Add working method

src/methods/my_method/config.vsh.yaml → src/methods/logistic_regression/config.vsh.yaml

@@ -8,27 +8,30 @@ __merge__: ../../api/comp_method.yaml
 
 # A unique identifier for your component (required).
 # Can contain only lowercase letters or underscores.
-name: my_method
+name: logistic_regression
 
 # Metadata for your component
 info:
   # A relatively short label, used when rendering visualisations (required)
-  label: My Method
+  label: Logistic Regression
   # A one sentence summary of how this method works (required). Used when 
   # rendering summary tables.
-  summary: "FILL IN: A one sentence summary of this method."
+  summary: "Logistic Regression with 100-dimensional PCA coordinates estimates parameters for multivariate classification by minimizing cross entropy loss over cell type classes."
   # A multi-line description of how this component works (required). Used
   # when rendering reference documentation.
   description: |
-    FILL IN: A (multi-line) description of how this method works.
+    Logistic Regression estimates parameters of a logistic function for
+    multivariate classification tasks. Here, we use 100-dimensional whitened PCA
+    coordinates as independent variables, and the model minimises the cross
+    entropy loss over all cell type classes.
   # Which normalisation method this component prefers to use (required).
   preferred_normalization: log_cp10k
   # A reference key from the bibtex library at src/common/library.bib (required).
-  reference: bibtex_reference_key
+  reference: "hosmer2013applied"
   # URL to the documentation for this method (required).
-  documentation_url: https://url.to/the/documentation
+  documentation_url: "https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html"
   # URL to the code repository for this method (required).
-  repository_url: https://github.com/organisation/repository
+  repository_url: https://github.com/scikit-learn/scikit-learn
 
 # Component-specific parameters (optional)
 # arguments:
@@ -49,17 +52,17 @@ resources:
 engines:
   # Specifications for the Docker image for this component.
   - type: docker
-    image: ghcr.io/openproblems-bio/base_python:1.0.4
+    image: ghcr.io/openproblems-bio/base_images/python:1.1.0
     # Add custom dependencies here (optional). For more information, see
     # https://viash.io/reference/config/engines/docker/#setup .
-    # setup:
-    #   - type: python
-    #     packages: scib==1.1.5
+    setup:
+      - type: python
+        packages: scikit-learn
 
 runners:
   # This platform allows running the component natively
   - type: executable
   # Allows turning the component into a Nextflow module / pipeline.
   - type: nextflow
     directives:
-      label: [midtime,midmem,midcpu]
+      label: [midtime,midmem,lowcpu]

src/methods/my_method/script.py → src/methods/logistic_regression/script.py

@@ -1,37 +1,44 @@
 import anndata as ad
+import sklearn.linear_model
 
 ## VIASH START
 # Note: this section is auto-generated by viash at runtime. To edit it, make changes
 # in config.vsh.yaml and then run `viash config inject config.vsh.yaml`.
 par = {
-  'train_h5ad': 'resources_test/task_template/pancreas/train_h5ad.h5ad',
+  'input_train': 'resources_test/task_template/pancreas/train.h5ad',
+  'input_test': 'resources_test/task_template/pancreas/test.h5ad',
   'output': 'output.h5ad'
 }
 meta = {
-  'name': 'my_method'
+  'name': 'logistic_regression'
 }
 ## VIASH END
 
 print('Reading input files', flush=True)
-train_h5ad = ad.read_h5ad(par['train_h5ad'])
+input_train = ad.read_h5ad(par['input_train'])
+input_test = ad.read_h5ad(par['input_test'])
 
 print('Preprocess data', flush=True)
 # ... preprocessing ...
 
 print('Train model', flush=True)
 # ... train model ...
+classifier = sklearn.linear_model.LogisticRegression()
+classifier.fit(input_train.obsm["X_pca"], input_train.obs["label"].astype(str))
 
 print('Generate predictions', flush=True)
 # ... generate predictions ...
+obs_label_pred = classifier.predict(input_test.obsm["X_pca"])
 
 print("Write output AnnData to file", flush=True)
 output = ad.AnnData(
   uns={
-    'dataset_id': train_h5ad.uns['dataset_id'],
+    'dataset_id': input_train.uns['dataset_id'],
+    'normalization_id': input_train.uns['normalization_id'],
     'method_id': meta['name']
   },
-  layers={
-    'prediction': layers_prediction
+  obs={
+    'label_pred': obs_label_pred
   }
 )
 output.write_h5ad(par['output'], compression='gzip')