Add SCimilarity

README.md

@@ -91,8 +91,7 @@ flowchart TB
 
 A subset of the common dataset.
 
-Example file:
-`resources_test/common/cxg_mouse_pancreas_atlas/dataset.h5ad`
+Example file: `resources_test/common/cxg_immune_cell_atlas/dataset.h5ad`
 
 Format:
 
@@ -158,7 +157,7 @@ Arguments:
 Unintegrated AnnData HDF5 file.
 
 Example file:
-`resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad`
+`resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad`
 
 Format:
 
@@ -202,7 +201,7 @@ Data structure:
 Uncensored dataset containing the true labels.
 
 Example file:
-`resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/solution.h5ad`
+`resources_test/task_batch_integration/cxg_immune_cell_atlas/solution.h5ad`
 
 Format:
 
@@ -317,7 +316,7 @@ Arguments:
 An integrated AnnData dataset.
 
 Example file:
-`resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/integrated.h5ad`
+`resources_test/task_batch_integration/cxg_immune_cell_atlas/integrated.h5ad`
 
 Description:
 
@@ -362,7 +361,7 @@ Data structure:
 An integrated AnnData dataset with additional outputs.
 
 Example file:
-`resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/integrated_full.h5ad`
+`resources_test/task_batch_integration/cxg_immune_cell_atlas/integrated_full.h5ad`
 
 Description:
 

_viash.yaml

@@ -31,21 +31,21 @@ description: |
 
 references:
   doi:
-    # Luecken, M.D., Büttner, M., Chaichoompu, K. et al. 
-    # Benchmarking atlas-level data integration in single-cell genomics. Nat Methods 19, 41–50 (2022). 
+    # Luecken, M.D., Büttner, M., Chaichoompu, K. et al.
+    # Benchmarking atlas-level data integration in single-cell genomics. Nat Methods 19, 41–50 (2022).
     - 10.1038/s41592-021-01336-8
-  
+
 info:
   image: thumbnail.svg
   test_resources:
     - type: s3
-      path: s3://openproblems-data/resources_test/common/cxg_mouse_pancreas_atlas/
-      dest: resources_test/common/cxg_mouse_pancreas_atlas
+      path: s3://openproblems-data/resources_test/common/cxg_immune_cell_atlas/
+      dest: resources_test/common/cxg_immune_cell_atlas
     - type: s3
       path: s3://openproblems-data/resources_test/task_batch_integration/
       dest: resources_test/task_batch_integration
 
-authors: 
+authors:
   - name: Michaela Mueller
     roles: [ maintainer, author ]
     info:

scripts/create_resources/test_resources.sh

@@ -15,36 +15,36 @@ mkdir -p $DATASET_DIR
 
 # process dataset
 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 "$DATASET_DIR/cxg_mouse_pancreas_atlas/solution.h5ad"
+  --input "$RAW_DATA/cxg_immune_cell_atlas/dataset.h5ad" \
+  --output_dataset "$DATASET_DIR/cxg_immune_cell_atlas/dataset.h5ad" \
+  --output_solution "$DATASET_DIR/cxg_immune_cell_atlas/solution.h5ad"
 
 # run one method
 viash run src/methods/combat/config.vsh.yaml -- \
-  --input $DATASET_DIR/cxg_mouse_pancreas_atlas/dataset.h5ad \
-  --output $DATASET_DIR/cxg_mouse_pancreas_atlas/integrated.h5ad
+  --input $DATASET_DIR/cxg_immune_cell_atlas/dataset.h5ad \
+  --output $DATASET_DIR/cxg_immune_cell_atlas/integrated.h5ad
 
 # run transformer
 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 \
+    --input_integrated $DATASET_DIR/cxg_immune_cell_atlas/integrated.h5ad \
+    --input_dataset $DATASET_DIR/cxg_immune_cell_atlas/dataset.h5ad \
     --expected_method_types feature \
-    --output $DATASET_DIR/cxg_mouse_pancreas_atlas/integrated_full.h5ad
+    --output $DATASET_DIR/cxg_immune_cell_atlas/integrated_full.h5ad
 
 # run one metric
 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
+    --input_integrated $DATASET_DIR/cxg_immune_cell_atlas/integrated_full.h5ad \
+    --input_solution $DATASET_DIR/cxg_immune_cell_atlas/solution.h5ad \
+    --output $DATASET_DIR/cxg_immune_cell_atlas/score.h5ad
 
 # write the state file
-cat > $DATASET_DIR/state.yaml << HERE
-id: cxg_mouse_pancreas_atlas
+cat > $DATASET_DIR/cxg_immune_cell_atlas/state.yaml << HERE
+id: cxg_immune_cell_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
+output_score: !file score_mod1.h5ad
 HERE
 
 # only run this if you have access to the openproblems-data bucket

src/api/base_method.yaml

@@ -0,0 +1,20 @@
+namespace: methods
+info:
+  type: method
+  type_info:
+    label: Method
+    summary: A method for the batch integration task.
+    description: |
+      A batch integration method which integrates multiple datasets.
+arguments:
+  - name: --input
+    __merge__: file_dataset.yaml
+    direction: input
+    required: true
+  - name: --output
+    __merge__: file_integrated.yaml
+    direction: output
+    required: true
+test_resources:
+  - type: python_script
+    path: /common/component_tests/check_config.py

src/api/comp_control_method.yaml

@@ -24,5 +24,5 @@ test_resources:
     path: /common/component_tests/check_config.py
   - type: python_script
     path: /common/component_tests/run_and_check_output.py
-  - path: /resources_test/task_batch_integration/cxg_mouse_pancreas_atlas
-    dest: resources_test/task_batch_integration/cxg_mouse_pancreas_atlas
+  - path: /resources_test/task_batch_integration/cxg_immune_cell_atlas
+    dest: resources_test/task_batch_integration/cxg_immune_cell_atlas

src/api/comp_method.yaml

@@ -1,24 +1,6 @@
-namespace: methods
-info:
-  type: method
-  type_info:
-    label: Method
-    summary: A method for the batch integration task.
-    description: |
-      A batch integration method which integrates multiple datasets.
-arguments:
-  - name: --input
-    __merge__: file_dataset.yaml
-    direction: input
-    required: true
-  - name: --output
-    __merge__: file_integrated.yaml
-    direction: output
-    required: true
+__merge__: base_method.yaml
 test_resources:
-  - type: python_script
-    path: /common/component_tests/check_config.py
   - type: python_script
     path: /common/component_tests/run_and_check_output.py
-  - path: /resources_test/task_batch_integration/cxg_mouse_pancreas_atlas
-    dest: resources_test/task_batch_integration/cxg_mouse_pancreas_atlas
+  - path: /resources_test/task_batch_integration/cxg_immune_cell_atlas
+    dest: resources_test/task_batch_integration/cxg_immune_cell_atlas

src/api/comp_metric.yaml

@@ -24,5 +24,5 @@ test_resources:
     path: /common/component_tests/check_config.py
   - type: python_script
     path: /common/component_tests/run_and_check_output.py
-  - path: /resources_test/task_batch_integration/cxg_mouse_pancreas_atlas
-    dest: resources_test/task_batch_integration/cxg_mouse_pancreas_atlas
+  - path: /resources_test/task_batch_integration/cxg_immune_cell_atlas
+    dest: resources_test/task_batch_integration/cxg_immune_cell_atlas

src/api/comp_process_dataset.yaml

@@ -25,7 +25,7 @@ arguments:
     default: 2000
     required: false
 test_resources:
-  - path: /resources_test/common/cxg_mouse_pancreas_atlas/
-    dest: resources_test/common/cxg_mouse_pancreas_atlas/
+  - path: /resources_test/common/cxg_immune_cell_atlas/
+    dest: resources_test/common/cxg_immune_cell_atlas/
   - type: python_script
-    path: /common/component_tests/run_and_check_output.py
+    path: /common/component_tests/run_and_check_output.py

src/api/comp_transformer.yaml

@@ -6,7 +6,7 @@ info:
     summary: Check the output and transform to create additional output types
     description: |
       This component will:
-      
+
         - Assert whether the input dataset and integrated dataset have the same shape.
         - Reorder the integrated dataset to match the input dataset if needed.
         - Transform the corrected feature output to an embedding.
@@ -26,7 +26,7 @@ arguments:
     required: true
     multiple: true
     description: |
-      The expected output types of the batch integration method. 
+      The expected output types of the batch integration method.
     choices: [ feature, embedding, graph ]
   - name: --output
     __merge__: file_integrated_full.yaml
@@ -35,5 +35,5 @@ arguments:
 test_resources:
   - type: python_script
     path: /common/component_tests/run_and_check_output.py
-  - path: /resources_test/task_batch_integration/cxg_mouse_pancreas_atlas
-    dest: resources_test/task_batch_integration/cxg_mouse_pancreas_atlas
+  - path: /resources_test/task_batch_integration/cxg_immune_cell_atlas
+    dest: resources_test/task_batch_integration/cxg_immune_cell_atlas

src/api/file_common_dataset.yaml

@@ -2,7 +2,7 @@
 # `src/datasets/api/file_common_dataset.yaml`. However, some fields
 # such as obs.cell_type and obs.batch are now required
 type: file
-example: "resources_test/common/cxg_mouse_pancreas_atlas/dataset.h5ad"
+example: "resources_test/common/cxg_immune_cell_atlas/dataset.h5ad"
 label: "Common Dataset"
 summary: A subset of the common dataset.
 info:

src/api/file_dataset.yaml

@@ -1,5 +1,5 @@
 type: file
-example: "resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad"
+example: "resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad"
 label: "Dataset"
 summary: Unintegrated AnnData HDF5 file.
 info:

src/api/file_integrated.yaml

@@ -1,5 +1,5 @@
 type: file
-example: "resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/integrated.h5ad"
+example: "resources_test/task_batch_integration/cxg_immune_cell_atlas/integrated.h5ad"
 label: Integration
 summary: An integrated AnnData dataset.
 description: |

src/api/file_integrated_full.yaml

@@ -1,5 +1,5 @@
 type: file
-example: "resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/integrated_full.h5ad"
+example: "resources_test/task_batch_integration/cxg_immune_cell_atlas/integrated_full.h5ad"
 label: Transformed integration
 summary: An integrated AnnData dataset with additional outputs.
 description: |
@@ -8,7 +8,7 @@ description: |
     - Feature: the corrected_counts layer
     - Embedding: the X_emb obsm
     - Graph: the connectivities and distances obsp
-  
+
   The Graph should always be present, but the Feature and Embedding are optional.
 info:
   format:

src/api/file_solution.yaml

@@ -1,5 +1,5 @@
 type: file
-example: "resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/solution.h5ad"
+example: "resources_test/task_batch_integration/cxg_immune_cell_atlas/solution.h5ad"
 label: "Solution"
 summary: Uncensored dataset containing the true labels.
 info:

src/control_methods/embed_cell_types/script.py

@@ -2,11 +2,11 @@
 
 ## VIASH START
 par = {
-    'input_dataset': 'resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad',
-    'input_solution': 'resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/solution.h5ad',
+    'input_dataset': 'resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad',
+    'input_solution': 'resources_test/task_batch_integration/cxg_immune_cell_atlas/solution.h5ad',
     'output': 'output.h5ad',
 }
-meta = { 
+meta = {
     'functionality': 'foo',
     'config': 'bar'
 }

src/control_methods/embed_cell_types_jittered/script.py

@@ -4,13 +4,13 @@
 ## VIASH START
 
 par = {
-    'input_dataset': 'resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad',
-    'input_solution': 'resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/solution.h5ad',
+    'input_dataset': 'resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad',
+    'input_solution': 'resources_test/task_batch_integration/cxg_immune_cell_atlas/solution.h5ad',
     'output': 'output.h5ad',
     'jitter': 0.01,
 }
 
-meta = { 
+meta = {
     'functionality': 'foo',
     'config': 'bar'
 }

src/control_methods/no_integration/script.py

@@ -2,7 +2,7 @@
 
 ## VIASH START
 par = {
-    'input_dataset': 'resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad',
+    'input_dataset': 'resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad',
     'output': 'output.h5ad',
 }
 ## VIASH END

src/control_methods/no_integration_batch/script.py

@@ -5,11 +5,11 @@
 ## VIASH START
 
 par = {
-    'input_dataset': 'resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad',
+    'input_dataset': 'resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad',
     'output': 'output.h5ad',
 }
 
-meta = { 
+meta = {
     'functionality': 'foo',
     'config': 'bar'
 }
@@ -46,4 +46,4 @@
 
 print("Store outputs", flush=True)
 adata.uns['method_id'] = meta['name']
-adata.write_h5ad(par['output'], compression='gzip')
+adata.write_h5ad(par['output'], compression='gzip')

src/control_methods/shuffle_integration/script.py

@@ -3,10 +3,10 @@
 
 ## VIASH START
 par = {
-    'input_dataset': 'resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad',
+    'input_dataset': 'resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad',
     'output': 'output.h5ad',
 }
-meta = { 
+meta = {
     "resources_dir": "src/tasks/batch_integration/control_methods/"
 }
 ## VIASH END

src/control_methods/shuffle_integration_by_batch/script.py

@@ -3,10 +3,10 @@
 
 ## VIASH START
 par = {
-    'input_dataset': 'resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad',
+    'input_dataset': 'resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad',
     'output': 'output.h5ad',
 }
-meta = { 
+meta = {
     "resources_dir": "src/tasks/batch_integration/control_methods/"
 }
 ## VIASH END

src/control_methods/shuffle_integration_by_cell_type/script.py

@@ -3,10 +3,10 @@
 
 ## VIASH START
 par = {
-    'input_dataset': 'resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad',
+    'input_dataset': 'resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad',
     'output': 'output.h5ad',
 }
-meta = { 
+meta = {
     "resources_dir": "src/tasks/batch_integration/control_methods/"
 }
 ## VIASH END

src/data_processors/transform/script.py

@@ -3,8 +3,8 @@
 
 ## VIASH START
 par = {
-    "input_integrated": "resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/integrated.h5ad",
-    "input_dataset": "resources_test/task_batch_integration/cxg_mouse_pancreas_atlas/dataset.h5ad",
+    "input_integrated": "resources_test/task_batch_integration/cxg_immune_cell_atlas/integrated.h5ad",
+    "input_dataset": "resources_test/task_batch_integration/cxg_immune_cell_atlas/dataset.h5ad",
     "expected_method_types": ["feature"],
     "ouput": "output.h5ad"
 }
@@ -28,7 +28,7 @@
 
 if "corrected_counts" in integrated.layers.keys():
     assert integrated.shape[1] == dataset.shape[1], "Number of genes do not match"
-    
+
     if not integrated.var.index.equals(dataset.var.index):
         assert integrated.var.index.sort_values().equals(dataset.var.index.sort_values()), "Gene names do not match"
         print("Reordering genes", flush=True)