genal-python 1.2.6__tar.gz → 1.2.7__tar.gz

{genal_python-1.2.6 → genal_python-1.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: genal-python
-Version: 1.2.6
+Version: 1.2.7
 Summary: A python toolkit for polygenic risk scoring and mendelian randomization.
 Author-email: Cyprien Rivier <riviercyprien@gmail.com>
 Requires-Python: >=3.8

{genal_python-1.2.6 → genal_python-1.2.7}/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__ = "1.2.6"
+__version__ = "1.2.7"
 
 config_path = os.path.join(CONFIG_DIR, "config.json")
 

{genal_python-1.2.6 → genal_python-1.2.7}/genal/extract_prs.py

@@ -23,6 +23,11 @@ def prs_func(data, weighted=True, path=None, ram=10000, name=""):
     if extracted_path == "FAILED":
         raise ValueError("No SNPs were extracted from the genetic data and the PRS can't be computed.")
 
+    # Additional check to ensure there are no duplicates in the data (need to think more about this, should be done upstream)
+    data.drop_duplicates(subset=["SNP"], keep="first", inplace=True)
+    if "CHR" in data.columns and "POS" in data.columns:
+        data.drop_duplicates(subset=["CHR", "POS"], keep="first", inplace=True)
+    
     # Write processed data to file and run plink on it
     data = data[["SNP", "EA", "BETA"]]
     data_path = os.path.join("tmp_GENAL", f"{name}_to_prs.txt")

{genal_python-1.2.6 → genal_python-1.2.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "flit_core.buildapi"
 
 [project]
 name = "genal-python"  # Updated name for PyPI
-version = "1.2.6"
+version = "1.2.7"
 authors = [{name = "Cyprien Rivier", email = "riviercyprien@gmail.com"}]
 description = "A python toolkit for polygenic risk scoring and mendelian randomization."
 readme = "README.md"