gsMap 1.73.4__tar.gz → 1.73.5__tar.gz

{gsmap-1.73.4 → gsmap-1.73.5}/.pre-commit-config.yaml

@@ -38,7 +38,7 @@ repos:
           )$
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.7
+    rev: v0.11.8
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{gsmap-1.73.4 → gsmap-1.73.5}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: gsMap
-Version: 1.73.4
-Summary: Genetics-informed pathogenic spatial mapping
+Version: 1.73.5
+Summary: Genetically informed spatial mapping of cells for complex traits
 Author-email: liyang <songliyang@westlake.edu.cn>, wenhao <chenwenhao@westlake.edu.cn>
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown

gsmap-1.73.5/src/gsMap/__init__.py

@@ -0,0 +1,5 @@
+"""
+Genetically informed spatial mapping of cells for complex traits
+"""
+
+__version__ = "1.73.5"

{gsmap-1.73.4 → gsmap-1.73.5}/src/gsMap/utils/generate_r2_matrix.py

@@ -94,26 +94,26 @@ class PlinkBEDFile:
         # Filter out invalid SNPs
         valid_mask = self.all_snp_info["valid_snp"]
         if num_invalid := np.sum(~valid_mask):
-            logger.warning(f"Filtering out {num_invalid} bad quality SNPs")
+            logger.warning(
+                f"Filtering out {num_invalid} bad quality SNPs: {self.bim_df.loc[~valid_mask, 'SNP'].tolist()}"
+            )
         else:
             logger.info("All SNPs passed the basic quality check")
 
-        # Only keep valid SNPs
-        self.kept_snps = np.arange(self.m_original)[valid_mask]
-
-        # Update bim_df to only include valid SNPs and reset index
-        self.bim_df = self.bim_df.loc[valid_mask].reset_index(drop=True)
-
         # Create new genotype data with only the valid SNPs
         new_geno = ba.bitarray()
-        for j in self.kept_snps:
+        for j in np.arange(self.m_original)[valid_mask]:
             new_geno += self.geno_original[
                 2 * self.nru_original * j : 2 * self.nru_original * (j + 1)
             ]
 
         # Update original data to only include valid SNPs
         self.geno_original = new_geno
-        self.m_original = len(self.kept_snps)
+
+        # Only keep valid SNPs
+        self.bim_df = self.bim_df.loc[valid_mask].reset_index(drop=True)
+        self.m_original = len(self.bim_df)
+        self.kept_snps = np.arange(self.m_original)
 
         # Initialize current state variables
         self._currentSNP = 0
@@ -292,8 +292,8 @@ class PlinkBEDFile:
 
         # Apply MAF filter using pre-calculated values
         if mafMin is not None and mafMin > 0:
-            maf_values = np.minimum(self.all_snp_info["freq"], 1 - self.all_snp_info["freq"])
-            maf_mask = (maf_values > mafMin) & self.all_snp_info["valid_snp"]
+            # Remove the redundant valid_snp check since all SNPs are already valid
+            maf_mask = self.maf > mafMin
             kept_snps = kept_snps[maf_mask]
             logger.info(f"After MAF filtering (>{mafMin}), {len(kept_snps)} SNPs remain")
 
@@ -369,9 +369,7 @@ class PlinkBEDFile:
         list
             List of SNP IDs that pass the MAF threshold
         """
-        # Use the pre-calculated MAF values
-        maf_values = np.minimum(self.all_snp_info["freq"], 1 - self.all_snp_info["freq"])
-        maf_mask = (maf_values > mafMin) & self.all_snp_info["valid_snp"]
+        maf_mask = self.maf > mafMin
 
         # Get SNP names from the BIM dataframe
         snp_pass_maf = self.bim_df.loc[maf_mask, "SNP"].tolist()

gsmap-1.73.4/src/gsMap/__init__.py

@@ -1,5 +0,0 @@
-"""
-Genetics-informed pathogenic spatial mapping
-"""
-
-__version__ = "1.73.4"