pylocuszoom 0.1.0__py3-none-any.whl → 0.2.0__py3-none-any.whl

pylocuszoom/gene_track.py

@@ -15,11 +15,11 @@ from matplotlib.patches import Polygon, Rectangle
 
 from .utils import normalize_chrom
 
-# Strand-specific colors (bold, distinct)
+# Strand-specific colors (distinct from LD palette)
 STRAND_COLORS: dict[Optional[str], str] = {
-    "+": "#6A3D9A",  # Bold purple for forward strand
-    "-": "#1F78B4",  # Bold teal/blue for reverse strand
-    None: "#666666",  # Grey if no strand info
+    "+": "#FFD700",  # Gold/bright yellow for forward strand
+    "-": "#DDA0DD",  # Plum/light purple for reverse strand
+    None: "#999999",  # Light grey if no strand info
 }
 
 # Layout constants
@@ -145,7 +145,7 @@ def plot_gene_track(
     ].copy()
 
     ax.set_xlim(start, end)
-    ax.set_ylabel("Genes", fontsize=10)
+    ax.set_ylabel("")
     ax.set_yticks([])
 
     # theme_classic: only bottom spine
@@ -255,43 +255,56 @@ def plot_gene_track(
                 )
             )
 
-        # Add strand direction triangle at gene tip
+        # Add strand direction triangles (tip, center, tail)
         if "strand" in gene.index:
             strand = gene["strand"]
             region_width = end - start
+            gene_width = gene_end - gene_start
             arrow_dir = 1 if strand == "+" else -1
 
-            # Triangle dimensions - whole arrow past gene end
+            # Triangle dimensions
             tri_height = EXON_HEIGHT * 0.35
             tri_width = region_width * 0.006
 
-            # Triangle entirely past gene tip
-            if arrow_dir == 1:  # Forward strand: arrow starts at gene end
-                base_x = gene_end
-                tip_x = base_x + tri_width
-                tri_points = [
-                    [tip_x, y_gene],  # Tip pointing right
-                    [base_x, y_gene + tri_height],
-                    [base_x, y_gene - tri_height],
+            # Arrow positions: front, middle, back
+            if arrow_dir == 1:  # Forward strand
+                arrow_positions = [
+                    gene_start,  # Front
+                    (gene_start + gene_end) / 2,  # Middle
+                    gene_end,  # Back (tip past gene end)
                 ]
-            else:  # Reverse strand: arrow starts at gene start
-                base_x = gene_start
-                tip_x = base_x - tri_width
-                tri_points = [
-                    [tip_x, y_gene],  # Tip pointing left
-                    [base_x, y_gene + tri_height],
-                    [base_x, y_gene - tri_height],
+            else:  # Reverse strand
+                arrow_positions = [
+                    gene_end,  # Front (arrows point left, so start from right)
+                    (gene_start + gene_end) / 2,  # Middle
+                    gene_start,  # Back (tip past gene start)
                 ]
 
-            triangle = Polygon(
-                tri_points,
-                closed=True,
-                facecolor="black",
-                edgecolor="black",
-                linewidth=0.5,
-                zorder=5,
-            )
-            ax.add_patch(triangle)
+            for base_x in arrow_positions:
+                if arrow_dir == 1:
+                    tip_x = base_x + tri_width
+                    tri_points = [
+                        [tip_x, y_gene],  # Tip pointing right
+                        [base_x, y_gene + tri_height],
+                        [base_x, y_gene - tri_height],
+                    ]
+                else:
+                    tip_x = base_x - tri_width
+                    tri_points = [
+                        [tip_x, y_gene],  # Tip pointing left
+                        [base_x, y_gene + tri_height],
+                        [base_x, y_gene - tri_height],
+                    ]
+
+                triangle = Polygon(
+                    tri_points,
+                    closed=True,
+                    facecolor="#000000",
+                    edgecolor="#000000",
+                    linewidth=0.5,
+                    zorder=5,
+                )
+                ax.add_patch(triangle)
 
         # Add gene name label in the gap above gene
         if gene_name:

pylocuszoom/labels.py

@@ -2,18 +2,15 @@
 
 Provides automatic labeling of top significant SNPs with:
 - SNP ID (rs number)
-- Nearest gene name (if gene annotations provided)
 - Automatic overlap avoidance (if adjustText installed)
 """
 
-from typing import List, Optional, Union
+from typing import Any, List, Optional, Union
 
 import pandas as pd
 from matplotlib.axes import Axes
 from matplotlib.text import Annotation
 
-from .gene_track import get_nearest_gene
-
 
 def add_snp_labels(
     ax: Axes,
@@ -25,11 +22,11 @@ def add_snp_labels(
     genes_df: Optional[pd.DataFrame] = None,
     chrom: Optional[Union[int, str]] = None,
     max_label_length: int = 15,
+    **kwargs: Any,
 ) -> List[Annotation]:
     """Add text labels to top SNPs in the regional plot.
 
-    Labels the most significant SNPs with either their SNP ID
-    or the nearest gene name (if genes_df provided).
+    Labels the most significant SNPs with their SNP ID (rs number).
 
     Args:
         ax: Matplotlib axes object.
@@ -39,10 +36,8 @@ def add_snp_labels(
         neglog10p_col: Column name for -log10(p-value).
         rs_col: Column name for SNP ID.
         label_top_n: Number of top SNPs to label.
-        genes_df: Optional gene annotations for gene-based labels.
-            If provided with chrom, labels will show nearest gene name
-            instead of SNP ID.
-        chrom: Chromosome number. Required if genes_df is provided.
+        genes_df: Unused, kept for backward compatibility.
+        chrom: Unused, kept for backward compatibility.
         max_label_length: Maximum label length before truncation.
 
     Returns:
@@ -53,6 +48,8 @@ def add_snp_labels(
         >>> # ... plot your data ...
         >>> texts = add_snp_labels(ax, df, label_top_n=5)
     """
+    # genes_df and chrom are unused but kept for backward compatibility
+    del genes_df, chrom, kwargs
     if neglog10p_col not in df.columns:
         raise ValueError(
             f"Column '{neglog10p_col}' not found in DataFrame. "
@@ -63,33 +60,34 @@ def add_snp_labels(
     top_snps = df.nlargest(label_top_n, neglog10p_col)
 
     texts = []
+    used_labels = set()  # Track used labels to avoid duplicates
+
     for _, snp in top_snps.iterrows():
         x = snp[pos_col]
         y = snp[neglog10p_col]
 
-        # Determine label text
+        # Use SNP ID as label
         label = str(snp[rs_col])
 
-        # Try to get gene name if genes_df provided
-        if genes_df is not None and chrom is not None:
-            nearest_gene = get_nearest_gene(genes_df, chrom, int(x))
-            if nearest_gene:
-                label = nearest_gene
+        # Skip duplicate labels
+        if label in used_labels:
+            continue
+        used_labels.add(label)
 
         # Truncate long labels
         if len(label) > max_label_length:
             label = label[: max_label_length - 3] + "..."
 
-        # Add text annotation with offset
+        # Add text annotation centered above marker
         text = ax.annotate(
             label,
             xy=(x, y),
-            xytext=(5, 5),
+            xytext=(0, 7),
             textcoords="offset points",
-            fontsize=8,
+            fontsize=6,
             fontweight="bold",
             color="#333333",
-            ha="left",
+            ha="center",
             va="bottom",
             zorder=15,
             bbox=dict(
@@ -101,18 +99,19 @@ def add_snp_labels(
         )
         texts.append(text)
 
-    # Try to adjust text positions to avoid overlap
-    try:
-        from adjustText import adjust_text
-
-        adjust_text(
-            texts,
-            ax=ax,
-            arrowprops=dict(arrowstyle="-", color="gray", lw=0.5),
-            expand_points=(1.5, 1.5),
-        )
-    except ImportError:
-        # adjustText not installed, labels may overlap
-        pass
+    # Only use adjustText when there are multiple labels to avoid overlap
+    if len(texts) > 1:
+        try:
+            from adjustText import adjust_text
+
+            adjust_text(
+                texts,
+                ax=ax,
+                arrowprops=dict(arrowstyle="-", color="gray", lw=0.5),
+                expand_points=(1.5, 1.5),
+            )
+        except ImportError:
+            # adjustText not installed, labels may overlap
+            pass
 
     return texts

pylocuszoom/ld.py

@@ -38,7 +38,7 @@ def build_ld_command(
     output_path: str,
     window_kb: int = 500,
     ld_window_r2: float = 0.0,
-    species: str = "dog",
+    species: str = "canine",
     threads: Optional[int] = None,
 ) -> list:
     """Build PLINK command for LD calculation.
@@ -50,7 +50,7 @@ def build_ld_command(
         output_path: Output prefix (creates .ld file).
         window_kb: Window size in kilobases.
         ld_window_r2: Minimum R² to report (0.0 reports all).
-        species: Species flag for PLINK ('dog', 'cat', or None for human).
+        species: Species flag for PLINK ('canine', 'feline', or None for human).
         threads: Number of threads (auto-detect if None).
 
     Returns:
@@ -58,10 +58,10 @@ def build_ld_command(
     """
     cmd = [plink_path]
 
-    # Species flag
-    if species == "dog":
+    # Species flag (maps to PLINK's --dog flag)
+    if species == "canine":
         cmd.append("--dog")
-    elif species == "cat":
+    elif species == "feline":
         # PLINK doesn't have --cat, use --chr-set for 18 autosomes + X
         cmd.extend(["--chr-set", "18"])
 
@@ -119,7 +119,7 @@ def calculate_ld(
     window_kb: int = 500,
     plink_path: Optional[str] = None,
     working_dir: Optional[str] = None,
-    species: str = "dog",
+    species: str = "canine",
     threads: Optional[int] = None,
 ) -> pd.DataFrame:
     """Calculate LD (R²) between a lead SNP and all SNPs in a region.
@@ -133,7 +133,7 @@ def calculate_ld(
         window_kb: Window size in kilobases around lead SNP.
         plink_path: Path to PLINK executable. Auto-detects if None.
         working_dir: Directory for PLINK output files. Uses temp dir if None.
-        species: Species flag ('dog', 'cat', or None for human).
+        species: Species flag ('canine', 'feline', or None for human).
         threads: Number of threads for PLINK.
 
     Returns:
@@ -142,6 +142,7 @@ def calculate_ld(
 
     Raises:
         FileNotFoundError: If PLINK executable not found.
+        ValidationError: If PLINK binary files (.bed/.bim/.fam) are missing.
 
     Example:
         >>> ld_df = calculate_ld(