A deep learning and novelty detection framework for rapid phenotyping in high-content screening

Supervised machine learning is a powerful and widely used method to analyze high-content screening data. Despite its accuracy, efficiency, and versatility, supervised machine learning has drawbacks, most notably its dependence on a priori knowledge of expected phenotypes and time-consuming classifier training. We provide a solution to these limitations with CellCognition Explorer, a generic novelty detection and deep learning framework. Application to several large-scale screening data sets on nuclear and mitotic cell morphologies demonstrates that CellCognition Explorer enables discovery of rare phenotypes without user training, which has broad implications for improved assay development in high-content screening.

[1]  Leopold Parts,et al.  Accurate Classification of Protein Subcellular Localization from High-Throughput Microscopy Images Using Deep Learning , 2016, G3: Genes, Genomes, Genetics.

[2]  Anne E Carpenter,et al.  CellProfiler: image analysis software for identifying and quantifying cell phenotypes , 2006, Genome Biology.

[3]  Pauli Rämö,et al.  CellClassifier: supervised learning of cellular phenotypes , 2009, Bioinform..

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Johannes E. Schindelin,et al.  Fiji: an open-source platform for biological-image analysis , 2012, Nature Methods.

[6]  Robert F. Murphy,et al.  Robust Numerical Features for Description and Classification of Subcellular Location Patterns in Fluorescence Microscope Images , 2003, J. VLSI Signal Process..

[7]  Holger Fröhlich,et al.  Unsupervised automated high throughput phenotyping of RNAi time-lapse movies , 2013, BMC Bioinformatics.

[8]  Jiri Bartek,et al.  TRIP12 and UBR5 Suppress Spreading of Chromatin Ubiquitylation at Damaged Chromosomes , 2014, Cell.

[9]  Lior Shamir,et al.  CHLOE: A Software Tool for Automatic Novelty Detection in Microscopy Image Datasets , 2014 .

[10]  Satwik Rajaram,et al.  PhenoRipper: software for rapidly profiling microscopy images , 2012, Nature Methods.

[11]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[12]  Michael D. Abràmoff,et al.  Image processing with ImageJ , 2004 .

[13]  Y. Nesterov.  A method for solving the convex programming problem with convergence rate O(1/k^2) , 1983 .

[14]  Yolanda T. Chong,et al.  Automated analysis of high‐content microscopy data with deep learning , 2017, Molecular systems biology.

[15]  Lucas Pelkmans,et al.  A Hierarchical Map of Regulatory Genetic Interactions in Membrane Trafficking , 2014, Cell.

[16]  C. Bakal,et al.  Quantitative Morphological Signatures Define Local Signaling Networks Regulating Cell Morphology , 2007, Science.

[17]  A. Madansky.  Identification of Outliers , 1988 .

[18]  R. Wollman,et al.  Genes Required for Mitotic Spindle Assembly in Drosophila S2 Cells , 2007, Science.

[19]  M. Boutros,et al.  Microscopy-Based High-Content Screening , 2015, Cell.

[20]  Péter Horváth,et al.  Enhanced CellClassifier: a multi-class classification tool for microscopy images , 2010, BMC Bioinformatics.

[21]  Bernd Fischer,et al.  CellH5: a format for data exchange in high-content screening , 2013, Bioinform..

[22]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[23]  Xiaobo Zhou,et al.  Using iterative cluster merging with improved gap statistics to perform online phenotype discovery in the context of high-throughput RNAi screens , 2008, BMC Bioinformatics.

[24]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[25]  D. Gerlich,et al.  Automated live microscopy to study mitotic gene function in fluorescent reporter cell lines. , 2009, Methods in molecular biology.

[26]  Christoph Sommer,et al.  Machine learning in cell biology – teaching computers to recognize phenotypes , 2013, Journal of Cell Science.

[27]  Anthony A. Hyman,et al.  Ki-67 acts as a biological surfactant to disperse mitotic chromosomes , 2016, Nature.

[28]  Stephen T. C. Wong,et al.  A Screen for Morphological Complexity Identifies Regulators of Switch-like Transitions between Discrete Cell Shapes , 2013, Nature Cell Biology.

[29]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[30]  Jan Ellenberg,et al.  Nuclear pore complexes form immobile networks and have a very low turnover in live mammalian cells , 2001, The Journal of cell biology.

[31]  Brendan J. Frey,et al.  Classifying and segmenting microscopy images with deep multiple instance learning , 2015, Bioinform..

[32]  R. Durbin,et al.  Phenotypic profiling of the human genome by time-lapse microscopy reveals cell division genes , 2010, Nature.

[33]  V. Vapnik.  Pattern recognition using generalized portrait method , 1963 .

[34]  Tara N. Sainath,et al.  Deep convolutional neural networks for LVCSR , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[35]  Bernd Fischer,et al.  CellCognition: time-resolved phenotype annotation in high-throughput live cell imaging , 2010, Nature Methods.

[36]  Adrian J. Verster,et al.  High-Content Screening for Quantitative Cell Biology. , 2016, Trends in cell biology.

[37]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[38]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[39]  H. Erfle,et al.  High-throughput RNAi screening by time-lapse imaging of live human cells , 2006, Nature Methods.

[40]  P. Mahalanobis.  On the generalized distance in statistics , 1936 .

[41]  Jean YH Yang,et al.  Bioconductor: open software development for computational biology and bioinformatics , 2004, Genome Biology.

[42]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[43]  Razvan Pascanu,et al.  Advances in optimizing recurrent networks , 2012, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[44]  Robert F. Murphy,et al.  A neural network classifier capable of recognizing the patterns of all major subcellular structures in fluorescence microscope images of HeLa cells , 2001, Bioinform..

[45]  Martin J. Wainwright,et al.  Randomized smoothing for (parallel) stochastic optimization , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

[46]  C. Conrad,et al.  Automated microscopy for high-content RNAi screening , 2010, The Journal of cell biology.

[47]  Polina Golland,et al.  Scoring diverse cellular morphologies in image-based screens with iterative feedback and machine learning , 2009, Proceedings of the National Academy of Sciences.

[48]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[49]  Joachim M Buhmann,et al.  Unsupervised modeling of cell morphology dynamics for time-lapse microscopy , 2012, Nature Methods.

[50]  Otto Hudecz,et al.  Live-cell imaging RNAi screen identifies PP2A–B55α and importin-β1 as key mitotic exit regulators in human cells , 2010, Nature Cell Biology.

[51]  Beate Sick,et al.  Single-Cell Phenotype Classification Using Deep Convolutional Neural Networks , 2016, Journal of biomolecular screening.