Pub Date : 2026-10-06DOI: 10.1038/s41587-026-03303-0
Srilaxmi Bearelly, Cassandra Areff, Matthew K. Hoffman, Daniel Sunko, Andrew F. Laine, Bin Choi, Hanna Rodriguez Coleman, Bianca Cordazzo Vargas, Chloe Y. Li, Jennifer J. Dawkins, Emily Amir, Sahar Paz, Lisa A. Hark, Whitney A. Booker, April A. Jauhal, Justin S. Brandt, Ronald J. Wapner, Liat Shenhav
Hypertensive disorders of pregnancy arise from early placental and systemic vascular dysfunction, yet current first-trimester screening remains imprecise, biologically opaque and logistically challenging. Here we present Visionary AI, an interpretable platform that integrates retinal imaging with graph-based vascular modeling to predict hypertensive disorders before clinical onset. Visionary AI converts retinal images into topological and geometric representations of microvascular structure, enabling risk prediction from biologically grounded vascular features rather than generic image embeddings or clinical variables. In a prospective development cohort of 1,267 pregnancies, Visionary AI achieved strong performance for preeclampsia across population-wide control settings (area under the curve (AUC) = 0.91, average precision (AP) = 0.81). A stability-optimized model transferred without retraining to an independent external validation cohort, achieving AUC = 0.81 and AP = 0.68 and outperforming clinical and deep learning benchmarks. Recurrent features involving retinal vascular topology, geometry, network complexity and hierarchical organization position the maternal retina as a minimally invasive biosensor of systemic vascular health and Visionary AI as a biologically interpretable framework for pregnancy risk stratification.
{"title":"Decoding systemic vascular health and hypertensive disorders in pregnancy through retinal imaging and Visionary AI","authors":"Srilaxmi Bearelly, Cassandra Areff, Matthew K. Hoffman, Daniel Sunko, Andrew F. Laine, Bin Choi, Hanna Rodriguez Coleman, Bianca Cordazzo Vargas, Chloe Y. Li, Jennifer J. Dawkins, Emily Amir, Sahar Paz, Lisa A. Hark, Whitney A. Booker, April A. Jauhal, Justin S. Brandt, Ronald J. Wapner, Liat Shenhav","doi":"10.1038/s41587-026-03303-0","DOIUrl":"https://doi.org/10.1038/s41587-026-03303-0","url":null,"abstract":"Hypertensive disorders of pregnancy arise from early placental and systemic vascular dysfunction, yet current first-trimester screening remains imprecise, biologically opaque and logistically challenging. Here we present Visionary AI, an interpretable platform that integrates retinal imaging with graph-based vascular modeling to predict hypertensive disorders before clinical onset. Visionary AI converts retinal images into topological and geometric representations of microvascular structure, enabling risk prediction from biologically grounded vascular features rather than generic image embeddings or clinical variables. In a prospective development cohort of 1,267 pregnancies, Visionary AI achieved strong performance for preeclampsia across population-wide control settings (area under the curve (AUC) = 0.91, average precision (AP) = 0.81). A stability-optimized model transferred without retraining to an independent external validation cohort, achieving AUC = 0.81 and AP = 0.68 and outperforming clinical and deep learning benchmarks. Recurrent features involving retinal vascular topology, geometry, network complexity and hierarchical organization position the maternal retina as a minimally invasive biosensor of systemic vascular health and Visionary AI as a biologically interpretable framework for pregnancy risk stratification.","PeriodicalId":19084,"journal":{"name":"Nature biotechnology","volume":"41 1","pages":""},"PeriodicalIF":46.9,"publicationDate":"2026-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149087608","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 : 2026-10-05DOI: 10.1038/s41587-026-03356-1
While mammalian delivery technologies are advancing to translation at an exceptional rate, delivery to plant tissues faces challenges, limiting their practical applications.
虽然哺乳动物的输送技术正以惊人的速度发展到翻译，但植物组织的输送面临着挑战，限制了它们的实际应用。
{"title":"Behind (cell) walls","authors":"","doi":"10.1038/s41587-026-03356-1","DOIUrl":"10.1038/s41587-026-03356-1","url":null,"abstract":"While mammalian delivery technologies are advancing to translation at an exceptional rate, delivery to plant tissues faces challenges, limiting their practical applications.","PeriodicalId":19084,"journal":{"name":"Nature biotechnology","volume":"44 10","pages":"1585-1586"},"PeriodicalIF":44.5,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41587-026-03356-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149112593","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 : 2026-10-05DOI: 10.1038/s41587-026-03334-7
Jihoon Han, Seth L. Shipman
Programmable RNA sensors such as toehold switches are used to detect specific RNA sequences. However, their reliance on protein-based or RNA-based outputs limits their use in multiplexed and sequencing-based applications. Here we introduce Detectrons, modular biosensors that couple programmable toehold switches with retron-mediated reverse transcription to transduce RNA inputs into unique DNA barcodes, converting dynamic RNA signals into durable DNA records within living cells. The framework enables alternative modes of transcript-based sensing with applications including viral infection detection. Through the construction of a synthetic toehold retron library and application of machine learning, we uncover key design principles that improve signal strength and specificity. We apply Detectrons to the multiplexed live-cell detection of specific phage infections, enabling transcript-triggered barcode synthesis and quantitative host susceptibility profiling in pooled bacterial populations. Detectrons provide a scalable and generalizable strategy for phage screening and for recording transcriptional events in complex bacterial communities.
{"title":"Detectrons convert transient RNA sequences into stable DNA barcodes for high-throughput analysis of RNA-dependent processes","authors":"Jihoon Han, Seth L. Shipman","doi":"10.1038/s41587-026-03334-7","DOIUrl":"https://doi.org/10.1038/s41587-026-03334-7","url":null,"abstract":"Programmable RNA sensors such as toehold switches are used to detect specific RNA sequences. However, their reliance on protein-based or RNA-based outputs limits their use in multiplexed and sequencing-based applications. Here we introduce Detectrons, modular biosensors that couple programmable toehold switches with retron-mediated reverse transcription to transduce RNA inputs into unique DNA barcodes, converting dynamic RNA signals into durable DNA records within living cells. The framework enables alternative modes of transcript-based sensing with applications including viral infection detection. Through the construction of a synthetic toehold retron library and application of machine learning, we uncover key design principles that improve signal strength and specificity. We apply Detectrons to the multiplexed live-cell detection of specific phage infections, enabling transcript-triggered barcode synthesis and quantitative host susceptibility profiling in pooled bacterial populations. Detectrons provide a scalable and generalizable strategy for phage screening and for recording transcriptional events in complex bacterial communities.","PeriodicalId":19084,"journal":{"name":"Nature biotechnology","volume":"36 1","pages":""},"PeriodicalIF":46.9,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149087611","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}
To discover unknown retrotransposons for genomic integration in human cells, we searched 1,139 avian genomes, identified 159 avian R2 retrotransposons and characterized conserved/nonconserved sequence features in their proteins and untranslated region elements. Engineered variants of these retrotransposons achieved up to 60% site-specific gene integration across human primary cells. This work expands the avian R2 resource and provides additional tools for all-RNA-mediated genome editing.
{"title":"Discovery and engineering of avian R2 retrotransposons for all-RNA-mediated targeted DNA integration in human cells","authors":"Yangcan Chen, Yanping Hu, Shengqiu Luo, Bangwei Mao, Na Tang, Chenxin Wang, Yuze Wang, Hanyu Bai, Xinge Wang, Changxian Peng, Qicheng Chen, Jiahui Xiao, Yu Zou, Peng Wang, Rui Niu, Jin Zhang, Yulong Zhao, Chen Liang, Yunlong Wang, Yiyun Li, Junjie Wang, Ng Shyh-Chang, Tuo Wei, Haoyi Wang, Qi Zhou, Wei Li","doi":"10.1038/s41587-026-03315-w","DOIUrl":"https://doi.org/10.1038/s41587-026-03315-w","url":null,"abstract":"To discover unknown retrotransposons for genomic integration in human cells, we searched 1,139 avian genomes, identified 159 avian R2 retrotransposons and characterized conserved/nonconserved sequence features in their proteins and untranslated region elements. Engineered variants of these retrotransposons achieved up to 60% site-specific gene integration across human primary cells. This work expands the avian R2 resource and provides additional tools for all-RNA-mediated genome editing.","PeriodicalId":19084,"journal":{"name":"Nature biotechnology","volume":"11 1","pages":""},"PeriodicalIF":46.9,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149087647","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 : 2026-10-01DOI: 10.1038/s41587-026-03307-w
Henry E. Miller, Gabriel M. Mejia, Francis J. A. Leblanc, Brendan Swain, Bo Wang, Lucas Paulo de Lima Camillo
Recent benchmarks report that deep-learning-based genetic perturbation models fail to outperform uninformative baselines. Here we introduce a positive control baseline and metric calibration framework, showing—across 14 datasets and 18 metrics—that common benchmarking metrics (for example, mean squared error and Pearson Δ) are frequently miscalibrated, with reduced sensitivity to measure positive model performance. Under well-calibrated metrics, we find that deep-learning-based genetic perturbation models can outperform uninformative baselines.
{"title":"Deep learning perturbation models can outperform baselines on calibrated metrics","authors":"Henry E. Miller, Gabriel M. Mejia, Francis J. A. Leblanc, Brendan Swain, Bo Wang, Lucas Paulo de Lima Camillo","doi":"10.1038/s41587-026-03307-w","DOIUrl":"https://doi.org/10.1038/s41587-026-03307-w","url":null,"abstract":"Recent benchmarks report that deep-learning-based genetic perturbation models fail to outperform uninformative baselines. Here we introduce a positive control baseline and metric calibration framework, showing—across 14 datasets and 18 metrics—that common benchmarking metrics (for example, mean squared error and Pearson Δ) are frequently miscalibrated, with reduced sensitivity to measure positive model performance. Under well-calibrated metrics, we find that deep-learning-based genetic perturbation models can outperform uninformative baselines.","PeriodicalId":19084,"journal":{"name":"Nature biotechnology","volume":"23 1","pages":""},"PeriodicalIF":46.9,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149087615","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 : 2026-09-28DOI: 10.1038/s41587-026-03342-7
Pritha Agarwalla, Edikan A. Ogunnaike, Sarah Ahn, Kristen A. Froehlich, Anton Jansson, Frances S. Ligler, Gianpietro Dotti, Yevgeny Brudno
{"title":"Author Correction: Bioinstructive implantable scaffolds for rapid in vivo manufacture and release of CAR-T cells","authors":"Pritha Agarwalla, Edikan A. Ogunnaike, Sarah Ahn, Kristen A. Froehlich, Anton Jansson, Frances S. Ligler, Gianpietro Dotti, Yevgeny Brudno","doi":"10.1038/s41587-026-03342-7","DOIUrl":"10.1038/s41587-026-03342-7","url":null,"abstract":"","PeriodicalId":19084,"journal":{"name":"Nature biotechnology","volume":"44 10","pages":"1735-1735"},"PeriodicalIF":44.5,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s41587-026-03342-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149075530","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 : 2026-09-28DOI: 10.1038/s41587-026-03297-9
{"title":"Cargo size matters when designing lipid nanoparticles for delivery of large gene editors.","authors":"","doi":"10.1038/s41587-026-03297-9","DOIUrl":"https://doi.org/10.1038/s41587-026-03297-9","url":null,"abstract":"","PeriodicalId":19084,"journal":{"name":"Nature biotechnology","volume":" ","pages":""},"PeriodicalIF":44.5,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149075500","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：