andata_version_other updates

Author: saurabhinfocusp

README.md

@@ -374,5 +374,4 @@ Performs evaluation of best model trained on user-defined metrics on the test se
   
 ## Citation
 
-Jogani Saiyam, Anand Santosh Pol, Mayur Prajapati, Amit Samal, Kriti Bhatia, Jayendra Parmar, Urvik Patel, Falak Shah, Nisarg Vyas, and Saurabh Gupta. "scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery." bioRxiv (2024): 2024-09.
-
+Jogani, S., Pol, A. S., Prajapati, M., Samal, A., Bhatia, K., Parmar, J., ... & Gupta, S. (2025). scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery. Briefings in Bioinformatics, 26(3), bbaf243.

config/config.yaml

@@ -1,7 +1,7 @@
 # Config file for pipeline run.
 
 # DEVICE SETUP.
-device: 'cuda'
+device: 'cpu'
 
 # EXPERIMENT.
 experiment:
@@ -16,8 +16,7 @@ data:
     num_workers: 1
 
     train_val_test:
-        full_datapath: '/path/to/anndata.h5ad'
-
+        full_datapath: 'data/modified_adata.h5ad'
         splitter_config:
             name: GroupSplitter
             params:
@@ -35,7 +34,7 @@ data:
     #       params: 
     #             **args
 
-    target: Cell_Type    
+    target: cell_type    
 
 
 # FEATURE SELECTION.

requirements.txt

@@ -1,4 +1,4 @@
-anndata==0.10.9
+anndata>=0.11.2,<0.12
 isort==5.13.2
 loky==3.4.1
 memory-profiler==0.61.0

tutorials/pipeline/config_celltype.yaml

@@ -1,7 +1,7 @@
 # Config file for pipeline run for cell type classification.
 
 # DEVICE SETUP.
-device: 'cuda'
+device: 'cpu'
 
 # EXPERIMENT.
 experiment:

tutorials/pipeline/config_clinical.yaml

@@ -1,7 +1,7 @@
 # Config file for pipeline run for clinical condition specific biomarker identification.
 
 # DEVICE SETUP.
-device: 'cuda'
+device: 'cpu'
 
 # EXPERIMENT.
 experiment:
@@ -15,7 +15,7 @@ data:
     sample_chunksize: 20000
 
     train_val_test:
-        full_datapath: 'data/modified_adata.h5ad'
+        full_datapath: 'data/21ef2ea2-cbed-4b6c-a572-0ddd1d9020bc.h5ad'
         num_workers: 2
 
         splitter_config:

tutorials/pipeline/scalr_pipeline.ipynb

@@ -358,7 +358,7 @@
    "outputs": [],
    "source": [
     "#Gene expression values of first 5 cells and 10 genes.\n",
-    "adata.X[:5,:10].A"
+    "adata.X[:5,:10]\n"
    ]
   },
   {
@@ -385,7 +385,7 @@
    "source": [
     "# Verifying normalized values in X\n",
     "# Getting the sum of gene expression values for the first 10 cells (should be floating-point values).\n",
-    "adata.X[:10,:].A.sum(axis=1)"
+    "adata.X[:10,:].sum(axis=1)"
    ]
   },
   {
@@ -411,8 +411,8 @@
    "outputs": [],
    "source": [
     "# Getting the maximum and minimum gene expression values for the first 1000 cells.\n",
-    "max_val = np.max(adata.X[:1000, :].A)\n",
-    "min_val = np.min(adata.X[:1000, :].A)\n",
+    "max_val = np.max(adata.X[:1000, :])\n",
+    "min_val = np.min(adata.X[:1000, :])\n",
     "print(f'Max value : {max_val} | Min value : {min_val}')\n",
     "# Raising a warning if the values are outside the 0-10 range\n",
     "if max_val > 10 or min_val < 0:\n",