October 21–22, 2019
Join Genedata team of experts at the SLAS Advanced 3D Human Models and High-Content Analysis Conference in London, UK. Ask for a demonstration of Genedata of Genedata Screener® and Genedata Imagence® at booth #12.
Don't miss the opportunity to see how Genedata Screener analyzes, visualizes, and manages screening data from in-vitro screening assay technologies across the enterprise, including very complex as well as ultra-high throughput experiments. Its screening-oriented business logic enables rapid processing and comprehensive analysis of complete campaigns. To schedule a meeting in advance or to receive more information on Genedata Screener, please contact email@example.com.
You also have a chance to find out more about our new solution, Genedata Imagence, a high content screening (HCS) image analysis software based on deep learning. To get more information about Imagence or to arrange a meeting, please contact firstname.lastname@example.org.
Genedata Imagence® - Deep Learning Automates the Analysis of Cell Painting Assays
Matthias Fassler, PhD, Scientific Account Manager, Genedata
Advances in Imaging and Analysis
Tuesday, October 22 | 11:50–12:00
Here we show how the new software solution Genedata Imagence enabled the complete analysis of a Cell Painting screen of 1’500 test compounds within a few hours. In our case study we employed this workflow to train a neural network to recognize the cell-painted phenotypes of reference compounds with known mode-of-action (MoA). This network was used to analyze the entire BBBC022 data set and successfully detected compounds with similar MoA.
Genedata Imagence provides a streamlined workflow that facilitates discovery by making powerful deep learning approaches intuitive and easily accessible to any HCS biologist.
Genedata Imagence®: An Evaluation of Deep Learning for High Content Analysis
Zaynab Neetoo-Isseljee, Michelle Newman, Matthias Fassler, Dorte Faust, Daniel Siegismund, Simon Fox, Marusa Kustec, Carolina Arguedas Villa, Stephan Heyse and Stephan Steigele
Deep Learning-Derived Features Outperform Classical Computer Vision in Low Dimension-Embedding of High Content Screening Data
Siegismund D., Kustec M., Fassler M., Heyse S., and Steigele S.