Pipelines in FCS Express are a set of data processing steps that stand alone or are connected in series.  The output of a step can be applied to a data file or utilized as the input of the next step, or series of steps, that may be applied to your data.

 

The vast majority of commonly used algorithms for data analysis are actually pipelines, with tSNE (and its variants) and SPADE being two examples. However, when those algorithms are implemented as a one calculation, user customizations are limited to the what the specific implementation allows. Pipelines in FCS Express increase the computational flexibility and granularity of running algorithms and data transformations while giving users the unique ability to create their own transformations.

 

As mentioned above, a pipeline is made of individual data processing steps with each step performing a specific calculation/transformation.

 

Pipeline steps are grouped by functionality in FCS Express (see list below). New steps and functionality are being developed all the time. Please contact support@denovosoftware.com if there is a step or algorithm you would like to see included.

 

To begin working with Pipelines in FCS Express please see the following topics:

 

1.Setting Up Pipelines

 

2.Available pipelines steps and algorithms

 

oPre-Defined Algorithms

▪FlowAI

▪FlowCut

▪FlowSOM

▪Phenograph

▪SPADE

 

oSampling

▪Gate Downsampling

▪Interval Downsampling

▪Mask Downsampling

▪Random Downsampling

▪Target Density Downsampling

▪Upsampling

▪Weighted Density Downsampling

 

oDimensionality Reduction

▪PCA

▪tSNE

▪UMAP

 

oClustering

▪Batch Self-Organizing Map

▪Consensus Clustering

▪Hierarchical Clustering

▪Kmeans

▪Louvain Communities

▪Self-Organizing Map

 

oVisualization

▪Graph layout

▪Minimum Spanning Tree

▪tSNE Layout

▪UMAP Layout

 

oMathematical

▪0 to 1 Scaling

▪Normalization

▪Scaling

▪Simple Parameter Math

▪Thresholding

 

oQuality Controls

▪Dynamic Range Downsampling

▪Flow Rate Check Downsampling

▪Low Time Density Downsampling

▪Signal Acquisition Downsampling

 

oRandom Parameters

 

oFeature Extraction

▪Binned Variance Feature Extraction

▪Variance Feature Extraction

 

oMiscellaneous

▪Classifications Folder

▪Folder

▪Jaccard Similarity Parameter

▪K-Nearest Neighbors Parameter

▪Merge to Spectra

▪Parameter Removal

▪Python Transformation

▪Ramp Parameter

▪Unmixing

▪Virtual bandpass