lamindb 1.2.0__py3-none-any.whl → 1.3.0__py3-none-any.whl

lamindb/__init__.py

@@ -72,7 +72,7 @@ Backward compatibility.
 
 # ruff: noqa: I001
 # denote a release candidate for 0.1.0 with 0.1rc1, 0.1a1, 0.1b1, etc.
-__version__ = "1.2.0"
+__version__ = "1.3.0"
 
 import warnings
 

lamindb/core/_context.py

@@ -301,6 +301,12 @@ class Context:
         """
         from lamindb.models import Project
 
+        instance_settings = ln_setup.settings.instance
+        # similar logic here: https://github.com/laminlabs/lamindb/pull/2527
+        # TODO: refactor upon new access management
+        if instance_settings.dialect == "postgresql" and "read" in instance_settings.db:
+            logger.warning("skipping track(), connected in read-only mode")
+            return None
         if project is not None:
             project_record = Project.filter(
                 Q(name=project) | Q(uid=project)

lamindb/core/datasets/__init__.py

@@ -83,6 +83,7 @@ from ._core import (
     mudata_papalexi21_subset,
     schmidt22_crispra_gws_IFNG,
     schmidt22_perturbseq,
+    spatialdata_blobs,
 )
 from ._fake import fake_bio_notebook_titles
 from ._small import (

lamindb/core/datasets/_core.py

@@ -13,6 +13,7 @@ from lamindb.core._settings import settings
 
 if TYPE_CHECKING:
     from mudata import MuData
+    from spatialdata import SpatialData
 
 
 def file_fcs() -> Path:
@@ -552,3 +553,25 @@ def schmidt22_perturbseq(basedir=".") -> Path:  # pragma: no cover
         "schmidt22_perturbseq.h5ad",
     )
     return Path(filepath).rename(Path(basedir) / filepath)
+
+
+def spatialdata_blobs() -> SpatialData:
+    """Example SpatialData dataset for tutorials."""
+    from spatialdata.datasets import blobs
+
+    sdata = blobs()
+    sdata.attrs["sample"] = {
+        "assay": "Visium Spatial Gene Expression",
+        "disease": "Alzheimer disease",
+        "developmental_stage": "adult stage",
+    }
+    sdata.tables["table"].var.index = [
+        "ENSG00000139618",  # BRCA2
+        "ENSG00000157764",  # BRAF
+        "ENSG00000999999",  # Does not exist
+    ]
+    sdata.tables["table"].obs["sample_region"] = pd.Categorical(
+        ["sample region 1"] * 13 + ["sample region 2"] * 13
+    )
+
+    return sdata

lamindb/core/datasets/_small.py

@@ -8,9 +8,11 @@ import pandas as pd
 
 
 def small_dataset1(
-    otype: Literal["DataFrame", "AnnData"],
+    otype: Literal["DataFrame", "AnnData"] = "DataFrame",
     gene_symbols_in_index: bool = False,
     with_typo: bool = False,
+    with_cell_type_synonym: bool = False,
+    with_cell_type_typo: bool = False,
 ) -> pd.DataFrame | ad.AnnData:
     # define the data in the dataset
     # it's a mix of numerical measurements and observation-level metadata
@@ -19,14 +21,25 @@ def small_dataset1(
         var_ids = ["CD8A", "CD4", "CD14"]
     else:
         var_ids = ["ENSG00000153563", "ENSG00000010610", "ENSG00000170458"]
+    abt_cell = (
+        "CD8-pos alpha-beta T cell"
+        if with_cell_type_typo
+        else "CD8-positive, alpha-beta T cell"
+    )
     dataset_dict = {
         var_ids[0]: [1, 2, 3],
         var_ids[1]: [3, 4, 5],
         var_ids[2]: [5, 6, 7],
         "perturbation": pd.Categorical(["DMSO", ifng, "DMSO"]),
         "sample_note": ["was ok", "looks naah", "pretty! 🤩"],
-        "cell_type_by_expert": pd.Categorical(["B cell", "T cell", "T cell"]),
+        "cell_type_by_expert": pd.Categorical(
+            ["B-cell" if with_cell_type_synonym else "B cell", abt_cell, abt_cell]
+        ),
         "cell_type_by_model": pd.Categorical(["B cell", "T cell", "T cell"]),
+        "assay_oid": pd.Categorical(["EFO:0008913", "EFO:0008913", "EFO:0008913"]),
+        "concentration": ["0.1%", "200 nM", "0.1%"],
+        "treatment_time_h": [24, 24, 6],
+        "donor": ["D0001", "D0002", None],
     }
     # define the dataset-level metadata
     metadata = {
@@ -100,6 +113,7 @@ def small_dataset3_cellxgene(
         "disease_ontology_term_id": ["MONDO:0004975", "MONDO:0004980", "MONDO:0004980"],
         "organism": ["human", "human", "human"],
         "sex": ["female", "male", "unknown"],
+        "sex_ontology_term_id": ["PATO:0000383", "PATO:0000384", "unknown"],
         "tissue": ["lungg", "lungg", "heart"],
         "donor": ["-1", "1", "2"],
     }

lamindb/core/storage/objects.py

@@ -45,8 +45,7 @@ def infer_suffix(dmem: SupportedDataTypes, format: str | None = None):
         dmem,
         "SpatialData",
         "spatialdata",
-        lambda obj: "."
-        + (
+        lambda obj: (
             format
             if format is not None and format in {"spatialdata.zarr", "zarr"}
             else ".zarr"