scdataloader 1.0.5__tar.gz → 1.1.3__tar.gz

{scdataloader-1.0.5 → scdataloader-1.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scdataloader
-Version: 1.0.5
+Version: 1.1.3
 Summary: a dataloader for single cell data in lamindb
 Home-page: https://github.com/jkobject/scDataLoader
 License: GPL3
@@ -13,7 +13,7 @@ Classifier: Programming Language :: Python :: 3.10
 Provides-Extra: dev
 Requires-Dist: anndata
 Requires-Dist: biomart
-Requires-Dist: bionty (==0.48.0)
+Requires-Dist: bionty (==0.49.0)
 Requires-Dist: black (>=23.10.1,<24.0.0) ; extra == "dev"
 Requires-Dist: cellxgene-census
 Requires-Dist: coverage (>=7.3.2,<8.0.0) ; extra == "dev"
@@ -23,7 +23,7 @@ Requires-Dist: flake8 (>=6.1.0,<7.0.0) ; extra == "dev"
 Requires-Dist: gitchangelog (>=3.0.4,<4.0.0) ; extra == "dev"
 Requires-Dist: ipykernel
 Requires-Dist: isort (>=5.12.0,<6.0.0) ; extra == "dev"
-Requires-Dist: lamindb (==0.75.1)
+Requires-Dist: lamindb (==0.76.3)
 Requires-Dist: leidenalg
 Requires-Dist: lightning
 Requires-Dist: matplotlib
@@ -82,13 +82,41 @@ I needed to create this Data Loader for my PhD project. I am using it to load &
 
 ```bash
 pip install scdataloader
+# or
+pip install scDataLoader[dev] # for dev dependencies
+
+lamin login <email> --key <API-key>
+lamin init --storage [folder-name-where-lamin-data-will-be-stored] --schema bionty
 ```
 
-### Install it locally and run the notebooks:
+if you start with lamin and had to do a `lamin init`, you will also need to populate your ontologies. This is because scPRINT is using ontologies to define its cell types, diseases, sexes, ethnicities, etc.
+
+you can do it manually or with our function:
+
+```python
+from scdataloader.utils import populate_my_ontology
+
+populate_my_ontology() #to populate everything (recommended) (can take 2-10mns)
+
+populate_my_ontology( #the minimum for scprint to run some inferences (denoising, grn inference)
+organisms: List[str] = ["NCBITaxon:10090", "NCBITaxon:9606"],
+    sex: List[str] = ["PATO:0000384", "PATO:0000383"],
+    celltypes = None,
+    ethnicities = None,
+    assays = None,
+    tissues = None,
+    diseases = None,
+    dev_stages = None,
+)
+```
+
+### Dev install
+
+If you want to use the latest version of scDataLoader and work on the code yourself use `git clone` and `pip -e` instead of `pip install`.
 
 ```bash
 git clone https://github.com/jkobject/scDataLoader.git
-pip install -e scDataLoader
+pip install -e scDataLoader[dev]
 ```
 
 ## Usage

{scdataloader-1.0.5 → scdataloader-1.1.3}/README.md

@@ -41,13 +41,41 @@ I needed to create this Data Loader for my PhD project. I am using it to load &
 
 ```bash
 pip install scdataloader
+# or
+pip install scDataLoader[dev] # for dev dependencies
+
+lamin login <email> --key <API-key>
+lamin init --storage [folder-name-where-lamin-data-will-be-stored] --schema bionty
 ```
 
-### Install it locally and run the notebooks:
+if you start with lamin and had to do a `lamin init`, you will also need to populate your ontologies. This is because scPRINT is using ontologies to define its cell types, diseases, sexes, ethnicities, etc.
+
+you can do it manually or with our function:
+
+```python
+from scdataloader.utils import populate_my_ontology
+
+populate_my_ontology() #to populate everything (recommended) (can take 2-10mns)
+
+populate_my_ontology( #the minimum for scprint to run some inferences (denoising, grn inference)
+organisms: List[str] = ["NCBITaxon:10090", "NCBITaxon:9606"],
+    sex: List[str] = ["PATO:0000384", "PATO:0000383"],
+    celltypes = None,
+    ethnicities = None,
+    assays = None,
+    tissues = None,
+    diseases = None,
+    dev_stages = None,
+)
+```
+
+### Dev install
+
+If you want to use the latest version of scDataLoader and work on the code yourself use `git clone` and `pip -e` instead of `pip install`.
 
 ```bash
 git clone https://github.com/jkobject/scDataLoader.git
-pip install -e scDataLoader
+pip install -e scDataLoader[dev]
 ```
 
 ## Usage

{scdataloader-1.0.5 → scdataloader-1.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "scdataloader"
-version = "1.0.5"
+version = "1.1.3"
 description = "a dataloader for single cell data in lamindb"
 authors = ["jkobject"]
 license = "GPL3"
@@ -10,8 +10,8 @@ keywords = ["scRNAseq", "dataloader", "pytorch", "lamindb", "scPRINT"]
 
 [tool.poetry.dependencies]
 python = "3.10.*"
-lamindb = "0.75.1"
-bionty = "0.48.0"
+lamindb = "0.76.3"
+bionty = "0.49.0"
 cellxgene-census = "*"
 torch = "*"
 lightning = "*"

scdataloader-1.1.3/scdataloader/VERSION

@@ -0,0 +1 @@
+1.1.3

{scdataloader-1.0.5 → scdataloader-1.1.3}/scdataloader/collator.py

@@ -161,7 +161,10 @@ class Collator:
                 raise ValueError("how must be either most expr or random expr")
             if (
                 (self.add_zero_genes > 0) or (self.max_len > len(nnz_loc))
-            ) and self.how not in ["all", "some"]:
+            ) and self.how not in [
+                "all",
+                "some",
+            ]:
                 zero_loc = np.where(expr == 0)[0]
                 zero_loc = zero_loc[
                     np.random.choice(

{scdataloader-1.0.5 → scdataloader-1.1.3}/scdataloader/utils.py

@@ -433,7 +433,7 @@ def populate_my_ontology(
         names = bt.Phenotype.public().df().index if not sex else sex
         records = [
             bt.Phenotype.from_source(
-                ontology_id=i,
+                ontology_id=i, source=bt.PublicSource.filter(name="pato").first()
             )
             for i in names
         ]
@@ -472,9 +472,12 @@ def populate_my_ontology(
 
         names = bt.DevelopmentalStage.public(organism="mouse").df().index
         records = [
-            bt.DevelopmentalStage.from_source(ontology_id=i) for i in names.tolist()
+            bt.DevelopmentalStage.from_source(
+                ontology_id=i,
+                source=bt.PublicSource.filter(organism="mouse", name="mmusdv").first(),
+            )
+            for i in names.tolist()
         ]
-        records[-4] = records[-4][0]
         ln.save(records)
     # Disease
     if diseases is not None:

scdataloader-1.0.5/scdataloader/VERSION

@@ -1 +0,0 @@
-1.0.5