Merge branch 'main' into adata_0109

laminlabs · Aug 30, 2024 · 6355a26 · 6355a26
2 parents 0b00885 + 2bee7b5
commit 6355a26
Show file tree

Hide file tree

Showing 7 changed files with 117 additions and 52 deletions.
diff --git a/docs/curate-df.ipynb b/docs/curate-df.ipynb
@@ -86,7 +86,7 @@
    "id": "c7d74af9",
    "metadata": {},
    "source": [
-    "Define validation criteria and create a {class}`~lamindb.Curate` object."
+    "Define validation criteria and create a {class}`~lamindb.Curator` object."
    ]
   },
   {
@@ -109,7 +109,7 @@
     "}\n",
     "\n",
     "# pass validation criteria\n",
-    "curate = ln.Curate.from_df(df, categoricals=categoricals)"
+    "curate = ln.Curator.from_df(df, categoricals=categoricals)"
    ]
   },
   {
@@ -340,7 +340,7 @@
    },
    "outputs": [],
    "source": [
-    "curate = ln.Curate.from_anndata(\n",
+    "curate = ln.Curator.from_anndata(\n",
     "    adata, \n",
     "    var_index=bt.Gene.ensembl_gene_id,  # validate var.index against Gene.ensembl_gene_id\n",
     "    categoricals=categoricals, \n",
@@ -362,6 +362,24 @@
     "curate.validate()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "71a917d1",
+   "metadata": {},
+   "source": [
+    "Save the validated genes following the instruction:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e31dabcc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "curate.add_validated_from_var_index()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "614545ea",
@@ -421,7 +439,7 @@
    },
    "outputs": [],
    "source": [
-    "curate = ln.Curate.from_anndata(\n",
+    "curate = ln.Curator.from_anndata(\n",
     "    adata_validated, \n",
     "    var_index=bt.Gene.ensembl_gene_id,  # validate var.index against Gene.ensembl_gene_id\n",
     "    categoricals=categoricals, \n",

diff --git a/docs/introduction.ipynb b/docs/introduction.ipynb
@@ -626,7 +626,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Let's use the high-level {class}`~lamindb.Curate` class to curate a `DataFrame`."
+    "Let's use the high-level {class}`~lamindb.Curator` class to curate a `DataFrame`."
    ]
   },
   {
@@ -639,8 +639,8 @@
    },
    "outputs": [],
    "source": [
-    "# construct a Curate object to validate & annotate a DataFrame\n",
-    "curate = ln.Curate.from_df(\n",
+    "# construct a Curator object to validate & annotate a DataFrame\n",
+    "curate = ln.Curator.from_df(\n",
     "    df_fixed_typo,\n",
     "    # define validation criteria\n",
     "    columns=ln.Feature.name,  # map column names\n",
@@ -712,7 +712,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Had we used `ln.Curate` from the beginning, we would have caught the typo."
+    "Had we used `ln.Cuartor` from the beginning, we would have caught the typo."
    ]
   },
   {
@@ -725,8 +725,8 @@
    },
    "outputs": [],
    "source": [
-    "# construct a Curate object to validate & annotate a DataFrame\n",
-    "curate = ln.Curate.from_df(\n",
+    "# construct a Curator object to validate & annotate a DataFrame\n",
+    "curate = ln.Curator.from_df(\n",
     "    df_with_typo,\n",
     "    # define validation criteria\n",
     "    columns=ln.Feature.name,  # map column names\n",
@@ -810,7 +810,7 @@
     "adata = ad.AnnData(df_fixed_typo[[\"CD8A\", \"CD4\", \"CD14\"]], obs=df_fixed_typo[[\"perturbation\"]])\n",
     "\n",
     "# create an annotation flow for an AnnData object\n",
-    "curate = ln.Curate.from_anndata(\n",
+    "curate = ln.Curator.from_anndata(\n",
     "    adata,\n",
     "    # define validation criteria\n",
     "    var_index=bt.Gene.symbol, # map .var.index onto Gene registry\n",
@@ -914,12 +914,13 @@
     "adata = ad.AnnData(df[[\"CD8A\", \"CD4\", \"CD38\"]], obs=df[[\"perturbation\"]])\n",
     "\n",
     "# validate, curate and save a new artifact\n",
-    "curate = ln.Curate.from_anndata(\n",
+    "curate = ln.Curator.from_anndata(\n",
     "    adata,\n",
     "    var_index=bt.Gene.symbol,\n",
     "    categoricals={adata.obs.perturbation.name: ln.ULabel.name},\n",
     "    organism=\"human\"\n",
     ")\n",
+    "curate.add_validated_from_var_index()\n",
     "curate.validate()\n",
     "artifact2 = curate.save_artifact(description=\"my RNA-seq dataset 2\")"
    ]