task_ist_preprocessing/src/workflows/run_benchmark/config.vsh.yaml at 6f76c6c0588a65fa085bd039170edbd7c66559c1 · openproblems-bio/task_ist_preprocessing · 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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
name: run_benchmark
namespace: workflows

argument_groups:
  - name: Inputs
    arguments:
      - name: "--input_sc"
        __merge__: /src/api/file_scrnaseq_reference.yaml
        type: file
        direction: input
        required: true
      - name: "--input_sp"
        __merge__: /src/api/file_raw_ist.yaml
        type: file
        direction: input
        required: true
  - name: Outputs
    arguments:
      - name: "--output_scores"
        type: file
        required: true
        direction: output
        description: A yaml file containing the scores of each of the methods
        default: score_uns.yaml
      - name: "--output_method_configs"
        type: file
        required: true
        direction: output
        default: method_configs.yaml
      - name: "--output_metric_configs"
        type: file
        required: true
        direction: output
        default: metric_configs.yaml
      - name: "--output_dataset_info"
        type: file
        required: true
        direction: output
        default: dataset_uns.yaml
      - name: "--output_task_info"
        type: file
        required: true
        direction: output
        default: task_info.yaml
  - name: Method selection
    description: |
      Use these arguments to select which methods are run for each processing
      step. Only the methods provided to these arguments will be run.

      If a method is NOT in `default_methods` it will only be run in combination
      with the default methods.
    arguments:
      - name: "--default_methods"
        description: |
          A list of default methods that are always run in combination with all
          other methods. If this is set it should contain a single method from
          each step.
        type: string
        multiple: true
      - name: "--segmentation_methods"
        description: |
          A list of segmentation methods to run.
        type: string
        multiple: true
        default: "custom_segmentation:cellpose:binning:stardist:watershed"
      - name: "--transcript_assignment_methods"
        description: |
          A list of transcript assignment methods to run.
        type: string
        multiple: true
        default: "basic_transcript_assignment:baysor:clustermap:pciseq:comseg:proseg"
      - name: "--count_aggregation_methods"
        description: |
          A list of count aggregation methods to run.
        type: string
        multiple: true
        default: "basic_count_aggregation"
      - name: "--qc_filtering_methods"
        description: |
          A list of QC filtering methods to run.
        type: string
        multiple: true
        default: "basic_qc_filter"
      - name: "--volume_calculation_methods"
        description: |
          A list of volume calculation methods to run.
        type: string
        multiple: true
        default: "alpha_shapes"
      - name: "--normalization_methods"
        description: |
          A list of normalization methods to run.
        type: string
        multiple: true
        default: "normalize_by_volume:normalize_by_counts:spanorm"
      - name: "--celltype_annotation_methods"
        description: |
          A list of cell type annotation methods to run.
        type: string
        multiple: true
        default: "ssam:tacco:moscot:mapmycells:tangram:singler:rctd"
      - name: "--expression_correction_methods"
        description: |
          A list of expression correction methods to run.
        type: string
        multiple: true
        default: "no_correction:gene_efficiency_correction:resolvi_correction:split"
  - name: Method parameters
    description: |
      Use these arguments to control the parameter sets that are run for each
      method
    arguments:
      - name: "--method_parameters_yaml"
        description: |
          Optional path to a YAML file that defines method parameter sets and sweeps.
          The YAML should either contain a top-level `parameters:` mapping or be the
          mapping itself. Example structure:
            parameters:
              binning:
                default:
                  bin_size: 30
                sweep:
                  bin_size: [20, 30, 40]
        type: file
        direction: input
        required: false
  - name: Output control
    description: |
      Control which outputs are saved
    arguments:
      - name: "--save_spatial_data"
        description: |
          Whether to save the aggregated spatial data (.zarr files) to the output directory.
          When true, the output_agg_spatial_data files will be saved in subfolders according to run_id.
        type: boolean
        default: false

resources:
  - type: nextflow_script
    path: main.nf
    entrypoint: run_wf
  - type: file
    path: /_viash.yaml
  - path: /common/nextflow_helpers/helper.nf

dependencies:
  - name: utils/extract_uns_metadata
    repository: openproblems
  - name: control_methods/identity
  - name: control_methods/permute_celltype_annotations
  - name: methods_segmentation/custom_segmentation
  - name: methods_segmentation/cellpose
  - name: methods_segmentation/binning
  - name: methods_segmentation/stardist
  - name: methods_segmentation/watershed
  - name: methods_transcript_assignment/basic_transcript_assignment
  - name: methods_transcript_assignment/baysor
  - name: methods_transcript_assignment/clustermap
  - name: methods_transcript_assignment/pciseq
  - name: methods_transcript_assignment/comseg
  - name: methods_transcript_assignment/proseg
  - name: methods_count_aggregation/basic_count_aggregation
  - name: methods_qc_filter/basic_qc_filter
  - name: methods_calculate_cell_volume/alpha_shapes
  - name: methods_normalization/normalize_by_counts
  - name: methods_normalization/normalize_by_volume
  - name: methods_normalization/spanorm
  - name: methods_cell_type_annotation/ssam
  - name: methods_cell_type_annotation/tacco
  - name: methods_cell_type_annotation/moscot
  - name: methods_cell_type_annotation/mapmycells
  - name: methods_cell_type_annotation/tangram
  - name: methods_cell_type_annotation/singler
  - name: methods_cell_type_annotation/rctd
  - name: methods_expression_correction/no_correction
  - name: methods_expression_correction/gene_efficiency_correction
  - name: methods_expression_correction/resolvi_correction
  - name: methods_expression_correction/split
  - name: methods_data_aggregation/aggregate_spatial_data
  - name: metrics/similarity
  - name: metrics/quality

runners:
  - type: nextflow