scdataloader 2.0.6__py3-none-any.whl → 2.0.8__py3-none-any.whl

scdataloader/data.py

@@ -200,7 +200,7 @@ class Dataset(torchDataset):
     def get_label_cats(
         self,
         obs_keys: Union[str, List[str]],
-    ):
+    ) -> np.ndarray:
         """
         Get combined categorical codes for one or more label columns.
 
@@ -226,7 +226,7 @@ class Dataset(torchDataset):
                 labels = concat_categorical_codes([labels, labels_to_str])
         return np.array(labels.codes)
 
-    def get_unseen_mapped_dataset_elements(self, idx: int):
+    def get_unseen_mapped_dataset_elements(self, idx: int) -> list[str]:
         """
         Get genes marked as unseen for a specific sample.
 

scdataloader/datamodule.py

@@ -136,7 +136,7 @@ class DataModule(L.LightningDataModule):
                 increases sampling weight balance over epochs. Defaults to 0.
             start_at (int, optional): Starting index for resuming inference. Requires same
                 number of GPUs as previous run. Defaults to 0.
-            **kwargs: Additional arguments passed to PyTorch DataLoader (e.g., batch_size,
+            **kwargs: dict[str, Any]: Additional arguments passed to PyTorch DataLoader (e.g., batch_size,
                 num_workers, pin_memory).
 
         Attributes:
@@ -256,7 +256,7 @@ class DataModule(L.LightningDataModule):
         )
 
     @property
-    def decoders(self):
+    def decoders(self) -> dict[str, dict[int, str]]:
         """
         decoders the decoders for any labels that would have been encoded
 
@@ -269,7 +269,7 @@ class DataModule(L.LightningDataModule):
         return decoders
 
     @property
-    def labels_hierarchy(self):
+    def labels_hierarchy(self) -> dict[str, dict[str, str]]:
         """
         labels_hierarchy the hierarchy of labels for any cls that would have a hierarchy
 
@@ -287,7 +287,7 @@ class DataModule(L.LightningDataModule):
         return labels_hierarchy
 
     @property
-    def genes(self):
+    def genes(self) -> list:
         """
         genes the genes used in this datamodule
 
@@ -343,7 +343,7 @@ class DataModule(L.LightningDataModule):
     def num_datasets(self):
         return len(self.dataset.mapped_dataset.storages)
 
-    def setup(self, stage=None):
+    def setup(self, stage: Optional[str] = None) -> list[str]:
         """
         Prepare data splits for training, validation, and testing.
 
@@ -512,7 +512,7 @@ class DataModule(L.LightningDataModule):
         print(f"done setup, took {time.time() - start_time:.2f} seconds")
         return self.test_datasets
 
-    def train_dataloader(self, **kwargs):
+    def train_dataloader(self, **kwargs) -> DataLoader:
         """
         Create the training DataLoader with weighted random sampling.
 
@@ -521,7 +521,7 @@ class DataModule(L.LightningDataModule):
         distributed training without weighting.
 
         Args:
-            **kwargs: Additional arguments passed to DataLoader, overriding defaults.
+            **kwargs: dict[str, Any]: Additional arguments passed to DataLoader, overriding defaults.
 
         Returns:
             DataLoader: Training DataLoader instance.
@@ -560,7 +560,7 @@ class DataModule(L.LightningDataModule):
             **current_loader_kwargs,
         )
 
-    def val_dataloader(self):
+    def val_dataloader(self) -> Union[DataLoader, list]:
         """
         Create the validation DataLoader.
 
@@ -576,7 +576,7 @@ class DataModule(L.LightningDataModule):
             else []
         )
 
-    def test_dataloader(self):
+    def test_dataloader(self) -> Union[DataLoader, list]:
         """
         Create the test DataLoader with sequential sampling.
 
@@ -591,7 +591,7 @@ class DataModule(L.LightningDataModule):
             else []
         )
 
-    def predict_dataloader(self):
+    def predict_dataloader(self) -> DataLoader:
         """
         Create a DataLoader for prediction over all training data.
 

scdataloader/preprocess.py

@@ -87,10 +87,12 @@ class Preprocessor:
                 If int, filters cells with counts. Defaults to False.
             normalize_sum (float or bool, optional): Determines whether to normalize the total counts of each cell to a specific value.
                 Defaults to 1e4.
-            log1p (bool, optional): Determines whether to apply log1p transform to the normalized data.
-                Defaults to True.
             n_hvg_for_postp (int or bool, optional): Determines whether to subset to highly variable genes for the PCA.
                 Defaults to False.
+            use_layer (str, optional): The layer to use for preprocessing.
+                Defaults to None.
+            is_symbol (bool, optional): Whether genes are provided as symbols instead of Ensembl IDs.
+                Defaults to False.
             hvg_flavor (str, optional): Specifies the flavor of highly variable genes selection.
                 See :func:`scanpy.pp.highly_variable_genes` for more details. Defaults to "seurat_v3".
             binning (int, optional): Determines whether to bin the data into discrete values of number of bins provided.
@@ -112,10 +114,20 @@ class Preprocessor:
                 Defaults to 5.
             pct_mt_outlier (int, optional): The maximum percentage of mitochondrial genes outlier.
                 Defaults to 8.
-            batch_key (str, optional): The key of :class:`~anndata.AnnData.obs` to use for batch information.
+            batch_keys (List[str], optional): The keys of :class:`~anndata.AnnData.obs` to use for batch information.
                 This arg is used in the highly variable gene selection step.
             skip_validate (bool, optional): Determines whether to skip the validation step.
                 Defaults to False.
+            additional_preprocess (Callable, optional): Additional preprocessing function.
+                Defaults to None.
+            additional_postprocess (Callable, optional): Additional postprocessing function.
+                Defaults to None.
+            do_postp (bool, optional): Whether to perform postprocessing.
+                Defaults to True.
+            organisms (List[str], optional): List of organisms to support.
+                Defaults to ["NCBITaxon:9606", "NCBITaxon:10090"].
+            use_raw (bool, optional): Whether to use raw counts.
+                Defaults to True.
             keepdata (bool, optional): Determines whether to keep the data in the AnnData object.
                 Defaults to False.
             drop_non_primary (bool, optional): Determines whether to drop non-primary cells.
@@ -483,13 +495,20 @@ class LaminPreprocessor(Preprocessor):
         version: str = "2",
     ):
         """
-        format controls the different input value wrapping, including categorical
-        binned style, fixed-sum normalized counts, log1p fixed-sum normalized counts, etc.
+        Process data with format controlling different input value wrapping.
+
+        Includes support for categorical binned style, fixed-sum normalized counts,
+        log1p fixed-sum normalized counts, etc.
 
         Args:
-            adata (AnnData): The AnnData object to preprocess.
-            batch_key (str, optional): The key of AnnData.obs to use for batch information. This arg
-                is used in the highly variable gene selection step.
+            data (Union[ln.Collection, AnnData]): The AnnData object or Collection to preprocess.
+            name (str, optional): Name for the preprocessed dataset. Defaults to "preprocessed dataset".
+            description (str, optional): Description for the preprocessed dataset.
+                Defaults to "preprocessed dataset using scprint".
+            start_at (int, optional): Starting index for resuming preprocessing.
+                Defaults to 0.
+            version (str, optional): Version string for the dataset.
+                Defaults to "2".
         """
         files = []
         all_ready_processed_keys = set()

scdataloader/utils.py

@@ -28,10 +28,11 @@ def fileToList(filename: str, strconv: callable = lambda x: x) -> list:
     loads an input file with a\\n b\\n.. into a list [a,b,..]
 
     Args:
-        input_str (str): The input string to be completed.
+        filename (str): The filename to load from.
+        strconv (callable): A function to convert each line. Defaults to identity function.
 
     Returns:
-        str: The completed string with 'complete' appended.
+        list: The list of converted elements from the file.
     """
     with open(filename) as f:
         return [strconv(val[:-1]) for val in f.readlines()]
@@ -44,7 +45,7 @@ def listToFile(
     listToFile loads a list with [a,b,..] into an input file a\\n b\\n..
 
     Args:
-        l (list): The list of elements to be written to the file.
+        li (list): The list of elements to be written to the file.
         filename (str): The name of the file where the list will be written.
         strconv (callable, optional): A function to convert each element of the list to a string. Defaults to str.
 
@@ -124,7 +125,7 @@ def getBiomartTable(
     attributes: List[str] = [],
     bypass_attributes: bool = False,
     database: str = "hsapiens_gene_ensembl",
-):
+) -> pd.DataFrame:
     """generate a genelist dataframe from ensembl's biomart
 
     Args:
@@ -175,14 +176,14 @@ def getBiomartTable(
     return res
 
 
-def validate(adata: AnnData, organism: str, need_all=False):
+def validate(adata: AnnData, organism: str, need_all: bool = False) -> bool:
     """
     validate checks if the adata object is valid for lamindb
 
     Args:
-        adata (anndata): the anndata object
-        lb (lamindb): the lamindb instance
-        organism (str): the organism
+        adata (AnnData): the anndata object
+        organism (str): the organism ontology ID
+        need_all (bool, optional): whether all columns should be present. Defaults to False.
 
     Raises:
         ValueError: if the adata object is not valid
@@ -298,7 +299,7 @@ def get_descendants(val, df):
     return r_onto | ontos
 
 
-def get_ancestry_mapping(all_elem: List[str], onto_df: pd.DataFrame):
+def get_ancestry_mapping(all_elem: List[str], onto_df: pd.DataFrame) -> dict:
     """
     This function generates a mapping of all elements to their ancestors in the ontology dataframe.
 
@@ -339,13 +340,12 @@ def load_dataset_local(
     description: str,
     use_cache: bool = True,
     only: Optional[List[int]] = None,
-):
+) -> ln.Dataset:
     """
     This function loads a remote lamindb dataset to local.
 
     Args:
-        lb (lamindb): The lamindb instance.
-        remote_dataset (lamindb.Dataset): The remote Dataset.
+        remote_dataset (lamindb.Collection): The remote Collection.
         download_folder (str): The path to the download folder.
         name (str): The name of the dataset.
         description (str): The description of the dataset.
@@ -396,7 +396,7 @@ def load_dataset_local(
 
 def load_genes(
     organisms: Union[str, List[str]] = "NCBITaxon:9606",
-):  # "NCBITaxon:10090",
+) -> pd.DataFrame:  # "NCBITaxon:10090",
     """
     Loads genes from the given organisms.
 
@@ -454,9 +454,18 @@ def _adding_scbasecamp_genes(
     if len(species) == 0:
         species = set(
             bt.Organism.using("laminlabs/arc-virtual-cell-atlas").df().ontology_id
-        )
-        -set(["NCBITaxon:10090", "NCBITaxon:9606"])
+        ) - set(["NCBITaxon:10090", "NCBITaxon:9606"])
     species = list(species)
+    for i in set(
+        bt.Organism.using("laminlabs/arc-virtual-cell-atlas").df().ontology_id
+    ) - set(bt.Organism.filter().df().ontology_id):
+        print(i)
+        rec = (
+            bt.Organism.using("laminlabs/arc-virtual-cell-atlas")
+            .filter(ontology_id=i)
+            .first()
+        )
+        rec.save()
     if len(bt.Organism.filter(ontology_id="NCBITaxon:9593")) == 0:
         bt.Organism(
             name="gorilla gorilla",
@@ -655,7 +664,7 @@ def populate_my_ontology(
             ln.save(records)
 
 
-def random_str(stringLength=6, stype="all", withdigits=True):
+def random_str(stringLength=6, stype="all", withdigits=True) -> str:
     """
     Generate a random string of letters and digits
 
@@ -664,7 +673,7 @@ def random_str(stringLength=6, stype="all", withdigits=True):
         stype (str, optional): one of lowercase, uppercase, all. Defaults to 'all'.
         withdigits (bool, optional): digits allowed in the string? Defaults to True.
 
-        Returns:
+    Returns:
         str: random string
     """
     if stype == "lowercase":
@@ -678,12 +687,12 @@ def random_str(stringLength=6, stype="all", withdigits=True):
     return "".join(random.choice(lettersAndDigits) for i in range(stringLength))
 
 
-def is_outlier(adata: AnnData, metric: str, nmads: int):
+def is_outlier(adata: AnnData, metric: str, nmads: int) -> pd.Series:
     """
     is_outlier detects outliers in adata.obs[metric]
 
     Args:
-        adata (annData): the anndata object
+        adata (AnnData): the anndata object
         metric (str): the metric column to use
         nmads (int): the number of median absolute deviations to use as a threshold
 
@@ -697,16 +706,16 @@ def is_outlier(adata: AnnData, metric: str, nmads: int):
     return outlier
 
 
-def length_normalize(adata: AnnData, gene_lengths: list):
+def length_normalize(adata: AnnData, gene_lengths: list) -> AnnData:
     """
     length_normalize normalizes the counts by the gene length
 
     Args:
-        adata (anndata): the anndata object
+        adata (AnnData): the anndata object
         gene_lengths (list): the gene lengths
 
     Returns:
-        anndata: the anndata object
+        AnnData: the normalized anndata object
     """
     adata.X = csr_matrix((adata.X.T / gene_lengths).T)
     return adata
@@ -714,13 +723,13 @@ def length_normalize(adata: AnnData, gene_lengths: list):
 
 def translate(
     val: Union[str, list, set, Counter, dict], t: str = "cell_type_ontology_term_id"
-):
+) -> dict:
     """
     translate translates the ontology term id to the name
 
     Args:
-        val (str, dict, set, list, dict): the object to translate
-        t (flat, optional): the type of ontology terms.
+        val (Union[str, dict, set, list]): the object to translate
+        t (str, optional): the type of ontology terms.
             one of cell_type_ontology_term_id, assay_ontology_term_id, tissue_ontology_term_id.
             Defaults to "cell_type_ontology_term_id".
 

{scdataloader-2.0.6.dist-info → scdataloader-2.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scdataloader
-Version: 2.0.6
+Version: 2.0.8
 Summary: a dataloader for single cell data in lamindb
 Project-URL: repository, https://github.com/jkobject/scDataLoader
 Author-email: jkobject <jkobject@gmail.com>
@@ -52,9 +52,10 @@ Description-Content-Type: text/markdown
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![DOI](https://zenodo.org/badge/731248665.svg)](https://doi.org/10.5281/zenodo.10573143)
 
-<img src="scdataloader.png" width="600">
+<img src="./docs/scdataloader.png" width="600">
 
-This single cell pytorch dataloader / lighting datamodule is designed to be used with:
+This single cell pytorch dataloader / lighting datamodule is designed to be used
+with:
 
 - [lamindb](https://lamin.ai/)
 
@@ -66,11 +67,13 @@ and:
 It allows you to:
 
 1. load thousands of datasets containing millions of cells in a few seconds.
-2. preprocess the data per dataset and download it locally (normalization, filtering, etc.)
+2. preprocess the data per dataset and download it locally (normalization,
+   filtering, etc.)
 3. create a more complex single cell dataset
 4. extend it to your need
 
-built on top of `lamindb` and the `.mapped()` function by Sergei: https://github.com/Koncopd
+built on top of `lamindb` and the `.mapped()` function by Sergei:
+https://github.com/Koncopd
 
 ```
 Portions of the mapped.py file are derived from Lamin Labs
@@ -81,11 +84,17 @@ Please see https://github.com/laminlabs/lamindb/blob/main/lamindb/core/_mapped_c
 for the original implementation
 ```
 
-The package has been designed together with the [scPRINT paper](https://doi.org/10.1101/2024.07.29.605556) and [model](https://github.com/cantinilab/scPRINT).
+The package has been designed together with the
+[scPRINT paper](https://doi.org/10.1101/2024.07.29.605556) and
+[model](https://github.com/cantinilab/scPRINT).
 
 ## More
 
-I needed to create this Data Loader for my PhD project. I am using it to load & preprocess thousands of datasets containing millions of cells in a few seconds. I believed that individuals employing AI for single-cell RNA sequencing and other sequencing datasets would eagerly utilize and desire such a tool, which presently does not exist.
+I needed to create this Data Loader for my PhD project. I am using it to load &
+preprocess thousands of datasets containing millions of cells in a few seconds.
+I believed that individuals employing AI for single-cell RNA sequencing and
+other sequencing datasets would eagerly utilize and desire such a tool, which
+presently does not exist.
 
 ![scdataloader.drawio.png](docs/scdataloader.drawio.png)
 
@@ -99,12 +108,14 @@ pip install scDataLoader[dev] # for dev dependencies
 lamin init --storage ./testdb --name test --schema bionty
 ```
 
-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.
+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
+from scdataloader.utils import populate_my_ontology, _adding_scbasecamp_genes
 
 populate_my_ontology() #to populate everything (recommended) (can take 2-10mns)
 
@@ -118,11 +129,14 @@ organisms: List[str] = ["NCBITaxon:10090", "NCBITaxon:9606"],
     diseases = None,
     dev_stages = None,
 )
+# if you want to load the gene names and species for the arc scbasecount species, also add this:
+_adding_scbasecamp_genes()
 ```
 
 ### 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`.
+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
@@ -161,6 +175,12 @@ datamodule = DataModule(
 )
 ```
 
+see the notebooks in [docs](https://www.jkobject.com/scDataLoader/) to learn
+more
+
+1. [load a dataset](https://www.jkobject.com/scDataLoader/notebooks/1_download_and_preprocess/)
+2. [create a dataset](https://www.jkobject.com/scDataLoader/notebooks/2_create_dataloader/)
+
 ### lightning-free usage (Dataset+Collator+DataLoader)
 
 ```python
@@ -211,7 +231,17 @@ for batch in tqdm(dataloader):
     )
 ```
 
-### Usage on all of cellxgene
+## Gathering a pre-training database
+
+Here I will explain how to gather and preprocess all of cellxgene (scPRINT-1
+pretraining database) with scDataLoader, and the scPRINT-2 corpus (scPRINT-2
+pretraining database).
+
+### Getting all of cellxgene
+
+Here is an example of how to download and preprocess all of cellxgene with
+scDataLoader as a script (a notebook version is also available in
+[./notebooks/update_lamin_or_cellxgene.ipynb](https://github.com/jkobject/scdataloader/blob/main/notebooks/update_lamin_or_cellxgene.ipynb)).
 
 ```python
 # initialize a local lamin database
@@ -226,11 +256,25 @@ DESCRIPTION='preprocessed by scDataLoader'
 cx_dataset = ln.Collection.using(instance="laminlabs/cellxgene").filter(name="cellxgene-census", version='2023-12-15').one()
 cx_dataset, len(cx_dataset.artifacts.all())
 
+# (OPTIONAL) if you want to do you preprocessing on a slurm cluster without internet connections,
+# you can first do this:
+load_dataset_local(
+    cx_dataset,
+    download_folder="/my_download_folder",
+    name="cached-cellxgene-census",
+    description="all of it topreprocess",
+)
 
+# preprocessing
 do_preprocess = LaminPreprocessor(additional_postprocess=additional_postprocess, additional_preprocess=additional_preprocess, skip_validate=True, subset_hvg=0)
 
 preprocessed_dataset = do_preprocess(cx_dataset, name=DESCRIPTION, description=DESCRIPTION, start_at=6, version="2")
 
+```
+
+After this you can use the preprocessed dataset with the DataModule below.
+
+```python
 # create dataloaders
 from scdataloader import DataModule
 import tqdm
@@ -252,27 +296,52 @@ for i in tqdm.tqdm(datamodule.train_dataloader()):
 
 # with lightning:
 # Trainer(model, datamodule)
+```
+
+You can use the command line to preprocess a large database of datasets like
+here for cellxgene. this allows parallelizing and easier usage.
 
+```bash
+scdataloader --instance "laminlabs/cellxgene" --name "cellxgene-census" --version "2023-12-15" --description "preprocessed for scprint" --new_name "scprint main" --start_at 10 >> scdataloader.out
 ```
 
-see the notebooks in [docs](https://www.jkobject.com/scDataLoader/):
+### Getting the rest of the scPRINT-2 corpus
 
-1. [load a dataset](https://www.jkobject.com/scDataLoader/notebooks/1_download_and_preprocess/)
-2. [create a dataset](https://www.jkobject.com/scDataLoader/notebooks/2_create_dataloader/)
+by now, using the command / scripts above you should be able to get all of
+cellxgene (and preprocess it). laminlabs now also hosts the rest of the
+scPRINT-2 corpus in `laminlabs/arc-virtual-cell-atlas` and they can be
+downloaded and preprocessed the same way as cellxgene above. Be careful however
+that there is no metadata for these datasets.
 
-### command line preprocessing
+You can have a look at my notebooks:
+[./notebooks/adding_tahoe.ipynb](https://github.com/jkobject/scdataloader/blob/main/notebooks/adding_tahoe.ipynb)
+and
+[./notebooks/adding_scbasecount.ipynb](https://github.com/jkobject/scdataloader/blob/main/notebooks/adding_scbasecount.ipynb)
+where I create some remmaping to retrive metadata that can be used by
+scdataloader and lamindb from these datasets.
 
-You can use the command line to preprocess a large database of datasets like here for cellxgene. this allows parallelizing and easier usage.
+If you do not have access for some reason to these datasets, please contact
+laminlabs. But another solution, is to download them from the original sources
+and add them one by one in your instance and then do the same preprocessing but
+this time use `your_account/your_instance` instead of
+`laminlabs/arc-virtual-cell-atlas`.
 
-```bash
-scdataloader --instance "laminlabs/cellxgene" --name "cellxgene-census" --version "2023-12-15" --description "preprocessed for scprint" --new_name "scprint main" --start_at 10 >> scdataloader.out
-```
+This is actually what I did in my own instance to create the full scPRINT-2
+corpus and you can see some of it in the notebooks above.
+
+### Getting even more
+
+They also host a pertubation atlas in `laminlabs/pertdata` that can be
+downloaded the same way.
 
-### command line usage
+### command line usage to train a moel
 
 The main way to use
 
-> please refer to the [scPRINT documentation](https://www.jkobject.com/scPRINT/) and [lightning documentation](https://lightning.ai/docs/pytorch/stable/cli/lightning_cli_intermediate.html) for more information on command line usage
+> please refer to the [scPRINT documentation](https://www.jkobject.com/scPRINT/)
+> and
+> [lightning documentation](https://lightning.ai/docs/pytorch/stable/cli/lightning_cli_intermediate.html)
+> for more information on command line usage
 
 ## FAQ
 
@@ -295,13 +364,36 @@ from scdataloader import utils
 utils.populate_ontologies() # this might take from 5-20mins
 ```
 
+### how to move my lamin instance to another folder?
+
+you cannot just move your folder from one place to another because lamin is
+using absolute paths. You need to do 3 things:
+
+1. move your folder to the new place
+2. update your lamin config file (usually in `~/.lamin/my_env.yml`) to point to
+   the new place
+3. update the absolute paths in your lamin database. You can do it like this:
+
+```python
+import lamin as ln
+ln.Storage.df()
+# view what is your current storage id (in my case it was GZgLW1TQ)
+ln.Storage.filter(uid="GZgLW1TI").update(
+    root=Path("your_new_locations").as_posix().rstrip("/")
+)
+```
+
 ## Development
 
-Read the [CONTRIBUTING.md](CONTRIBUTING.md) file.
+Read the
+[CONTRIBUTING.md](https://github.com/jkobject/scdataloader/blob/main/CONTRIBUTING.md)
+file.
 
 ## License
 
-This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+This project is licensed under the MIT License - see the
+[LICENSE](https://github.com/jkobject/scdataloader/blob/main/LICENSE) file for
+details.
 
 ## Acknowledgments
 

scdataloader-2.0.8.dist-info/RECORD

@@ -0,0 +1,15 @@
+scdataloader/__init__.py,sha256=Z5HURehoWw1GrecImmTXIkv4ih8Q5RxNQWPm8zjjXOA,226
+scdataloader/__main__.py,sha256=xPOtrEpQQQZUGTnm8KTvsQcA_jR45oMG_VHqd0Ny7_M,8677
+scdataloader/base.py,sha256=M1gD59OffRdLOgS1vHKygOomUoAMuzjpRtAfM3SBKF8,338
+scdataloader/collator.py,sha256=VcFJcVAIeKvYkG1DPRXzoBaw2wQ6D_0lsv5Mcv-9USI,17419
+scdataloader/config.py,sha256=wGlCR3tWyEVa69ajovJKYc86CTCJR8e1xC7BTlUOJQE,34582
+scdataloader/data.py,sha256=tXvONJNgcdMQIRh2KlAq9KCsf-Sz2L4GUlcGyf1OMhw,25160
+scdataloader/datamodule.py,sha256=pFBGUOHl3ibi8QhiV8x5ukjzVjnJMsZWNw3Ekk3P83Y,43810
+scdataloader/mapped.py,sha256=h9YKQ8SG9tyZL8c6_Wu5Xov5ODGK6FzVuFopz58xwN4,29887
+scdataloader/preprocess.py,sha256=VFmyJluk4drR4fcH5qBAcJLf0cJg26ElA0HDuHOK68s,40730
+scdataloader/utils.py,sha256=B81iwnR6aJs9lzkOCSRF85RszAdwS-dvPZPXA7yoMg4,27734
+scdataloader-2.0.8.dist-info/METADATA,sha256=g7UW_1EeYX1P0LoJsL9MENZ9f0Q7JjLu8opWbV7CnDo,13448
+scdataloader-2.0.8.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+scdataloader-2.0.8.dist-info/entry_points.txt,sha256=VXAN1m_CjbdLJ6SKYR0sBLGDV4wvv31ri7fWWuwbpno,60
+scdataloader-2.0.8.dist-info/licenses/LICENSE,sha256=rGy_eYmnxtbOvKs7qt5V0czSWxJwgX_MlgMyTZwDHbc,1073
+scdataloader-2.0.8.dist-info/RECORD,,

scdataloader/data.json

@@ -1,384 +0,0 @@
-'lung': 42877488
-'blood': 34180713
-'brain': 29530595
-'colon': 25830811
-'unknown': 23810521
-'pancreas': 21597602
-'embryo': 16976623
-'skin': 12513695
-'liver': 10683313
-'breast': 10539762
-'marrow': 9543512
-'kidney': 8213043
-'heart': 4800567
-'immune system': 4687291
-'eye': 4677504
-# 'other (310 tissues)': 87200000
-'UBERON:0002106': 4559701
-'UBERON:0000029': 4314740
-'UBERON:0000945': 4244624
-'UBERON:0001295': 3485757
-'UBERON:0002049': 3350893
-'UBERON:0002108': 3226581
-'UBERON:0001255': 2961628
-'UBERON:0001434': 2823653
-'UBERON:0001004': 2588530
-'UBERON:0002037': 2101623
-'UBERON:0001015': 1920181
-'UBERON:0000995': 1864451
-'UBERON:0001013': 1853702
-'UBERON:0001017': 1818861
-'UBERON:0002240': 1704269
-'UBERON:0009834': 1631471
-'UBERON:0000002': 1596082
-'UBERON:0001893': 1565863
-'UBERON:0001851': 1513857
-'UBERON:0002771': 1317262
-'UBERON:0002367': 1301074
-'UBERON:0002369': 1279963
-'UBERON:0000956': 1252422
-'UBERON:0013682': 1195809
-'UBERON:0000160': 1156931
-'UBERON:0001987': 1127465
-'UBERON:0001043': 1015278
-'UBERON:0001032': 1011915
-'UBERON:0000992': 948464
-'UBERON:0000010': 897312
-'UBERON:0000473': 838235
-'UBERON:0002368': 814761
-'UBERON:0002084': 761793
-'UBERON:0001870': 730928
-'UBERON:0000344': 655220
-'UBERON:0001384': 625538
-'UBERON:0000966': 598023
-'UBERON:0002421': 578257
-'UBERON:0001225': 542410
-'UBERON:0000991': 507126
-'UBERON:0002116': 506392
-'UBERON:8440012': 494325
-'UBERON:0001898': 483451
-'UBERON:0000990': 440483
-'UBERON:0002370': 405221
-'UBERON:0002436': 399661
-'UBERON:0001965': 387483
-'UBERON:0000006': 362898
-'UBERON:0001005': 358584
-'UBERON:0010225': 343320
-'UBERON:0002102': 335470
-'UBERON:0008946': 334444
-'UBERON:0000053': 310875
-'UBERON:0008933': 310653
-'UBERON:0001117': 308212
-'UBERON:0001007': 307511
-'UBERON:0000059': 288232
-'UBERON:0002080': 286423
-'UBERON:0002094': 284283
-'UBERON:0000362': 283305
-'UBERON:0002365': 282382
-'UBERON:0002103': 264447
-'UBERON:0001891': 249305
-'UBERON:0001894': 249065
-'UBERON:0000411': 236082
-'UBERON:0002728': 221808
-'UBERON:0000451': 219655
-'UBERON:0001161': 214938
-'UBERON:0000030': 207230
-'UBERON:0009835': 206197
-'UBERON:0000988': 204168
-'UBERON:0001707': 198868
-'UBERON:0016538': 192147
-'UBERON:0002450': 189973
-'UBERON:0016540': 187526
-'UBERON:0000977': 185185
-'UBERON:0001913': 183332
-'UBERON:0001786': 179309
-'UBERON:0034751': 145757
-'UBERON:0001040': 144260
-'UBERON:0016530': 141537
-'UBERON:0001238': 136529
-'UBERON:0003889': 132985
-'UBERON:0000453': 125672
-'UBERON:0001723': 125523
-'UBERON:0002098': 120306
-'UBERON:0016525': 118039
-'UBERON:0000004': 114936
-'UBERON:0002686': 110752
-'UBERON:0022352': 110671
-'UBERON:0002351': 107573
-'UBERON:0001828': 105079
-'UBERON:0001003': 104237
-'UBERON:0002067': 100247
-'UBERON:0002190': 99711
-'UBERON:0005290': 99110
-'UBERON:0002811': 98536
-'UBERON:0001871': 97537
-'UBERON:0003688': 92733
-'UBERON:0010410': 91248
-'UBERON:0000403': 90975
-'UBERON:0000175': 90741
-'UBERON:0001976': 87947
-'UBERON:0002822': 87214
-'UBERON:0001890': 86604
-'UBERON:0014454': 86134
-'UBERON:0002810': 85525
-'UBERON:0002079': 82676
-'UBERON:0010414': 80085
-'UBERON:0003126': 79986
-'UBERON:0003027': 75807
-'UBERON:0008345': 73634
-'UBERON:0002352': 73045
-'UBERON:8410025': 72957
-'UBERON:0001393': 72549
-'UBERON:0010412': 71752
-'UBERON:0001159': 69025
-'UBERON:0014918': 65710
-'UBERON:0002078': 64486
-'UBERON:0007650': 64093
-'UBERON:0002808': 63227
-'UBERON:0007644': 62647
-'UBERON:8410010': 61264
-'UBERON:0001157': 60907
-'UBERON:0002185': 59377
-'UBERON:0002114': 59363
-'UBERON:0000916': 59001
-'UBERON:0014455': 58536
-'UBERON:0002661': 58226
-'UBERON:0001873': 57571
-'UBERON:0001769': 57422
-'UBERON:0008953': 56919
-'UBERON:0002372': 56899
-'UBERON:0002509': 55694
-'UBERON:0000397': 55666
-'UBERON:0001156': 54735
-'UBERON:0023787': 54666
-'UBERON:0002299': 54085
-'UBERON:0034893': 53956
-'UBERON:0001872': 53269
-'UBERON:0007177': 49990
-'UBERON:0004026': 48185
-'UBERON:0012648': 48068
-'UBERON:0001630': 47291
-'UBERON:0002803': 47176
-'UBERON:0016632': 45130
-'UBERON:0008803': 43943
-'UBERON:0001049': 43485
-'UBERON:0016475': 42323
-'UBERON:0002363': 42319
-'UBERON:0001874': 41277
-'UBERON:0000964': 40990
-'UBERON:0011189': 40231
-'UBERON:0036288': 36574
-'UBERON:0008954': 35284
-'UBERON:0018131': 34687
-'UBERON:0004648': 34173
-'UBERON:0034891': 34153
-'UBERON:0001775': 34132
-'UBERON:0018707': 33610
-'UBERON:0003661': 32722
-'UBERON:0003403': 32138
-'UBERON:0035328': 31696
-'UBERON:0001728': 31325
-'UBERON:0001388': 30877
-'UBERON:0008952': 29895
-'UBERON:0000080': 29606
-'UBERON:0004024': 29064
-'UBERON:0035886': 28873
-'UBERON:0004023': 28857
-'UBERON:0013473': 28621
-'UBERON:0018105': 28367
-'UBERON:0005969': 27736
-'UBERON:0012168': 27154
-'UBERON:0001886': 27092
-'UBERON:0000400': 27087
-'UBERON:0001911': 26952
-'UBERON:0000088': 26853
-'UBERON:0001153': 25865
-'UBERON:0001471': 24982
-'UBERON:0001085': 24807
-'UBERON:0000057': 24700
-'UBERON:0006761': 24573
-'UBERON:0002809': 24445
-'UBERON:0001158': 23887
-'UBERON:0008972': 23110
-'UBERON:0002807': 22796
-'UBERON:0010506': 22652
-'UBERON:0001459': 21633
-'UBERON:8410000': 21592
-'UBERON:0001831': 21003
-'UBERON:0003544': 20212
-'UBERON:0002110': 19880
-'UBERON:0014614': 19650
-'UBERON:8300000': 19408
-'UBERON:0035895': 18814
-'UBERON:0035213': 18775
-'UBERON:0001162': 18404
-'UBERON:0000056': 18354
-'UBERON:0001228': 17958
-'UBERON:0008971': 17831
-'UBERON:0013756': 17625
-'UBERON:0001052': 16913
-'UBERON:0012474': 16607
-'UBERON:0039167': 16527
-'UBERON:0002317': 15963
-'UBERON:0002115': 15762
-'UBERON:0014648': 15580
-'UBERON:8480028': 15307
-'UBERON:0000014': 15215
-'UBERON:0002489': 15127
-'UBERON:0001836': 14502
-'UBERON:0005343': 14336
-'UBERON:8410026': 14090
-'UBERON:0002132': 13953
-'UBERON:0000965': 13900
-'UBERON:0010415': 12330
-'UBERON:0000017': 11977
-'UBERON:0018303': 11937
-'UBERON:0002382': 11898
-'UBERON:0002046': 11840
-'UBERON:0001087': 11702
-'UBERON:0009958': 11377
-'UBERON:0005616': 11243
-'UBERON:8480009': 10533
-'UBERON:0013535': 9915
-'UBERON:0007106': 9898
-'UBERON:0001513': 9887
-'UBERON:0015790': 9816
-'UBERON:0001068': 9773
-'UBERON:0035894': 9667
-'UBERON:0015476': 9656
-'UBERON:0001637': 9652
-'UBERON:0002129': 9649
-'UBERON:0010033': 9467
-'UBERON:0000947': 9290
-'UBERON:0001511': 9288
-'UBERON:0004946': 9195
-'UBERON:0016435': 9097
-'UBERON:0002420': 9000
-'UBERON:0001868': 8799
-'UBERON:0002021': 8799
-'UBERON:0001542': 8683
-'UBERON:0002081': 8279
-'UBERON:0004070': 8033
-'UBERON:0008612': 7825
-'UBERON:0001901': 7228
-'UBERON:0004929': 7133
-'UBERON:0003528': 6670
-'UBERON:0002427': 6529
-'UBERON:0004025': 6448
-'UBERON:0009472': 6348
-'UBERON:0002756': 6279
-'UBERON:0001832': 6196
-'UBERON:0002378': 6142
-'UBERON:0004167': 5874
-'UBERON:0002228': 5725
-'UBERON:0003968': 5625
-'UBERON:0001154': 5515
-'UBERON:0001046': 5420
-'UBERON:0010032': 5367
-'UBERON:0004339': 4969
-'UBERON:0002385': 4881
-'UBERON:0001621': 4867
-'UBERON:0001416': 4808
-'UBERON:0001638': 4395
-'UBERON:0002429': 4355
-'UBERON:0001165': 4028
-'UBERON:0008989': 3997
-'UBERON:0001902': 3883
-'UBERON:0003532': 3443
-'UBERON:0003428': 3406
-'UBERON:0002082': 3226
-'UBERON:0001296': 3025
-'UBERON:0015143': 3014
-'UBERON:0000074': 3011
-'UBERON:0002245': 2971
-'UBERON:0001293': 2693
-'UBERON:0007625': 2348
-'UBERON:0003547': 2344
-'UBERON:0022277': 2333
-'UBERON:0001554': 2272
-'UBERON:0001348': 2223
-'UBERON:0005406': 2121
-'UBERON:0001811': 2084
-'UBERON:0013531': 2055
-'UBERON:0008934': 1866
-'UBERON:0001103': 1858
-'UBERON:0005636': 1651
-'UBERON:0007225': 1594
-'UBERON:0007224': 1564
-'UBERON:0000016': 1520
-'UBERON:8440075': 1482
-'UBERON:0004264': 1475
-'UBERON:0001773': 1431
-'UBERON:0013706': 1150
-'UBERON:0023852': 1143
-'UBERON:0001294': 849
-'UBERON:0001134': 835
-'UBERON:0003902': 675
-'UBERON:0001224': 569
-'UBERON:0005564': 399
-'UBERON:0001817': 248
-'UBERON:0002802': 163
-'UBERON:0003072': 146
-'UBERON:0000926': 139
-'UBERON:0000416': 82
-'UBERON:0003517': 48
-'UBERON:0001483': 37
-'UBERON:1000021': 37
-'UBERON:0002023': 1
-
-
-
-human: 230822337
-mouse: 102753838
-# other 14070000
-macaque: 3161179
-zebrafish: 3117237
-pig: 1641179
-thale cress: 1564711
-drosophila: 1564460
-chicken: 606680
-nake mole rat: 441042
-rabbit: 417091
-cow: 390675
-corn: 336166
-chimpanzee: 293472
-c. elegans: 251759
-sheep: 177871
-marmoset: 115584
-
-10x 3': 146909525
-10x 3' v2: 12021763
-10x 3' v3: 121241920
-# 10x 3': 280173208
-10x 5' v1: 4716686
-10x 5' v2: 3104399
-10x 5': 28919386
-# 10x 5': 36740471
-10x multiome: 6942314
-10x (vdj): 1620181
-10x (CITE): 1580477
-# 10x multiome: 10142972
-sciRNA-seq: 14924076
-slide-seq: 1867286
-scalebio: 685024
-microwell: 599459
-sciPlex: 581480
-drop-seq: 517799
-# other (17 assays): 1423506
-EFO:0010961: 286087
-EFO:0008931: 192101
-EFO:0700003: 146278
-EFO:0700010: 133430
-EFO:0700016: 128855
-EFO:0030007: 105584
-EFO:0008919: 87181
-EFO:0009901: 76022
-EFO:0008796: 68645
-EFO:0009919: 68544
-EFO:0700011: 58981
-EFO:0030019: 31775
-EFO:0008780: 25652
-EFO:0010010: 5231
-EFO:0008953: 4693
-EFO:0008720: 2768
-EFO:0008930: 1679

scdataloader-2.0.6.dist-info/RECORD

@@ -1,16 +0,0 @@
-scdataloader/__init__.py,sha256=Z5HURehoWw1GrecImmTXIkv4ih8Q5RxNQWPm8zjjXOA,226
-scdataloader/__main__.py,sha256=xPOtrEpQQQZUGTnm8KTvsQcA_jR45oMG_VHqd0Ny7_M,8677
-scdataloader/base.py,sha256=M1gD59OffRdLOgS1vHKygOomUoAMuzjpRtAfM3SBKF8,338
-scdataloader/collator.py,sha256=VcFJcVAIeKvYkG1DPRXzoBaw2wQ6D_0lsv5Mcv-9USI,17419
-scdataloader/config.py,sha256=wGlCR3tWyEVa69ajovJKYc86CTCJR8e1xC7BTlUOJQE,34582
-scdataloader/data.json,sha256=Zb8c27yk3rwMgtAU8kkiWWAyUwYBrlCqKUyEtaAx9i8,8785
-scdataloader/data.py,sha256=fMW1OgllPCz87si3DpkzOSoqnufgKlh8aW5rEVmeC_c,25133
-scdataloader/datamodule.py,sha256=ojX0zr2cpGLoKGjWE1S_bHAEdwbFg0Ljl55hqTagW1k,43600
-scdataloader/mapped.py,sha256=h9YKQ8SG9tyZL8c6_Wu5Xov5ODGK6FzVuFopz58xwN4,29887
-scdataloader/preprocess.py,sha256=oAGMilgdIgggyp9B9c9627kdo6SCco2tnFhhIHY4-yc,39642
-scdataloader/utils.py,sha256=2zIgmQHPVKHOFWqLX56Ihqtqci3_rOfCcOs642CPnX4,27183
-scdataloader-2.0.6.dist-info/METADATA,sha256=lnOF9PLih91AxcSI3L2OsD-0FH2kh3Qt2G7p6h3JESk,10314
-scdataloader-2.0.6.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-scdataloader-2.0.6.dist-info/entry_points.txt,sha256=VXAN1m_CjbdLJ6SKYR0sBLGDV4wvv31ri7fWWuwbpno,60
-scdataloader-2.0.6.dist-info/licenses/LICENSE,sha256=rGy_eYmnxtbOvKs7qt5V0czSWxJwgX_MlgMyTZwDHbc,1073
-scdataloader-2.0.6.dist-info/RECORD,,