genal-python 1.2.4__tar.gz → 1.2.6__tar.gz

{genal_python-1.2.4 → genal_python-1.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: genal-python
-Version: 1.2.4
+Version: 1.2.6
 Summary: A python toolkit for polygenic risk scoring and mendelian randomization.
 Author-email: Cyprien Rivier <riviercyprien@gmail.com>
 Requires-Python: >=3.8

{genal_python-1.2.4 → genal_python-1.2.6}/genal/Geno.py

@@ -41,7 +41,8 @@ from .constants import STANDARD_COLUMNS, REF_PANEL_COLUMNS, CHECKS_DICT, MR_METH
 # Consider reference panels in build 38
 # Add proxying function (input is df + searchspace (list of SNP or path to .bim, can be separated by chromosomes) and returns proxied df)
 # Get proxies (simply return a list of proxies)
-# Multi-MR with python MR
+# Include proxying option to association_test
+# Multi-MR
 # Check stability with variants on sexual chromosomes
 
 
@@ -482,6 +483,8 @@ class Geno:
         # Extract the SNP list
         snp_list = self.data["SNP"]
 
+        # Renaming to avoid conflicts with previous extraction
+        self.name = str(uuid.uuid4())[:8]
         # Extract SNPs using the provided path and SNP list
         _ = extract_snps_func(snp_list, self.name, path)
 
@@ -638,6 +641,9 @@ class Geno:
                     if n_del > 0:
                         data_prs.drop(index=duplicate_indices, inplace=True)
                         print(f"After proxying, {n_del} SNPs had duplicated IDs and were removed.")
+        
+        # Renaming to avoid conflicts with previous extraction
+        self.name = str(uuid.uuid4())[:8]
         # Compute PRS
         prs_data = prs_func(data_prs, weighted, path, ram=self.ram, name=self.name)
 
@@ -729,6 +735,8 @@ class Geno:
         # Extract the SNP list
         snp_list = data["SNP"]
 
+        # Renaming to avoid conflicts with previous extraction
+        self.name = str(uuid.uuid4())[:8]
         # Extract SNPs using the provided path and SNP list
         path = extract_snps_func(snp_list, self.name, path)
         if path == "FAILED":

{genal_python-1.2.4 → genal_python-1.2.6}/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__ = "1.2.4"
+__version__ = "1.2.6"
 
 config_path = os.path.join(CONFIG_DIR, "config.json")
 

{genal_python-1.2.4 → genal_python-1.2.6}/genal/association.py

@@ -90,7 +90,27 @@ def _run_plink2_assoc_test(
 
     command.extend(["--out", output])
     
-    subprocess.run(command, capture_output=True, text=True, check=True)
+    try:
+        subprocess.run(command, capture_output=True, text=True, check=True)
+    except Exception as e:
+        #Handle the case where the association fails because of numerical instability in the covariates
+        if "scales vary too widely" in str(e):
+            print("The association test failed because of numerical instability in the covariates. Rescaling the covariates.")
+            command.extend(["--covar-variance-standardize"])
+            try:
+                subprocess.run(command, capture_output=True, text=True, check=True)
+            except Exception as e:
+                print(f"Error running PLINK command: {e}")
+                print(f"PLINK stdout: {e.stdout}")
+                print(f"PLINK stderr: {e.stderr}")
+                raise ValueError("PLINK command failed. Check the error messages above for details.")
+            
+        else:
+            print(f"Error running PLINK command: {e}")
+            print(f"PLINK stdout: {e.stdout}")
+            print(f"PLINK stderr: {e.stderr}")
+            raise ValueError("PLINK command failed. Check the error messages above for details.")
+    
     return output
 
 def _process_results_plink2(output, data, pheno_type):
@@ -113,7 +133,7 @@ def _process_results_plink2(output, data, pheno_type):
     
     # Merge results with the clumped data
     data = data.drop(axis=1, columns=["BETA", "SE", "P"], errors="ignore").merge(
-        assoc[["CHR","POS", "BETA", "A1", "P"]], how="inner", on=["CHR", "POS"]
+        assoc[["CHR","POS", "BETA", "SE", "A1", "P"]], how="inner", on=["CHR", "POS"]
     )
 
     # Adjust beta values based on allele match
@@ -309,7 +329,7 @@ def _standardize_column_names(data, PHENO, IID, FID):
     else:
         data["FID"] = data["IID"]
         print(
-            "The FID column was not provided. The IID column will be used as the FID column."
+            "The FID column was not provided. The FIDs are assumed to be the same as the IIDs."
         )
     
     return data

{genal_python-1.2.4 → genal_python-1.2.6}/genal/extract_prs.py

@@ -193,17 +193,17 @@ def create_bedlist(bedlist_path, output_name, not_found):
         not_found (List[int]): List of chromosome numbers for which no files were found.
     """
     with open(bedlist_path, "w+") as bedlist_file:
-        n_lines = 0
+        found = []
         for i in range(1, 23):
             if i in not_found:
                 print(f"bed/bim/fam or pgen/pvar/psam files not found for chr{i}.")
             elif check_pfiles(f"{output_name}_chr{i}"):
                 bedlist_file.write(f"{output_name}_chr{i}\n")
-                n_lines += 1
+                found.append(i)
                 print(f"SNPs extracted for chr{i}.")
             else:
                 print(f"No SNPs extracted for chr{i}.")
-    return n_lines
+    return found
 
 
 def extract_snps_from_split_data(name, path, output_path, snp_list_path, filetype):
@@ -225,11 +225,18 @@ def extract_snps_from_split_data(name, path, output_path, snp_list_path, filetyp
     # Merge extracted SNPs from each chromosome
     bedlist_name = f"{name}_bedlist.txt"
     bedlist_path = os.path.join("tmp_GENAL", bedlist_name)
-    n_lines = create_bedlist(
+    found = create_bedlist(
         bedlist_path, os.path.join("tmp_GENAL", f"{name}_extract"), not_found
     )
-    if n_lines == 0:
+    if len(found) == 0:
         raise Warning("No SNPs were extracted from any chromosome.")
+    
+    # If only one chromosome was extracted, no need to merge, simply rename the files
+    if len(found) == 1:
+        chr_path = os.path.join("tmp_GENAL", f"{name}_extract_chr{found[0]}")
+        for ext in [".pgen", ".pvar", ".psam", ".log"]:
+            os.rename(f"{chr_path}{ext}", f"{output_path}{ext}")
+        return None, bedlist_path
 
     print("Merging SNPs extracted from each chromosome...")
     merge_command = f"{get_plink_path()} --pmerge-list {bedlist_path} pfile --out {output_path}"
@@ -286,6 +293,9 @@ def report_snps_not_found(nrow, name):
 def handle_multiallelic_variants(name, merge_command, bedlist_path):
     """Handle multiallelic variants detected during merging."""
 
+    if merge_command is None:
+        return
+    
     def remove_multiallelic():
         missnp_path = os.path.join(
             "tmp_GENAL", f"{name}_allchr.vmiss"

{genal_python-1.2.4 → genal_python-1.2.6}/genal/lift.py

@@ -156,9 +156,13 @@ def lift_coordinates_liftover(data, object_id, chain_path, liftover_path):
     # Call the liftOver software
     command = f"{liftover_path} {to_lift_filename} \
     {chain_path} {lifted_filename} {unmapped_filename}"
-    output = subprocess.run(
-        command, shell=True, capture_output=True, text=True, check=True
-    )
+    try:
+        output = subprocess.run(
+            command, shell=True, capture_output=True, text=True, check=True
+        )
+    except Exception as e:
+        print(f"Error running liftOver: {e}")
+        raise ValueError("Error running liftOver. Check error message for more details.")
 
     ## Read the output, print the number of unlifted SNPs and remove them from the prelift data.
     df_post = pd.read_csv(lifted_filename, sep="\t", header=None)

{genal_python-1.2.4 → genal_python-1.2.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "flit_core.buildapi"
 
 [project]
 name = "genal-python"  # Updated name for PyPI
-version = "1.2.4"
+version = "1.2.6"
 authors = [{name = "Cyprien Rivier", email = "riviercyprien@gmail.com"}]
 description = "A python toolkit for polygenic risk scoring and mendelian randomization."
 readme = "README.md"