SCENERY: a web application for (causal) network reconstruction from cytometry data

Abstract

Flow and mass cytometry technologies can probe proteins as biological markers in thousands of individual cells simultaneously, providing unprecedented opportunities for reconstructing networks of protein interactions through machine learning algorithms. The network reconstruction (NR) problem has been well-studied by the machine learning community. However, the potentials of available methods remain largely unknown to the cytometry community, mainly due to their intrinsic complexity and the lack of comprehensive, powerful and easy-to-use NR software implementations specific for cytometry data. To bridge this gap, we present Single CEll NEtwork Reconstruction sYstem (SCENERY), a web server featuring several standard and advanced cytometry data analysis methods coupled with NR algorithms in a user-friendly, on-line environment. In SCENERY, users may upload their data and set their own study design. The server offers several data analysis options categorized into three classes of methods: data (pre)processing, statistical analysis and NR. The server also provides interactive visualization and download of results as ready-to-publish images or multimedia reports. Its core is modular and based on the widely-used and robust R platform allowing power users to extend its functionalities by submitting their own NR methods. SCENERY is available at scenery.csd.uoc.gr or http://mensxmachina.org/en/software/.

Advances in automated real‐time flow cytometry for monitoring of bioreactor processes

“…Data quality flowAI Cleans flow cytometry files from anomalies during measurement procedure [87] Data visualization flowFit quantitative analysis of cell proliferation in tracking dye-based experiments after gating [88] flowViz plots flow cytometry data in different layers avoiding information loss [89] ggCyto Algorithms based transformation of data and axes and visualization according to specific structures [86] SCENERY Web server featuring several standard and advanced cytometry data analysis methods [81] Automated gating Supervised flowPeaks Gating of high-dimensional data, identification of irregular shape clusters [96] flowDensity Gating analogous to a manual gating strategy based on data density clouds [79] OpenCyto Hierarchical automated gating [91] DeepCyTOF Deep learning algorithm for automated gating [92] GateFinder Gating by stepwise creating two-dimensional convex gates of best fit [93] Semi-Unsupervised flowLearn Gating combining flowDensity with a deep learning algorithm [94] NetFCM Gating combining clustering and principal component analysis [95] Unsupervised flowMeans Gating based on K-means [98] SPADE Gating based on hierarchical clustering [100] Citrus Gating based on hierarchical clustering [101] flowPeaks Gating based on K-means and finite mixture modeling [96] FLAME Gating based on finite mixture modeling [97] Hypergate Gating via a best fit hyperrectangle [99] Automated identification and classification CHIC Grey scale images are automatically processed and batch-wise compared [108] CyBar Following manual gating, a mask compromising all gates of all samples is compared within a batch [107] FlowFP Uses probability distributions functions to equal sized bins that are combined to a template [104] Dalmatian Plot Black and white images of manually gated samples automatically processed via images analysis [106] (pre-)processing, visualization, statistical analysis and modelling [81].…”

“…These were also topic of some review articles [8,22,23,78,80]. However, they have not yet made it into mainstream due to intrinsic complexity and lack of comprehensive and easy-to use [78,81]. Analysis of FCM data mainly takes place in R or MATLAB.…”

Analysis of big data job requirements based on K-means text clustering in China

“…used descriptive statistics to analyze gender differences in self-evaluation and salary expectation in Online recruitment information in China. Papoutsoglou [ 8 ]. used multivariate statistical analysis to explore the skills and abilities of IT talents from recruitment advertisements, and analyzed the correlation between skills and abilities.…”

A unified approach for sparse dynamical system inference from temporal measurements

“…Additional demonstrations can be found in Appendix E. Particularly, the reconstructed networks when additional activators and/or subpopulations are considered are presented as well as how important is the high sampling rate for protein interactions inference through mass cytometry data. For instance, the reconstruction accuracy is severely reduced when removing half of the time-points as it is shown in Appendix E. Finally, we have integrated the USDL algorithm in SCENERY (http://scenery.csd.uoc.gr/) [44] which is an web tool for single-cell cytometry analysis. SCENERY provides a comprehensive and easy-to-use graphical user interface where users may upload their data and perform various types of protein network reconstruction.…”