• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

SAM数字PCR:利用零样本分割一切模型进行准确且通用的核酸定量

SAM-dPCR: Accurate and Generalist Nuclei Acid Quantification Leveraging the Zero-Shot Segment Anything Model.

作者信息

Wei Yuanyuan, Luo Shanhang, Xu Changran, Fu Yingqi, Zhang Yi, Qu Fuyang, Zhang Guoxun, Ho Yi-Ping, Ho Ho-Pui, Yuan Wu

机构信息

Department of Biomedical Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China.

Department of Biomedical Engineering, National University of Singapore, Singapore, Singapore.

出版信息

Adv Sci (Weinh). 2025 Feb;12(7):e2406797. doi: 10.1002/advs.202406797. Epub 2024 Dec 27.

DOI:10.1002/advs.202406797
PMID:39731324
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11831435/
Abstract

Digital PCR (dPCR) has transformed nucleic acid diagnostics by enabling the absolute quantification of rare mutations and target sequences. However, traditional dPCR detection methods, such as those involving flow cytometry and fluorescence imaging, may face challenges due to high costs, complexity, limited accuracy, and slow processing speeds. In this study, SAM-dPCR is introduced, a training-free open-source bioanalysis paradigm that offers swift and precise absolute quantification of biological samples. SAM-dPCR leverages the robustness of the zero-shot Segment Anything Model (SAM) to achieve rapid processing times (<4 seconds) with an accuracy exceeding 97.10%. This method has been extensively validated across diverse samples and reactor morphologies, demonstrating its broad applicability. Utilizing standard laboratory fluorescence microscopes, SAM-dPCR can measure nucleic acid template concentrations ranging from 0.154 copies µL to 1.295 × 10 copies µL for droplet dPCR and 0.160 × 10 to 3.629 × 10 copies µL for microwell dPCR. Experimental validation shows a strong linear relationship (r > 0.96) between expected and determined sample concentrations. SAM-dPCR offers high accuracy, accessibility, and the ability to address bioanalytical needs in resource-limited settings, as it does not rely on hand-crafted "ground truth" data.

摘要

数字PCR(dPCR)通过实现对罕见突变和靶序列的绝对定量,改变了核酸诊断技术。然而,传统的dPCR检测方法,如涉及流式细胞术和荧光成像的方法,可能会因成本高、操作复杂、准确性有限和处理速度慢而面临挑战。在本研究中,引入了SAM-dPCR,这是一种无需训练的开源生物分析范式,可对生物样品进行快速、精确的绝对定量。SAM-dPCR利用零样本分割一切模型(SAM)的稳健性,实现了快速处理时间(<4秒),准确率超过97.10%。该方法已在各种样品和反应器形态上得到广泛验证,证明了其广泛的适用性。利用标准实验室荧光显微镜,SAM-dPCR可以测量液滴dPCR中核酸模板浓度范围为0.154拷贝/微升至1.295×10拷贝/微升,微孔dPCR中核酸模板浓度范围为0.160×10至3.629×10拷贝/微升。实验验证表明,预期样品浓度与测定样品浓度之间存在很强的线性关系(r>0.96)。SAM-dPCR具有高精度、易获取性,并且能够满足资源有限环境中的生物分析需求,因为它不依赖手工制作的“真实”数据。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/abca892afbcd/ADVS-12-2406797-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/c4c4fa12fcfe/ADVS-12-2406797-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/96e1272e56b5/ADVS-12-2406797-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/e92f4eb6b2c8/ADVS-12-2406797-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/287ef96d3509/ADVS-12-2406797-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/948ae4347277/ADVS-12-2406797-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/0f2cbdafd879/ADVS-12-2406797-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/abca892afbcd/ADVS-12-2406797-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/c4c4fa12fcfe/ADVS-12-2406797-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/96e1272e56b5/ADVS-12-2406797-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/e92f4eb6b2c8/ADVS-12-2406797-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/287ef96d3509/ADVS-12-2406797-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/948ae4347277/ADVS-12-2406797-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/0f2cbdafd879/ADVS-12-2406797-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/293d/11831435/abca892afbcd/ADVS-12-2406797-g001.jpg

相似文献

1
SAM-dPCR: Accurate and Generalist Nuclei Acid Quantification Leveraging the Zero-Shot Segment Anything Model.SAM数字PCR:利用零样本分割一切模型进行准确且通用的核酸定量
Adv Sci (Weinh). 2025 Feb;12(7):e2406797. doi: 10.1002/advs.202406797. Epub 2024 Dec 27.
2
Droplet Digital Polymerase Chain Reaction Method for Absolute Quantification of Influenza A Viruses.用于甲型流感病毒绝对定量的液滴数字聚合酶链反应方法
Bing Du Xue Bao. 2017 Jan;33(1):1-5.
3
An approach for integrating droplet generation and detection in digital polymerase chain reaction applications based on a bifunctional microfluidic cross-structure.基于双功能微流控十字结构的数字聚合酶链反应应用中液滴生成与检测的集成方法。
Talanta. 2024 Jan 15;267:125240. doi: 10.1016/j.talanta.2023.125240. Epub 2023 Sep 28.
4
Digital polymerase chain reaction strategies for accurate and precise detection of vector copy number in chimeric antigen receptor T-cell products.数字聚合酶链反应策略可准确、精确地检测嵌合抗原受体 T 细胞产品中的载体拷贝数。
Cytotherapy. 2023 Jan;25(1):94-102. doi: 10.1016/j.jcyt.2022.09.004. Epub 2022 Oct 14.
5
Deep-qGFP: A Generalist Deep Learning Assisted Pipeline for Accurate Quantification of Green Fluorescent Protein Labeled Biological Samples in Microreactors.深 qGFP:一种通用深度学习辅助的微流控器中绿色荧光蛋白标记生物样本精确定量的流水线。
Small Methods. 2024 Mar;8(3):e2301293. doi: 10.1002/smtd.202301293. Epub 2023 Nov 27.
6
Clarity™ digital PCR system: a novel platform for absolute quantification of nucleic acids.Clarity™数字PCR系统:一种用于核酸绝对定量的新型平台。
Anal Bioanal Chem. 2017 Mar;409(7):1869-1875. doi: 10.1007/s00216-016-0131-7. Epub 2016 Dec 17.
7
Digital PCR and its applications in noninvasive prenatal testing.数字 PCR 及其在无创产前检测中的应用。
Brief Funct Genomics. 2022 Sep 16;21(5):376-386. doi: 10.1093/bfgp/elac024.
8
Applications of Digital Polymerase Chain Reaction (dPCR) in Molecular and Clinical Testing.数字聚合酶链反应 (dPCR) 在分子和临床检测中的应用。
J Appl Lab Med. 2024 Jan 3;9(1):124-137. doi: 10.1093/jalm/jfad103.
9
High-Resolution Melting (HRM) analysis of DNA methylation using semiconductor chip-based digital PCR.基于半导体芯片的数字 PCR 的 DNA 甲基化高分辨率熔解(HRM)分析。
Genes Genomics. 2024 Aug;46(8):909-915. doi: 10.1007/s13258-024-01527-5. Epub 2024 Jun 8.
10
Digital PCR for accurate quantification of pathogens: Principles, applications, challenges and future prospects.数字 PCR 用于病原体的精确定量:原理、应用、挑战与未来展望。
Int J Biol Macromol. 2021 Aug 1;184:750-759. doi: 10.1016/j.ijbiomac.2021.06.132. Epub 2021 Jun 24.

本文引用的文献

1
An Integrated ddPCR Lab-on-a-Disc Device for Rapid Screening of Infectious Diseases.一种用于传染病快速筛查的集成式数字PCR芯片实验室设备。
Biosensors (Basel). 2023 Dec 21;14(1):2. doi: 10.3390/bios14010002.
2
StratoLAMP: Label-free, multiplex digital loop-mediated isothermal amplification based on visual stratification of precipitate.StratoLAMP:基于沉淀可视化分层的无标记、多重数字环介导等温扩增。
Proc Natl Acad Sci U S A. 2024 Jan 9;121(2):e2314030121. doi: 10.1073/pnas.2314030121. Epub 2024 Jan 2.
3
Deep-qGFP: A Generalist Deep Learning Assisted Pipeline for Accurate Quantification of Green Fluorescent Protein Labeled Biological Samples in Microreactors.
深 qGFP:一种通用深度学习辅助的微流控器中绿色荧光蛋白标记生物样本精确定量的流水线。
Small Methods. 2024 Mar;8(3):e2301293. doi: 10.1002/smtd.202301293. Epub 2023 Nov 27.
4
Label-Free Virtual HER2 Immunohistochemical Staining of Breast Tissue using Deep Learning.使用深度学习对乳腺组织进行无标记虚拟HER2免疫组织化学染色
BME Front. 2022 Oct 25;2022:9786242. doi: 10.34133/2022/9786242. eCollection 2022.
5
Unraveling the complexity of Optical Coherence Tomography image segmentation using machine and deep learning techniques: A review.利用机器学习和深度学习技术解析光学相干断层扫描图像分割的复杂性:综述。
Comput Med Imaging Graph. 2023 Sep;108:102269. doi: 10.1016/j.compmedimag.2023.102269. Epub 2023 Jul 14.
6
A one-stage deep learning based method for automatic analysis of droplet-based digital PCR images.基于深度学习的一步法自动分析液滴式数字 PCR 图像。
Analyst. 2023 Jun 26;148(13):3065-3073. doi: 10.1039/d3an00615h.
7
Rapid Prototyping of Multi-Functional and Biocompatible Parafilm-Based Microfluidic Devices by Laser Ablation and Thermal Bonding.通过激光烧蚀和热键合实现基于多功能且生物相容的石蜡膜的微流控装置的快速原型制作
Micromachines (Basel). 2023 Mar 14;14(3):656. doi: 10.3390/mi14030656.
8
Deep learning-enabled virtual histological staining of biological samples.基于深度学习的生物样本虚拟组织学染色
Light Sci Appl. 2023 Mar 3;12(1):57. doi: 10.1038/s41377-023-01104-7.
9
A deep learning based method for automatic analysis of high-throughput droplet digital PCR images.一种基于深度学习的高通量微滴数字PCR图像自动分析方法。
Analyst. 2023 Jan 16;148(2):239-247. doi: 10.1039/d2an01631a.
10
Incorporating the image formation process into deep learning improves network performance.将图像形成过程纳入深度学习可以提高网络性能。
Nat Methods. 2022 Nov;19(11):1427-1437. doi: 10.1038/s41592-022-01652-7. Epub 2022 Oct 31.