fix error in control methods (#107)

* fix error in control methods

* update changelog

Author: ghar1821

CHANGELOG.md

@@ -97,6 +97,8 @@
 * Added EMD vertical global metric and split perfect integration into horizontal and vertical 
   for computing horizontal and vertical metrics (PR #63).
 
+* Fix problems identified during a full run (PR #99).
+
 ## MINOR CHANGES
 
 * Enabled unit tests (PR #2).
@@ -153,5 +155,6 @@
 
 * Fix missing anndata in yaml file and set the base_r docker image version to 1 instead of 1.0.0 (PR #89).
 
+* Fix bug in control methods (PR #107).
 
 

src/control_methods/shuffle_integration/script.py

@@ -4,10 +4,11 @@
 
 ## VIASH START
 par = {
-    "input_unintegrated": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/unintegrated_censored.h5ad",
-    "output": "output.h5ad",
+    "input_unintegrated": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/unintegrated.h5ad",
+    "output_integrated_split1": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/control_integrated_split1.h5ad",
+    "output_integrated_split2": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/control_integrated_split2.h5ad",
 }
-meta = {"name": "harmonypy"}
+meta = {"name": "shuffle_integration_by_cell_type", "resources_dir": "src/control_methods"}
 ## VIASH END
 
 print("Importing helper functions", flush=True)
@@ -16,25 +17,44 @@
 
 print("Reading and preparing input files", flush=True)
 adata = ad.read_h5ad(par["input_unintegrated"])
+adata_split1 = adata[(adata.obs.is_control > 0) | (adata.obs.split == 1)].copy()
+adata_split2 = adata[(adata.obs.is_control > 0) | (adata.obs.split == 2)].copy()
 
-adata.obs["batch_str"] = adata.obs["batch"].astype(str)
-
-print("Randomise features", flush=True)
+print("Randomise features - split 1", flush=True)
+adata_split1.obs["batch_str"] = adata_split1.obs["batch"].astype(str)
 integrated = _randomize_features(
-    adata.layers["preprocessed"]
+    adata_split1.layers["preprocessed"]
 )
 
 # create new anndata
-output = ad.AnnData(
-    obs=adata.obs[[]],
-    var=adata.var[[]],
+output_split1 = ad.AnnData(
+    obs=adata_split1.obs[[]],
+    var=adata_split1.var[[]],
+    layers={"integrated": integrated},
+    uns={
+        "dataset_id": adata_split1.uns["dataset_id"],
+        "method_id": meta["name"],
+        "parameters": {},
+    },
+)
+
+print("Randomise features - split 2", flush=True)
+adata_split2.obs["batch_str"] = adata_split2.obs["batch"].astype(str)
+integrated = _randomize_features(
+    adata_split2.layers["preprocessed"]
+)
+# create new anndata
+output_split2 = ad.AnnData(
+    obs=adata_split2.obs[[]],
+    var=adata_split2.var[[]],
     layers={"integrated": integrated},
     uns={
-        "dataset_id": adata.uns["dataset_id"],
+        "dataset_id": adata_split2.uns["dataset_id"],
         "method_id": meta["name"],
         "parameters": {},
     },
 )
 
 print("Write output AnnData to file", flush=True)
-output.write_h5ad(par["output"], compression="gzip")
+output_split1.write_h5ad(par["output_integrated_split1"], compression="gzip")
+output_split2.write_h5ad(par["output_integrated_split2"], compression="gzip")

src/control_methods/shuffle_integration_by_batch/script.py

@@ -16,7 +16,7 @@
 
 print("Reading and preparing input files", flush=True)
 adata = ad.read_h5ad(par["input_unintegrated"])
-adata_split1 = adata[(adata.obs.is_control > 0) | (adata.obs.batch == 1)].copy()
+adata_split1 = adata[(adata.obs.is_control > 0) | (adata.obs.split == 1)].copy()
 adata_split2 = adata[(adata.obs.is_control > 0) | (adata.obs.split == 2)].copy()
 
 print("Randomise features - split 1", flush=True)

src/control_methods/shuffle_integration_by_cell_type/script.py

@@ -5,9 +5,10 @@
 ## VIASH START
 par = {
     "input_unintegrated": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/unintegrated.h5ad",
-    "output": "output.h5ad",
+    "output_integrated_split1": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/control_integrated_split1.h5ad",
+    "output_integrated_split2": "resources_test/task_cyto_batch_integration/mouse_spleen_flow_cytometry_subset/control_integrated_split2.h5ad",
 }
-meta = {"name": "harmonypy"}
+meta = {"name": "shuffle_integration_by_cell_type", "resources_dir": "src/control_methods"}
 ## VIASH END
 
 print("Importing helper functions", flush=True)
@@ -16,7 +17,7 @@
 
 print("Reading and preparing input files", flush=True)
 adata = ad.read_h5ad(par["input_unintegrated"])
-adata_split1 = adata[(adata.obs.is_control > 0) | (adata.obs.batch == 1)].copy()
+adata_split1 = adata[(adata.obs.is_control > 0) | (adata.obs.split == 1)].copy()
 adata_split2 = adata[(adata.obs.is_control > 0) | (adata.obs.split == 2)].copy()
 
 print("Randomise features - split 1", flush=True)