using .connect

Author: jkobject

README.md

@@ -211,7 +211,7 @@ from scdataloader.preprocess import LaminPreprocessor, additional_postprocess, a
 # preprocess datasets
 DESCRIPTION='preprocessed by scDataLoader'
 
-cx_dataset = ln.Collection.using(instance="laminlabs/cellxgene").filter(name="cellxgene-census", version='2023-12-15').one()
+cx_dataset = ln.Collection.connect(instance="laminlabs/cellxgene").filter(name="cellxgene-census", version='2023-12-15').one()
 cx_dataset, len(cx_dataset.artifacts.all())
 
 # (OPTIONAL) if you want to do you preprocessing on a slurm cluster without internet connections,

docs/index.md

@@ -201,7 +201,7 @@ from scdataloader.preprocess import LaminPreprocessor, additional_postprocess, a
 # preprocess datasets
 DESCRIPTION='preprocessed by scDataLoader'
 
-cx_dataset = ln.Collection.using(instance="laminlabs/cellxgene").filter(name="cellxgene-census", version='2023-12-15').one()
+cx_dataset = ln.Collection.connect(instance="laminlabs/cellxgene").filter(name="cellxgene-census", version='2023-12-15').one()
 cx_dataset, len(cx_dataset.artifacts.all())
 
 # (OPTIONAL) if you want to do you preprocessing on a slurm cluster without internet connections,

docs/notebooks/1_download_and_preprocess.ipynb

@@ -99,7 +99,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -116,12 +116,12 @@
     }
    ],
    "source": [
-    "list(ln.Collection.using(instance=\"laminlabs/cellxgene\").filter(name=\"cellxgene-census\").all())"
+    "list(ln.Collection.connect(instance=\"laminlabs/cellxgene\").filter(name=\"cellxgene-census\").all())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -144,7 +144,7 @@
     }
    ],
    "source": [
-    "cx_dataset = ln.Collection.using(instance=\"laminlabs/cellxgene\").filter(name=\"cellxgene-census\", version='2023-12-15').one()\n",
+    "cx_dataset = ln.Collection.connect(instance=\"laminlabs/cellxgene\").filter(name=\"cellxgene-census\", version='2023-12-15').one()\n",
     "cx_dataset, len(cx_dataset.artifacts.all())"
    ]
   },

docs/notebooks/2_create_dataloader.ipynb

@@ -112,7 +112,7 @@
     "\n",
     "example:\n",
     "```python\n",
-    "dataset = ln.Collection.using(\"laminlabs/cellxgene\").one()\n",
+    "dataset = ln.Collection.connect(\"laminlabs/cellxgene\").one()\n",
     "```"
    ]
   },

notebooks/update_lamin_or_cellxgene.ipynb

@@ -1677,7 +1677,7 @@
     "import lamindb as ln\n",
     "\n",
     "files = (\n",
-    "    ln.Collection.using(instance=\"laminlabs/cellxgene\")\n",
+    "    ln.Collection.connect(instance=\"laminlabs/cellxgene\")\n",
     "    .filter(name=\"cellxgene-census\")\n",
     "    .first()\n",
     "    .artifacts.all()\n",
@@ -1720,7 +1720,7 @@
    "outputs": [],
    "source": [
     "cx_dataset = (\n",
-    "    ln.Collection.using(instance=\"laminlabs/cellxgene\")\n",
+    "    ln.Collection.connect(instance=\"laminlabs/cellxgene\")\n",
     "    .filter(name=\"cellxgene-census\", version=\"2024-11-10\")\n",
     "    .one()\n",
     ")"
@@ -1753,7 +1753,7 @@
    ],
    "source": [
     "cx_dataset_prev = (\n",
-    "    ln.Collection.using(instance=\"laminlabs/cellxgene\")\n",
+    "    ln.Collection.connect(instance=\"laminlabs/cellxgene\")\n",
     "    .filter(name=\"cellxgene-census\", version=\"2023-12-15\")\n",
     "    .one()\n",
     ")\n",

scdataloader/__main__.py

@@ -228,7 +228,7 @@ def main():
     #    return
     if args.instance is not None:
         collection = (
-            ln.Collection.using(instance=args.instance)
+            ln.Collection.connect(instance=args.instance)
             .filter(key=args.name, version=args.version)
             .first()
         )

scdataloader/utils.py

@@ -454,19 +454,19 @@ def _adding_scbasecamp_genes(
 ):
     if len(species) == 0:
         species = set(
-            bt.Organism.using("laminlabs/arc-virtual-cell-atlas")
+            bt.Organism.connect("laminlabs/arc-virtual-cell-atlas")
             .to_dataframe(limit=None)
             .ontology_id
         ) - set(["NCBITaxon:10090", "NCBITaxon:9606"])
     species = list(species)
     for i in set(
-        bt.Organism.using("laminlabs/arc-virtual-cell-atlas")
+        bt.Organism.connect("laminlabs/arc-virtual-cell-atlas")
         .to_dataframe(limit=None)
         .ontology_id
     ) - set(bt.Organism.filter().to_dataframe(limit=None).ontology_id):
         print(i)
         rec = (
-            bt.Organism.using("laminlabs/arc-virtual-cell-atlas")
+            bt.Organism.connect("laminlabs/arc-virtual-cell-atlas")
             .filter(ontology_id=i)
             .first()
         )
@@ -487,7 +487,7 @@ def _adding_scbasecamp_genes(
     for i in species:
         print(i)
         df = (
-            bt.Gene.using("laminlabs/arc-virtual-cell-atlas")
+            bt.Gene.connect("laminlabs/arc-virtual-cell-atlas")
             .filter(organism__ontology_id=i)
             .all()
             .to_dataframe(limit=None)
@@ -633,11 +633,7 @@ def populate_my_ontology(
         if len(tissues) == 0:
             bt.Tissue.import_source()
         else:
-            names = (
-                bt.Tissue.public().to_dataframe().index
-                if not tissues
-                else tissues
-            )
+            names = bt.Tissue.public().to_dataframe().index if not tissues else tissues
             records = bt.Tissue.from_values(names, field="ontology_id")
             ln.save(records)
         elem = bt.Tissue(name="unknown", ontology_id="unknown").save()
@@ -663,9 +659,7 @@ def populate_my_ontology(
             bt.Disease.import_source()
         else:
             names = (
-                bt.Disease.public().to_dataframe().index
-                if not diseases
-                else diseases
+                bt.Disease.public().to_dataframe().index if not diseases else diseases
             )
             records = bt.Disease.from_values(names, field="ontology_id")
             ln.save(records)
@@ -675,9 +669,7 @@ def populate_my_ontology(
     for organism in genes_from:
         # convert onto to name
         organism = bt.Organism.filter(ontology_id=organism).one().name
-        names = bt.Gene.public(organism=organism).to_dataframe()[
-            "ensembl_gene_id"
-        ]
+        names = bt.Gene.public(organism=organism).to_dataframe()["ensembl_gene_id"]
 
         # Process names in blocks of 10,000 elements
         block_size = 10000