config_discovery_scRNA.yml

default :
  Input :    
    Discovery dataset name : "discovery_scRNA_CRC"
    Expression matrix : "example_data/scRNA_CRC_data.txt"    
    Annotation file : "example_data/scRNA_CRC_annotation.txt" 
    Annotation file column to scale by : NULL
    Annotation file column(s) to plot : []
    
  Output :
    Output folder : "DiscoveryOutput_scRNA"

  Pipeline settings :
    #Pipeline steps:
    #   step 1 (extract cell type specific genes)
    #   step 2 (cell state discovery on correrlation matrices)
    #   step 3 (choosing the number of cell states)
    #   step 4 (extracting cell state information)
    #   step 5 (cell state re-discovery in expression matrices)
    #   step 6 (extracting information for re-discovered cell states)
    #   step 7 (cell state QC filter)
    #   step 8 (ecotype discovery)
    Pipeline steps to skip : [] 
    # Accepted values: 
    # "cell type specific" - select genes overexpressed in a cell type
    # "no filter" - use all genes
    # <integer> - e.g. 1000, select top <integer> genes with highest variance in a cell type
    Filter genes : "cell type specific"
    Number of threads : 10
    Number of NMF restarts : 5
    Maximum number of states per cell type : 20
    Cophenetic coefficient cutoff : 0.975
    #The p-value cutoff used for filtering non-significant overlaps in the jaccard matrix used for 
    #discovering ecotypes in step 8. Default: 1 (no filtering).
    Jaccard matrix p-value cutoff : 1
    Minimum number of states in ecotypes : 3