fix workflows

scripts/create_resources/test_resources.sh

@@ -14,7 +14,7 @@ DATASET_DIR=resources_test/task_batch_integration
 mkdir -p $DATASET_DIR
 
 # process dataset
-viash run src/process_dataset/config.vsh.yaml -- \
+viash run src/data_processors/process_dataset/config.vsh.yaml -- \
   --input "$RAW_DATA/cxg_mouse_pancreas_atlas/dataset.h5ad" \
   --output_dataset "$DATASET_DIR/cxg_mouse_pancreas_atlas/dataset.h5ad" \
   --output_solution "$DATASET_DIR/cxg_mouse_pancreas_atlas/solution.h5ad"
@@ -25,18 +25,28 @@ viash run src/methods/combat/config.vsh.yaml -- \
   --output $DATASET_DIR/cxg_mouse_pancreas_atlas/integrated.h5ad
 
 # run transformer
-viash run src/transformers/transform/config.vsh.yaml -- \
+viash run src/data_processors/transform/config.vsh.yaml -- \
     --input_integrated $DATASET_DIR/cxg_mouse_pancreas_atlas/integrated.h5ad \
     --input_dataset $DATASET_DIR/cxg_mouse_pancreas_atlas/dataset.h5ad \
     --expected_method_types feature \
     --output $DATASET_DIR/cxg_mouse_pancreas_atlas/integrated_full.h5ad
 
 # run one metric
-viash run src/metrics/accuracy/config.vsh.yaml -- \
-    --input_prediction $DATASET_DIR/cxg_mouse_pancreas_atlas/integrated.h5ad \
+viash run src/metrics/graph_connectivity/config.vsh.yaml -- \
+    --input_integrated $DATASET_DIR/cxg_mouse_pancreas_atlas/integrated_full.h5ad \
     --input_solution $DATASET_DIR/cxg_mouse_pancreas_atlas/solution.h5ad \
     --output $DATASET_DIR/cxg_mouse_pancreas_atlas/score.h5ad
 
+# write the state file
+cat > $DATASET_DIR/state.yaml << HERE
+id: cxg_mouse_pancreas_atlas
+output_dataset: !file dataset.h5ad
+output_solution: !file solution.h5ad
+output_integrated: !file integrated.h5ad
+output_integrated_full: !file integrated_full.h5ad
+output_score: !file score.h5ad
+HERE
+
 # only run this if you have access to the openproblems-data bucket
 aws s3 sync --profile op \
   "resources_test/task_batch_integration" \

scripts/run_benchmark/run_test_local.sh

@@ -6,14 +6,6 @@ REPO_ROOT=$(git rev-parse --show-toplevel)
 # ensure that the command below is run from the root of the repository
 cd "$REPO_ROOT"
 
-# remove this when you have implemented the script
-echo "TODO: once the 'run_benchmark' workflow has been implemented, update this script to use it."
-echo "  Step 1: replace 'task_batch_integration' with the name of the task in the following command."
-echo "  Step 2: replace the rename keys parameters to fit your run_benchmark inputs"
-echo "  Step 3: replace the settings parameter to fit your run_benchmark outputs"
-echo "  Step 4: remove this message"
-exit 1
-
 set -e
 
 echo "Running benchmark on test data"
@@ -26,7 +18,7 @@ publish_dir="resources/results/${RUN_ID}"
 # write the parameters to file
 cat > /tmp/params.yaml << HERE
 input_states: s3://openproblems-data/resources_test/task_batch_integration/**/state.yaml
-rename_keys: 'input_train:output_train;input_test:output_test;input_solution:output_solution'
+rename_keys: 'input_dataset:output_dataset;input_solution:output_solution'
 output_state: "state.yaml"
 publish_dir: "$publish_dir"
 HERE

src/api/comp_transformer.yaml

@@ -1,4 +1,4 @@
-namespace: transformers
+namespace: data_processors
 info:
   type: transformer
   type_info:

src/workflows/process_datasets/config.vsh.yaml

@@ -1,29 +1,23 @@
 name: process_datasets
 namespace: workflows
 
-status: disabled
-
 argument_groups:
-  # - name: Inputs
-  #   arguments:
-  #     - name: "--input"
-  #       __merge__: /src/api/file_common_dataset.yaml
-  #       required: true
-  #       direction: input
-  # - name: Outputs
-  #   arguments:
-  #     - name: "--output_train"
-  #       __merge__: /src/api/file_train_h5ad.yaml
-  #       required: true
-  #       direction: output
-  #     - name: "--output_test"
-  #       __merge__: /src/api/file_test_h5ad.yaml
-  #       required: true
-  #       direction: output
-  #     - name: "--output_solution"
-  #       __merge__: /src/api/file_solution.yaml
-  #       required: true
-  #       direction: output
+  - name: Inputs
+    arguments:
+      - name: "--input"
+        __merge__: /src/api/file_common_dataset.yaml
+        required: true
+        direction: input
+  - name: Outputs
+    arguments:
+      - name: "--output_dataset"
+        __merge__: /src/api/file_dataset.yaml
+        required: true
+        direction: output
+      - name: "--output_solution"
+        __merge__: /src/api/file_solution.yaml
+        required: true
+        direction: output
 
 resources:
   - type: nextflow_script

src/workflows/process_datasets/main.nf

@@ -1,7 +1,7 @@
 include { findArgumentSchema } from "${meta.resources_dir}/helper.nf"
 
 workflow auto {
-  findStatesTemp(params, meta.config)
+  findStates(params, meta.config)
     | meta.workflow.run(
       auto: [publish: "state"]
     )
@@ -41,133 +41,14 @@ workflow run_wf {
     | process_dataset.run(
       fromState: [ input: "dataset" ],
       toState: [
-        output_train: "output_train",
-        output_test: "output_test",
+        output_dataset: "output_dataset",
         output_solution: "output_solution"
       ]
     )
 
     // only output the files for which an output file was specified
-    | setState(["output_train", "output_test", "output_solution"])
+    | setState(["output_dataset", "output_solution"])
 
   emit:
   output_ch
 }
-
-
-// temp fix for rename_keys typo
-
-def findStatesTemp(Map params, Map config) {
-  def auto_config = deepClone(config)
-  def auto_params = deepClone(params)
-
-  auto_config = auto_config.clone()
-  // override arguments
-  auto_config.argument_groups = []
-  auto_config.arguments = [
-    [
-      type: "string",
-      name: "--id",
-      description: "A dummy identifier",
-      required: false
-    ],
-    [
-      type: "file",
-      name: "--input_states",
-      example: "/path/to/input/directory/**/state.yaml",
-      description: "Path to input directory containing the datasets to be integrated.",
-      required: true,
-      multiple: true,
-      multiple_sep: ";"
-    ],
-    [
-      type: "string",
-      name: "--filter",
-      example: "foo/.*/state.yaml",
-      description: "Regex to filter state files by path.",
-      required: false
-    ],
-    // to do: make this a yaml blob?
-    [
-      type: "string",
-      name: "--rename_keys",
-      example: ["newKey1:oldKey1", "newKey2:oldKey2"],
-      description: "Rename keys in the detected input files. This is useful if the input files do not match the set of input arguments of the workflow.",
-      required: false,
-      multiple: true,
-      multiple_sep: ";"
-    ],
-    [
-      type: "string",
-      name: "--settings",
-      example: '{"output_dataset": "dataset.h5ad", "k": 10}',
-      description: "Global arguments as a JSON glob to be passed to all components.",
-      required: false
-    ]
-  ]
-  if (!(auto_params.containsKey("id"))) {
-    auto_params["id"] = "auto"
-  }
-
-  // run auto config through processConfig once more
-  auto_config = processConfig(auto_config)
-
-  workflow findStatesTempWf {
-    helpMessage(auto_config)
-
-    output_ch = 
-      channelFromParams(auto_params, auto_config)
-        | flatMap { autoId, args ->
-
-          def globalSettings = args.settings ? readYamlBlob(args.settings) : [:]
-
-          // look for state files in input dir
-          def stateFiles = args.input_states
-
-          // filter state files by regex
-          if (args.filter) {
-            stateFiles = stateFiles.findAll{ stateFile ->
-              def stateFileStr = stateFile.toString()
-              def matcher = stateFileStr =~ args.filter
-              matcher.matches()}
-          }
-
-          // read in states
-          def states = stateFiles.collect { stateFile ->
-            def state_ = readTaggedYaml(stateFile)
-            [state_.id, state_]
-          }
-
-          // construct renameMap
-          if (args.rename_keys) {
-            def renameMap = args.rename_keys.collectEntries{renameString ->
-              def split = renameString.split(":")
-              assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey;newKey:oldKey'"
-              split
-            }
-
-            // rename keys in state, only let states through which have all keys
-            // also add global settings
-            states = states.collectMany{id, state ->
-              def newState = [:]
-
-              for (key in renameMap.keySet()) {
-                def origKey = renameMap[key]
-                if (!(state.containsKey(origKey))) {
-                  return []
-                }
-                newState[key] = state[origKey]
-              }
-
-              [[id, globalSettings + newState]]
-            }
-          }
-
-          states
-        }
-    emit:
-    output_ch
-  }
-
-  return findStatesTempWf
-}

src/workflows/run_benchmark/config.vsh.yaml

@@ -1,26 +1,19 @@
 name: run_benchmark
 namespace: workflows
 
-status: disabled
-
 argument_groups:
   - name: Inputs
     arguments:
-      # - name: "--input_train"
-      #   __merge__: /src/api/file_train_h5ad.yaml
-      #   type: file
-      #   direction: input
-      #   required: true
-      # - name: "--input_test"
-      #   __merge__: /src/api/file_test_h5ad.yaml
-      #   type: file
-      #   direction: input
-      #   required: true
-      # - name: "--input_solution"
-      #   __merge__: /src/api/file_solution.yaml
-      #   type: file
-      #   direction: input
-      #   required: true
+      - name: "--input_dataset"
+        __merge__: /src/api/file_dataset.yaml
+        type: file
+        direction: input
+        required: true
+      - name: "--input_solution"
+        __merge__: /src/api/file_solution.yaml
+        type: file
+        direction: input
+        required: true
   - name: Outputs
     arguments:
       - name: "--output_scores"
@@ -66,9 +59,36 @@ resources:
 dependencies:
   - name: h5ad/extract_uns_metadata
     repository: core
-  - name: control_methods/true_labels
-  - name: methods/logistic_regression
-  - name: metrics/accuracy
+  - name: control_methods/embed_cell_types
+  - name: control_methods/embed_cell_types_jittered
+  - name: control_methods/no_integration
+  - name: control_methods/no_integration_batch
+  - name: control_methods/shuffle_integration
+  - name: control_methods/shuffle_integration_by_batch
+  - name: control_methods/shuffle_integration_by_cell_type
+  - name: methods/bbknn
+  - name: methods/combat
+  - name: methods/fastmnn
+  - name: methods/liger
+  - name: methods/mnn_correct
+  - name: methods/mnnpy
+  - name: methods/pyliger
+  - name: methods/scalex
+  - name: methods/scanorama
+  - name: methods/scanvi
+  - name: methods/scvi
+  - name: metrics/asw_batch
+  - name: metrics/aws_label
+  - name: metrics/cell_cycle_conservation
+  - name: metrics/clustering_overlap
+  - name: metrics/graph_connectivity
+  - name: metrics/hvg_overlap
+  - name: metrics/isolated_label_asw
+  - name: metrics/isolated_label_f1
+  - name: metrics/kbet
+  - name: metrics/lisi
+  - name: metrics/pcr
+  - name: data_processors/transform
 
 runners:
   - type: nextflow