Variational autoencoding tissue response to microenvironment perturbation

This work applies deep variational autoencoder learning architecture to study multi-cellular growth characteristics of human mammary epithelial cells in response to diverse microenvironment perturbations. Our approach introduces a novel method of visualizing learned feature spaces of trained variational autoencoding models that enables visualization of principal features in two dimensions. We find that unsupervised learned features more closely associate with expert annotation of cell colony organization than biologically-inspired hand-crafted features, demonstrating the utility of deep learning systems to meaningfully characterize features of multi-cellular growth characteristics in a fully unsupervised and data-driven manner.

[1]  Samuel J. Yang,et al.  In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images , 2018, Cell.

[2]  J. Massagué,et al.  TGFβ in Cancer , 2008, Cell.

[3]  Lassi Paavolainen,et al.  Data-analysis strategies for image-based cell profiling , 2017, Nature Methods.

[4]  Joe Gray,et al.  Combinatorial Microenvironments Impose a Continuum of Cellular Responses to a Single Pathway-Targeted Anti-cancer Compound. , 2017, Cell reports.

[5]  Jacob Cohen,et al.  The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of Reliability , 1973 .

[6]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[7]  Anne E Carpenter,et al.  Reconstructing cell cycle and disease progression using deep learning , 2017, Nature Communications.

[8]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[9]  M. Junttila,et al.  Influence of tumour micro-environment heterogeneity on therapeutic response , 2013, Nature.

[10]  Tom Misteli,et al.  High-Throughput Imaging for the Discovery of Cellular Mechanisms of Disease. , 2017, Trends in genetics : TIG.

[11]  Anne E Carpenter,et al.  CytoGAN: Generative Modeling of Cell Images , 2017, bioRxiv.

[12]  Eric P. Xing,et al.  On Unifying Deep Generative Models , 2017, ICLR.

[13]  Mark A. LaBarge,et al.  Fabrication and use of microenvironment microarrays (MEArrays). , 2012, Journal of visualized experiments : JoVE.

[14]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[15]  Joe W. Gray,et al.  Microenvironment-Mediated Mechanisms of Resistance to HER2 Inhibitors Differ between HER2+ Breast Cancer Subtypes , 2018, Cell systems.

[16]  Joe W. Gray,et al.  SHIFT: speedy histopathological-to-immunofluorescent translation of whole slide images using conditional generative adversarial networks , 2018, Medical Imaging.