Partek Flow Documentation

Page tree

Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

  • Click the Merged counts data node
  • Click Exploratory analysis in the toolbox
  • Click Graph-based clustering 
  • Click Gene Expression for Include features where "Feature type" is
  • Click Configure to access the advanced settings
  • Set Number of principal components to 15
  • Click Apply 
  • Click Finish to run (Figure 17)

Numbered figure captions
SubtitleTextRunning Graph-based clustering on the Gene Expression data
AnchorNameGraph-based clustering configuration

Image Added

Once Graph-based clustering has finished running and produced a Clustering result data node, we can visualize the results using UMAP or t-SNE.  

...

Both are dimensional reduction techniques that group cells with similar expression into visible clusters. 

  • Click the Clustering result data node 
  • Click Exploratory analysis in the toolbox
  • Click UMAP
  • Click Gene Expression for Include features where "Feature type" is
  • Click Configure to access the advanced settings
  • Set Number of principal components to 15
  • Click Apply 
  • Click Finish to run (Figure 18)

Numbered figure captions
SubtitleTextRunning UMAP on the Gene Expression data
AnchorNameRunning UMAP

Image Added

The Analyses tab now includes a UMAP task node (Figure 18).

 

Numbered figure captions
SubtitleTextAppearance of the Analyses tab after Graph-based clustering and UMAP on Gene Expression data
AnchorNameResults of UMAP

Image Added

  • Double-click the UMAP task node to open the task report

The UMAP task report includes a scatter plot with the clustering results coloring the points (Figure 19).

 

 

 

Numbered figure captions
SubtitleTextUMAP calculated on Gene Expression values. Colored by Graph-based clustering results.
AnchorNameUMAP results

Image Added