pylocuszoom 0.6.0__py3-none-any.whl → 0.8.0__py3-none-any.whl

pylocuszoom/plotter.py

@@ -15,12 +15,9 @@ from typing import Any, List, Optional, Tuple
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
-from matplotlib.axes import Axes
-from matplotlib.figure import Figure
-from matplotlib.lines import Line2D
-from matplotlib.patches import Patch
 
 from .backends import BackendType, get_backend
+from .backends.hover import HoverConfig, HoverDataBuilder
 from .colors import (
     EQTL_NEGATIVE_BINS,
     EQTL_POSITIVE_BINS,
@@ -33,6 +30,7 @@ from .colors import (
     get_ld_color_palette,
     get_phewas_category_palette,
 )
+from .ensembl import get_genes_for_region
 from .eqtl import validate_eqtl_df
 from .finemapping import (
     get_credible_sets,
@@ -41,16 +39,13 @@ from .finemapping import (
 from .forest import validate_forest_df
 from .gene_track import (
     assign_gene_positions,
-    plot_gene_track,
     plot_gene_track_generic,
 )
-from .labels import add_snp_labels
 from .ld import calculate_ld, find_plink
 from .logging import enable_logging, logger
 from .phewas import validate_phewas_df
 from .recombination import (
     RECOMB_COLOR,
-    add_recombination_overlay,
     download_canine_recombination_maps,
     get_default_data_dir,
     get_recombination_rate_for_region,
@@ -119,8 +114,21 @@ class LocusZoomPlotter:
         recomb_data_dir: Optional[str] = None,
         genomewide_threshold: float = DEFAULT_GENOMEWIDE_THRESHOLD,
         log_level: Optional[str] = "INFO",
+        auto_genes: bool = False,
     ):
-        """Initialize the plotter."""
+        """Initialize the plotter.
+
+        Args:
+            species: Species name ('canine', 'feline', or None for custom).
+            genome_build: Genome build for coordinate system.
+            backend: Plotting backend ('matplotlib', 'plotly', or 'bokeh').
+            plink_path: Path to PLINK executable for LD calculation.
+            recomb_data_dir: Directory containing recombination maps.
+            genomewide_threshold: P-value threshold for significance line.
+            log_level: Logging level.
+            auto_genes: If True, automatically fetch genes from Ensembl when
+                genes_df is not provided. Default False for backward compatibility.
+        """
         # Configure logging
         if log_level is not None:
             enable_logging(log_level)
@@ -129,12 +137,12 @@ class LocusZoomPlotter:
         self.genome_build = (
             genome_build if genome_build else self._default_build(species)
         )
-        self.backend_name = backend
         self._backend = get_backend(backend)
         self.plink_path = plink_path or find_plink()
         self.recomb_data_dir = recomb_data_dir
         self.genomewide_threshold = genomewide_threshold
         self._genomewide_line = -np.log10(genomewide_threshold)
+        self._auto_genes = auto_genes
 
         # Cache for loaded data
         self._recomb_cache = {}
@@ -248,6 +256,22 @@ class LocusZoomPlotter:
         """
         # Validate inputs
         validate_gwas_df(gwas_df, pos_col=pos_col, p_col=p_col)
+
+        # Auto-fetch genes if enabled and not provided
+        if genes_df is None and self._auto_genes:
+            logger.debug(
+                f"auto_genes enabled, fetching genes for chr{chrom}:{start}-{end}"
+            )
+            genes_df = get_genes_for_region(
+                species=self.species,
+                chrom=chrom,
+                start=start,
+                end=end,
+            )
+            if genes_df.empty:
+                logger.debug("No genes found in region from Ensembl")
+                genes_df = None
+
         if genes_df is not None:
             validate_genes_df(genes_df)
 
@@ -305,10 +329,10 @@ class LocusZoomPlotter:
             zorder=1,
         )
 
-        # Add SNP labels (matplotlib only - interactive backends use hover tooltips)
+        # Add SNP labels (capability check - interactive backends use hover tooltips)
         if snp_labels and rs_col in df.columns and label_top_n > 0 and not df.empty:
-            if self.backend_name == "matplotlib":
-                add_snp_labels(
+            if self._backend.supports_snp_labels:
+                self._backend.add_snp_labels(
                     ax,
                     df,
                     pos_col=pos_col,
@@ -319,12 +343,10 @@ class LocusZoomPlotter:
                     chrom=chrom,
                 )
 
-        # Add recombination overlay (all backends)
+        # Add recombination overlay (all backends with secondary axis support)
         if recomb_df is not None and not recomb_df.empty:
-            if self.backend_name == "matplotlib":
-                add_recombination_overlay(ax, recomb_df, start, end)
-            else:
-                self._add_recombination_overlay_generic(ax, recomb_df, start, end)
+            if self._backend.supports_secondary_axis:
+                self._add_recombination_overlay(ax, recomb_df, start, end)
 
         # Format axes
         self._backend.set_ylabel(ax, r"$-\log_{10}$ P")
@@ -333,19 +355,13 @@ class LocusZoomPlotter:
 
         # Add LD legend (all backends)
         if ld_col is not None and ld_col in df.columns:
-            if self.backend_name == "matplotlib":
-                self._add_ld_legend(ax)
-            else:
-                self._backend.add_ld_legend(ax, LD_BINS, LEAD_SNP_COLOR)
+            self._backend.add_ld_legend(ax, LD_BINS, LEAD_SNP_COLOR)
 
-        # Plot gene track (all backends)
+        # Plot gene track (all backends use generic function)
         if genes_df is not None and gene_ax is not None:
-            if self.backend_name == "matplotlib":
-                plot_gene_track(gene_ax, genes_df, chrom, start, end, exons_df)
-            else:
-                plot_gene_track_generic(
-                    gene_ax, self._backend, genes_df, chrom, start, end, exons_df
-                )
+            plot_gene_track_generic(
+                gene_ax, self._backend, genes_df, chrom, start, end, exons_df
+            )
             self._backend.set_xlabel(gene_ax, f"Chromosome {chrom} (Mb)")
             self._backend.hide_spines(gene_ax, ["top", "right", "left"])
         else:
@@ -366,7 +382,7 @@ class LocusZoomPlotter:
         start: int,
         end: int,
         figsize: Tuple[int, int],
-    ) -> Tuple[Figure, Axes, Optional[Axes]]:
+    ) -> Tuple[Any, Any, Optional[Any]]:
         """Create figure with optional gene track."""
         if genes_df is not None:
             # Calculate dynamic height based on gene rows
@@ -410,7 +426,7 @@ class LocusZoomPlotter:
 
     def _plot_association(
         self,
-        ax: Axes,
+        ax: Any,
         df: pd.DataFrame,
         pos_col: str,
         ld_col: Optional[str],
@@ -419,23 +435,14 @@ class LocusZoomPlotter:
         p_col: Optional[str] = None,
     ) -> None:
         """Plot association scatter with LD coloring."""
-
-        def _build_hover_data(subset_df: pd.DataFrame) -> Optional[pd.DataFrame]:
-            """Build hover data for interactive backends."""
-            hover_cols = {}
-            # RS ID first (will be bold in hover)
-            if rs_col and rs_col in subset_df.columns:
-                hover_cols["SNP"] = subset_df[rs_col].values
-            # Position
-            if pos_col in subset_df.columns:
-                hover_cols["Position"] = subset_df[pos_col].values
-            # P-value
-            if p_col and p_col in subset_df.columns:
-                hover_cols["P-value"] = subset_df[p_col].values
-            # LD
-            if ld_col and ld_col in subset_df.columns:
-                hover_cols["R²"] = subset_df[ld_col].values
-            return pd.DataFrame(hover_cols) if hover_cols else None
+        # Build hover data using HoverDataBuilder
+        hover_config = HoverConfig(
+            snp_col=rs_col if rs_col and rs_col in df.columns else None,
+            pos_col=pos_col if pos_col in df.columns else None,
+            p_col=p_col if p_col and p_col in df.columns else None,
+            ld_col=ld_col if ld_col and ld_col in df.columns else None,
+        )
+        hover_builder = HoverDataBuilder(hover_config)
 
         # LD-based coloring
         if ld_col is not None and ld_col in df.columns:
@@ -454,7 +461,7 @@ class LocusZoomPlotter:
                     edgecolor="black",
                     linewidth=0.5,
                     zorder=2,
-                    hover_data=_build_hover_data(bin_data),
+                    hover_data=hover_builder.build_dataframe(bin_data),
                 )
         else:
             # Default: grey points
@@ -467,7 +474,7 @@ class LocusZoomPlotter:
                 edgecolor="black",
                 linewidth=0.5,
                 zorder=2,
-                hover_data=_build_hover_data(df),
+                hover_data=hover_builder.build_dataframe(df),
             )
 
         # Highlight lead SNP with larger, more prominent marker
@@ -484,57 +491,21 @@ class LocusZoomPlotter:
                     edgecolor="black",
                     linewidth=1.5,
                     zorder=10,
-                    hover_data=_build_hover_data(lead_snp),
+                    hover_data=hover_builder.build_dataframe(lead_snp),
                 )
 
-    def _add_ld_legend(self, ax: Axes) -> None:
-        """Add LD color legend to plot."""
-        palette = get_ld_color_palette()
-        legend_elements = [
-            Line2D(
-                [0],
-                [0],
-                marker="D",
-                color="w",
-                markerfacecolor=LEAD_SNP_COLOR,
-                markeredgecolor="black",
-                markersize=6,
-                label="Lead SNP",
-            ),
-        ]
-
-        for threshold, label, _ in LD_BINS:
-            legend_elements.append(
-                Patch(
-                    facecolor=palette[label],
-                    edgecolor="black",
-                    label=label,
-                )
-            )
-
-        ax.legend(
-            handles=legend_elements,
-            loc="upper right",
-            fontsize=9,
-            frameon=True,
-            framealpha=0.9,
-            title=r"$r^2$",
-            title_fontsize=10,
-            handlelength=1.5,
-            handleheight=1.0,
-            labelspacing=0.4,
-        )
-
-    def _add_recombination_overlay_generic(
+    def _add_recombination_overlay(
         self,
         ax: Any,
         recomb_df: pd.DataFrame,
         start: int,
         end: int,
     ) -> None:
-        """Add recombination overlay for interactive backends (plotly/bokeh).
+        """Add recombination overlay for all backends.
 
         Creates a secondary y-axis with recombination rate line and fill.
+        Uses backend-agnostic secondary axis methods that work across
+        matplotlib, plotly, and bokeh.
         """
         # Filter to region
         region_recomb = recomb_df[
@@ -591,7 +562,7 @@ class LocusZoomPlotter:
 
     def _plot_finemapping(
         self,
-        ax: Axes,
+        ax: Any,
         df: pd.DataFrame,
         pos_col: str = "pos",
         pip_col: str = "pip",
@@ -610,22 +581,15 @@ class LocusZoomPlotter:
             show_credible_sets: Whether to color points by credible set.
             pip_threshold: Minimum PIP to display as scatter point.
         """
-
-        def _build_finemapping_hover_data(
-            subset_df: pd.DataFrame,
-        ) -> Optional[pd.DataFrame]:
-            """Build hover data for interactive backends."""
-            hover_cols = {}
-            # Position
-            if pos_col in subset_df.columns:
-                hover_cols["Position"] = subset_df[pos_col].values
-            # PIP
-            if pip_col in subset_df.columns:
-                hover_cols["PIP"] = subset_df[pip_col].values
-            # Credible set
-            if cs_col and cs_col in subset_df.columns:
-                hover_cols["Credible Set"] = subset_df[cs_col].values
-            return pd.DataFrame(hover_cols) if hover_cols else None
+        # Build hover data using HoverDataBuilder
+        extra_cols = {pip_col: "PIP"}
+        if cs_col and cs_col in df.columns:
+            extra_cols[cs_col] = "Credible Set"
+        hover_config = HoverConfig(
+            pos_col=pos_col if pos_col in df.columns else None,
+            extra_cols=extra_cols,
+        )
+        hover_builder = HoverDataBuilder(hover_config)
 
         # Sort by position for line plotting
         df = df.sort_values(pos_col)
@@ -660,7 +624,7 @@ class LocusZoomPlotter:
                     edgecolor="black",
                     linewidth=0.5,
                     zorder=3,
-                    hover_data=_build_finemapping_hover_data(cs_data),
+                    hover_data=hover_builder.build_dataframe(cs_data),
                 )
             # Plot variants not in any credible set
             non_cs_data = df[(df[cs_col].isna()) | (df[cs_col] == 0)]
@@ -677,7 +641,7 @@ class LocusZoomPlotter:
                         edgecolor="black",
                         linewidth=0.3,
                         zorder=2,
-                        hover_data=_build_finemapping_hover_data(non_cs_data),
+                        hover_data=hover_builder.build_dataframe(non_cs_data),
                     )
         else:
             # No credible sets - show all points above threshold
@@ -694,7 +658,7 @@ class LocusZoomPlotter:
                         edgecolor="black",
                         linewidth=0.5,
                         zorder=3,
-                        hover_data=_build_finemapping_hover_data(high_pip),
+                        hover_data=hover_builder.build_dataframe(high_pip),
                     )
 
     def plot_stacked(
@@ -912,10 +876,10 @@ class LocusZoomPlotter:
                 zorder=1,
             )
 
-            # Add SNP labels (matplotlib only - interactive backends use hover tooltips)
+            # Add SNP labels (capability check - interactive backends use hover tooltips)
             if snp_labels and rs_col in df.columns and label_top_n > 0 and not df.empty:
-                if self.backend_name == "matplotlib":
-                    add_snp_labels(
+                if self._backend.supports_snp_labels:
+                    self._backend.add_snp_labels(
                         ax,
                         df,
                         pos_col=pos_col,
@@ -928,10 +892,8 @@ class LocusZoomPlotter:
 
             # Add recombination overlay (only on first panel, all backends)
             if i == 0 and recomb_df is not None and not recomb_df.empty:
-                if self.backend_name == "matplotlib":
-                    add_recombination_overlay(ax, recomb_df, start, end)
-                else:
-                    self._add_recombination_overlay_generic(ax, recomb_df, start, end)
+                if self._backend.supports_secondary_axis:
+                    self._add_recombination_overlay(ax, recomb_df, start, end)
 
             # Format axes
             self._backend.set_ylabel(ax, r"$-\log_{10}$ P")
@@ -940,50 +902,11 @@ class LocusZoomPlotter:
 
             # Add panel label
             if panel_labels and i < len(panel_labels):
-                if self.backend_name == "matplotlib":
-                    ax.annotate(
-                        panel_labels[i],
-                        xy=(0.02, 0.95),
-                        xycoords="axes fraction",
-                        fontsize=11,
-                        fontweight="bold",
-                        va="top",
-                        ha="left",
-                    )
-                elif self.backend_name == "plotly":
-                    fig, row = ax
-                    fig.add_annotation(
-                        text=f"<b>{panel_labels[i]}</b>",
-                        xref=f"x{row} domain" if row > 1 else "x domain",
-                        yref=f"y{row} domain" if row > 1 else "y domain",
-                        x=0.02,
-                        y=0.95,
-                        showarrow=False,
-                        font=dict(size=11),
-                        xanchor="left",
-                        yanchor="top",
-                    )
-                elif self.backend_name == "bokeh":
-                    from bokeh.models import Label
-
-                    # Get y-axis range for positioning
-                    y_max = ax.y_range.end if ax.y_range.end else 10
-                    x_min = ax.x_range.start if ax.x_range.start else start
-                    label = Label(
-                        x=x_min + (end - start) * 0.02,
-                        y=y_max * 0.95,
-                        text=panel_labels[i],
-                        text_font_size="11pt",
-                        text_font_style="bold",
-                    )
-                    ax.add_layout(label)
+                self._backend.add_panel_label(ax, panel_labels[i])
 
             # Add LD legend (only on first panel, all backends)
             if i == 0 and panel_ld_col is not None and panel_ld_col in df.columns:
-                if self.backend_name == "matplotlib":
-                    self._add_ld_legend(ax)
-                else:
-                    self._backend.add_ld_legend(ax, LD_BINS, LEAD_SNP_COLOR)
+                self._backend.add_ld_legend(ax, LD_BINS, LEAD_SNP_COLOR)
 
         # Track current panel index
         panel_idx = n_gwas
@@ -1050,24 +973,18 @@ class LocusZoomPlotter:
                     eqtl_data["p_value"].clip(lower=1e-300)
                 )
 
-                def _build_eqtl_hover_data(
-                    subset_df: pd.DataFrame,
-                ) -> Optional[pd.DataFrame]:
-                    """Build hover data for eQTL interactive backends."""
-                    hover_cols = {}
-                    # Position
-                    if "pos" in subset_df.columns:
-                        hover_cols["Position"] = subset_df["pos"].values
-                    # P-value
-                    if "p_value" in subset_df.columns:
-                        hover_cols["P-value"] = subset_df["p_value"].values
-                    # Effect size
-                    if "effect_size" in subset_df.columns:
-                        hover_cols["Effect"] = subset_df["effect_size"].values
-                    # Gene
-                    if "gene" in subset_df.columns:
-                        hover_cols["Gene"] = subset_df["gene"].values
-                    return pd.DataFrame(hover_cols) if hover_cols else None
+                # Build hover data using HoverDataBuilder
+                eqtl_extra_cols = {}
+                if "effect_size" in eqtl_data.columns:
+                    eqtl_extra_cols["effect_size"] = "Effect"
+                if "gene" in eqtl_data.columns:
+                    eqtl_extra_cols["gene"] = "Gene"
+                eqtl_hover_config = HoverConfig(
+                    pos_col="pos" if "pos" in eqtl_data.columns else None,
+                    p_col="p_value" if "p_value" in eqtl_data.columns else None,
+                    extra_cols=eqtl_extra_cols,
+                )
+                eqtl_hover_builder = HoverDataBuilder(eqtl_hover_config)
 
                 # Check if effect_size column exists for directional coloring
                 has_effect = "effect_size" in eqtl_data.columns
@@ -1090,7 +1007,7 @@ class LocusZoomPlotter:
                             edgecolor="black",
                             linewidth=0.5,
                             zorder=2,
-                            hover_data=_build_eqtl_hover_data(row_df),
+                            hover_data=eqtl_hover_builder.build_dataframe(row_df),
                         )
                     # Plot negative effects (down triangles)
                     for _, row in neg_effects.iterrows():
@@ -1105,7 +1022,7 @@ class LocusZoomPlotter:
                             edgecolor="black",
                             linewidth=0.5,
                             zorder=2,
-                            hover_data=_build_eqtl_hover_data(row_df),
+                            hover_data=eqtl_hover_builder.build_dataframe(row_df),
                         )
                     # Add eQTL effect legend (all backends)
                     self._backend.add_eqtl_legend(
@@ -1125,7 +1042,7 @@ class LocusZoomPlotter:
                         linewidth=0.5,
                         zorder=2,
                         label=label,
-                        hover_data=_build_eqtl_hover_data(eqtl_data),
+                        hover_data=eqtl_hover_builder.build_dataframe(eqtl_data),
                     )
                     self._backend.add_simple_legend(ax, label, loc="upper right")
 
@@ -1141,15 +1058,12 @@ class LocusZoomPlotter:
             self._backend.hide_spines(ax, ["top", "right"])
             panel_idx += 1
 
-        # Plot gene track (all backends)
+        # Plot gene track (all backends use generic function)
         if genes_df is not None:
             gene_ax = axes[panel_idx]
-            if self.backend_name == "matplotlib":
-                plot_gene_track(gene_ax, genes_df, chrom, start, end, exons_df)
-            else:
-                plot_gene_track_generic(
-                    gene_ax, self._backend, genes_df, chrom, start, end, exons_df
-                )
+            plot_gene_track_generic(
+                gene_ax, self._backend, genes_df, chrom, start, end, exons_df
+            )
             self._backend.set_xlabel(gene_ax, f"Chromosome {chrom} (Mb)")
             self._backend.hide_spines(gene_ax, ["top", "right", "left"])
         else:
@@ -1281,10 +1195,13 @@ class LocusZoomPlotter:
         self._backend.set_ylabel(ax, "Phenotype")
         self._backend.set_ylim(ax, -0.5, len(df) - 0.5)
 
-        # Set y-tick labels to phenotype names (matplotlib only)
-        if self.backend_name == "matplotlib":
-            ax.set_yticks(df["y_pos"])
-            ax.set_yticklabels(df[phenotype_col], fontsize=8)
+        # Set y-tick labels to phenotype names
+        self._backend.set_yticks(
+            ax,
+            positions=df["y_pos"].tolist(),
+            labels=df[phenotype_col].tolist(),
+            fontsize=8,
+        )
 
         self._backend.set_title(ax, f"PheWAS: {variant_id}")
         self._backend.hide_spines(ax, ["top", "right"])
@@ -1399,10 +1316,19 @@ class LocusZoomPlotter:
         self._backend.set_xlabel(ax, effect_label)
         self._backend.set_ylim(ax, -0.5, len(df) - 0.5)
 
-        # Set y-tick labels to study names (matplotlib only)
-        if self.backend_name == "matplotlib":
-            ax.set_yticks(df["y_pos"])
-            ax.set_yticklabels(df[study_col], fontsize=10)
+        # Ensure x-axis includes the null value with some padding
+        x_min = min(df[ci_lower_col].min(), null_value)
+        x_max = max(df[ci_upper_col].max(), null_value)
+        x_padding = (x_max - x_min) * 0.1
+        self._backend.set_xlim(ax, x_min - x_padding, x_max + x_padding)
+
+        # Set y-tick labels to study names
+        self._backend.set_yticks(
+            ax,
+            positions=df["y_pos"].tolist(),
+            labels=df[study_col].tolist(),
+            fontsize=10,
+        )
 
         self._backend.set_title(ax, f"Forest Plot: {variant_id}")
         self._backend.hide_spines(ax, ["top", "right"])

pylocuszoom/recombination.py

@@ -18,6 +18,7 @@ from matplotlib.axes import Axes
 from tqdm import tqdm
 
 from .logging import logger
+from .utils import filter_by_region
 
 # Recombination overlay color
 RECOMB_COLOR = "#7FCDFF"  # Light blue
@@ -252,10 +253,20 @@ def download_canine_recombination_maps(
 
         logger.debug(f"Downloaded {tar_path.stat().st_size / 1024:.1f} KB")
 
-        # Extract tar.gz
+        # Extract tar.gz with path traversal protection
         logger.debug("Extracting genetic maps...")
         with tarfile.open(tar_path, "r:gz") as tar:
-            tar.extractall(tmpdir)
+            # Filter to prevent path traversal attacks
+            safe_members = []
+            for member in tar.getmembers():
+                # Resolve the path and ensure it stays within tmpdir
+                member_path = Path(tmpdir) / member.name
+                try:
+                    member_path.resolve().relative_to(Path(tmpdir).resolve())
+                    safe_members.append(member)
+                except ValueError:
+                    logger.warning(f"Skipping unsafe path in archive: {member.name}")
+            tar.extractall(tmpdir, members=safe_members)
 
         # Find and process the extracted files
         extracted_dir = Path(tmpdir)
@@ -374,7 +385,12 @@ def get_recombination_rate_for_region(
         )
 
     # Filter to region
-    region_df = df[(df["pos"] >= start) & (df["pos"] <= end)].copy()
+    region_df = filter_by_region(
+        df,
+        region=(chrom, start, end),
+        chrom_col="",  # Recomb maps don't have chromosome column
+        pos_col="pos",
+    )
 
     return region_df[["pos", "rate"]]
 

pylocuszoom/utils.py

@@ -106,6 +106,58 @@ def normalize_chrom(chrom: Union[int, str]) -> str:
     return str(chrom).replace("chr", "")
 
 
+def filter_by_region(
+    df: pd.DataFrame,
+    region: tuple,
+    chrom_col: str = "chrom",
+    pos_col: str = "pos",
+) -> pd.DataFrame:
+    """Filter DataFrame to genomic region with inclusive bounds.
+
+    Filters rows where position is within [start, end] (inclusive).
+    If chrom_col exists in DataFrame, also filters by chromosome.
+    Chromosome comparison normalizes types (int/str, chr prefix).
+
+    Args:
+        df: DataFrame to filter.
+        region: Tuple of (chrom, start, end) defining the region.
+        chrom_col: Column name for chromosome (default: "chrom").
+            If column doesn't exist, filters by position only.
+        pos_col: Column name for position (default: "pos").
+
+    Returns:
+        Filtered DataFrame (copy, not view).
+
+    Raises:
+        KeyError: If pos_col is not found in DataFrame.
+
+    Example:
+        >>> filtered = filter_by_region(df, region=(1, 1000000, 2000000))
+        >>> filtered = filter_by_region(df, region=("chr1", 1e6, 2e6), pos_col="position")
+    """
+    chrom, start, end = region
+
+    # Validate position column exists
+    if pos_col not in df.columns:
+        raise KeyError(
+            f"Position column '{pos_col}' not found in DataFrame. "
+            f"Available columns: {list(df.columns)}"
+        )
+
+    # Position filtering (inclusive bounds)
+    mask = (df[pos_col] >= start) & (df[pos_col] <= end)
+
+    # Chromosome filtering (if column exists)
+    if chrom_col in df.columns:
+        chrom_normalized = normalize_chrom(chrom)
+        df_chrom_normalized = (
+            df[chrom_col].astype(str).str.replace("chr", "", regex=False)
+        )
+        mask = mask & (df_chrom_normalized == chrom_normalized)
+
+    return df[mask].copy()
+
+
 def validate_dataframe(
     df: pd.DataFrame,
     required_cols: List[str],