lamindb 1.0rc1__tar.gz → 1.0.1__tar.gz

{lamindb-1.0rc1 → lamindb-1.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.0rc1
+Version: 1.0.1
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.10,<3.13
@@ -10,7 +10,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: lamin_utils==0.13.10
 Requires-Dist: lamin_cli==1.0.2
-Requires-Dist: lamindb_setup[aws]==1.0.1
+Requires-Dist: lamindb_setup[aws]==1.0.3
 Requires-Dist: pyarrow
 Requires-Dist: typing_extensions!=4.6.0
 Requires-Dist: python-dateutil

{lamindb-1.0rc1 → lamindb-1.0.1}/lamindb/__init__.py

@@ -53,7 +53,7 @@ Modules and settings.
 """
 
 # denote a release candidate for 0.1.0 with 0.1rc1, 0.1a1, 0.1b1, etc.
-__version__ = "1.0rc1"
+__version__ = "1.0.1"
 
 from lamindb_setup._check_setup import InstanceNotSetupError as _InstanceNotSetupError
 from lamindb_setup._check_setup import _check_instance_setup

{lamindb-1.0rc1 → lamindb-1.0.1}/lamindb/migrations/0073_merge_ourprojects.py

@@ -2,6 +2,7 @@
 
 import django.core.validators
 import django.db.models.deletion
+import lamindb_setup
 from django.db import migrations, models
 
 import lamindb.base.fields
@@ -943,3 +944,9 @@ class Migration(migrations.Migration):
             migrate_data,
         ),
     ]
+
+
+if "ourprojects" in lamindb_setup.settings.instance.modules:
+    Migration.dependencies += [
+        ("ourprojects", "0003_alter_person_space_alter_project_space_and_more"),
+    ]

{lamindb-1.0rc1 → lamindb-1.0.1}/pyproject.toml

@@ -17,7 +17,7 @@ dependencies = [
     # Lamin PINNED packages
     "lamin_utils==0.13.10",
     "lamin_cli==1.0.2",
-    "lamindb_setup[aws]==1.0.1",
+    "lamindb_setup[aws]==1.0.3",
     # others
     "pyarrow",
     "typing_extensions!=4.6.0",

{lamindb-1.0rc1 → lamindb-1.0.1}/sub/lamindb-setup/lamindb_setup/__init__.py

@@ -33,7 +33,7 @@ Modules & settings:
 
 """
 
-__version__ = "1.0.1"  # denote a release candidate for 0.1.0 with 0.1rc1
+__version__ = "1.0.3"  # denote a release candidate for 0.1.0 with 0.1rc1
 
 import os
 

{lamindb-1.0rc1 → lamindb-1.0.1}/sub/lamindb-setup/lamindb_setup/_connect_instance.py

@@ -394,6 +394,24 @@ def migrate_lnschema_core(
                 if response != "y":
                     print("Aborted.")
                     quit()
+                if isettings.is_on_hub:
+                    from lamindb_setup.core._hub_client import call_with_fallback_auth
+                    from lamindb_setup.core._hub_crud import (
+                        select_collaborator,
+                    )
+
+                    # double check that user is an admin, otherwise will fail below
+                    # due to insufficient SQL permissions with cryptic error
+                    collaborator = call_with_fallback_auth(
+                        select_collaborator,
+                        instance_id=settings.instance._id,
+                        account_id=settings.user._uuid,
+                    )
+                    if collaborator is None or collaborator["role"] != "admin":
+                        raise SystemExit(
+                            "❌ Only admins can deploy migrations, please ensure that you're an"
+                            f" admin: https://lamin.ai/{settings.instance.slug}/settings"
+                        )
                 for table in tables_to_rename:
                     if db_type == "sqlite":
                         cur.execute(

{lamindb-1.0rc1 → lamindb-1.0.1}/sub/lamindb-setup/tests/hub-local/test_all.py

@@ -325,7 +325,10 @@ def test_connect_instance_hub_corrupted_or_expired_credentials(
     create_myinstance, create_testadmin1_session
 ):
     # assume token & password are corrupted or expired
-    ln_setup.settings.user.access_token = "corrupted_or_expired_token"
+    # make realisticly looking token that passes
+    # supafunc is_valid_jwt but is actually not a real token
+    invalid_token = "header1.payload1.signature1"
+    ln_setup.settings.user.access_token = invalid_token
     correct_password = ln_setup.settings.user.password
     ln_setup.settings.user.password = "corrupted_password"
     with pytest.raises(FunctionsHttpError):
@@ -336,7 +339,7 @@ def test_connect_instance_hub_corrupted_or_expired_credentials(
     # now, let's assume only the token is expired or corrupted
     # re-creating the auth client triggers a re-generated token because it
     # excepts the error assuming the token is expired
-    ln_setup.settings.user.access_token = "corrupted_or_expired_token"
+    ln_setup.settings.user.access_token = invalid_token
     ln_setup.settings.user.password = correct_password
     connect_instance_hub(
         owner="testadmin1",
@@ -344,7 +347,7 @@ def test_connect_instance_hub_corrupted_or_expired_credentials(
     )
     # check access_token renewal
     access_token = ln_setup.settings.user.access_token
-    assert access_token != "corrupted_or_expired_token"
+    assert access_token != invalid_token
     # check that the access_token was written to the settings
     ln_setup.settings._user_settings = None
     assert ln_setup.settings.user.access_token == access_token

{lamindb-1.0rc1 → lamindb-1.0.1}/sub/wetlab/.github/workflows/build.yml

@@ -15,7 +15,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.12"]
-    timeout-minutes: 8
+    timeout-minutes: 15
 
     steps:
       - uses: actions/checkout@v4

{lamindb-1.0rc1 → lamindb-1.0.1}/sub/wetlab/docs/guide/pert-curator.ipynb

@@ -11,7 +11,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Here we use `PertCurator` to curate perturbation related columns in an `AnnData` object of [McFarland et al. 2020](https://www.nature.com/articles/s41467-020-17440-w)."
+    "Here we use `PertCurator` to curate perturbation related columns in a subsetted `AnnData` object of [McFarland et al. 2020](https://www.nature.com/articles/s41467-020-17440-w)."
    ]
   },
   {
@@ -21,7 +21,7 @@
    "outputs": [],
    "source": [
     "# pip install 'lamindb[jupyter,wetlab]' cellxgene-lamin\n",
-    "!lamin init --storage ./test-pert-curator --modules bionty,wetlab,ourprojects"
+    "!lamin init --storage ./test-pert-curator --modules bionty,wetlab"
    ]
   },
   {
@@ -37,11 +37,9 @@
     "import lamindb as ln\n",
     "import wetlab as wl\n",
     "import bionty as bt\n",
-    "import ourprojects as ops\n",
     "import pandas as pd\n",
-    "import scanpy as sc\n",
     "\n",
-    "ln.track(\"HIRTYxL3aZc70000\")"
+    "ln.track()"
    ]
   },
   {
@@ -54,16 +52,6 @@
     "adata.obs.head()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Calculate an embedding because CELLxGENE requires one\n",
-    "sc.tl.pca(adata)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -96,7 +84,9 @@
     "# fix the perturbation type as suggested by the curator\n",
     "adata.obs[\"pert_type\"] = adata.obs[\"pert_type\"].cat.rename_categories(\n",
     "    {\"CRISPR\": \"genetic\", \"drug\": \"compound\"}\n",
-    ")"
+    ")\n",
+    "\n",
+    "adata.obs[\"tissue_type\"] = \"cell culture\""
    ]
   },
   {
@@ -149,16 +139,28 @@
     "    \"sgor2j2\": \"OR2J2\",  # cutting control\n",
     "}\n",
     "\n",
+    "ln.settings.creation.search_names = False\n",
     "for sg_name, gene_symbol in pert_target_map.items():\n",
-    "    pert = wl.GeneticPerturbation(\n",
-    "        system=\"CRISPR-Cas9\",\n",
-    "        name=sg_name,\n",
-    "        description=\"cutting control\" if sg_name == \"sgor2j2\" else None,\n",
-    "    ).save()\n",
-    "    target = wl.PerturbationTarget(name=gene_symbol).save()\n",
+    "    pert = wl.GeneticPerturbation.filter(\n",
+    "        system=\"CRISPR-Cas9\", name=sg_name\n",
+    "    ).one_or_none()\n",
+    "    if pert is None:\n",
+    "        pert = wl.GeneticPerturbation(\n",
+    "            system=\"CRISPR-Cas9\",\n",
+    "            name=sg_name,\n",
+    "            description=\"cutting control\" if sg_name == \"sgor2j2\" else None,\n",
+    "        ).save()\n",
+    "    target = wl.PerturbationTarget.filter(name=gene_symbol).one_or_none()\n",
+    "    if target is None:\n",
+    "        target = wl.PerturbationTarget(name=gene_symbol).save()\n",
     "    pert.targets.add(target)\n",
-    "    gene = bt.Gene.from_source(symbol=gene_symbol, organism=\"human\").save()\n",
-    "    target.genes.set([gene] if isinstance(gene, bt.Gene) else gene)\n",
+    "    genes = bt.Gene.filter(symbol=gene_symbol).all()\n",
+    "    if len(genes) == 0:\n",
+    "        genes = bt.Gene.from_values(\n",
+    "            [gene_symbol], field=bt.Gene.symbol, organism=\"human\"\n",
+    "        ).save()\n",
+    "    target.genes.add(*genes)\n",
+    "ln.settings.creation.search_names = True\n",
     "\n",
     "adata.obs[\"pert_target\"] = adata.obs[\"pert_genetic\"].map(pert_target_map)\n",
     "\n",
@@ -207,15 +209,14 @@
    "outputs": [],
    "source": [
     "# manually fix sex and set assay\n",
-    "adata.obs[\"sex\"] = adata.obs[\"sex\"].cat.rename_categories({\"Unknown\": \"unknown\"})\n",
+    "adata.obs[\"sex\"] = adata.obs[\"sex\"].astype(str).str.lower()\n",
     "adata.obs[\"assay\"] = \"10x 3' v3\"\n",
     "\n",
     "# subset the adata to only include the validated genes\n",
     "adata = adata[:, ~adata.var_names.isin(curator.non_validated[\"var_index\"])].copy()\n",
     "\n",
     "# standardize disease and sex as suggested\n",
-    "curator.standardize(\"disease\")\n",
-    "curator.standardize(\"sex\")"
+    "curator.standardize(\"disease\")"
    ]
   },
   {
@@ -272,7 +273,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "reference = ops.Reference(\n",
+    "reference = ln.Reference(\n",
     "    name=\"Multiplexed single-cell transcriptional response profiling to define cancer vulnerabilities and therapeutic mechanism of action\",\n",
     "    abbr=\"McFarland 2020\",\n",
     "    url=\"https://www.nature.com/articles/s41467-020-17440-w\",\n",
@@ -311,7 +312,7 @@
    },
    "outputs": [],
    "source": [
-    "artifact = curator.save_artifact(description=\"McFarland AnnData\")"
+    "artifact = curator.save_artifact(key=\"mini_mcFarland20.h5ad\")"
    ]
   },
   {
@@ -336,7 +337,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "py312",
+   "display_name": "py310",
    "language": "python",
    "name": "python3"
   },
@@ -350,7 +351,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.8"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,

{lamindb-1.0rc1 → lamindb-1.0.1}/sub/wetlab/noxfile.py

@@ -35,6 +35,6 @@ def test(session: nox.Session) -> None:
 
 @nox.session
 def docs(session: nox.Session) -> None:
-    run(session, "lamin init --storage ./docsbuild --modules bionty,wetlab,ourprojects")
+    run(session, "lamin init --storage ./docsbuild --modules bionty,wetlab")
     build_docs(session, strict=True)
     upload_docs_artifact(aws=True)

{lamindb-1.0rc1 → lamindb-1.0.1}/sub/wetlab/wetlab/__init__.py

@@ -55,7 +55,7 @@ Types:
 
 """
 
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 
 from lamindb_setup import _check_instance_setup
 

{lamindb-1.0rc1 → lamindb-1.0.1}/sub/wetlab/wetlab/_pert_curator.py

@@ -24,6 +24,7 @@ except ImportError:
 from .models import (
     Biologic,
     Compound,
+    Donor,
     EnvironmentalPerturbation,
     GeneticPerturbation,
     PerturbationTarget,
@@ -220,37 +221,6 @@ class PertCurator(CellxGeneCurate):
             schema_version=cxg_schema_version,
         )
 
-        # sort columns
-        first_columns = [
-            "pert_target",
-            "pert_genetic",
-            "pert_compound",
-            "pert_biologic",
-            "pert_physical",
-            "pert_dose",
-            "pert_time",
-            "organism",
-            "cell_line",
-            "cell_type",
-            "disease",
-            "tissue_type",
-            "tissue",
-            "assay",
-            "suspension_type",
-            "donor_id",
-            "sex",
-            "self_reported_ethnicity",
-            "development_stage",
-            "pert_name",
-            "pert_type",
-        ]
-        sorted_columns = [
-            col for col in first_columns if col in self._adata.obs.columns
-        ] + [col for col in self._adata.obs.columns if col not in first_columns]
-        # must assign to self._df to ensure .standardize works correctly
-        self._df = self._adata.obs[sorted_columns]
-        self._adata.obs = self._df
-
     def _setup_configuration(self, adata: ad.AnnData):
         """Set up default configuration values."""
         self.PT_DEFAULT_VALUES = CellxGeneFields.OBS_FIELD_DEFAULTS | {
@@ -270,6 +240,8 @@ class PertCurator(CellxGeneCurate):
             }.items()
             if k in adata.obs.columns
         }
+        # if "donor_id" in self.PT_CATEGORICALS:
+        #     self.PT_CATEGORICALS["donor_id"] = Donor.name
 
     def _setup_sources(self, adata: ad.AnnData, using_key: str):
         """Set up data sources."""
@@ -352,8 +324,44 @@ class PertCurator(CellxGeneCurate):
             validated &= self._validate_time_column()
 
         self._validated = validated
+
+        # sort columns
+        first_columns = [
+            "pert_target",
+            "pert_genetic",
+            "pert_compound",
+            "pert_biologic",
+            "pert_physical",
+            "pert_dose",
+            "pert_time",
+            "organism",
+            "cell_line",
+            "cell_type",
+            "disease",
+            "tissue_type",
+            "tissue",
+            "assay",
+            "suspension_type",
+            "donor_id",
+            "sex",
+            "self_reported_ethnicity",
+            "development_stage",
+            "pert_name",
+            "pert_type",
+        ]
+        sorted_columns = [
+            col for col in first_columns if col in self._adata.obs.columns
+        ] + [col for col in self._adata.obs.columns if col not in first_columns]
+        # must assign to self._df to ensure .standardize works correctly
+        self._df = self._adata.obs[sorted_columns]
+        self._adata.obs = self._df
         return validated
 
+    def standardize(self, key: str) -> pd.DataFrame:
+        """Standardize the AnnData object."""
+        super().standardize(key)
+        self._adata.obs = self._df
+
     def _validate_dose_column(self) -> bool:
         """Validate the dose column."""
         if not ln.Feature.filter(name="pert_dose").exists():