Merge branch 'main' of https://github.com/openproblems-bio/task-spati…

…al-decomposition

.github/workflows/build.yml

@@ -15,6 +15,8 @@ jobs:
 
     steps:
     - uses: actions/checkout@v4
+      with:
+        submodules: true
 
     - uses: viash-io/viash-actions/setup@v5
 
@@ -83,6 +85,8 @@ jobs:
     - uses: data-intuitive/reclaim-the-bytes@v2
 
     - uses: actions/checkout@v4
+      with:
+        submodules: true
 
     - uses: viash-io/viash-actions/setup@v5
 

.github/workflows/test.yml

@@ -40,6 +40,7 @@ jobs:
     - uses: actions/checkout@v4
       with:
         fetch-depth: 0 
+        submodules: true
 
     - uses: viash-io/viash-actions/setup@v5
 
@@ -86,6 +87,8 @@ jobs:
     - uses: data-intuitive/reclaim-the-bytes@v2
 
     - uses: actions/checkout@v4
+      with:
+        submodules: true
 
     - uses: viash-io/viash-actions/setup@v5
 

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "common"]
+	path = common
+	url = https://github.com/openproblems-bio/common-resources.git

scripts/add_component.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+echo "This script is not supposed to be run directly."
+echo "Please run the script step-by-step."
+exit 1
+
+# create a new component (types: method, metric, control_method)
+type="method"
+lang="python" # change this to "r" if need be
+
+common/create_component/create_component \
+  --task spatial_decomposition \
+  --type $type \
+  --name component_name \
+  --language $lang
+
+# TODO: fill in required fields in src/methods/foo/config.vsh.yaml
+# TODO: edit src/methods/foo/script.py/R
+
+# test the component
+viash test src/$type/component_name/config.vsh.yaml

scripts/build_components.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+# Build all components in namespace
+viash ns build --parallel --setup cb

scripts/download_resources.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+# Downloading test resources
+directories=("common" "spatial_decomposition")
+for dir in ${directories[@]}; do 
+    common/sync_resources/sync_resources \
+        --input "s3://openproblems-data/resources_test/$dir/cxg_mouse_pancreas_atlas" \
+        --output "resources_test/$dir/cxg_mouse_pancreas_atlas"
+done

scripts/render_readme.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+common/create_task_readme/create_task_readme \
+  --task "spatial_decomposition" \
+  --task_dir "src/" \
+  --github_url "https://github.com/openproblems-bio/task-spatial-decomposition/tree/main/" \
+  --output "README.md"

scripts/run_benchmark.sh

@@ -0,0 +1,35 @@
+#!/bin/bash
+
+# Process dataset
+RAW_DATA=resources_test/common
+DATASET_DIR=resources_test/spatial_decomposition
+echo "Running process_dataset"
+nextflow run . \
+    -main-script target/nextflow/workflows/process_datasets/main.nf \
+    -profile docker \
+    -entry auto \
+    -c common/nextflow_helpers/labels_ci.config \
+    --input_states "$RAW_DATA/**/state.yaml" \
+    --rename_keys 'input:output_dataset' \
+    --settings '{"output_spatial_masked": "$id/spatial_masked.h5ad", "output_single_cell": "$id/single_cell_ref.h5ad", "output_solution": "$id/solution.h5ad", "alpha": 1.0, "simulated_data": "$id/dataset_simulated.h5ad"}' \
+    --publish_dir "$DATASET_DIR" \
+    --output_state '$id/state.yaml'
+
+# Run benchmark
+DATASETS_DIR="resources_test/spatial_decomposition"
+OUTPUT_DIR="output/temp"
+if [ ! -d "$OUTPUT_DIR" ]; then
+  mkdir -p "$OUTPUT_DIR"
+fi
+echo "Running the benchmark"
+nextflow run . \
+  -main-script target/nextflow/workflows/run_benchmark/main.nf \
+  -profile docker \
+  -resume \
+  -entry auto \
+  -c common/nextflow_helpers/labels_ci.config \
+  --input_states "$DATASETS_DIR/**/state.yaml" \
+  --rename_keys 'input_single_cell:output_single_cell,input_spatial_masked:output_spatial_masked,input_solution:output_solution' \
+  --settings '{"output_scores": "scores.yaml", "output_dataset_info": "dataset_info.yaml", "output_method_configs": "method_configs.yaml", "output_metric_configs": "metric_configs.yaml", "output_task_info": "task_info.yaml"}' \
+  --publish_dir "$OUTPUT_DIR" \
+  --output_state "state.yaml"

scripts/run_benchmark_tw.sh

@@ -0,0 +1,60 @@
+#!/bin/bash
+
+### Process datasets
+# Simulating spot-resolution spatial data with alpha = 1
+
+cat > /tmp/params.yaml << 'HERE'
+id: spatial_decomposition_process_datasets
+input_states: s3://openproblems-data/resources/datasets/**/log_cp10k/state.yaml
+settings: '{"output_spatial_masked": "$id/spatial_masked.h5ad", "output_single_cell": "$id/single_cell_ref.h5ad", "output_solution": "$id/solution.h5ad", "alpha": 1.0, "simulated_data": "$id/dataset_simulated.h5ad"}'
+rename_keys: 'input:output_dataset'
+output_state: "$id/state.yaml"
+publish_dir: s3://openproblems-data/resources/spatial_decomposition/datasets
+HERE
+
+cat > /tmp/nextflow.config << HERE
+process {
+  executor = 'awsbatch'
+  withName:'.*publishStatesProc' {
+    memory = '16GB'
+    disk = '100GB'
+  }
+  withLabel:highmem {
+    memory = '350GB'
+  }
+}
+HERE
+
+tw launch https://github.com/openproblems-bio/task-spatial-decomposition.git \
+  --revision main_build \
+  --pull-latest \
+  --main-script target/nextflow/workflows/process_datasets/main.nf \
+  --workspace 53907369739130 \
+  --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
+  --params-file /tmp/params.yaml \
+  --entry-name auto \
+  --config /tmp/nextflow.config \
+
+
+
+### Run benchmark
+
+RUN_ID="run_$(date +%Y-%m-%d_%H-%M-%S)"
+publish_dir="s3://openproblems-data/resources/spatial_decomposition/results/${RUN_ID}"
+
+cat > /tmp/params.yaml << HERE
+input_states: s3://openproblems-data/resources/spatial_decomposition/datasets/**/log_cp10k/state.yaml
+rename_keys: 'input_single_cell:output_single_cell,input_spatial_masked:output_spatial_masked,input_solution:output_solution'
+output_state: "state.yaml"
+publish_dir: "$publish_dir"
+HERE
+
+tw launch https://github.com/openproblems-bio/task-spatial-decomposition.git \
+  --revision main_build \
+  --pull-latest \
+  --main-script target/nextflow/workflows/run_benchmark/main.nf \
+  --workspace 53907369739130 \
+  --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
+  --params-file /tmp/params.yaml \
+  --entry-name auto \
+  --config common/nextflow_helpers/labels_tw.config \

scripts/test_components.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+# Test all components in a namespace (refer https://viash.io/reference/cli/ns_test.html)
+viash ns test --parallel
+
+# Test individual components
+viash test src/methods/nnls/config.vsh.yaml
+
+
+DATASET_DIR=resources_test/spatial_decomposition
+
+# run one method
+viash run src/methods/nnls/config.vsh.yaml -- \
+    --input_single_cell $DATASET_DIR/cxg_mouse_pancreas_atlas/single_cell_ref.h5ad \
+    --input_spatial_masked $DATASET_DIR/cxg_mouse_pancreas_atlas/spatial_masked.h5ad \
+    --output $DATASET_DIR/cxg_mouse_pancreas_atlas/output.h5ad
+
+# run one metric
+viash run src/metrics/r2/config.vsh.yaml -- \
+    --input_method $DATASET_DIR/cxg_mouse_pancreas_atlas/output.h5ad \
+    --input_solution $DATASET_DIR/cxg_mouse_pancreas_atlas/solution.h5ad \
+    --output $DATASET_DIR/cxg_mouse_pancreas_atlas/score.h5ad

src/api/comp_control_method.yaml

@@ -0,0 +1,38 @@
+functionality:
+  namespace: "control_methods"
+  info:
+    type: control_method
+    type_info:
+      label: Control method
+      summary: Quality control methods for verifying the pipeline.
+      description: |
+        Control methods have the same interface as the regular methods
+        but also receive the solution object as input. It serves as a
+        starting point to test the relative accuracy of new methods in
+        the task, and also as a quality control for the metrics defined
+        in the task.
+  arguments:
+    - name: "--input_single_cell"
+      __merge__: file_single_cell.yaml
+      direction: input
+      required: true
+    - name: "--input_spatial_masked"
+      __merge__: file_spatial_masked.yaml
+      direction: input
+      required: true
+    - name: "--input_solution"
+      __merge__: file_solution.yaml
+      direction: input
+      required: true
+    - name: "--output"
+      __merge__: file_output.yaml
+      direction: output
+      required: true
+  test_resources:
+    - type: python_script
+      path: /common/component_tests/check_method_config.py
+    - type: python_script
+      path: /common/component_tests/run_and_check_output.py
+    - path: /resources_test/spatial_decomposition/cxg_mouse_pancreas_atlas
+      dest: resources_test/spatial_decomposition/cxg_mouse_pancreas_atlas
+    - path: /common/library.bib

src/api/comp_method.yaml

@@ -0,0 +1,29 @@
+functionality:
+  namespace: "methods"
+  info:
+    type: method
+    type_info:
+      label: Method
+      summary: A spatial composition method.
+      description: "Method to estimate cell type proportions from spatial and single cell data"
+  arguments:
+    - name: "--input_single_cell"
+      __merge__: file_single_cell.yaml
+      direction: input
+      required: true
+    - name: "--input_spatial_masked"
+      __merge__: file_spatial_masked.yaml
+      direction: input
+      required: true
+    - name: "--output"
+      __merge__: file_output.yaml
+      direction: output
+      required: true
+  test_resources:
+    - type: python_script
+      path: /common/component_tests/check_method_config.py
+    - type: python_script
+      path: /common/component_tests/run_and_check_output.py
+    - path: /resources_test/spatial_decomposition/cxg_mouse_pancreas_atlas
+      dest: resources_test/spatial_decomposition/cxg_mouse_pancreas_atlas
+    - path: /common/library.bib

src/api/comp_metric.yaml

@@ -0,0 +1,31 @@
+functionality:
+  namespace: "metrics"
+  info:
+    type: metric
+    type_info:
+      label: Metric
+      summary: A spatial decomposition metric.  
+      description: |
+        A metric for evaluating accuracy of cell type proportion estimate
+  arguments:
+    - name: "--input_method"
+      __merge__: file_output.yaml
+      direction: input
+      required: true
+    - name: "--input_solution"
+      __merge__: file_solution.yaml
+      direction: input
+      required: true
+    - name: "--output"
+      __merge__: file_score.yaml
+      direction: output
+      required: true
+  test_resources:
+    - type: python_script
+      path: /common/component_tests/check_metric_config.py
+    - type: python_script
+      path: /common/component_tests/run_and_check_output.py
+    - path: /resources_test/spatial_decomposition/cxg_mouse_pancreas_atlas
+      dest: resources_test/spatial_decomposition/cxg_mouse_pancreas_atlas
+    - path: /common/library.bib
+

src/api/comp_process_dataset.yaml

@@ -0,0 +1,33 @@
+functionality:
+  namespace: process_dataset
+  info:
+    type: process_dataset
+    type_info:
+      label: Data processor
+      summary: A spatial decomposition dataset processor.
+      description: |
+        Prepare a common dataset for the spatial_decomposition task.
+  arguments:
+    - name: "--input"
+      __merge__: file_common_dataset.yaml
+      direction: input
+      required: true
+    - name: "--output_single_cell"
+      __merge__: file_single_cell.yaml
+      direction: output
+      required: true
+    - name: "--output_spatial_masked"
+      __merge__: file_spatial_masked.yaml
+      direction: output
+      required: true
+    - name: "--output_solution"
+      __merge__: file_solution.yaml
+      direction: output
+      required: true
+  test_resources:
+    - type: python_script
+      path: /common/component_tests/run_and_check_output.py
+    # - path: /resources_test/common/cxg_mouse_pancreas_atlas
+    #   dest: resources_test/common/cxg_mouse_pancreas_atlas
+    - path: /resources_test/spatial_decomposition/cxg_mouse_pancreas_atlas
+      dest: resources_test/spatial_decomposition/cxg_mouse_pancreas_atlas