在Cellprofiler中使用机器学习进行高通量成像实验的质量控制
Quality Control for High-Throughput Imaging Experiments Using Machine Learning in Cellprofiler.
作者信息
Bray Mark-Anthony, Carpenter Anne E
机构信息
Novartis Institutes for BioMedical Research, Cambridge, MA, USA.
Imaging Platform, Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA, 02142, USA.
出版信息
Methods Mol Biol. 2018;1683:89-112. doi: 10.1007/978-1-4939-7357-6_7.
Abstract
Robust high-content screening of visual cellular phenotypes has been enabled by automated microscopy and quantitative image analysis. The identification and removal of common image-based aberrations is critical to the screening workflow. Out-of-focus images, debris, and auto-fluorescing samples can cause artifacts such as focus blur and image saturation, contaminating downstream analysis and impairing identification of subtle phenotypes. Here, we describe an automated quality control protocol implemented in validated open-source software, leveraging the suite of image-based measurements generated by CellProfiler and the machine-learning functionality of CellProfiler Analyst.
摘要
自动化显微镜和定量图像分析实现了对视觉细胞表型的强大高内涵筛选。识别和去除常见的基于图像的像差对于筛选工作流程至关重要。失焦图像、碎片和自发荧光样本会导致诸如焦点模糊和图像饱和等伪像，污染下游分析并妨碍对细微表型的识别。在这里，我们描述了一种在经过验证的开源软件中实施的自动化质量控制方案，利用CellProfiler生成的一系列基于图像的测量值以及CellProfiler Analyst的机器学习功能。
相似文献
1
Quality Control for High-Throughput Imaging Experiments Using Machine Learning in Cellprofiler.在Cellprofiler中使用机器学习进行高通量成像实验的质量控制
Methods Mol Biol. 2018;1683:89-112. doi: 10.1007/978-1-4939-7357-6_7.
2
Automated Classification of Cellular Phenotypes Using Machine Learning in Cellprofiler and CellProfiler Analyst.基于 Cellprofiler 和 CellProfiler Analyst 中的机器学习对细胞表型进行自动分类。
Methods Mol Biol. 2022;2488:207-226. doi: 10.1007/978-1-0716-2277-3_14.
3
An open-source solution for advanced imaging flow cytometry data analysis using machine learning.一种使用机器学习进行高级成像流式细胞术数据分析的开源解决方案。
Methods. 2017 Jan 1;112:201-210. doi: 10.1016/j.ymeth.2016.08.018. Epub 2016 Sep 2.
4
A cell-level quality control workflow for high-throughput image analysis.一种用于高通量图像分析的细胞层质量控制工作流程。
BMC Bioinformatics. 2020 Jul 2;21(1):280. doi: 10.1186/s12859-020-03603-5.
5
CellProfiler Analyst 3.0: accessible data exploration and machine learning for image analysis.CellProfiler Analyst 3.0：适用于图像分析的可访问数据探索和机器学习。
Bioinformatics. 2021 Nov 5;37(21):3992-3994. doi: 10.1093/bioinformatics/btab634.
6
Workflow and metrics for image quality control in large-scale high-content screens.大规模高内涵筛选中图像质量控制的工作流程和指标
J Biomol Screen. 2012 Feb;17(2):266-74. doi: 10.1177/1087057111420292. Epub 2011 Sep 28.
7
Objective detection of apoptosis in rat renal tissue sections using light microscopy and free image analysis software with subsequent machine learning: Detection of apoptosis in renal tissue.使用光学显微镜和免费图像分析软件并随后进行机器学习对大鼠肾组织切片中的细胞凋亡进行客观检测：肾组织中细胞凋亡的检测
Tissue Cell. 2017 Feb;49(1):22-27. doi: 10.1016/j.tice.2016.12.006. Epub 2016 Dec 28.
8
Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification.使用基于像素的分类方法在高通量条件下对共培养细胞表型进行定量分析。
Methods. 2016 Mar 1;96:6-11. doi: 10.1016/j.ymeth.2015.12.002. Epub 2015 Dec 11.
9
Comparison between two programs for image analysis, machine learning and subsequent classification.两种图像分析、机器学习和后续分类程序的比较。
Tissue Cell. 2019 Jun;58:12-16. doi: 10.1016/j.tice.2019.03.002. Epub 2019 Mar 27.
10
CellProfiler Tracer: exploring and validating high-throughput, time-lapse microscopy image data.CellProfiler Tracer：探索和验证高通量、延时显微镜图像数据。
BMC Bioinformatics. 2015 Nov 4;16:368. doi: 10.1186/s12859-015-0759-x.
引用本文的文献
1
Fluorescence lifetime sorting reveals tunable enzyme interactions within cytoplasmic condensates.荧光寿命分选揭示细胞质液滴中可调节的酶相互作用。
J Cell Biol. 2025 Jan 6;224(1). doi: 10.1083/jcb.202311105. Epub 2024 Oct 14.
2
CLEMSite, a software for automated phenotypic screens using light microscopy and FIB-SEM.CLEMSite，一款用于使用光学显微镜和 FIB-SEM 进行自动表型筛选的软件。
J Cell Biol. 2023 Mar 6;222(3). doi: 10.1083/jcb.202209127. Epub 2022 Dec 23.
3
Quality assessment in light microscopy for routine use through simple tools and robust metrics.通过简单工具和稳健指标进行常规使用的明场显微镜质量评估。
J Cell Biol. 2022 Nov 7;221(11). doi: 10.1083/jcb.202107093. Epub 2022 Sep 29.
4
Next-Generation Pathology Using Multiplexed Immunohistochemistry: Mapping Tissue Architecture at Single-Cell Level.使用多重免疫组织化学的新一代病理学：在单细胞水平绘制组织结构图
Front Oncol. 2022 Jul 29;12:918900. doi: 10.3389/fonc.2022.918900. eCollection 2022.
5
Serine/Threonine Protein Phosphatase 2A Regulates the Transport of Axonal Mitochondria.丝氨酸/苏氨酸蛋白磷酸酶2A调节轴突线粒体的运输。
Front Cell Neurosci. 2022 Mar 18;16:852245. doi: 10.3389/fncel.2022.852245. eCollection 2022.
6
Data Integration Challenges for Machine Learning in Precision Medicine.精准医学中机器学习的数据整合挑战
Front Med (Lausanne). 2022 Jan 25;8:784455. doi: 10.3389/fmed.2021.784455. eCollection 2021.
7
Systematic High-Content Screening of Fluorescently Tagged Yeast Double Mutant Strains.系统的荧光标记酵母双突变株高通量筛选
Methods Mol Biol. 2021;2381:57-78. doi: 10.1007/978-1-0716-1740-3_3.
8
Marine dissolved organic matter: a vast and unexplored molecular space.海洋溶解有机物：广阔而未知的分子空间。
Appl Microbiol Biotechnol. 2021 Oct;105(19):7225-7239. doi: 10.1007/s00253-021-11489-3. Epub 2021 Sep 18.
9
High-Throughput Imaging of Arrays of Fluorescently Tagged Yeast Mutant Strains.高通量成像阵列的荧光标记酵母突变株。
Methods Mol Biol. 2021;2304:221-242. doi: 10.1007/978-1-0716-1402-0_12.
10
Barriers and Enablers for Artificial Intelligence in Dental Diagnostics: A Qualitative Study.牙科诊断中人工智能的障碍与促进因素：一项定性研究。
J Clin Med. 2021 Apr 10;10(8):1612. doi: 10.3390/jcm10081612.
本文引用的文献
1
Annotated high-throughput microscopy image sets for validation.用于验证的带注释的高通量显微镜图像集。
Nat Methods. 2012 Jun 28;9(7):637. doi: 10.1038/nmeth.2083.
2
PhenoRipper: software for rapidly profiling microscopy images.PhenoRipper：用于快速分析显微镜图像的软件。
Nat Methods. 2012 Jun 28;9(7):635-7. doi: 10.1038/nmeth.2097.
3
Workflow and metrics for image quality control in large-scale high-content screens.大规模高内涵筛选中图像质量控制的工作流程和指标
J Biomol Screen. 2012 Feb;17(2):266-74. doi: 10.1177/1087057111420292. Epub 2011 Sep 28.
4
Improved structure, function and compatibility for CellProfiler: modular high-throughput image analysis software.改进 CellProfiler 的结构、功能和兼容性：用于高通量图像分析的模块化软件。
Bioinformatics. 2011 Apr 15;27(8):1179-80. doi: 10.1093/bioinformatics/btr095. Epub 2011 Feb 23.
5
High-content phenotypic profiling of drug response signatures across distinct cancer cells.高内涵表型分析鉴定不同癌细胞中药物反应特征。
Mol Cancer Ther. 2010 Jun;9(6):1913-26. doi: 10.1158/1535-7163.MCT-09-1148. Epub 2010 Jun 8.
6
Screening cellular feature measurements for image-based assay development.为基于图像的分析方法开发筛选细胞特征测量值。
J Biomol Screen. 2010 Aug;15(7):840-6. doi: 10.1177/1087057110370895. Epub 2010 Jun 1.
7
Automated microscopy for high-content RNAi screening.自动化显微镜高通量 RNAi 筛选
J Cell Biol. 2010 Feb 22;188(4):453-61. doi: 10.1083/jcb.200910105.
8
High-content screening: a decade of evolution.高内涵筛选：十年发展历程
J Biomol Screen. 2010 Jan;15(1):1-9. doi: 10.1177/1087057109353790. Epub 2009 Dec 11.
9
Image analysis in high-content screening.高内涵筛选中的图像分析
Comb Chem High Throughput Screen. 2009 Nov;12(9):899-907. doi: 10.2174/138620709789383213.
10
Scoring diverse cellular morphologies in image-based screens with iterative feedback and machine learning.通过迭代反馈和机器学习在基于图像的筛选中对多种细胞形态进行评分。
Proc Natl Acad Sci U S A. 2009 Feb 10;106(6):1826-31. doi: 10.1073/pnas.0808843106. Epub 2009 Feb 2.
Zotero 插件