scholarly journals Faculty Opinions recommendation of Single-cell morphology encodes metastatic potential.

Author(s):  
Kandice Tanner
2020 ◽  
Vol 6 (4) ◽  
pp. eaaw6938 ◽  
Author(s):  
Pei-Hsun Wu ◽  
Daniele M. Gilkes ◽  
Jude M. Phillip ◽  
Akshay Narkar ◽  
Thomas Wen-Tao Cheng ◽  
...  

A central goal of precision medicine is to predict disease outcomes and design treatments based on multidimensional information from afflicted cells and tissues. Cell morphology is an emergent readout of the molecular underpinnings of a cell’s functions and, thus, can be used as a method to define the functional state of an individual cell. We measured 216 features derived from cell and nucleus morphology for more than 30,000 breast cancer cells. We find that single cell–derived clones (SCCs) established from the same parental cells exhibit distinct and heritable morphological traits associated with genomic (ploidy) and transcriptomic phenotypes. Using unsupervised clustering analysis, we find that the morphological classes of SCCs predict distinct tumorigenic and metastatic potentials in vivo using multiple mouse models of breast cancer. These findings lay the groundwork for using quantitative morpho-profiling in vitro as a potentially convenient and economical method for phenotyping function in cancer in vivo.


2019 ◽  
Author(s):  
Ruixin Wang ◽  
Dongni Wang ◽  
Dekai Kang ◽  
Xusen Guo ◽  
Chong Guo ◽  
...  

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.


2020 ◽  
Vol 8 (Suppl 3) ◽  
pp. A799-A799
Author(s):  
Dhiraj Kumar ◽  
Sreeharsha Gurrapu ◽  
Hyunho Han ◽  
Yan Wang ◽  
Seongyeon Bae ◽  
...  

BackgroundLong non-coding RNAs (lncRNAs) are involved in various biological processes and diseases. Malat1 (metastasis-associated lung adenocarcinoma transcript 1), also known as Neat2, is one of the most abundant and highly conserved nuclear lncRNAs. Several studies have shown that the expression of lncRNA Malat1 is associated with metastasis and serving as a predictive marker for various tumor progression. Metastatic relapse often develops years after primary tumor removal as a result of disseminated tumor cells undergoing a period of latency in the target organ.1–4 However, the correlation of tumor intrinsic lncRNA in regulation of tumor dormancy and immune evasion is largely unknown.MethodsUsing an in vivo screening platform for the isolation of genetic entities involved in either dormancy or reactivation of breast cancer tumor cells, we have identified Malat1 as a positive mediator of metastatic reactivation. To functionally uncover the role of Malat1 in metastatic reactivation, we have developed a knock out (KO) model by using paired gRNA CRISPR-Cas9 deletion approach in metastatic breast and other cancer types, including lung, colon and melanoma. As proof of concept we also used inducible knockdown system under in vivo models. To delineate the immune micro-environment, we have used 10X genomics single cell RNA-seq, ChIRP-seq, multi-color flowcytometry, RNA-FISH and immunofluorescence.ResultsOur results reveal that the deletion of Malat1 abrogates the tumorigenic and metastatic potential of these tumors and supports long-term survival without affecting their ploidy, proliferation, and nuclear speckles formation. In contrast, overexpression of Malat1 leads to metastatic reactivation of dormant breast cancer cells. Moreover, the loss of Malat1 in metastatic cells induces dormancy features and inhibits cancer stemness. Our RNA-seq and ChIRP-seq data indicate that Malat1 KO downregulates several immune evasion and stemness associated genes. Strikingly, Malat1 KO cells exhibit metastatic outgrowth when injected in T cells defective mice. Our single-cell RNA-seq cluster analysis and multi-color flow cytometry data show a greater proportion of T cells and reduce Neutrophils infiltration in KO mice which indicate that the immune microenvironment playing an important role in Malat1-dependent immune evasion. Mechanistically, loss of Malat1 is associated with reduced expression of Serpinb6b, which protects the tumor cells from cytotoxic killing by the T cells. Indeed, overexpression of Serpinb6b rescued the metastatic potential of Malat1 KO cells by protecting against cytotoxic T cells.ConclusionsCollectively, our data indicate that targeting this novel cancer-cell-initiated domino effect within the immune system represents a new strategy to inhibit tumor metastatic reactivation.Trial RegistrationN/AEthics ApprovalFor all the animal studies in the present study, the study protocols were approved by the Institutional Animal Care and Use Committee(IACUC) of UT MD Anderson Cancer Center.ConsentN/AReferencesArun G, Diermeier S, Akerman M, et al., Differentiation of mammary tumors and reduction in metastasis upon Malat1 lncRNA loss. Genes Dev 2016 Jan 1;30(1):34–51.Filippo G. Giancotti, mechanisms governing metastatic dormancy and reactivation. Cell 2013 Nov 7;155(4):750–764.Gao H, Chakraborty G, Lee-Lim AP, et al., The BMP inhibitor Coco reactivates breast cancer cells at lung metastatic sites. Cell 2012b;150:764–779.Gao H, Chakraborty G, Lee-Lim AP, et al., Forward genetic screens in mice uncover mediators and suppressors of metastatic reactivation. Proc Natl Acad Sci U S A 2014 Nov 18; 111(46): 16532–16537.


2021 ◽  
Author(s):  
Rory Donovan-Maiye ◽  
Jackson Brown ◽  
Caleb Chan ◽  
Liya Ding ◽  
Calysta Yan ◽  
...  

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.


2020 ◽  
Author(s):  
Santosh Kumar Paidi ◽  
Vaani Shah ◽  
Piyush Raj ◽  
Kristine Glunde ◽  
Rishikesh Pandey ◽  
...  

AbstractIdentification of the metastatic potential represents one of the most important tasks for molecular imaging of cancer. While molecular imaging of metastases has witnessed substantial progress as an area of clinical inquiry, determining precisely what differentiates the metastatic phenotype has proven to be more elusive underscoring the need to marry emerging imaging techniques with tumor biology. In this study, we utilize both the morphological and molecular information provided by 3D optical diffraction tomography and Raman spectroscopy, respectively, to propose a label-free route for optical phenotyping of cancer cells at single-cell resolution. By using an isogenic panel of cell lines derived from MDA-MB-231 breast cancer cells that vary in their metastatic potential, we show that 3D refractive index tomograms can capture subtle morphological differences among the parental, circulating tumor cells, and lung metastatic cells. By leveraging the molecular specificity of Raman spectroscopy, we demonstrate that coarse Raman microscopy is capable of rapidly mapping a sufficient number of cells for training a random forest classifier that can accurately predict the metastatic potential of cells at a single-cell level. We also leverage multivariate curve resolution – alternating least squares decomposition of the spectral dataset to demarcate spectra from cytoplasm and nucleus, and test the feasibility of identifying metastatic phenotypes using the spectra only from the cytoplasmic and nuclear regions. Overall, our study provides a rationale for employing coarse Raman mapping to substantially reduce measurement time thereby enabling the acquisition of reasonably large training datasets that hold the key for label-free single-cell analysis and, consequently, for differentiation of indolent from aggressive phenotypes.


1985 ◽  
Vol 5 (12) ◽  
pp. 3552-3559 ◽  
Author(s):  
L Ossowski ◽  
D Belin

Human carcinoma HEp-3 lost its tumorigenic and metastatic potential upon prolonged culture in vitro. This change was accompanied by a reduced production of plasminogen activator (PA) of the urokinase type (uPA), which is secreted by HEp-3 cells, a change in response to effectors that modulate uPA production, and an alteration of cell morphology. Similar but more rapid changes occurred when malignant HEp-3 cells were exposed to dimethyl sulfoxide (DMSO). uPA activity in the culture medium dropped below 50% of the control level within 6 h after the addition of DMSO and became undetectable after 24 h of treatment. This drop in uPA activity was not caused by an increased production of PA inhibitors. The cell-associated uPA decreased to 25 to 30% of the control level within 6 h of DMSO treatment and remained at this level for at least 96 h; the reduced uPA production was partially accounted for by a rapid decrease in the functional and chemical concentration of uPA mRNA. In contrast, the concentrations of most of the abundant mRNA species did not appear to be significantly affected, and cell growth was only slightly inhibited in the presence of DMSO. Malignant HEp-3 cells treated with DMSO responded to cholera toxin with an enhanced production of uPA, and their morphology became indistinguishable from that of nonmalignant HEp-3 cells grown in vitro for prolonged periods of time. All of the above changes were fully and rapidly reversible. The inhibitory effect of DMSO on PA production appears to be specific for uPA of human cell lines.


2019 ◽  
Vol 91 (21) ◽  
pp. 13398-13406 ◽  
Author(s):  
Xinwu Xie ◽  
Zhiwei Zhang ◽  
Xiang Ge ◽  
Xiaohao Zhao ◽  
Limei Hao ◽  
...  

2020 ◽  
Vol 16 (2) ◽  
pp. 147-160
Author(s):  
C. Petit ◽  
M. Kechiche ◽  
I. A. Ivan ◽  
R. Toscano ◽  
V. Bolcato ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document