✨ Manually save collection (#78)

Signed-off-by: zethson <[email protected]>

.github/workflows/build.yml

@@ -102,7 +102,7 @@ jobs:
           aws-region: us-east-1
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
+          python-version: "3.11"
 
       - name: install Python deps
         run: pip install laminci

cellxgene_lamin/curate.py

@@ -2,11 +2,13 @@
 
 import re
 from importlib import resources
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Iterable
 
 import bionty as bt
+import lamindb_setup as ln_setup
 import pandas as pd
-from lamin_utils import logger
+from lamin_utils import colors, logger
+from lamindb import Collection
 from lamindb._curate import AnnDataCurator, validate_categories_in_df
 
 from .fields import CellxGeneFields
@@ -16,6 +18,7 @@
     from pathlib import Path
 
     import anndata as ad
+    from lamindb import Artifact
     from lnschema_core.types import FieldAttr
 
 
@@ -173,7 +176,6 @@ def to_cellxgene_anndata(
         Args:
             is_primary_data: Whether the measured data is primary data or not.
             title: Title of the AnnData object. Commonly the name of the publication.
-                   This parameter is required if the AnnData object is not a part of a Collection.
 
         Returns:
             An AnnData object which adheres to the cellxgene-schema.

docs/cellxgene-curate.ipynb

@@ -374,16 +374,14 @@
    "outputs": [],
    "source": [
     "# register a new collection\n",
-    "collection = curate.save_collection(\n",
+    "title = \"Cross-tissue immune cell analysis reveals tissue-specific features in humans (for test demo only)\"\n",
+    "collection = ln.Collection(\n",
     "    [artifact],  # registered artifact above, can also pass a list of artifacts\n",
-    "    name=(  # title of the publication\n",
-    "        \"Cross-tissue immune cell analysis reveals tissue-specific features in humans\"\n",
-    "        \" (for test demo only)\"\n",
-    "    ),\n",
+    "    name=title,  # title of the publication\n",
     "    description=\"10.1126/science.abl5197\",  # DOI of the publication\n",
     "    reference=\"E-MTAB-11536\",  # accession number (e.g. GSE#, E-MTAB#, etc.)\n",
     "    reference_type=\"ArrayExpress\",  # source type (e.g. GEO, ArrayExpress, SRA, etc.)\n",
-    ")"
+    ").save()"
    ]
   },
   {
@@ -405,7 +403,7 @@
    },
    "outputs": [],
    "source": [
-    "adata_cxg = curate.to_cellxgene_anndata(is_primary_data=True)\n",
+    "adata_cxg = curate.to_cellxgene_anndata(is_primary_data=True, title=title)\n",
     "adata_cxg"
    ]
   },