A robust unsupervised machine-learning method to quantify the morphological heterogeneity of cells and nuclei

• Published in: Nature protocols Vol. 16; no. 2; pp. 754 - 774
• Main Authors: Phillip, Jude M., Han, Kyu-Sang, Chen, Wei-Chiang, Wirtz, Denis, Wu, Pei-Hsun
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01.02.2021; Nature Publishing Group
• Subjects: 631/114/1564; 631/1647/245/2225; 631/1647/794; 631/57/2266; 631/80; Algorithms; Analytical Chemistry; Biological activity; Biological Techniques; Biomedical and Life Sciences; Cell morphology; Cell Nucleus - physiology; Cell physiology; Cell research; Cell Shape - physiology; Computational Biology/Bioinformatics; Cytology; Fluorescence; Heterogeneity; Humans; Hydrogels; Imaging, Three-Dimensional - methods; Learning algorithms; Life Sciences; Machine learning; Medical imaging; Methods; Microarrays; Microenvironments; Microscopy, Confocal - methods; Morphology; Organic Chemistry; Populations; Protocol; Protocol (computers); Public software; Software; Substrates; Unsupervised learning; Unsupervised Machine Learning - statistics & numerical data; United States
• ISSN: 1754-2189; 1750-2799; 1750-2799
• DOI: 10.1038/s41596-020-00432-x

Cell morphology encodes essential information on many underlying biological processes. It is commonly used by clinicians and researchers in the study, diagnosis, prognosis, and treatment of human diseases. Quantification of cell morphology has seen tremendous advances in recent years. However, effectively defining morphological shapes and evaluating the extent of morphological heterogeneity within cell populations remain challenging. Here we present a protocol and software for the analysis of cell and nuclear morphology from fluorescence or bright-field images using the VAMPIRE algorithm ( https://github.com/kukionfr/VAMPIRE_open ). This algorithm enables the profiling and classification of cells into shape modes based on equidistant points along cell and nuclear contours. Examining the distributions of cell morphologies across automatically identified shape modes provides an effective visualization scheme that relates cell shapes to cellular subtypes based on endogenous and exogenous cellular conditions. In addition, these shape mode distributions offer a direct and quantitative way to measure the extent of morphological heterogeneity within cell populations. This protocol is highly automated and fast, with the ability to quantify the morphologies from 2D projections of cells seeded both on 2D substrates or embedded within 3D microenvironments, such as hydrogels and tissues. The complete analysis pipeline can be completed within 60 minutes for a dataset of ~20,000 cells/2,400 images. This protocol describes VAMPIRE, an unsupervised machine-learning approach that can be used to quantify and categorize cellular morphology from fluorescence or bright-field images of cells grown in 2D, 3D and tissue slices.