Fixed the error of subset of cell using isin (#144)

Starlitnightly · Sep 11, 2024 · 4f0838a · 4f0838a
1 parent a501c93
commit 4f0838a
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 38 deletions.
diff --git a/omicverse/pp/_preprocess.py b/omicverse/pp/_preprocess.py
@@ -478,7 +478,7 @@ def preprocess(adata, mode='shiftlog|pearson', target_sum=50*1e4, n_HVGs=2000,
     adata.var = adata.var.drop(columns=['highly_variable_features'])
     adata.var['highly_variable_features'] = adata.var['highly_variable']
     adata.var = adata.var.drop(columns=['highly_variable'])
-    adata.var = adata.var.rename(columns={'means':'mean', 'variances':'var'})
+    #adata.var = adata.var.rename(columns={'means':'mean', 'variances':'var'})
     print(f'End of size normalization: {method_list[0]} and HVGs selection {method_list[1]}')
     return adata
 def normalize_pearson_residuals(adata,**kwargs):

diff --git a/omicverse/single/_batch.py b/omicverse/single/_batch.py
@@ -34,8 +34,9 @@ def batch_correction(adata:anndata.AnnData,batch_key:str,
             )
 
         adata3=adata.copy()
-        scale(adata3)
-        pca(adata3,layer='scaled',n_pcs=n_pcs)
+        if 'scaled|original|X_pca' not in adata3.obsm.keys():
+            scale(adata3)
+            pca(adata3,layer='scaled',n_pcs=n_pcs)
         sc.external.pp.harmony_integrate(adata3, batch_key,basis=use_rep,**kwargs)
         adata.obsm['X_harmony']=adata3.obsm['X_pca_harmony'].copy()
         return adata3

diff --git a/omicverse_guide/docs/Tutorials-single/t_single_batch.ipynb b/omicverse_guide/docs/Tutorials-single/t_single_batch.ipynb
@@ -276,40 +276,6 @@
     "We can store the raw counts if we need the raw counts after filtered the HVGs."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "cba5294c-0ade-4f23-807a-4fd71f4f640a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "......The X of adata have been stored in counts\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "AnnData object with n_obs × n_vars = 26707 × 13953\n",
-       "    obs: 'GEX_n_genes_by_counts', 'GEX_pct_counts_mt', 'GEX_size_factors', 'GEX_phase', 'ADT_n_antibodies_by_counts', 'ADT_total_counts', 'ADT_iso_count', 'cell_type', 'batch', 'ADT_pseudotime_order', 'GEX_pseudotime_order', 'Samplename', 'Site', 'DonorNumber', 'Modality', 'VendorLot', 'DonorID', 'DonorAge', 'DonorBMI', 'DonorBloodType', 'DonorRace', 'Ethnicity', 'DonorGender', 'QCMeds', 'DonorSmoker', 'is_train', 'nUMIs', 'mito_perc', 'detected_genes', 'cell_complexity', 'n_genes', 'doublet_score', 'predicted_doublet', 'passing_mt', 'passing_nUMIs', 'passing_ngenes'\n",
-       "    var: 'feature_types', 'gene_id', 'mt', 'n_cells'\n",
-       "    uns: 'scrublet', 'layers_counts'\n",
-       "    obsm: 'ADT_X_pca', 'ADT_X_umap', 'ADT_isotype_controls', 'GEX_X_pca', 'GEX_X_umap'\n",
-       "    layers: 'counts'"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "ov.utils.store_layers(adata,layers='counts')\n",
-    "adata"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 10,
@@ -431,7 +397,7 @@
    ],
    "source": [
     "ov.pp.scale(adata)\n",
-    "ov.pp.pca(adata,layer='scaled',n_pcs=50)\n",
+    "ov.pp.pca(adata,layer='scaled',n_pcs=50,mask_var='highly_variable_features')\n",
     "\n",
     "adata.obsm[\"X_mde_pca\"] = ov.utils.mde(adata.obsm[\"scaled|original|X_pca\"])"
    ]