...

• Click the t-SNE node
• Click Task report from the task menu or double click the t-SNE SNE node

The t-SNE plot will open to the first sample in the data set, MGH36 (Figure 3). Please note that the appearance of the t-SNE plot will differ each time it is drawn so your t-SNE plots will look different than those shown in this tutorial; however, the cell-to-cell relationships indicated will be the same. 

...

Each sample has its own plot. We can switch between samples using the Back and Next buttons and Next buttons on the upper left. 

• Select Next
  

...

The goal of this analysis is to compare malignant cells from two different glioma subtypes, astrocytoma and oligodendroglioma. To do this, we need to identify which cells are the malignant cells we want to include and which cell cells are the normal cells we want to exclude. 

The t-SNE plot in Partek Flow offers several options for identifying, selecting, and classifying cells. In this tutorial, we will use expression of known marker genes to identify normal cellscell types. 

To visualize expression of a marker gene, we can color cells on the t-SNE plot by their expression level. 

...

Numerical expression levels for each gene can be viewed for individual cells. 

• Switch modes by selecting clicking 
• Select a cell by pointing and clicking

...

• Activate the 3D lasso tool by selecting clicking 
• Draw the lasso around the cluster of yellow cells and click the circle to close the lasso. You may need to switch to selection mode and rotate the 3D plot to select only cells from the yellow cluster

...

• Name the classification Glioma
• Select Click Save (Figure 13)
  
  

Once cells have been classified, the classification is added to the Classifications section the Classifications section of the panel. The number of cells belonging to the classification is listed; in MGH42, there are 413 462 glioma cells (Figure 14). 

• Select Click Next to move to the next sample, MGH45
• Rotate the 3D t-SNE plot to allow you to select only cells from the yellow cluster
• Activate the 3D lasso tool by selecting 
• Draw the lasso around the cluster of black cells and click the circle to close the lasso (Figure 14). 
  
  

...

• Select Classify selection 
• Type Glioma or select Glioma from the prompt (Figure 15)
• Select Click Save
  
  

...

Once all samples have been classified, it is useful to check the number of cells in each sample assigned to each classification. 

• Select Click Summary (Figure 16)
  
  

...

• Click Apply classifications 
• Select Click Apply when asked to confirm

...

For some data sets, cell types can be distinguished when all samples can be visualized together on one t-SNE plot. We will use a t-SNE plot of all samples to classify glioma, microglia, and oligodendrocyte cell types. 

• Select Click the Filtered counts data node
• Select Click t-SNE from in the Exploratory analysis section of the task menu
• Select Click Configure on the t-SNE dialog (Figure 19)
  
  

...

Once the task has completed, we can view the plot.

• Select Double-click the green t-SNE plot node Select Task Report from the task menuto open the t-SNE scatter plot

In the multi-sample t-SNE plot, each cell is initially colored by its sample (Figure 22).

...

Using maker genes, BCAN (glioma), CD14 (microglia), and MAG (oligodendrocytes), we can assess whether these multi-sample clusters belong to our known cell types. 

• Select Choose Gene expression from the Color by drop-down menu
• Type BCAN in the new Gene ID box
• Select Choose BCAN from the list of genes in the data set
• Select Click the  icon next to BCAN
• Type CD14 in the new Gene ID box
• Select Choose CD14 from the list of genes in the data set
• Select Click the  icon next to CD14
• Type MAG in the new Gene ID box
• Select Choose MAG from the list of genes in the data set

...

• Activate the 3D lasso tool by selecting clicking 
• Draw the lasso around the cluster of red cells and click the circle to close the lasso (Figure 25)
  
  

...

The pipeline view will open and the Classify cells tasks task will run, generating a new green-layer Classified groupsgroups  data node (Figure 29). 

...