, Aik Yong Chok, Matthew Chau Hsien Ng, Patrick Tan, Daniel Tan, Limsoon Wong, Pui Mun Wong, Iain Beehuat Tan, Anders Jacobsen Skanderup","doi":"10.1038/s41551-025-01370-3","DOIUrl":"10.1038/s41551-025-01370-3","url":null,"abstract":"The quantification of circulating tumour DNA (ctDNA) in blood enables non-invasive surveillance of cancer progression. Here we show that a deep-learning model can accurately quantify ctDNA from the density distribution of cell-free DNA-fragment lengths. We validated the model, which we named ‘Fragle’, by using low-pass whole-genome-sequencing data from multiple cancer types and healthy control cohorts. In independent cohorts, Fragle outperformed tumour-naive methods, achieving higher accuracy and lower detection limits. We also show that Fragle is compatible with targeted sequencing data. In plasma samples from patients with colorectal cancer, longitudinal analysis with Fragle revealed strong concordance between ctDNA dynamics and treatment responses. In patients with resected lung cancer, Fragle outperformed a tumour-naive gene panel in the prediction of minimal residual disease for risk stratification. The method’s versatility, speed and accuracy for ctDNA quantification suggest that it may have broad clinical utility. A deep-learning model can accurately quantify circulating tumour DNA from the density distribution of cell-free DNA-fragment lengths in plasma from patients with cancer and from healthy individuals.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"9 3","pages":"307-319"},"PeriodicalIF":26.8,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143569680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0