Suppr超能文献

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。

Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification.

作者信息

Logan David J, Shan Jing, Bhatia Sangeeta N, Carpenter Anne E

机构信息

The Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA 02142, United States.

Harvard-MIT Division of Health Sciences and Technology, MIT, E25-518, 77 Massachusetts Ave, Cambridge, MA 02139, United States.

出版信息

Methods. 2016 Mar 1;96:6-11. doi: 10.1016/j.ymeth.2015.12.002. Epub 2015 Dec 11.

Abstract

Biologists increasingly use co-culture systems in which two or more cell types are grown in cell culture together in order to better model cells' native microenvironments. Co-cultures are often required for cell survival or proliferation, or to maintain physiological functioning in vitro. Having two cell types co-exist in culture, however, poses several challenges, including difficulties distinguishing the two populations during analysis using automated image analysis algorithms. We previously analyzed co-cultured primary human hepatocytes and mouse fibroblasts in a high-throughput image-based chemical screen, using a combination of segmentation, measurement, and subsequent machine learning to score each cell as hepatocyte or fibroblast. While this approach was successful in counting hepatocytes for primary screening, segmentation of the fibroblast nuclei was less accurate. Here, we present an improved approach that more accurately identifies both cell types. Pixel-based machine learning (using the software ilastik) is used to seed segmentation of each cell type individually (using the software CellProfiler). This streamlined and accurate workflow can be carried out using freely available and open source software.

摘要

生物学家越来越多地使用共培养系统,在这种系统中,两种或更多种细胞类型在细胞培养中一起生长,以便更好地模拟细胞的天然微环境。共培养通常是细胞存活或增殖所必需的,或者是为了在体外维持生理功能。然而,让两种细胞类型在培养中共存会带来几个挑战,包括在使用自动图像分析算法进行分析时难以区分这两个群体。我们之前在基于图像的高通量化学筛选中分析了共培养的原代人肝细胞和小鼠成纤维细胞,使用分割、测量以及随后的机器学习相结合的方法,将每个细胞分类为肝细胞或成纤维细胞。虽然这种方法在初级筛选中成功地对肝细胞进行了计数,但成纤维细胞核的分割不太准确。在这里,我们提出了一种改进的方法,能更准确地识别这两种细胞类型。基于像素的机器学习(使用ilastik软件)用于分别对每种细胞类型进行种子分割(使用CellProfiler软件)。这种简化且准确的工作流程可以使用免费的开源软件来执行。

相似文献

1
Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification.
Methods. 2016 Mar 1;96:6-11. doi: 10.1016/j.ymeth.2015.12.002. Epub 2015 Dec 11.
2
Quality Control for High-Throughput Imaging Experiments Using Machine Learning in Cellprofiler.
Methods Mol Biol. 2018;1683:89-112. doi: 10.1007/978-1-4939-7357-6_7.
3
An open-source solution for advanced imaging flow cytometry data analysis using machine learning.
Methods. 2017 Jan 1;112:201-210. doi: 10.1016/j.ymeth.2016.08.018. Epub 2016 Sep 2.
4
Machine Learning: Advanced Image Segmentation Using ilastik.
Methods Mol Biol. 2019;2040:449-463. doi: 10.1007/978-1-4939-9686-5_21.
5
Automated phenotype pattern recognition of zebrafish for high-throughput screening.
Bioengineered. 2016 Jul 3;7(4):261-5. doi: 10.1080/21655979.2016.1197710.
6
A cell-level quality control workflow for high-throughput image analysis.
BMC Bioinformatics. 2020 Jul 2;21(1):280. doi: 10.1186/s12859-020-03603-5.
7
: High-Throughput Quantification of Fluorescent Synaptic Protein Puncta by Machine Learning.
eNeuro. 2017 Dec 6;4(6). doi: 10.1523/ENEURO.0219-17.2017. eCollection 2017 Nov-Dec.
8
A micropatterned hepatocyte coculture model for assessment of liver toxicity using high-content imaging analysis.
Assay Drug Dev Technol. 2014 Jan-Feb;12(1):16-27. doi: 10.1089/adt.2013.525. Epub 2014 Jan 20.
9
Accurate Detection of Dysmorphic Nuclei Using Dynamic Programming and Supervised Classification.
PLoS One. 2017 Jan 26;12(1):e0170688. doi: 10.1371/journal.pone.0170688. eCollection 2017.
10
An open access, machine learning pipeline for high-throughput quantification of cell morphology.
STAR Protoc. 2023 Mar 17;4(1):101947. doi: 10.1016/j.xpro.2022.101947. Epub 2022 Dec 15.

引用本文的文献

4
Disease phenotypic screening in neuron-glia cocultures identifies blockers of inflammatory neurodegeneration.
iScience. 2024 Mar 8;27(4):109454. doi: 10.1016/j.isci.2024.109454. eCollection 2024 Apr 19.
5
: Processing utilities for high-resolution images for spatially resolved transcriptomics data.
Biol Imaging. 2023 Nov 13;3:e23. doi: 10.1017/S2633903X23000235. eCollection 2023.
7
Identifying In Vitro Cultured Human Hepatocytes Markers with Machine Learning Methods Based on Single-Cell RNA-Seq Data.
Front Bioeng Biotechnol. 2022 May 30;10:916309. doi: 10.3389/fbioe.2022.916309. eCollection 2022.
9
An in vitro ovarian explant culture system to examine sex change in a hermaphroditic fish.
PeerJ. 2020 Nov 11;8:e10323. doi: 10.7717/peerj.10323. eCollection 2020.
10

本文引用的文献

1
Pipeline for illumination correction of images for high-throughput microscopy.
J Microsc. 2014 Dec;256(3):231-6. doi: 10.1111/jmi.12178. Epub 2014 Sep 16.
2
Machine learning in cell biology - teaching computers to recognize phenotypes.
J Cell Sci. 2013 Dec 15;126(Pt 24):5529-39. doi: 10.1242/jcs.123604. Epub 2013 Nov 20.
3
Niche-based screening identifies small-molecule inhibitors of leukemia stem cells.
Nat Chem Biol. 2013 Dec;9(12):840-848. doi: 10.1038/nchembio.1367. Epub 2013 Oct 27.
4
A microscale human liver platform that supports the hepatic stages of Plasmodium falciparum and vivax.
Cell Host Microbe. 2013 Jul 17;14(1):104-15. doi: 10.1016/j.chom.2013.06.005.
5
Identification of small molecules for human hepatocyte expansion and iPS differentiation.
Nat Chem Biol. 2013 Aug;9(8):514-20. doi: 10.1038/nchembio.1270. Epub 2013 Jun 2.
8
Using a co-culture microsystem for cell migration under fluid shear stress.
Lab Chip. 2011 Aug 7;11(15):2583-90. doi: 10.1039/c1lc20113a. Epub 2011 Jun 21.
9
Improved structure, function and compatibility for CellProfiler: modular high-throughput image analysis software.
Bioinformatics. 2011 Apr 15;27(8):1179-80. doi: 10.1093/bioinformatics/btr095. Epub 2011 Feb 23.
10
Review: role of tubal environment in preimplantation embryogenesis: application to co-culture assays.
Zygote. 2011 Feb;19(1):47-54. doi: 10.1017/S0967199410000092. Epub 2010 Jul 13.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验