genal-python 1.2.2__tar.gz → 1.2.4__tar.gz

{genal_python-1.2.2 → genal_python-1.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: genal-python
-Version: 1.2.2
+Version: 1.2.4
 Summary: A python toolkit for polygenic risk scoring and mendelian randomization.
 Author-email: Cyprien Rivier <riviercyprien@gmail.com>
 Requires-Python: >=3.8

{genal_python-1.2.2 → genal_python-1.2.4}/genal/__init__.py

@@ -4,7 +4,7 @@ from .tools import default_config, write_config, set_plink, install_plink, delet
 from .geno_tools import Combine_Geno
 from .constants import CONFIG_DIR
 
-__version__ = "1.2.2"
+__version__ = "1.2.4"
 
 config_path = os.path.join(CONFIG_DIR, "config.json")
 

{genal_python-1.2.2 → genal_python-1.2.4}/genal/association.py

@@ -78,6 +78,7 @@ def _run_plink2_assoc_test(
         "--glm", 
         *(["allow-no-covars"] if len(covar_list) == 0 else []),
         "no-x-sex",
+        "--no-input-missing-phenotype",
         "--pheno-name", "PHENO1"
     ]
     
@@ -141,11 +142,13 @@ def _prepare_psam_file(genetic_path, data_pheno, pheno_type, standardize):
     # Read the PSAM file
     psam = pd.read_csv(genetic_path + ".psam", delimiter="\t")
     
-    # Extract relevant phenotype data with both FID and IID
-    data_pheno_trait = data_pheno[["FID", "IID", "PHENO"]].rename(columns={"FID": "#FID", "PHENO": "PHENO1"}).copy()
-    
-    # Merge phenotype data with the PSAM dataframe
-    psam = psam.merge(data_pheno_trait, how="left", on=["#FID", "IID"], indicator=True)
+    # Merge phenotype data with the PSAM dataframe depending on column present
+    if "#FID" in psam.columns:
+        data_pheno_trait = data_pheno[["FID", "IID", "PHENO"]].rename(columns={"FID": "#FID", "PHENO": "PHENO1"}).copy()
+        psam = psam.merge(data_pheno_trait, how="left", on=["#FID", "IID"], indicator=True)
+    else:
+        data_pheno_trait = data_pheno[["IID", "PHENO"]].rename(columns={"IID": "#IID", "PHENO": "PHENO1"}).copy()
+        psam = psam.merge(data_pheno_trait, how="left", on=["#IID"], indicator=True)
     
     # Verify that the merge was successful
     if (psam["_merge"] == "both").sum() == 0:
@@ -173,6 +176,9 @@ def _prepare_psam_file(genetic_path, data_pheno, pheno_type, standardize):
         psam["PHENO1"] = (psam["PHENO1"] - psam["PHENO1"].mean(skipna=True)) / psam["PHENO1"].std(skipna=True)
         psam["PHENO1"] = psam["PHENO1"].fillna('NA')
 
+    # Make sure the SEX column is not empty without modifying existing values
+    psam["SEX"] = psam["SEX"].replace('', 'NA').fillna('NA')
+
     psam.to_csv(genetic_path + ".psam", sep="\t", index=False)
     return psam
 

{genal_python-1.2.2 → genal_python-1.2.4}/genal/geno_tools.py

@@ -242,10 +242,7 @@ def check_int_column(data, int_col):
     """Set the type of the int_col column to Int64 and non-numeric values to NA."""
     nrows = data.shape[0]
     # Remove any non-digit characters, convert to numeric, setting non-numeric to NaN
-    data[int_col] = pd.to_numeric(
-        data[int_col].astype(str).str.replace(r'(\d+)', '', regex=True),
-        errors='coerce'
-    )
+    data[int_col] = pd.to_numeric(data[int_col].astype(str).str.extract('(\d+)', expand=False), errors='coerce')
     # Convert to Int64 which handles NaN values, using round() first to handle floats
     data[int_col] = data[int_col].round().astype('Int64')
     n_nan = data[int_col].isna().sum()

{genal_python-1.2.2 → genal_python-1.2.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "flit_core.buildapi"
 
 [project]
 name = "genal-python"  # Updated name for PyPI
-version = "1.2.2"
+version = "1.2.4"
 authors = [{name = "Cyprien Rivier", email = "riviercyprien@gmail.com"}]
 description = "A python toolkit for polygenic risk scoring and mendelian randomization."
 readme = "README.md"