lamindb 1.0.4__py3-none-any.whl → 1.1.0__py3-none-any.whl

{lamindb-1.0.4.dist-info → lamindb-1.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.0.4
+Version: 1.1.0
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.10,<3.13
@@ -9,9 +9,11 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: lamin_utils==0.13.10
-Requires-Dist: lamin_cli==1.0.4
-Requires-Dist: lamindb_setup[aws]==1.0.3
+Requires-Dist: lamin_cli==1.1.0
+Requires-Dist: lamindb_setup[aws]==1.1.0
+Requires-Dist: pyyaml
 Requires-Dist: pyarrow
+Requires-Dist: pandera
 Requires-Dist: typing_extensions!=4.6.0
 Requires-Dist: python-dateutil
 Requires-Dist: scipy<1.15.0
@@ -20,9 +22,10 @@ Requires-Dist: anndata>=0.8.0,<=0.11.3
 Requires-Dist: fsspec
 Requires-Dist: graphviz
 Requires-Dist: psycopg2-binary
-Requires-Dist: bionty==1.0.0 ; extra == "bionty"
+Requires-Dist: bionty==1.1.0 ; extra == "bionty"
 Requires-Dist: cellregistry ; extra == "cellregistry"
-Requires-Dist: clinicore==1.0.0 ; extra == "clinicore"
+Requires-Dist: clinicore==1.1.0 ; extra == "clinicore"
+Requires-Dist: tomlkit ; extra == "dev"
 Requires-Dist: line_profiler ; extra == "dev"
 Requires-Dist: pre-commit ; extra == "dev"
 Requires-Dist: nox ; extra == "dev"
@@ -34,14 +37,14 @@ Requires-Dist: mudata ; extra == "dev"
 Requires-Dist: nbproject_test>=0.6.0 ; extra == "dev"
 Requires-Dist: faker-biology ; extra == "dev"
 Requires-Dist: django-schema-graph ; extra == "erdiagram"
-Requires-Dist: readfcs>=1.1.9 ; extra == "fcs"
+Requires-Dist: readfcs>=2.0.1 ; extra == "fcs"
 Requires-Dist: lamindb_setup[gcp] ; extra == "gcp"
 Requires-Dist: nbproject==0.10.5 ; extra == "jupyter"
 Requires-Dist: jupytext ; extra == "jupyter"
 Requires-Dist: nbconvert>=7.2.1 ; extra == "jupyter"
 Requires-Dist: mistune!=3.1.0 ; extra == "jupyter"
 Requires-Dist: omop ; extra == "omop"
-Requires-Dist: wetlab==1.0.1 ; extra == "wetlab"
+Requires-Dist: wetlab==1.1.0 ; extra == "wetlab"
 Requires-Dist: zarr>=2.16.0,<3.0.0a0 ; extra == "zarr"
 Project-URL: Home, https://github.com/laminlabs/lamindb
 Provides-Extra: bionty

lamindb-1.1.0.dist-info/RECORD

@@ -0,0 +1,95 @@
+lamindb/__init__.py,sha256=tfnXH1mSnAnNlt_u6GoNwf66Dd-AMhCGelvFgMoQm50,2391
+lamindb/_artifact.py,sha256=n1bLUBzmHOSwDMmRdI_81Nnm59_YVL0UupRFRdwvR7E,50856
+lamindb/_can_curate.py,sha256=2vIvyJVqdFJs9q2a7j6kU8_TgY60PIobHX-ZHRvGTC0,20965
+lamindb/_collection.py,sha256=c9I0XU_OtJkWmwPRBim_FuOiAk-J7-UOU91M5Nx62IM,15885
+lamindb/_feature.py,sha256=A-3pjZavUTqr1VUsfF-7zSkOUVbWWsS6yyE_0-WHesI,11532
+lamindb/_finish.py,sha256=_9yPSDE1xtuHtW08IO72go2n0Hw7GFkpio3SpqklHHM,19115
+lamindb/_from_values.py,sha256=2Le2xrVMsZFCROWSh7hrhwq9HkRof8ddJ-fCu7pbeig,13596
+lamindb/_is_versioned.py,sha256=6_LBAKD_fng6BReqitJUIxTUaQok3AeIpNnE_D8kHnQ,1293
+lamindb/_parents.py,sha256=SMl9YbeLyg4KiNL3Oz_9MOK_lpv7OlUpo2AcC9xAPAc,17254
+lamindb/_query_manager.py,sha256=znUAYeNuUk13YVXq51CllpGr33F15_PW_dQYcok0gO8,3636
+lamindb/_query_set.py,sha256=9UdArhet0UweMlU1w3vqspp2ovJQOz8blBQgMmfWrAE,25414
+lamindb/_record.py,sha256=BiREwu7wbtbIpcNWzLOLRElmMXVk-QJjm4UJXRgC8fk,38761
+lamindb/_run.py,sha256=Ef8PGag2AnzpOQoOrh-L6DzMygxBcwwJvX3JGDEqv24,2062
+lamindb/_save.py,sha256=t7cWmksCSC-cwx-YdmPBvSiaBgO80d_H3NlR6oNnXcM,12783
+lamindb/_schema.py,sha256=py0bUgRjNeRxAGRp8-0zySTKbH6lPpkzrJG5XYflbHI,12506
+lamindb/_storage.py,sha256=8HA_0aIc_utOWV20wdH6-vOOhz6dgE5tK6wJJDgt64Q,431
+lamindb/_tracked.py,sha256=D3996sfch0tKXEk_1aWNG4LHCwWMBahHQeoasBLd2fg,3626
+lamindb/_transform.py,sha256=KBXjXRiL7uvGqlS9EvjCLP9td3kGgilWpdOzZ59JeTE,6394
+lamindb/_ulabel.py,sha256=TTDBRB3GVJa6x78HI9gbEYWqIhabObIFH3Mihy4x4j0,1786
+lamindb/_utils.py,sha256=LGdiW4k3GClLz65vKAVRkL6Tw-Gkx9DWAdez1jyA5bE,428
+lamindb/_view.py,sha256=c4eN5hcBlg3TVnljKefbyWAq0eBncjMp2xQcb5OaGWg,4982
+lamindb/errors.py,sha256=hT79cjnDucvtBP41uJqWrSMZjMdved5Nm1GnZwuq38w,1738
+lamindb/models.py,sha256=nkBdj2QmM-XRaQV9izXU6GM3G-AOYUMCGSR_2J3EdMc,159252
+lamindb/base/__init__.py,sha256=J0UpYObi9hJBFyBpAXp4wB3DaJx48R2SaUeB4wjiFvc,267
+lamindb/base/fields.py,sha256=RdwYHQmB7B-jopD_K2QNL5vjhOelu7DWGgqQItXr3pg,8024
+lamindb/base/ids.py,sha256=WzHWiHZtlRUKqxz_p-76ks_JSW669ztvriE7Z3A0yHg,1736
+lamindb/base/types.py,sha256=JfZk0xmhLsWusU0s4SNjhRnQ52mn-cSiG5Gf4SsACBs,1227
+lamindb/base/users.py,sha256=g4ZLQb6eey66FO9eEumbfDpJi_FZZsiLVe2Frz9JuLI,978
+lamindb/base/validation.py,sha256=RESPeSCPzeELaKto8SEb2WB5sWPv76VkOUIPxUsxOGY,2250
+lamindb/core/__init__.py,sha256=4eizMbkZAd0f7UhTyzepsLOyXNQmvtATHwmkfPKAUuc,1663
+lamindb/core/_context.py,sha256=qht_oNj9s4ZWJp74o77PEYAOaw0h5BpbFJuNTTqP9ik,28901
+lamindb/core/_data.py,sha256=PbE1ryKwmJh30EooceZBhYQr82dGxvWIEiaLnp5aLFE,19138
+lamindb/core/_describe.py,sha256=dnpxpvwJpXIWtrnQ1l_9xDjSxw-zb73-oD6z_rumXE4,4888
+lamindb/core/_django.py,sha256=1g1kWWF_3WCTdENGo1k5eoEulfvHJz8a0zI7oJcKBxU,7629
+lamindb/core/_feature_manager.py,sha256=IVo3IXQw2ayx3cXxNhdNGvVHcf7UPbRy0MsBW0S8AG8,48551
+lamindb/core/_label_manager.py,sha256=hDRAJLS-PDP_hHySfuJG-13463jN1sZwE5j4pRGVW_c,11908
+lamindb/core/_mapped_collection.py,sha256=a8Ks18eIg699K5rkaPPYS_efyPS63WfYDGyJyHYq8gU,25523
+lamindb/core/_settings.py,sha256=haLHE1dhog_Sz6gnecTW8E548njWH5nVt8mTFPEs6ZM,5733
+lamindb/core/_sync_git.py,sha256=xu1o6zlBD_pTRpBPVXiHKOI2tmtGaUfXvuuII2AAfM4,5875
+lamindb/core/_track_environment.py,sha256=nVEO98P7ZrUWyixMI3AdoD7vcUszIVciZwgPOsQUsNU,814
+lamindb/core/exceptions.py,sha256=FMEoSvT3FvtLkxQAt2oDXPeaPem8V5x5UBbTsPFYU5w,53
+lamindb/core/fields.py,sha256=zM6G7CiE6mU_5heLWwIhE3d5LqAjPCEwgs0eechFm0c,175
+lamindb/core/loaders.py,sha256=yQA3d07N3t4B53k5JTlihp0fbFXBU4UC415aQFHPEos,4571
+lamindb/core/relations.py,sha256=mZWt2cImMoF3HElyMOG99IP_2NUglOhwktwqey6uR8k,3546
+lamindb/core/types.py,sha256=DS4uXaCswAW9tqz4MZ_sYc1_QZ6il--Z4x8HeHNQgRw,162
+lamindb/core/versioning.py,sha256=tUZthgDwbz7UBx1wx_MsdsXXsltE1E9clapmRkmvKlU,4953
+lamindb/core/datasets/__init__.py,sha256=PPraqD4nMr-DvI1_6aDQde2p9MkgJY-ukV0Qb34xnyg,1722
+lamindb/core/datasets/_core.py,sha256=9-By-vT7KUbdD8jFQK7KaRcvODj0hiwQMeM2d9mgmss,19661
+lamindb/core/datasets/_fake.py,sha256=BZF9R_1iF0HDnvtZNqL2FtsjSMuqDIfuFxnw_LJYIh4,953
+lamindb/core/datasets/_small.py,sha256=uqVY3Qg0Mf7uHGGpIaYhWzo8M7mBtK3DZDOZ-ROVUeM,5002
+lamindb/core/storage/__init__.py,sha256=JOIMu_7unbyhndtH1j0Q-9AvY8knSuc1IJO9sQnyBAQ,498
+lamindb/core/storage/_anndata_accessor.py,sha256=umQFD0r8tolX2z9sWZYt88rb1nv-yIIHHO_IuhTYLzU,25858
+lamindb/core/storage/_anndata_sizes.py,sha256=aXO3OB--tF5MChenSsigW6Q-RuE8YJJOUTVukkLrv9A,1029
+lamindb/core/storage/_backed_access.py,sha256=FGGNmu-2LaMo0UmPe6rxtxkaeGcGSFYgR7dgzri6URY,3589
+lamindb/core/storage/_pyarrow_dataset.py,sha256=0hFjuajLMnasRQCwSXhyire-s3aoHCqZFdYHR5tz_Do,1455
+lamindb/core/storage/_tiledbsoma.py,sha256=t3wwfbisl33kVkDHO3aoGxb7TJybbRQ_h-QuFFU5YZE,10202
+lamindb/core/storage/_valid_suffixes.py,sha256=vUSeQ4s01rdhD_vSd6wKmFBsgMJAKkBMnL_T9Y1znMg,501
+lamindb/core/storage/_zarr.py,sha256=sVd9jVt2q91maeL6GAqMhT6sqtD04vQRfxY3mvIUQlc,3854
+lamindb/core/storage/objects.py,sha256=5vM2T_upuzrXt2b7fQeQ2FUO710-FRbubxTzKzV2ECU,1812
+lamindb/core/storage/paths.py,sha256=IcHSC7tcK1UO75wAMsqWjwxVaW-GE6sN0oRq8IWfmrI,7015
+lamindb/core/subsettings/__init__.py,sha256=j6G9WAJLK-x9FzPSFw-HJUmOseZKGTbK-oLTKI_X_zs,126
+lamindb/core/subsettings/_creation_settings.py,sha256=NGHWKqCFSzVNBxAr2VnmdYguiFdW29XUK7T9wRsVshg,906
+lamindb/curators/__init__.py,sha256=Ei8T7137JggXc-zCwcbvI_e66OQc4O1fkqI4vToiQcs,142919
+lamindb/curators/_cellxgene_schemas/__init__.py,sha256=z-GL_JtFiZhEHUHxQuJBN6SgBCKAMHw9hheDbCje-zk,819
+lamindb/curators/_cellxgene_schemas/schema_versions.yml,sha256=nipsuquq-H9n0KNOxctYV6EVshh55FB5AjujLbxsabI,1942
+lamindb/integrations/__init__.py,sha256=RWGMYYIzr8zvmNPyVB4m-p4gMDhxdRbjES2Ed23OItw,215
+lamindb/integrations/_vitessce.py,sha256=gt3o1sCCcdrKHgM8sJJGFPZggoQEAYfa7ntmA5ThPXo,3992
+lamindb/migrations/0069_squashed.py,sha256=gMWv65ErtjJZyWWo1b4uFHXWa6MSuBcmqz4ElZ6GPf4,62639
+lamindb/migrations/0070_lamindbv1_migrate_data.py,sha256=tyq_xi6U8TXi9C2Raf6v_UTtfyfqQOUIFJzYj4oCgAE,2429
+lamindb/migrations/0071_lamindbv1_migrate_schema.py,sha256=r3PPpq4RK7rhrLWjhVACd5i-tSUTBF0X6Luc5v-g0Lg,25125
+lamindb/migrations/0072_remove_user__branch_code_remove_user_aux_and_more.py,sha256=Nek9Mkuop3LgjAuW3moY-dyPXroCFq8UyvCAAWEquCM,4443
+lamindb/migrations/0073_merge_ourprojects.py,sha256=f0uZ63X0iEylKDlYWD6CAYMge5RcwPSH6yGsoA1KgPQ,35032
+lamindb/migrations/0074_lamindbv1_part4.py,sha256=NqYjEAmm2bNuK42ufLaJZDBjCjAJNv-N9pEXK7iCfyA,11557
+lamindb/migrations/0075_lamindbv1_part5.py,sha256=-3pqXz7e-NbWGTqMhOStcx8zU6HjS-8dlqdyxqexWao,8960
+lamindb/migrations/0076_lamindbv1_part6.py,sha256=G_Wgog-OgquE0-h_CykjiDWUyPdYlCwA8gXjeuBY2OM,21349
+lamindb/migrations/0077_lamindbv1_part6b.py,sha256=v7k8OZX9o5ppSJU_yhHlIXGTobTm30bo1dAIi8tUkEI,8211
+lamindb/migrations/0078_lamindbv1_part6c.py,sha256=RWRXBwyyQ_rFTN5kwstBziV6tqHJcGYI2vsFmuYCCz0,17084
+lamindb/migrations/0079_alter_rundata_value_json_and_more.py,sha256=yQmbs8yWrFLOVQJqAfzLNMZOqTSnXyG-mQgpO7ls1u8,995
+lamindb/migrations/0080_polish_lamindbv1.py,sha256=VfCwJtHlBsMPIyFQ2oh24oWkiRXjDvXRpKe5fBZ63aM,17660
+lamindb/migrations/0081_revert_textfield_collection.py,sha256=uHuJ0W4Ips7BrnQnQBGPMn2eFQz29a1QAdHzN7XlDxo,490
+lamindb/migrations/0082_alter_feature_dtype.py,sha256=qAmZL2g0x43Jk4nbwE-c5z_29Q6vzvrL8DYJE16ZTVo,508
+lamindb/migrations/0083_alter_feature_is_type_alter_flextable_is_type_and_more.py,sha256=ANFJmrd7rtpDvk0OP0EwAhkB-K4GJobdOaEWmjrQqhM,2725
+lamindb/migrations/0084_alter_schemafeature_feature_and_more.py,sha256=ATL1Tyfvtvs0ZUH3JwWfBhcRsOGepCoMEjp9yZmO7z0,1012
+lamindb/migrations/0085_alter_feature_is_type_alter_flextable_is_type_and_more.py,sha256=09KGDirJWH1wkmYBREaF_UrkDGS9qwGxOQuleKydDbI,1941
+lamindb/migrations/0086_various.py,sha256=6-_vkiBEiv0ZVp-JCMVdea-AaKRU61DHyMWprU_VUrg,2824
+lamindb/migrations/0087_rename__schemas_m2m_artifact_feature_sets_and_more.py,sha256=zRlBS89VhmECwGA_y9LghKibxJjtEAmHsEavKdj1ces,1132
+lamindb/migrations/0088_schema_components.py,sha256=9EeoEXX2mf8RtGv_eqOH9zpI2Dg7jhOT9Kxe-9vCiTQ,9230
+lamindb/migrations/0088_squashed.py,sha256=HbbVHaDJX4QQaErOUaSrnayWNrUVf5LWIyirS50YgcE,157984
+lamindb/migrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lamindb/setup/__init__.py,sha256=OwZpZzPDv5lPPGXZP7-zK6UdO4FHvvuBh439yZvIp3A,410
+lamindb/setup/core/__init__.py,sha256=SevlVrc2AZWL3uALbE5sopxBnIZPWZ1IB0NBDudiAL8,167
+lamindb-1.1.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lamindb-1.1.0.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
+lamindb-1.1.0.dist-info/METADATA,sha256=0J09sRvpHzRbXbUhmIjUEIE3n-EwwSQd-woFAzzjvfc,2696
+lamindb-1.1.0.dist-info/RECORD,,

lamindb/curators/_spatial.py

@@ -1,528 +0,0 @@
-import random
-from collections.abc import Iterable, MutableMapping
-from typing import Any
-
-import lamindb_setup as ln_setup
-import pandas as pd
-from lamin_utils import colors, logger
-from spatialdata import SpatialData
-
-from lamindb.base.types import FieldAttr
-from lamindb.core._data import add_labels
-from lamindb.core._feature_manager import parse_staged__schemas_m2m_from_anndata
-from lamindb.core._settings import settings
-from lamindb.core.exceptions import ValidationError
-from lamindb.curators import (
-    AnnDataCurator,
-    CurateLookup,
-    DataFrameCurator,
-    _maybe_curation_keys_not_present,
-    _ref_is_name,
-    check_registry_organism,
-    get_current_filter_kwargs,
-)
-from lamindb.models import Artifact, Collection, Feature, Record, Run, Schema
-
-
-class SpatialDataCurator:
-    """Curation flow for a ``Spatialdata`` object.
-
-    See also :class:`~lamindb.Curator`.
-
-    Note that if genes or other measurements are removed from the SpatialData object,
-    the object should be recreated.
-
-    In the following docstring, an accessor refers to either a ``.table`` key or the ``sample_metadata_key``.
-
-    Args:
-        sdata: The SpatialData object to curate.
-        var_index: A dictionary mapping table keys to the ``.var`` indices.
-        categoricals: A nested dictionary mapping an accessor to dictionaries that map columns to a registry field.
-        using_key: A reference LaminDB instance.
-        organism: The organism name.
-        sources: A dictionary mapping an accessor to dictionaries that map columns to Source records.
-        exclude: A dictionary mapping an accessor to dictionaries of column names to values to exclude from validation.
-            When specific :class:`~bionty.Source` instances are pinned and may lack default values (e.g., "unknown" or "na"),
-            using the exclude parameter ensures they are not validated.
-        verbosity: The verbosity level of the logger.
-        sample_metadata_key: The key in ``.attrs`` that stores the sample level metadata.
-
-    Examples:
-        >>> from lnschema_spatial import SpatialDataCurator
-        >>> import bionty as bt
-        >>> curator = SpatialDataCurator(
-        ...     sdata,
-        ...     var_index={
-        ...         "table_1": bt.Gene.ensembl_gene_id,
-        ...     },
-        ...     categoricals={
-        ...         "table1":
-        ...             {"cell_type_ontology_id": bt.CellType.ontology_id, "donor_id": ln.ULabel.name},
-        ...         "sample":
-        ...             {"experimental_factor": bt.ExperimentalFactor.name},
-        ...     },
-        ...     organism="human",
-        ... )
-    """
-
-    def __init__(
-        self,
-        sdata: SpatialData,
-        var_index: dict[str, FieldAttr],
-        categoricals: dict[str, dict[str, FieldAttr]] | None = None,
-        using_key: str | None = None,
-        verbosity: str = "hint",
-        organism: str | None = None,
-        sources: dict[str, dict[str, Record]] | None = None,
-        exclude: dict[str, dict] | None = None,
-        *,
-        sample_metadata_key: str = "sample",
-    ) -> None:
-        if sources is None:
-            sources = {}
-        self._sources = sources
-        if exclude is None:
-            exclude = {}
-        self._exclude = exclude
-        self._sdata = sdata
-        self._sample_metadata_key = sample_metadata_key
-        self._kwargs = {"organism": organism} if organism else {}
-        self._var_fields = var_index
-        self._verify_accessor_exists(self._var_fields.keys())
-        self._categoricals = categoricals
-        self._table_keys = set(self._var_fields.keys()) | set(
-            self._categoricals.keys() - {self._sample_metadata_key}
-        )
-        self._using_key = using_key
-        self._verbosity = verbosity
-        self._sample_df_curator = None
-        self._sample_metadata = self._sdata.get_attrs(
-            key=self._sample_metadata_key, return_as="df", flatten=True
-        )
-        self._validated = False
-
-        # Check validity of keys in categoricals
-        nonval_keys = []
-        for accessor, accessor_categoricals in self._categoricals.items():
-            if accessor == self._sample_metadata_key:
-                for key in accessor_categoricals.keys():
-                    if key not in self._sample_metadata.columns:
-                        nonval_keys.append(key)
-            else:
-                for key in accessor_categoricals.keys():
-                    if key not in self._sdata[accessor].obs.columns:
-                        nonval_keys.append(key)
-
-        _maybe_curation_keys_not_present(nonval_keys, "categoricals")
-
-        # check validity of keys in sources and exclude
-        for name, dct in (("sources", self._sources), ("exclude", self._exclude)):
-            nonval_keys = []
-            for accessor, accessor_sources in dct.items():
-                columns = (
-                    self._sample_metadata.columns
-                    if accessor == self._sample_metadata_key
-                    else self._sdata[accessor].obs.columns
-                )
-                for key in accessor_sources:
-                    if key not in columns:
-                        nonval_keys.append(key)
-            _maybe_curation_keys_not_present(nonval_keys, name)
-
-        # Set up sample level metadata and table Curator objects
-        if self._sample_metadata_key in self._categoricals.keys():
-            self._sample_df_curator = DataFrameCurator(
-                df=self._sample_metadata,
-                columns=Feature.name,
-                categoricals=self._categoricals.get(self._sample_metadata_key, {}),
-                using_key=using_key,
-                verbosity=verbosity,
-                sources=self._sources.get(self._sample_metadata_key),
-                exclude=self._exclude.get(self._sample_metadata_key),
-                check_valid_keys=False,
-                **self._kwargs,
-            )
-        self._table_adata_curators = {
-            table: AnnDataCurator(
-                data=sdata[table],
-                var_index=var_index.get(table),
-                categoricals=self._categoricals.get(table),
-                using_key=using_key,
-                verbosity=verbosity,
-                sources=self._sources.get(table),
-                exclude=self._exclude.get(table),
-                **self._kwargs,
-            )
-            for table in self._table_keys
-        }
-
-        self._non_validated = None
-
-    @property
-    def var_index(self) -> FieldAttr:
-        """Return the registry fields to validate variables indices against."""
-        return self._var_fields
-
-    @property
-    def categoricals(self) -> dict[str, dict[str, FieldAttr]]:
-        """Return the categorical keys and fields to validate against."""
-        return self._categoricals
-
-    @property
-    def non_validated(self) -> dict[str, dict[str, list[str]]]:
-        """Return the non-validated features and labels."""
-        if self._non_validated is None:
-            raise ValidationError("Please run validate() first!")
-        return self._non_validated
-
-    def _verify_accessor_exists(self, accessors: Iterable[str]) -> None:
-        """Verify that the accessors exist (either a valid table or in attrs)."""
-        for acc in accessors:
-            is_present = False
-            try:
-                self._sdata.get_attrs(key=acc)
-                is_present = True
-            except KeyError:
-                if acc in self._sdata.tables.keys():
-                    is_present = True
-            if not is_present:
-                raise ValidationError(f"Accessor '{acc}' does not exist!")
-
-    def lookup(
-        self, using_key: str | None = None, public: bool = False
-    ) -> CurateLookup:
-        """Look up categories.
-
-        Args:
-            using_key: The instance where the lookup is performed.
-            public: Whether the lookup is performed on the public reference.
-        """
-        cat_values_dict = list(self.categoricals.values())[0]
-        return CurateLookup(
-            categoricals=cat_values_dict,
-            slots={"accessors": cat_values_dict.keys()},
-            using_key=using_key or self._using_key,
-            public=public,
-        )
-
-    def _update_registry_all(self) -> None:
-        """Saves labels of all features for sample and table metadata."""
-        if self._sample_df_curator is not None:
-            self._sample_df_curator._update_registry_all(
-                validated_only=True, **self._kwargs
-            )
-        for _, adata_curator in self._table_adata_curators.items():
-            adata_curator._update_registry_all(validated_only=True, **self._kwargs)
-
-    def add_new_from_var_index(
-        self, table: str, organism: str | None = None, **kwargs
-    ) -> None:
-        """Save new values from ``.var.index`` of table.
-
-        Args:
-            table: The table key.
-            organism: The organism name.
-            **kwargs: Additional keyword arguments to pass to create new records.
-        """
-        if self._non_validated is None:
-            raise ValidationError("Run .validate() first.")
-        self._kwargs.update({"organism": organism} if organism else {})
-        self._table_adata_curators[table].add_new_from_var_index(
-            **self._kwargs, **kwargs
-        )
-        self._non_validated[table].pop("var_index")
-
-        if len(self.non_validated[table].values()) == 0:
-            self.non_validated.pop(table)
-
-    def add_new_from(
-        self,
-        key: str,
-        accessor: str | None = None,
-        organism: str | None = None,
-        **kwargs,
-    ) -> None:
-        """Save new values of categorical from sample level metadata or table.
-
-        Args:
-            key: The key referencing the slot in the DataFrame.
-            accessor: The accessor key such as 'sample' or 'table x'.
-            organism: The organism name.
-            **kwargs: Additional keyword arguments to pass to create new records.
-        """
-        if self._non_validated is None:
-            raise ValidationError("Run .validate() first.")
-
-        if len(kwargs) > 0 and key == "all":
-            raise ValueError("Cannot pass additional arguments to 'all' key!")
-
-        self._kwargs.update({"organism": organism} if organism else {})
-        if accessor in self._table_adata_curators:
-            adata_curator = self._table_adata_curators[accessor]
-            adata_curator.add_new_from(key=key, **self._kwargs, **kwargs)
-        if accessor == self._sample_metadata_key:
-            self._sample_df_curator.add_new_from(key=key, **self._kwargs, **kwargs)
-
-        if len(self.non_validated[accessor].values()) == 0:
-            self.non_validated.pop(accessor)
-
-    def standardize(self, key: str, accessor: str | None = None) -> None:
-        """Replace synonyms with canonical values.
-
-        Modifies the dataset inplace.
-
-        Args:
-            key: The key referencing the slot in the table or sample metadata.
-            accessor: The accessor key such as 'sample_key' or 'table_key'.
-        """
-        if len(self.non_validated) == 0:
-            logger.warning("values are already standardized")
-            return
-
-        if accessor == self._sample_metadata_key:
-            if key not in self._sample_metadata.columns:
-                raise ValueError(f"key '{key}' not present in '{accessor}'!")
-        else:
-            if key not in self._sdata.tables[accessor].obs.columns:
-                raise ValueError(f"key '{key}' not present in '{accessor}'!")
-
-        if accessor in self._table_adata_curators.keys():
-            adata_curator = self._table_adata_curators[accessor]
-            adata_curator.standardize(key)
-        if accessor == self._sample_metadata_key:
-            self._sample_df_curator.standardize(key)
-
-        if len(self.non_validated[accessor].values()) == 0:
-            self.non_validated.pop(accessor)
-
-    def validate(self, organism: str | None = None) -> bool:
-        """Validate variables and categorical observations.
-
-        This method also registers the validated records in the current instance:
-        - from public sources
-        - from the using_key instance
-
-        Args:
-            organism: The organism name.
-
-        Returns:
-            Whether the SpatialData object is validated.
-        """
-        from lamindb.core._settings import settings
-
-        self._kwargs.update({"organism": organism} if organism else {})
-        if self._using_key is not None and self._using_key != "default":
-            logger.important(
-                f"validating using registries of instance {colors.italic(self._using_key)}"
-            )
-
-        # add all validated records to the current instance
-        verbosity = settings.verbosity
-        try:
-            settings.verbosity = "error"
-            self._update_registry_all()
-        finally:
-            settings.verbosity = verbosity
-
-        self._non_validated = {}  # type: ignore
-
-        sample_validated = True
-        if self._sample_df_curator:
-            logger.info(f"validating categoricals of '{self._sample_metadata_key}' ...")
-            sample_validated &= self._sample_df_curator.validate(**self._kwargs)
-            if len(self._sample_df_curator.non_validated) > 0:
-                self._non_validated["sample"] = self._sample_df_curator.non_validated  # type: ignore
-            logger.print("")
-
-        mods_validated = True
-        for table, adata_curator in self._table_adata_curators.items():
-            logger.info(f"validating categoricals of table '{table}' ...")
-            mods_validated &= adata_curator.validate(**self._kwargs)
-            if len(adata_curator.non_validated) > 0:
-                self._non_validated[table] = adata_curator.non_validated  # type: ignore
-            logger.print("")
-
-        self._validated = sample_validated & mods_validated
-        return self._validated
-
-    def save_artifact(
-        self,
-        description: str | None = None,
-        key: str | None = None,
-        revises: Artifact | None = None,
-        run: Run | None = None,
-    ) -> Artifact:
-        """Save the validated ``SpatialData`` object and metadata.
-
-        Args:
-            description: A description of the ``SpatialData`` object.
-            key: A path-like key to reference artifact in default storage, e.g., `"myfolder/myfile.zarr"`.
-                Artifacts with the same key form a revision family.
-            revises: Previous version of the artifact. Triggers a revision.
-            run: The Run that creates the artifact.
-
-        Returns:
-            A saved Artifact record.
-        """
-        if not self._validated:
-            self.validate()
-            if not self._validated:
-                raise ValidationError("Dataset does not validate. Please curate.")
-
-        verbosity = settings.verbosity
-        try:
-            settings.verbosity = "warning"
-
-            # Write the SpatialData object to a random path in tmp directory
-            # The Artifact constructor will move it to the cache
-            write_path = f"{settings.cache_dir}/{random.randint(10**7, 10**8 - 1)}.zarr"
-            self._sdata.write(write_path)
-
-            # Create the Artifact and associate Artifact metadata
-            self._artifact = Artifact(
-                write_path,
-                description=description,
-                key=key,
-                revises=revises,
-                run=run,
-            )
-            # According to Tim it is not easy to calculate the number of observations.
-            # We would have to write custom code to iterate over labels (which might not even exist at that point)
-            self._artifact.otype = "spatialdata"
-            self._artifact.save()
-
-            # Link schemas
-            feature_kwargs = check_registry_organism(
-                (list(self._var_fields.values())[0].field.model),
-                self._kwargs.get("organism"),
-            )
-
-            def _add_set_from_spatialdata(
-                host: Artifact | Collection | Run,
-                var_fields: dict[str, FieldAttr],
-                obs_fields: dict[str, FieldAttr] = None,
-                mute: bool = False,
-                organism: str | Record | None = None,
-            ):
-                """Add Schemas from SpatialData."""
-                if obs_fields is None:
-                    obs_fields = {}
-                assert host.otype == "spatialdata"  # noqa: S101
-
-                _schemas_m2m = {}
-
-                # sample features
-                sample_features = Feature.from_values(self._sample_metadata.columns)
-                if len(sample_features) > 0:
-                    _schemas_m2m[self._sample_metadata_key] = Schema(
-                        features=sample_features
-                    )
-
-                # table features
-                for table, field in var_fields.items():
-                    table_fs = parse_staged__schemas_m2m_from_anndata(
-                        self._sdata[table],
-                        var_field=field,
-                        obs_field=obs_fields.get(table, Feature.name),
-                        mute=mute,
-                        organism=organism,
-                    )
-                    for k, v in table_fs.items():
-                        _schemas_m2m[f"['{table}'].{k}"] = v
-
-                def _unify_staged__schemas_m2m_by_hash(
-                    _schemas_m2m: MutableMapping[str, Schema],
-                ):
-                    unique_values: dict[str, Any] = {}
-
-                    for key, value in _schemas_m2m.items():
-                        value_hash = (
-                            value.hash
-                        )  # Assuming each value has a .hash attribute
-                        if value_hash in unique_values:
-                            _schemas_m2m[key] = unique_values[value_hash]
-                        else:
-                            unique_values[value_hash] = value
-
-                    return _schemas_m2m
-
-                # link feature sets
-                host._staged__schemas_m2m = _unify_staged__schemas_m2m_by_hash(
-                    _schemas_m2m
-                )
-                host.save()
-
-            _add_set_from_spatialdata(
-                self._artifact, var_fields=self._var_fields, **feature_kwargs
-            )
-
-            # Link labels
-            def _add_labels_from_spatialdata(
-                data,
-                artifact: Artifact,
-                fields: dict[str, FieldAttr],
-                feature_ref_is_name: bool | None = None,
-            ):
-                """Add Labels from SpatialData."""
-                features = Feature.lookup().dict()
-                for key, field in fields.items():
-                    feature = features.get(key)
-                    registry = field.field.model
-                    filter_kwargs = check_registry_organism(
-                        registry, self._kwargs.get("organism")
-                    )
-                    filter_kwargs_current = get_current_filter_kwargs(
-                        registry, filter_kwargs
-                    )
-                    df = data if isinstance(data, pd.DataFrame) else data.obs
-                    labels = registry.from_values(
-                        df[key],
-                        field=field,
-                        **filter_kwargs_current,
-                    )
-                    if len(labels) == 0:
-                        continue
-
-                    label_ref_is_name = None
-                    if hasattr(registry, "_name_field"):
-                        label_ref_is_name = field.field.name == registry._name_field
-                    add_labels(
-                        artifact,
-                        records=labels,
-                        feature=feature,
-                        feature_ref_is_name=feature_ref_is_name,
-                        label_ref_is_name=label_ref_is_name,
-                        from_curator=True,
-                    )
-
-            for accessor, accessor_fields in self._categoricals.items():
-                column_field = self._var_fields.get(accessor)
-                if accessor == self._sample_metadata_key:
-                    _add_labels_from_spatialdata(
-                        self._sample_metadata,
-                        self._artifact,
-                        accessor_fields,
-                        feature_ref_is_name=(
-                            None if column_field is None else _ref_is_name(column_field)
-                        ),
-                    )
-                else:
-                    _add_labels_from_spatialdata(
-                        self._sdata.tables[accessor],
-                        self._artifact,
-                        accessor_fields,
-                        feature_ref_is_name=(
-                            None if column_field is None else _ref_is_name(column_field)
-                        ),
-                    )
-
-        finally:
-            settings.verbosity = verbosity
-
-        slug = ln_setup.settings.instance.slug
-        if ln_setup.settings.instance.is_remote:  # pragma: no cover
-            logger.important(
-                f"go to https://lamin.ai/{slug}/artifact/{self._artifact.uid}"
-            )
-
-        return self._artifact