Improve logging and docs

Author: Marius1311

src/methods/cellmapper_scvi/__pycache__/utils.cpython-312.pyc

@@ -4,7 +4,11 @@ label: CellMapper+scVI
 summary: "Modality prediction in an scVI latent space using CellMapper"
 description: |
   CellMapper is a general framework for k-NN based mapping tasks in single-cell and spatial genomics.
-  This variant uses CellMapper to project modalities from a reference dataset (train) onto a query dataset (test) in an scVI latent space.
+  This variant uses CellMapper to project modalities from a reference dataset (train) onto a query dataset 
+  (test) in a modality-specific latent space computed with suitable scvi-tools models. For gene expression data, 
+  we use the scVI model on raw counts (nb likelihood), for ADT data, we use the scVI models on normalized counts 
+  (gaussian likelihood), and for ATAC data, we use the PeakVI model on raw counts. The actual CellMapper pipeline is 
+  modality-agnostic. 
 references:
   doi: 
     - 10.5281/zenodo.15683594

src/methods/cellmapper_scvi/config.vsh.yaml

@@ -7,13 +7,13 @@
 # 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 = {
-    'input_train_mod1': 'resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap/train_mod1.h5ad',
-    'input_train_mod2': 'resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap/train_mod2.h5ad',
-    'input_test_mod1': 'resources_test/task_predict_modality/openproblems_neurips2021/bmmc_cite/swap/test_mod1.h5ad',
+    'input_train_mod1': 'resources_test/task_predict_modality/openproblems_neurips2021/bmmc_multiome/normal/train_mod1.h5ad',
+    'input_train_mod2': 'resources_test/task_predict_modality/openproblems_neurips2021/bmmc_multiome/normal/train_mod2.h5ad',
+    'input_test_mod1': 'resources_test/task_predict_modality/openproblems_neurips2021/bmmc_multiome/normal/test_mod1.h5ad',
     'output': 'output.h5ad',
     'n_neighbors': 30, 
     'kernel_method': 'hnoca',
-    'use_hvg': False,
+    'use_hvg': True,
 
 }
 meta = {

src/methods/cellmapper_scvi/script.py

@@ -54,8 +54,9 @@ def get_representation(adata: ad.AnnData, modality: Literal["GEX", "ADT", "ATAC"
         raise ValueError(f"Unknown modality: {modality}")
 
     example_data = adata.layers[layer].data if issparse(adata.layers[layer]) else adata.layers[layer]
-    print(f"Set up AnnData for modality: {modality}, layer={layer}", flush=True)
+    print(f"Set up AnnData for modality: '{modality}' using layer: '{layer}'", flush=True)
     print(f"Data looks like this: {example_data}", flush=True)
+    print(model, flush=True)
 
     # Train the model
     model.train(early_stopping=True)