grn-nextflow/example_config.yaml at main · bionetslab/grn-nextflow · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
comparison: # Always keep this line as is
  # You can add as many comparisons as you want (see e.g. comparison2 below)
  - comparison1:
      # comparison_id: Must be a unique ID across the whole config.yaml file
      #                Use a sensible id because the results folder gets named after this
      comparison_id: "Arm_vs_Doc_D28:Spleen"
      # assay: Assay in Seurat object to use. If you use an anndata object as an input, this will always be "RNA"
      assay: "SCTmerged"
      # covariate_config: The covariate configuration consists of 2 selections s1,s2
      # WIP (grn only mode does not work currently): If you are using only GRN inference methods, a single selection is enough
      covariate_config:
        # You can name the selections (here: s1, s2) anyway that you want
        s1:
          # output_file: Determines the folder name where the results for the given selection are saved. No file types are needed, only the filename.
          # Must be unique across the two selections in one comparison.
          ### NOTE: ###
          # DO NOT USE ".", ":", "-", ";", "," IN THE NAME! Also refrain from using "out_" as part of the string this will be appended in the pipeline and may cause issues in the shiny app.
          output_file: "Doc_Spleen_d28"
          # The following key : value pairs in the selection are data specific! This is used to group the cells for the specific selection
          # Key (here: infection, tissue, ...) represents the column name in the data object
          # Value (here: Doc, Spleen, [1,2,4], ...) represents the values of the given key to select for in the data object
          infection: "Doc"
          tissue: "Spleen"
          subject: [1, 2, 4]
          time: "d28"
        # Same principles applay as for selection s1.
        s2:
          output_file: "Arm_Spleen_d28"
          infection: "Arm"
          tissue: "Spleen"
          subject: [1, 3, 5]
          time: "d28"
      # Additional filter option to apply on every selection. It is not required to provide a filter.
      # However, only one filter can be provided!
      filter:
        # name: specifices the column name in the meta.data (for seurat objects)
        name: "cluster"
        # ids: specifcies the values to filter for in the given name column
        ids: [1, 2]
  # You can provide as many comparisons as you want following the same structure as comparison1.
  - comparison2:
      comparison_id: "Arm_vs_Doc_D10:Spleen"
      assay: "SCTmerged"
      covariate_config:
        s1:
          output_file: "Doc_Spleen_d10"
          infection: "Doc"
          tissue: "Spleen"
          subject: [1, 3, 5]
          time: "d10"
        s2:
          output_file: "Arm_Spleen_d10"
          infection: "Arm"
          tissue: "Spleen"
          subject: [2, 3, 4]
          time: "d10"
      filter:
        name: "cluster"
        ids: [1, 2]