A deep generative model of 3D single-cell organization

We introduce a framework for end-to-end integrative modeling of 3D single-cell multi-channel fluorescent image data of diverse subcellular structures. We employ stacked conditional β-variational autoencoders to first learn a latent representation of cell morphology, and then learn a latent representation of subcellular structure localization which is conditioned on the learned cell morphology. Our model is flexible and can be trained on images of arbitrary subcellular structures and at varying degrees of sparsity and reconstruction fidelity. We train our full model on 3D cell image data and explore design trade-offs in the 2D setting. Once trained, our model can be used to impute structures in cells where they were not imaged and to quantify the variation in the location of all subcellular structures by generating plausible instantiations of each structure in arbitrary cell geometries. We apply our trained model to a small drug perturbation screen to demonstrate its applicability to new data. We show how the latent representations of drugged cells differ from unperturbed cells as expected by on-target effects of the drugs.

Download Full-text

Cervical Cancer Single Cell Image Data Augmentation Using Residual Condition Generative Adversarial Networks

2020 3rd International Conference on Artificial Intelligence and Big Data (ICAIBD) ◽

10.1109/icaibd49809.2020.9137494 ◽

2020 ◽

Author(s):

Siyu Chen ◽

Dongrui Gao ◽

Lutao Wang ◽

Yongqing Zhang

Keyword(s):

Cervical Cancer ◽

Single Cell ◽

Data Augmentation ◽

Image Data ◽

Generative Adversarial Networks ◽

Cell Image ◽

Adversarial Networks

Download Full-text

An artificial intelligent platform for live cell identification and the detection of cross-contamination (Preprint)

10.2196/preprints.13932 ◽

2019 ◽

Author(s):

Ruixin Wang ◽

Dongni Wang ◽

Dekai Kang ◽

Xusen Guo ◽

Chong Guo ◽

...

Keyword(s):

Single Cell ◽

Cell Line ◽

Cell Lines ◽

Cell Morphology ◽

Single Cell Level ◽

Cross Contamination ◽

Cell Level ◽

Cell Identification ◽

Pure Cell ◽

Microscopy Images

BACKGROUND In vitro human cell line models have been widely used for biomedical research to predict clinical response, identify novel mechanisms and drug response. However, one-fifth to one-third of cell lines have been cross-contaminated, which can seriously result in invalidated experimental results, unusable therapeutic products and waste of research funding. Cell line misidentification and cross-contamination may occur at any time, but authenticating cell lines is infrequent performed because the recommended genetic approaches are usually require extensive expertise and may take a few days. Conversely, the observation of live-cell morphology is a direct and real-time technique. OBJECTIVE The purpose of this study was to construct a novel computer vision technology based on deep convolutional neural networks (CNN) for “cell face” recognition. This was aimed to improve cell identification efficiency and reduce the occurrence of cell-line cross contamination. METHODS Unstained optical microscopy images of cell lines were obtained for model training (about 334 thousand patch images), and testing (about 153 thousand patch images). The AI system first trained to recognize the pure cell morphology. In order to find the most appropriate CNN model，we explored the key image features in cell morphology classification tasks using the classical CNN model-Alexnet. After that, a preferred fine-grained recognition model BCNN was used for the cell type identification (seven classifications). Next, we simulated the situation of cell cross-contamination and mixed the cells in pairs at different ratios. The detection of the cross-contamination was divided into two levels, whether the cells are mixed and what the contaminating cell is. The specificity, sensitivity, and accuracy of the model were tested separately by external validation. Finally, the segmentation model DialedNet was used to present the classification results at the single cell level. RESULTS The cell texture and density were the influencing factors that can be better recognized by the bilinear convolutional neural network (BCNN) comparing to AlexNet. The BCNN achieved 99.5% accuracy in identifying seven pure cell lines and 86.3% accuracy for detecting cross-contamination (mixing two of the seven cell lines). DilatedNet was applied to the semantic segment for analyzing in single-cell level and achieved an accuracy of 98.2%. CONCLUSIONS This study successfully demonstrated that cell lines can be morphologically identified using deep learning models. Only light-microscopy images and no reagents are required, enabling most labs to routinely perform cell identification tests.

Download Full-text

The Ethanologenic Bacterium Zymomonas mobilis Divides Asymmetrically and Exhibits Heterogeneity in DNA Content

Applied and Environmental Microbiology ◽

10.1128/aem.02441-20 ◽

2021 ◽

Vol 87 (6) ◽

Author(s):

Katsuya Fuchino ◽

Helena Chan ◽

Ling Chin Hwang ◽

Per Bruheim

Keyword(s):

Cell Growth ◽

Single Cell ◽

Cell Size ◽

Dna Content ◽

Bacterial Cell ◽

Zymomonas Mobilis ◽

Biofuel Production ◽

Public Attention ◽

Content Type ◽

Cell Organization

ABSTRACT The alphaproteobacterium Zymomonas mobilis exhibits extreme ethanologenic physiology, making this species a promising biofuel producer. Numerous studies have investigated its biology relevant to industrial applications and mostly at the population level. However, the organization of single cells in this industrially important polyploid species has been largely uncharacterized. In the present study, we characterized basic cellular behavior of Z. mobilis strain Zm6 under anaerobic conditions at the single-cell level. We observed that growing Z. mobilis cells often divided at a nonmidcell position, which contributed to variant cell size at birth. However, the cell size variance was regulated by a modulation of cell cycle span, mediated by a correlation of bacterial tubulin homologue FtsZ ring accumulation with cell growth. The Z. mobilis culture also exhibited heterogeneous cellular DNA content among individual cells, which might have been caused by asynchronous replication of chromosome that was not coordinated with cell growth. Furthermore, slightly angled divisions might have resulted in temporary curvatures of attached Z. mobilis cells. Overall, the present study uncovers a novel bacterial cell organization in Z. mobilis. IMPORTANCE With increasing environmental concerns about the use of fossil fuels, development of a sustainable biofuel production platform has been attracting significant public attention. Ethanologenic Z. mobilis species are endowed with an efficient ethanol fermentation capacity that surpasses, in several respects, that of baker’s yeast (Saccharomyces cerevisiae), the most-used microorganism for ethanol production. For development of a Z. mobilis culture-based biorefinery, an investigation of its uncharacterized cell biology is important, because bacterial cellular organization and metabolism are closely associated with each other in a single cell compartment. In addition, the current work demonstrates that the polyploid bacterium Z. mobilis exhibits a distinctive mode of bacterial cell organization, likely reflecting its unique metabolism that does not prioritize incorporation of nutrients for cell growth. Thus, another significant result of this work is to advance our general understanding in the diversity of bacterial cell architecture.

Download Full-text

ME-VAE: Multi-Encoder Variational AutoEncoder for Controlling Multiple Transformational Features in Single Cell Image Analysis

10.1101/2021.04.22.441005 ◽

2021 ◽

Author(s):

Luke Ternes ◽

Mark Dane ◽

Marilyne Labrie ◽

Gordon Mills ◽

Joe Gray ◽

...

Keyword(s):

Image Analysis ◽

Single Cell ◽

Imaging Features ◽

Phenotypic Differences ◽

Cell Image ◽

Intensity Measurements ◽

Quantitative Measurements ◽

Variational Autoencoder ◽

Cell Image Analysis ◽

Organizational Features

AbstractImage-based cell phenotyping relies on quantitative measurements as encoded representations of cells; however, defining suitable representations that capture complex imaging features is challenging since there are many obstacles, including segmentation and identifying subcellular compartments for feature extraction. Variational autoencoder (VAE) approaches produce encouraging results by mapping from an image to a representative descriptor, and outperform classical hand-crafted features for morphology, intensity, and texture at differentiating data. Although VAEs show promising results for capturing morphological and organizational features in tissue, single cell image analyses based on VAEs often fail to identify biologically informative features due to the intrinsic amount of uninformative variability. Herein, we propose a multi-encoder VAE (ME-VAE) in single cell image analysis using transformed images as a self-supervised signal to extract transform-invariant biologically meaningful features. We show that the proposed architecture improves analysis by making distinct populations more separable compared to traditional VAEs and intensity measurements by enhancing phenotypic differences between cells and by improving correlations to other modalities.

Download Full-text

Predicting drug polypharmacology from cell morphology readouts using variational autoencoder latent space arithmetic

10.1101/2021.09.02.458673 ◽

2021 ◽

Author(s):

Yuen Ler Chow ◽

Shantanu Singh ◽

Anne E Carpenter ◽

Gregory P. Way

Keyword(s):

Gene Expression ◽

Cell Morphology ◽

Learning Algorithm ◽

Simulated Data ◽

Biomedical Data ◽

Data Types ◽

Generative Capacity ◽

Latent Space ◽

Variational Autoencoder ◽

Target Effects

A variational autoencoder (VAE) is a machine learning algorithm, useful for generating a compressed and interpretable latent space. These representations have been generated from various biomedical data types and can be used to produce realistic-looking simulated data. However, standard vanilla VAEs suffer from entangled and uninformative latent spaces, which can be mitigated using other types of VAEs such as β-VAE and MMD-VAE. In this project, we evaluated the ability of VAEs to learn cell morphology characteristics derived from cell images. We trained and evaluated these three VAE variants-Vanilla VAE, β-VAE, and MMD-VAE-on cell morphology readouts and explored the generative capacity of each model to predict compound polypharmacology (the interactions of a drug with more than one target) using an approach called latent space arithmetic (LSA). To test the generalizability of the strategy, we also trained these VAEs using gene expression data of the same compound perturbations and found that gene expression provides complementary information. We found that the β-VAE and MMD-VAE disentangle morphology signals and reveal a more interpretable latent space. We reliably simulated morphology and gene expression readouts from certain compounds thereby predicting cell states perturbed with compounds of known polypharmacology. Inferring cell state for specific drug mechanisms could aid researchers in developing and identifying targeted therapeutics and categorizing off-target effects in the future.

Download Full-text

Planar organization of airway epithelial cell morphology using hydrogel grooves during ciliogenesis fails to induce ciliary alignment

Biomaterials Science ◽

10.1039/d1bm01327k ◽

2021 ◽

Author(s):

Ratna Varma ◽

James Poon ◽

Zhongfa Liao ◽

Stewart Aitchison ◽

Thomas K Waddell ◽

...

Keyword(s):

Epithelial Cell ◽

Cell Morphology ◽

Airway Epithelial Cell ◽

Epithelial Lining ◽

Airway Epithelial ◽

Collagen Fibres ◽

The Matrix ◽

Cell Organization ◽

Topographical Cues

Topographical cues are known to influence cell organization both in native tissues and in vitro. In the trachea, the matrix beneath the epithelial lining is composed of collagen fibres that...

Download Full-text