cellXpess :: Cellular Phenotype Profiling Software Platform

Fast processing speed Written in C/C++ and optimized for modern 64-bit and multi-core CPUs. Support parallel processing and dynamic job scheduling for high-throughput applications.
Single-cell phenotype quantification Automatically identify individual cells from fluorescence microscopy images; and quantify cellular morphology, protein sub-cellular localization and other features.
User-friendly interface Intuitive graphical user interface for interactive configuration of computational algorithms and visualization of segmentation and feature extraction results.

Cellular phenotype profiling
	cellXpress is a cellular phenotype profiling software platform developed by the Loo Lab at the Bioinformatics Institute, A*STAR, Singapore. The platform is designed for fast and high-throughput analysis of cellular phenotypes based on microscopy images. It is especially useful for large-scale profiling of cellular responses to pharmacological compounds, gene knockdowns, and/or toxic substances.

5 Oct 2015 cellXpress pro 1.3 is available now. New improvements include optimizations for 64-bit CPUs with AVX/AVX2 support.
27 July 2015 The cellXpress platform was used to analyze renal cells in a paper published in Scientific Reports.
30 May 2014 cellXpress pro 1.2 is available now. New improvements include better handling of corrupted images, faster processing speed, and ability to add multiple plates under a folder and resume unfinished jobs.

Features Highlight

Single-cell phenotype quantification Automatically identify individual cells from fluorescence microscopy images; and quantify cellular morphology, protein sub-cellular localization and other features.
Plate-based data organization Design to handle high volume of image data acquired from 96/384-well plates. Analyses of different fluorescent-marker configurations can be performed on the same plate data.
Quick plate analysis Perform cell count and fluorescence intensity measurements over the whole plates, and visualize well-to-well trend and variability.
Phenotypic profiling Transform raw image features into discriminative profiles that can be used to characaterize changes in cellular phenotypes.

Fast processing speed Written in C++ and optimized for modern 64-bit and multi-core CPUs. Support parallel processing and dynamic job scheduling for high-throughput applications.
User-friendly interface Intuitive graphical user interface for interactive configuration of computational algorithms and visualization of segmentation and feature extraction results.
Split-screen viewer View and compare different cell images, segmentation results and feature values side-by-side in the same windows.
Cross-platform data sharing Access the same projects under different operating systems. Data files can be imported into the R software environment for further processing or visualization.