• Product manuals

Browse the manual

• Introduction
  • The concept of CLC Single Cell Analysis Module
  • Contact information
  • System requirements and installation
    • System requirements
    • Installation of modules
    • Uninstalling modules
  • Licensing modules
    • Server License
  • Reference data management
    • The Reference Data Manager
  • Running tools and workflows
• Data import
  • Import Expression Matrix
  • Import Cell Annotations
  • Import Cell Clusters
• Data export
  • Export Cell Ranger HDF5 expression matrix
  • Export Loom expression matrix
  • Export MEX expression matrix
• Creating a count matrix from FASTQ
  • Annotate Reads with Cell and UMI
    • Interpreting the output of Annotate Reads with Cell and UMI
  • Single Cell RNA-Seq Analysis
    • The Single Cell RNA-Seq Analysis report
    • The Single Cell RNA-Seq Analysis algorithm
• Cell preparation
  • QC for Single Cell
    • Empty droplets filter
    • Count-based and extra-chromosomal filters
    • Interpreting the output of QC for Single Cell
    • Choosing barcodes to retain
    • The cell calling algorithm
  • Normalize Single Cell Data
    • When is batch correction appropriate?
    • Interpreting the output of Normalize Single Cell Data
    • The Normalize Single Cell Data algorithm
  • Combine Cell Annotations
  • Combine Cell Clusters
  • Convert Metadata to Cell Annotations
• Noise reduction through feature selection and PCA
  • Feature selection and PCA
    • Calculation of estimated biological variation
• Cell Annotation
  • Predict Cell Types
  • Train Cell Type Classifier
    • Interpreting the output of Train Cell Type Classifier
    • Features used for training and prediction
    • SVMs for cell type classification
  • Cluster Single Cell Data
    • The Cluster Single Cell Data algorithm
• Dimensionality reduction
  • Create UMAP Plot
  • Create tSNE Plot
  • Add Information to Plot
• Expression Analysis
  • Differential Expression for Single Cell
    • Interpreting the output of Differential Expression for Single Cell
  • Create Expression Plot
    • The Heat Map output of Create Expression Plot
    • The Dot Plot output of Create Expression Plot
• Single cell workflows
  • Perform Single Cell Analysis from Expression Matrix
    • Output from Perform Single Cell Analysis from Expression Matrix
  • Perform Single Cell Analysis from Reads
    • Configuring the batch units
    • Output from Perform Single Cell Analysis from Reads
• UMAP and tSNE plot functionality
  • Manual Annotation
  • Create Subset
  • Extract to Table
  • Launching of Create Expression Plot
  • Launching of Differential Expression for Single Cell
• Licensing requirements for the CLC Single Cell Analysis Module
  • Licensing modules on a Workbench
    • Request an evaluation license
    • Download a license using a license order ID
    • Import a license from a file
    • Configure License Server connection
    • Download a static license on a non-networked computer
  • Licensing Server Extensions on a CLC Server
    • Download a static license on a non-networked machine
• Bibliography

Interpreting the output of Train Cell Type Classifier

The tool outputs a Cell Type Classifier () object. The table view of the object gives a summary of the cell types the classifier has been trained on, including the number of cells that have been used from each sample (figure 7.3). The impact of the strategy for choosing cells during training when extending a classifier with new data (see Train Cell Type Classifier) can be investigated in this table view.

Figure 7.3: The table view of a Cell Type Classifier trained on HCL data (http://bis.zju.edu.cn/HCL) containing 106 different samples. For cell types present in more than 50 samples, one cell is chosen from each sample. The sample columns (the two right-most columns and the remaining unselected columns) contain the number of training cells used from the respective sample.

---