What is CellCognition?
CellCognition is a computational framework dedicated to the automatic analysis of live cell imaging data in the context of High-Content Screening (HCS). It contains algorithms for segmentation of cells and cellular compartments based on various fluorescent markers, features to describe cellular morphology by both texture and shape, tools for visualizing and annotating the phenotypes, classification, tracking and error correction. Events such as mitosis can be automatically identified and aligned to study the temporal kinetics of various cellular processes during cell cycle. CellCognition can be used by novices in the field of image analysis and is applicable to hundreds of thousands of images by parallelization on compute clusters with minimal effort. The tool has been successfully applied to quantitative phenotypic profiling of cell division, yet machine learning enables CellCognition to be used for the analysis of other dynamic processes.
CellCognition is based on VIGRA and Python and is a common software project between the IMBA Vienna, Institut Curie Paris, EMBL Heidelberg, and ETH Zurich. With this framework we developed the CecogAnalyzer - a graphical user-interface for the parametrization and execution of our analysis workflow on a local machine and the submission to a computational cluster. This web page also contains reference sets of raw images and analysis data of the Held et al. (2010) paper.
Who is CellCognition?
|Daniel Gerlich - project leader
Senior scientist at IMBA Vienna and interested in the
understanding of molecular mechanisms underlying
the cell division machinery as well as methods for
automated cell phenotyping based on supervised and
unsupervised machine learning.
|Christoph Sommer - main developer
Bioimage analyst and software developer at IMBA Vienna
interested in image analysis and machine learning methods
for high-content screening as well as their seamless
integration into useable software. He is also co-inventor
of ilastik and main developer of the data format CellH5.
|Rudolf Höfler - main developer
Software developer at the IMBA Vienna with focus
on software architecture and quality of the CellCogniton
code base. He is also working on online microscopy
workflows and the integration of unsupervised learning
|Thomas Walter - main developer
Researcher at the Institut Curie Paris (formerly at EMBL
Heidelberg) with focus on biological image analysis and
machine learning to systematically study biological
processes by analyzing cellular phenotypes and heterogeneity.
Former developers and contributors
- Michael Held - project leader and main developer (linkedin)
- Qing Zhong - contributor (University Zurich)
- Bernd Fischer - contributor (DKFZ)
- Alice Schoenauer Sebag - contributor (MINES Paristech)
Work in the Gerlich laboratory is supported by Swiss National Science Foundation (SNF) research grant 3100A0-114120, SNF ProDoc grant PDFMP3_124904, a European Young Investigator (EURYI) award of the European Science Foundation, an EMBO YIP fellowship, and a MBL Summer Research Fellowship, an ETH TH grant, a grant by the UBS foundation, a Roche Ph.D. fellowship, and a Mueller fellowship of the Molecular Life Sciences Ph.D. program Zurich.
Work in the Ellenberg laboratory is supported by a European Commission grant within the Mitocheck consortium (LSHG-CT-2004-503464).
Bernd Fischer was supported by European Commission’s seventh framework program project Cancer Pathways.
Held M, Schmitz MHA, Fischer B, Walter T, Neumann B, Olma
MH, Peter M, Ellenberg J, and Gerlich DW.
CellCognition: time-resolved phenotype annotation in high-throughput live cell imaging.
Nature Methods (2010) Sep;7(9):747-54. Epub 2010 Aug 8. - PubMed
Schmitz MHA, Held M, Janssens V, Hutchins JR, Hudecz O, Ivanova E, Goris J, Trinkle-Mulcahy L, Lamond AI, Poser I, Hyman AA, Mechtler K, Peters JM, and Gerlich DW.
Live-cell imaging RNAi screen identifies PP2A-B55alpha and importin-beta1 as key mitotic exit regulators in human cells.
Nature Cell Biology (2010) Sep;12(9):886-93. Epub 2010 Aug 15. - PubMed
Piwko W, Olma MH, Held M, Bianco JN, Pedrioli PG, Hofmann K, Pasero P, Gerlich DW, Peter M.
RNAi-based screening identifies the Mms22L-Nfkbil2 complex as a novel regulator of DNA replication in human cells.
EMBO Journal (2010) Nov 26. - PubMed
Wurzenberger C, Held M, Lampson MA, Poser I, Hyman AA, Gerlich DW.
Sds22 and Repo-Man stabilize chromosome segregation by counteracting Aurora B on anaphase kinetochores.
Journal of Cell Biology (2012) Jul 23;198(2):173-83. Epub 2012 Jul 16. PubMed
Mall M, Walter T, Gorjánácz M, Davidson IF, Nga Ly-Hartig TB, Ellenberg J, Mattaj IW.
Mitotic lamin disassembly is triggered by lipid-mediated signaling.
Journal of Cell Biology (2012) Sep 17;198(6):981-90. PubMed
Zhong Q, Busetto AG, Fededa JP, Buhmann JM, Gerlich DW.
Unsupervised modeling of cell morphology dynamics for time-lapse microscopy.
Nature Methods (2012) May 27;9(7):711-3. PubMed
Sommer C, Held M, Fischer B, Huber W, Gerlich DW.
CellH5: a format for data exchange in high-content screening.
Bioinformatics (2013) Jun 15;29(12):1580-2. doi: Epub 2013 Apr 16. PubMed
This mosaic image shows images of human cell nuclei assigned to the compartments of the underlying cell by their mitotic phenotype. Phenotype cells were detected automatically within the MitoCheck screen. This image was created by Thomas Walter. Please note that all rights are reserved.