gsMap 1.73.1__tar.gz → 1.73.3__tar.gz

{gsmap-1.73.1 → gsmap-1.73.3}/.pre-commit-config.yaml

@@ -38,7 +38,7 @@ repos:
           )$
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.5
+    rev: v0.11.6
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{gsmap-1.73.1 → gsmap-1.73.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gsMap
-Version: 1.73.1
+Version: 1.73.3
 Summary: Genetics-informed pathogenic spatial mapping
 Author-email: liyang <songliyang@westlake.edu.cn>, wenhao <chenwenhao@westlake.edu.cn>
 Requires-Python: >=3.10

{gsmap-1.73.1 → gsmap-1.73.3}/src/gsMap/__init__.py

@@ -2,4 +2,4 @@
 Genetics-informed pathogenic spatial mapping
 """
 
-__version__ = "1.73.1"
+__version__ = "1.73.3"

{gsmap-1.73.1 → gsmap-1.73.3}/src/gsMap/diagnosis.py

@@ -51,8 +51,8 @@ def compute_gene_diagnostic_info(config: DiagnosisConfig):
     mk_score = mk_score.loc[trait_ldsc_result.index]
 
     # Filter out genes with no variation
-    non_zero_std_cols = mk_score.columns[mk_score.std() > 0]
-    mk_score = mk_score.loc[:, non_zero_std_cols]
+    has_variation = (~mk_score.eq(mk_score.iloc[0], axis=1)).any()
+    mk_score = mk_score.loc[:, has_variation]
 
     logger.info("Calculating correlation between gene marker scores and trait logp-values...")
     corr = mk_score.corrwith(trait_ldsc_result["logp"])
@@ -69,10 +69,6 @@ def compute_gene_diagnostic_info(config: DiagnosisConfig):
         }
     )
 
-    # Filter based on median GSS score
-    high_GSS_Gene_annotation_pair = high_GSS_Gene_annotation_pair[
-        high_GSS_Gene_annotation_pair["Median_GSS"] >= 1.0
-    ]
     high_GSS_Gene_annotation_pair = high_GSS_Gene_annotation_pair.merge(
         corr, left_on="Gene", right_index=True
     )
@@ -161,6 +157,20 @@ def generate_manhattan_plot(config: DiagnosisConfig):
         + gwas_data_to_plot["Annotation"].astype(str)
     )
 
+    # Verify data integrity
+    if gwas_data_with_gene_annotation_sort.empty:
+        logger.error("Filtered GWAS data is empty, cannot create Manhattan plot")
+        return
+
+    if len(gwas_data_to_plot) == 0:
+        logger.error("No SNPs passed filtering criteria for Manhattan plot")
+        return
+
+    # Log some diagnostic information
+    logger.info(f"Creating Manhattan plot with {len(gwas_data_to_plot)} SNPs")
+    logger.info(f"Columns available: {list(gwas_data_to_plot.columns)}")
+    logger.info(f"Chromosome column values: {gwas_data_to_plot['CHR'].unique()}")
+
     fig = ManhattanPlot(
         dataframe=gwas_data_to_plot,
         title="gsMap Diagnosis Manhattan Plot",

{gsmap-1.73.1 → gsmap-1.73.3}/src/gsMap/generate_ldscore.py

@@ -57,7 +57,8 @@ def load_gtf(
     gtf = gtf[gtf["Feature"] == "gene"]
 
     # Find common genes between GTF and marker scores
-    common_gene = np.intersect1d(mk_score.index, gtf.gene_name)
+    # common_gene = np.intersect1d(mk_score.index, gtf.gene_name)
+    common_gene = list(set(mk_score.index) & set(gtf.gene_name))
     logger.info(f"Found {len(common_gene)} common genes between GTF and marker scores")
 
     # Filter GTF and marker scores to common genes
@@ -69,6 +70,9 @@ def load_gtf(
 
     # Process the GTF (open window around gene coordinates)
     gtf_bed = gtf[["Chromosome", "Start", "End", "gene_name", "Strand"]].copy()
+    gtf_bed["Chromosome"] = gtf_bed["Chromosome"].apply(
+        lambda x: f"chr{x}" if not str(x).startswith("chr") else x
+    )
     gtf_bed.loc[:, "TSS"] = gtf_bed["Start"]
     gtf_bed.loc[:, "TED"] = gtf_bed["End"]
 
@@ -128,7 +132,7 @@ def load_bim(bfile_root: str, chrom: int) -> tuple[pd.DataFrame, pr.PyRanges]:
         - bim_pr is a PyRanges object with BIM data
     """
     bim_file = f"{bfile_root}.{chrom}.bim"
-    logger.debug(f"Loading BIM file: {bim_file}")
+    logger.info(f"Loading BIM file: {bim_file}")
 
     bim = pd.read_csv(bim_file, sep="\t", header=None)
     bim.columns = ["CHR", "SNP", "CM", "BP", "A1", "A2"]
@@ -311,6 +315,8 @@ def get_ldscore(
         bfile_chr_prefix=f"{bfile_root}.{chrom}", keep_snps=keep_snps_index
     )
 
+    annot_matrix = annot_matrix[geno_array.kept_snps, :]
+
     # Configure LD window based on specified unit
     if ld_unit == "SNP":
         max_dist = ld_wind

{gsmap-1.73.1 → gsmap-1.73.3}/src/gsMap/utils/manhattan_plot.py

@@ -308,13 +308,21 @@ class _ManhattanPlot:
         self.index = "INDEX"
         self.pos = "POSITION"
 
-        # Fixes the bug where one chromosome is missing by adding a sequential
-        # index column.
-        idx = 0
-        for i in self.data[chrm].unique():
-            idx = idx + 1
-            self.data.loc[self.data[chrm] == i, self.index] = int(idx)
-        # Set the type to be the same as provided for chrm column
+        self.data[self.index] = 0  # Initialize with zeros as default value
+
+        if not self.data.empty and len(self.data[chrm].unique()) > 0:
+            idx = 0
+            for i in self.data[chrm].unique():
+                idx = idx + 1
+                self.data.loc[self.data[chrm] == i, self.index] = int(idx)
+        else:
+            import logging
+
+            logger = logging.getLogger("gsMap.utils.manhattan_plot")
+            logger.warning(
+                "No chromosome data found or empty dataframe when creating Manhattan plot"
+            )
+
         self.data[self.index] = self.data[self.index].astype(self.data[chrm].dtype)
 
         # This section sets up positions and ticks. Ticks should be placed in