scanpex 0.3.2__tar.gz → 0.3.4__tar.gz

{scanpex-0.3.2 → scanpex-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scanpex
-Version: 0.3.2
+Version: 0.3.4
 Summary: ScanPy Extension and kwarg Preferences
 License-File: AUTHORS.rst
 License-File: LICENSE

{scanpex-0.3.2 → scanpex-0.3.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "scanpex"
-version = "0.3.2"
+version = "0.3.4"
 description = "ScanPy Extension and kwarg Preferences"
 authors = ["yo-aka-gene <yujiokano@keio.jp>"]
 readme = "README.md"

{scanpex-0.3.2 → scanpex-0.3.4}/src/scanpex/sq/__init__.py

@@ -1,8 +1,10 @@
+from ._ensembl_mapper import ensembl_mapper
 from ._gene_cache_mgr import GeneCacheManager
 from ._gene_query import gene_query
 from ._xor import xor
 
 __all__ = [
+    "ensembl_mapper",
     "gene_query",
     "GeneCacheManager",
     "xor",

scanpex-0.3.4/src/scanpex/sq/_ensembl_mapper.py

@@ -0,0 +1,63 @@
+from typing import List
+
+import pandas as pd
+
+
+def ensembl_mapper(
+    ensembl_list: List[str],
+    species: str = "human",
+) -> pd.DataFrame:
+    """Map a list of Ensembl gene IDs to their corresponding gene symbols.
+
+    This function queries the MyGene.info API to translate Ensembl IDs into
+    gene symbols. If a gene symbol cannot be found for a given ID, the original
+    Ensembl ID is retained in the 'symbol' column. Duplicate queries are dropped,
+    keeping only the first matched record.
+
+    Parameters
+    ----------
+    ensembl_list : List[str]
+        A list of Ensembl gene IDs to be mapped (e.g., ['ENSG00000139618']).
+    species : str, optional
+        The species name or taxonomy ID to restrict the query. Common values
+        include 'human' or 'mouse'. Default is 'human'.
+
+    Returns
+    -------
+    pd.DataFrame
+        A pandas DataFrame containing two columns:
+        - 'query': The original Ensembl ID.
+        - 'symbol': The mapped gene symbol (or the original ID if unmapped).
+
+    Raises
+    ------
+    ImportError
+        If the `mygene` package is not installed in the current environment.
+
+    Examples
+    --------
+    >>> ensembl_ids = ["ENSG00000139618", "ENSG00000157764", "INVALID_ID"]
+    >>> df = ensembl_mapper(ensembl_ids, species="human")
+    >>> print(df)
+                 query      symbol
+    0  ENSG00000139618       BRCA2
+    1  ENSG00000157764        BRAF
+    2       INVALID_ID  INVALID_ID
+    """
+    try:
+        import mygene
+    except ImportError:
+        raise ImportError(
+            "mygene is not installed. Please install it using `pip install mygene`."
+        )
+
+    mg = mygene.MyGeneInfo()
+    gene_symbols = mg.querymany(
+        ensembl_list,
+        scopes="ensembl.gene",
+        fields="symbol",
+        species=species,
+        as_dataframe=True,
+    ).reset_index()[["query", "symbol"]]
+    gene_symbols["symbol"] = gene_symbols["symbol"].fillna(gene_symbols["query"])
+    return gene_symbols.drop_duplicates(subset=["query"], keep="first")

{scanpex-0.3.2 → scanpex-0.3.4}/src/scanpex/tl/_degs.py

@@ -1,4 +1,4 @@
-import anndat as ad
+import anndata as ad
 import numpy as np