genal-python 1.3.2__tar.gz → 1.3.4__tar.gz

{genal_python-1.3.2 → genal_python-1.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: genal-python
-Version: 1.3.2
+Version: 1.3.4
 Summary: A python toolkit for polygenic risk scoring and mendelian randomization.
 Author-email: Cyprien Rivier <riviercyprien@gmail.com>
 Requires-Python: >=3.8

{genal_python-1.3.2 → genal_python-1.3.4}/genal/Geno.py

@@ -655,7 +655,8 @@ class Geno:
                     kb=kb,
                     r2=r2,
                     window_snps=window_snps,
-                    threads=self.cpus
+                    threads=self.cpus,
+                    name=self.name
                 )
                 # Apply proxies if found
                 if isinstance(ld, pd.DataFrame) and not ld.empty:

{genal_python-1.3.2 → genal_python-1.3.4}/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, filter_by_gene_func
 from .constants import CONFIG_DIR
 
-__version__ = "1.3.2"
+__version__ = "1.3.4"
 
 config_path = os.path.join(CONFIG_DIR, "config.json")
 

{genal_python-1.3.2 → genal_python-1.3.4}/genal/clump.py

@@ -1,5 +1,4 @@
 import os
-import subprocess
 import pandas as pd
 import uuid
 import re
@@ -13,7 +12,7 @@ def clump_data_plink2(
     r2=0.01,
     p1=5e-8,
     p2=0.01,
-    name="",
+    name=None,
     ram=10000,
 ):
     """
@@ -37,7 +36,7 @@ def clump_data_plink2(
     """
 
     # Create unique ID for the name if none is passed
-    if not name:
+    if name is None:
         name = str(uuid.uuid4())[:8]
 
     # Save the relevant data columns to a temporary file

{genal_python-1.3.2 → genal_python-1.3.4}/genal/extract_prs.py

@@ -1,5 +1,5 @@
 import pandas as pd
-import os, subprocess, re
+import os, subprocess, re, uuid
 from functools import partial
 from concurrent.futures import ProcessPoolExecutor
 
@@ -10,13 +10,17 @@ from .tools import check_bfiles, check_pfiles, setup_genetic_path, get_plink_pat
 ### PRS functions
 ### ____________________
 
-def prs_func(data, weighted=True, path=None, ram=10000, name=""):
+def prs_func(data, weighted=True, path=None, ram=10000, name=None):
     """
     Compute a PRS (Polygenic Risk Score) using provided SNP-level data. Corresponds to the :meth:`Geno.prs` method
     """
     # Get path and filetype
     path, filetype = setup_genetic_path(path)
 
+    # Generate a default name if none is provided
+    if name is None:
+        name = str(uuid.uuid4())[:8]
+
     # Call extract_snps
     extracted_path = extract_snps_func(data.SNP, name, path)
 
@@ -94,7 +98,7 @@ def prs_func(data, weighted=True, path=None, ram=10000, name=""):
 
 # We are currently excluding all multiallelic variants by forcing first on all duplicates. 
 # Could be improved by keeping the relevant version of the multiallelic SNPs based on allele matching
-def extract_snps_func(snp_list, name, path=None):
+def extract_snps_func(snp_list, name=None, path=None):
     """
     Extracts a list of SNPs from the given path. This function corresponds to the following Geno method: :meth:`Geno.extract_snps`.
 
@@ -114,6 +118,10 @@ def extract_snps_func(snp_list, name, path=None):
         print("The provided SNP list is empty.")
         return "FAILED"
     
+    # Generate a default name if none is provided
+    if name is None:
+        name = str(uuid.uuid4())[:8]
+
     # Get path and filetype
     path, filetype = setup_genetic_path(path)
 

{genal_python-1.3.2 → genal_python-1.3.4}/genal/geno_tools.py

@@ -406,7 +406,7 @@ def save_data(data, name, path="", fmt="h5", sep="\t", header=True):
     - data (pd.DataFrame): The data to be saved.
     - name (str): The name of the file without extension.
     - path (str, optional): Directory path for saving. Default is the current directory.
-    - fmt (str, optional): Format for the file, e.g., "h5", "csv", "txt", "vcf", "vcf.gz". Default is "h5".
+    - fmt (str, optional): Format for the file, e.g., "h5", "csv", "txt". Default is "h5".
     - sep (str, optional): Delimiter for csv or txt files. Default is tab.
     - header (bool, optional): Whether to include header in csv or txt files. Default is True.
 
@@ -417,7 +417,7 @@ def save_data(data, name, path="", fmt="h5", sep="\t", header=True):
     - ValueError: If the provided format is not recognized.
     """
     if path:
-        path_name = f"{path}/{name}.{fmt}"
+        path_name = os.path.join(path, f"{name}.{fmt}")
     else:
         path_name = f"{name}.{fmt}"
 
@@ -430,13 +430,9 @@ def save_data(data, name, path="", fmt="h5", sep="\t", header=True):
     elif fmt in ["csv", "txt"]:
         data.to_csv(path_name, sep=sep, header=header, index=False)
 
-    elif fmt in ["vcf", "vcf.gz"]:
-        # to do
-        return
-
     else:
         raise ValueError(
-            "The fmt argument takes value in (h5 (default), csv, txt, vcf, vcf.gz)."
+            "The fmt argument takes value in (h5 (default), csv, txt)."
         )
 
     print(f"Data saved to {path_name}")

{genal_python-1.3.2 → genal_python-1.3.4}/genal/lift.py

@@ -4,7 +4,7 @@ import numpy as np
 import wget
 import gzip
 import shutil
-from tqdm import tqdm
+import uuid
 import pandas as pd
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
@@ -44,6 +44,9 @@ def lift_data(
     Notes:
         Function for the :meth:`Geno.lift` method.
     """
+    # Generate a default name if none is provided
+    if name is None:
+        name = str(uuid.uuid4())[:8]
 
     # Prepare chain file and get its path
     chain_path = prepare_chain_file(chain_file, start, end)

{genal_python-1.3.2 → genal_python-1.3.4}/genal/proxy.py

@@ -3,6 +3,7 @@ import numpy as np
 import os
 import subprocess
 import re
+import uuid
 
 from .tools import get_reference_panel_path, get_plink_path, run_plink_command
 
@@ -196,7 +197,8 @@ def find_proxies(
     kb=5000,
     r2=0.8,
     window_snps=1000000,
-    threads=1
+    threads=1,
+    name=None
 ):
     """
     Given a list of SNPs, return a table of proxies using PLINK 2.0.
@@ -219,6 +221,10 @@ def find_proxies(
     # Ensure tmp_GENAL directory exists
     os.makedirs(f"tmp_GENAL/", exist_ok=True)
 
+    # Generate a default name if none is provided
+    if name is None:
+        name = str(uuid.uuid4())[:8]
+
     # Convert snp_list to numpy array
     snp_list = np.array(list(snp_list))
 
@@ -227,13 +233,13 @@ def find_proxies(
         extract_arg = ""
     else:
         print("Searching proxies in the provided searchspace.")
-        with open("tmp_GENAL/searchspace.txt", "w") as file:
+        with open(f"tmp_GENAL/{name}_searchspace.txt", "w") as file:
             for s in searchspace + snp_list:
                 file.write(str(s) + "\n")
-        extract_arg = "--extract tmp_GENAL/searchspace.txt"
+        extract_arg = "--extract tmp_GENAL/{name}_searchspace.txt"
 
     # Save snp_list to a file
-    np.savetxt("tmp_GENAL/snps_to_proxy.txt", snp_list, fmt="%s", delimiter=" ")
+    np.savetxt(f"tmp_GENAL/{name}_snps_to_proxy.txt", snp_list, fmt="%s", delimiter=" ")
 
     # Get reference panel path and type
     ref_path, filetype = get_reference_panel_path(reference_panel)
@@ -256,18 +262,18 @@ def find_proxies(
     command = (
         f"{base_cmd} {extract_arg} "
         f"--r-unphased 'cols=chrom,pos,id,maj,nonmaj,freq' "
-        f"--ld-snp-list tmp_GENAL/snps_to_proxy.txt "
+        f"--ld-snp-list tmp_GENAL/{name}_snps_to_proxy.txt "
         f"--ld-window-kb {kb} "
         f"--ld-window-r2 {r2} "
         f"--ld-window {window_snps} "
         f"--threads {threads} "
-        f"--out tmp_GENAL/proxy.targets"
+        f"--out tmp_GENAL/{name}_proxy.targets"
     )
     
     run_plink_command(command)
 
     # Read log file to return amount of SNPs to be proxied present in the ref panel
-    log_path = os.path.join("tmp_GENAL", "proxy.targets.log")
+    log_path = os.path.join("tmp_GENAL", f"{name}_proxy.targets.log")
     log_content = open(log_path).read()
     match = re.search(r'(\d+) variant[s] remaining', log_content)
     if match:
@@ -280,7 +286,7 @@ def find_proxies(
 
     # Read and process the output
     try:
-        ld = pd.read_csv("tmp_GENAL/proxy.targets.vcor", sep="\s+")
+        ld = pd.read_csv(f"tmp_GENAL/{name}_proxy.targets.vcor", sep="\s+")
     except FileNotFoundError:
         print("No proxies found that meet the specified criteria.")
         return None

{genal_python-1.3.2 → genal_python-1.3.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "flit_core.buildapi"
 
 [project]
 name = "genal-python"  # Updated name for PyPI
-version = "1.3.2"
+version = "1.3.4"
 authors = [{name = "Cyprien Rivier", email = "riviercyprien@gmail.com"}]
 description = "A python toolkit for polygenic risk scoring and mendelian randomization."
 readme = "README.md"