feat(altair): implement manhattan-gwas

plots/manhattan-gwas/implementations/python/altair.py

@@ -1,15 +1,30 @@
-""" pyplots.ai
+""" anyplot.ai
 manhattan-gwas: Manhattan Plot for GWAS
-Library: altair 6.0.0 | Python 3.13.11
-Quality: 91/100 | Created: 2025-12-31
+Library: altair 6.1.0 | Python 3.13.13
+Quality: 88/100 | Updated: 2026-05-15
 """
 
+import os
+
 import altair as alt
 import numpy as np
 import pandas as pd
 
 
-# Data - Simulated GWAS data with random p-values and significant peaks
+# Theme configuration
+THEME = os.getenv("ANYPLOT_THEME", "light")
+
+PAGE_BG = "#FAF8F1" if THEME == "light" else "#1A1A17"
+ELEVATED_BG = "#FFFDF6" if THEME == "light" else "#242420"
+INK = "#1A1A17" if THEME == "light" else "#F0EFE8"
+INK_SOFT = "#4A4A44" if THEME == "light" else "#B8B7B0"
+INK_MUTED = "#6B6A63" if THEME == "light" else "#A8A79F"
+RULE = "rgba(26,26,23,0.10)" if THEME == "light" else "rgba(240,239,232,0.10)"
+
+# Okabe-Ito palette for alternating chromosomes
+OKABE_ITO = ["#009E73", "#D55E00", "#0072B2", "#CC79A7", "#E69F00", "#56B4E9"]
+
+# Data generation
 np.random.seed(42)
 
 # Chromosome lengths (approximate human chromosome sizes in Mb)
@@ -87,82 +102,99 @@
 suggestive_threshold = -np.log10(1e-5)  # 5.0
 
 # Create chromosome label data
-chrom_label_df = pd.DataFrame(
-    [{"chrom_label": chrom, "center": center, "y_pos": -0.5} for chrom, center in chrom_centers.items()]
-)
+chrom_label_df = pd.DataFrame([{"chrom_label": chrom, "center": center} for chrom, center in chrom_centers.items()])
 
-# Define color scheme - alternating for chromosomes
-color_scale = alt.Scale(
-    domain=[str(i) for i in range(1, 23)],
-    range=["#306998", "#7F7F7F"] * 11,  # Alternating Python blue and gray
-)
+# Create alternating color mapping with Okabe-Ito palette
+chrom_list = list(chrom_lengths.keys())
+color_mapping = {}
+for i, chrom in enumerate(chrom_list):
+    color_mapping[chrom] = OKABE_ITO[i % len(OKABE_ITO)]
+
+color_scale = alt.Scale(domain=chrom_list, range=[color_mapping[chrom] for chrom in chrom_list])
 
 # Main scatter plot
 points = (
     alt.Chart(df)
-    .mark_circle(opacity=0.7)
+    .mark_circle(opacity=0.7, size=80)
     .encode(
         x=alt.X(
             "cumulative_position:Q",
-            axis=alt.Axis(title="Chromosome", labels=False, ticks=False, titleFontSize=22),
+            axis=alt.Axis(title="Genomic Position", labels=False, ticks=False, titleFontSize=22, titleColor=INK),
             scale=alt.Scale(domain=[0, cumulative_pos]),
         ),
         y=alt.Y(
             "neg_log_p:Q",
             title="-log₁₀(p-value)",
-            axis=alt.Axis(titleFontSize=22, labelFontSize=16),
+            axis=alt.Axis(
+                titleFontSize=22,
+                labelFontSize=18,
+                titleColor=INK,
+                labelColor=INK_SOFT,
+                domainColor=INK_SOFT,
+                tickColor=INK_SOFT,
+                gridColor=INK,
+                gridOpacity=0.10,
+            ),
             scale=alt.Scale(domain=[0, max(df["neg_log_p"]) + 1]),
         ),
         color=alt.Color("chromosome:N", scale=color_scale, legend=None),
         size=alt.condition(
             alt.datum.neg_log_p > genome_wide_threshold,
             alt.value(100),  # Larger for significant hits
-            alt.value(30),  # Smaller for others
+            alt.value(60),  # Smaller for others
         ),
-        tooltip=["chromosome:N", "position:Q", "p_value:Q", "neg_log_p:Q"],
+        tooltip=[
+            "chromosome:N",
+            alt.Tooltip("position:Q", format=","),
+            alt.Tooltip("p_value:Q", format=".2e"),
+            "neg_log_p:Q",
+        ],
     )
 )
 
 # Genome-wide significance threshold line
 gw_line = (
     alt.Chart(pd.DataFrame({"y": [genome_wide_threshold]}))
-    .mark_rule(strokeDash=[8, 4], color="#E74C3C", strokeWidth=2)
+    .mark_rule(strokeDash=[8, 4], color=INK_MUTED, size=2, opacity=0.8)
     .encode(y="y:Q")
 )
 
 # Suggestive threshold line
 sug_line = (
     alt.Chart(pd.DataFrame({"y": [suggestive_threshold]}))
-    .mark_rule(strokeDash=[4, 4], color="#F39C12", strokeWidth=2)
+    .mark_rule(strokeDash=[4, 4], color=INK_MUTED, size=1.5, opacity=0.6)
     .encode(y="y:Q")
 )
 
-# Chromosome labels as text marks at bottom
+# Chromosome labels at bottom
 chrom_text = (
     alt.Chart(chrom_label_df)
-    .mark_text(fontSize=14, fontWeight="bold", baseline="top", dy=5)
-    .encode(x=alt.X("center:Q", scale=alt.Scale(domain=[0, cumulative_pos])), text="chrom_label:N")
+    .mark_text(fontSize=16, baseline="top", dy=10, color=INK_SOFT, fontWeight="normal")
+    .encode(x=alt.X("center:Q", axis=None, scale=alt.Scale(domain=[0, cumulative_pos])), text="chrom_label:N")
 )
 
-# Combine layers - points with threshold lines
-main_chart = alt.layer(points, gw_line, sug_line).properties(width=1500, height=750)
+# Combine layers
+main_chart = alt.layer(points, gw_line, sug_line).properties(width=1600, height=850)
 
-# Chromosome labels at bottom
-labels_chart = (
-    alt.Chart(chrom_label_df)
-    .mark_text(fontSize=16, baseline="middle")
-    .encode(x=alt.X("center:Q", scale=alt.Scale(domain=[0, cumulative_pos]), axis=None), text="chrom_label:N")
-    .properties(width=1500, height=30)
-)
-
-# Vertical concat with shared x-axis
+# Final chart with labels
 chart = (
-    alt.vconcat(main_chart, labels_chart, spacing=0)
-    .properties(title=alt.Title("manhattan-gwas · altair · pyplots.ai", fontSize=28, anchor="middle"))
-    .configure_axis(labelFontSize=16, titleFontSize=22, grid=True, gridOpacity=0.3)
-    .configure_view(strokeWidth=0)
+    alt.vconcat(main_chart, chrom_text.properties(width=1600, height=40), spacing=5)
+    .properties(
+        title=alt.Title(
+            "Manhattan Plot: GWAS Results",
+            fontSize=28,
+            anchor="middle",
+            color=INK,
+            subtitle="Genome-wide association study with significance thresholds",
+        ),
+        background=PAGE_BG,
+    )
+    .configure_view(fill=PAGE_BG, stroke=INK_SOFT, strokeWidth=1)
+    .configure_axis(labelFontSize=18, titleFontSize=22, labelColor=INK_SOFT, titleColor=INK)
+    .configure_title(fontSize=28, color=INK, subtitleFontSize=16, subtitleColor=INK_SOFT)
+    .configure_legend(fillColor=ELEVATED_BG, strokeColor=INK_SOFT, labelColor=INK_SOFT, titleColor=INK)
 )
 
-# Save as PNG and HTML
-chart.save("plot.png", scale_factor=3.0)
-chart.save("plot.html")
+# Save with theme-specific filenames
+chart.save(f"plot-{THEME}.png", scale_factor=3.0)
+chart.save(f"plot-{THEME}.html")