genal-python 1.4.9__tar.gz → 1.5.0__tar.gz

{genal_python-1.4.9 → genal_python-1.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: genal-python
-Version: 1.4.9
+Version: 1.5.0
 Summary: A python toolkit for polygenic risk scoring and mendelian randomization.
 Author-email: Cyprien Rivier <riviercyprien@gmail.com>
 Requires-Python: >=3.8

{genal_python-1.4.9 → genal_python-1.5.0}/docs/requirements.txt

@@ -1,7 +1,7 @@
 sphinx
 sphinx_rtd_theme
 myst-parser
-aiohttp==3.9.5
+aiohttp>=3.13.3
 nest_asyncio==1.5.5
 numpy>=1.24.4,<2.0
 pandas>=2.0.3

{genal_python-1.4.9 → genal_python-1.5.0}/genal/Geno.py

@@ -92,6 +92,7 @@ class Geno:
         P="P",
         EAF="EAF",
         keep_columns=True,
+        F="F",
     ):
         """
         Initializes the Geno object used to store and transform Single Nucleotide Polymorphisms (SNP) data.
@@ -108,6 +109,7 @@ class Geno:
             P (str, optional): Column name for p-value. Defaults to "P".
             EAF (str, optional): Column name for effect allele frequency. Defaults to "EAF".
             keep_columns (bool, optional): Determines if non-main columns should be kept. Defaults to True.
+            F (str, optional): Column name for F-statistic. Defaults to "F".
 
         Attributes:
             name (str): Randomly generated ID for the Geno object.
@@ -136,7 +138,7 @@ class Geno:
 
         # Standardize column names based on provided parameters +/- delete other columns
         data = adjust_column_names(
-            data, CHR, POS, SNP, EA, NEA, BETA, SE, P, EAF, keep_columns
+            data, CHR, POS, SNP, EA, NEA, BETA, SE, P, EAF, keep_columns, F
         )
 
         # Set object attributes

{genal_python-1.4.9 → genal_python-1.5.0}/genal/__init__.py

@@ -5,7 +5,7 @@ from .geno_tools import Combine_Geno
 from .genes import filter_by_gene_func
 from .constants import CONFIG_DIR
 
-__version__ = "1.4.9"
+__version__ = "1.5.0"
 
 config_path = os.path.join(CONFIG_DIR, "config.json")
 

{genal_python-1.4.9 → genal_python-1.5.0}/genal/geno_tools.py

@@ -141,7 +141,6 @@ def fill_fstatistic(data, overwrite=False):
     # Primary route: FSTAT = (BETA / SE)² when BETA and SE are available (SE=0 produces inf)
     beta_se_computable = pd.Series([False] * nrows, index=data.index)
     if "BETA" in data.columns and "SE" in data.columns:
-        method = "BETA/SE"
         beta_se_computable = (
             rows_to_compute & 
             data["BETA"].notna() & 
@@ -157,7 +156,6 @@ def fill_fstatistic(data, overwrite=False):
     # Fallback route: FSTAT = χ²_isf(P, df=1) for remaining rows where P is present
     # Allow P=0 (produces inf for extremely significant variants)
     if "P" in data.columns:
-        method = "P-values"
         p_fallback_computable = (
             rows_to_compute & 
             ~beta_se_computable & 
@@ -174,19 +172,19 @@ def fill_fstatistic(data, overwrite=False):
     # Logging
     if column_created:
         print(
-            f"The FSTAT (F-statistic) column has been created using {method}. "
+            f"The FSTAT (F-statistic) column has been created. "
             f"{n_assigned}({n_assigned/nrows*100:.3f}%) values computed."
         )
     elif overwrite:
         print(
-            f"The FSTAT (F-statistic) column has been re-created using {method}. "
+            f"The FSTAT (F-statistic) column has been re-created. "
             f"{n_assigned}({n_assigned/nrows*100:.3f}%) values computed."
         )
     else:
         if n_assigned > 0:
             print(
                 f"The FSTAT (F-statistic) column: {n_assigned}({n_assigned/nrows*100:.3f}%)"
-                f"missing values have been filled using {method}."
+                f"missing values have been filled."
             )
     
     return
@@ -402,7 +400,7 @@ def check_int_column(data, int_col):
         )
     return
 
-def adjust_column_names(data, CHR, POS, SNP, EA, NEA, BETA, SE, P, EAF, keep_columns):
+def adjust_column_names(data, CHR, POS, SNP, EA, NEA, BETA, SE, P, EAF, keep_columns, F):
     """
     Rename columns to the standard names making sure that there are no duplicated names.
     Delete other columns if keep_columns=False, keep them if True.
@@ -422,6 +420,7 @@ def adjust_column_names(data, CHR, POS, SNP, EA, NEA, BETA, SE, P, EAF, keep_col
         SE: "SE",
         P: "P",
         EAF: "EAF",
+        F: "F",
     }
     for key, value in rename_dict.items():
         if key != value and key not in data.columns:

{genal_python-1.4.9 → genal_python-1.5.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "flit_core.buildapi"
 
 [project]
 name = "genal-python"  # Updated name for PyPI
-version = "1.4.9"
+version = "1.5.0"
 authors = [{name = "Cyprien Rivier", email = "riviercyprien@gmail.com"}]
 description = "A python toolkit for polygenic risk scoring and mendelian randomization."
 readme = "README.md"