feat(letsplot): implement manhattan-gwas

[github-actions]

Implementation: manhattan-gwas - letsplot

Implements the letsplot version of manhattan-gwas.

File: plots/manhattan-gwas/implementations/letsplot.py

Parent Issue: #2925

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The Manhattan plot displays GWAS results across 22 chromosomes arranged along the x-axis with cumulative genomic positions. Points are colored in alternating blue (#306998) and light blue (#7A9BBD) for adjacent chromosomes. The y-axis shows -log₁₀(p-value) ranging from 0 to 12. A horizontal dashed red line indicates the genome-wide significance threshold at approximately 7.3 (-log₁₀(5×10⁻⁸)), and a dotted gray line marks the suggestive threshold at 5. Significant SNPs above the genome-wide threshold are highlighted with larger red points. Clear peaks are visible on chromosomes 2, 6, 11, and 17, with additional suggestive signals on chromosomes 1, 5, 8, 14, and 19. The title "manhattan-gwas · letsplot · pyplots.ai" is displayed at the top in bold. The overall layout is well-balanced with good use of the canvas space.

Quality Score: 92/100

Criteria Checklist

Visual Quality (36/40 pts)

• VQ-01: Text Legibility (9/10) - Title large and bold, axis labels clear, chromosome labels readable but slightly small
• VQ-02: No Overlap (8/8) - No overlapping text elements
• VQ-03: Element Visibility (7/8) - Points well-sized with appropriate alpha for dense data, significant points clearly highlighted
• VQ-04: Color Accessibility (5/5) - Blue/gray alternating scheme is colorblind-safe, red highlights distinct
• VQ-05: Layout Balance (5/5) - Good use of canvas, plot fills appropriate area
• VQ-06: Axis Labels (1/2) - Y-axis has subscript notation (-log₁₀), but no units needed for this type
• VQ-07: Grid & Legend (1/2) - Minimal grid (major x removed), no legend needed (guide="none" appropriate)

Spec Compliance (25/25 pts)

• SC-01: Plot Type (8/8) - Correct Manhattan plot
• SC-02: Data Mapping (5/5) - Cumulative position on X, -log₁₀(p) on Y
• SC-03: Required Features (5/5) - All features: alternating colors, threshold lines, significant SNP highlighting
• SC-04: Data Range (3/3) - All chromosomes 1-22 visible, y-axis shows full range
• SC-05: Legend Accuracy (2/2) - Legend hidden appropriately (colors self-explanatory)
• SC-06: Title Format (2/2) - Correct format: "manhattan-gwas · letsplot · pyplots.ai"

Data Quality (19/20 pts)

• DQ-01: Feature Coverage (8/8) - Shows significant peaks, suggestive signals, and background noise
• DQ-02: Realistic Context (7/7) - Simulated GWAS data with realistic patterns (44,000 SNPs across 22 chromosomes)
• DQ-03: Appropriate Scale (4/5) - P-values span realistic range, chromosome sizes vary appropriately

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - Clean linear flow: imports → data → plot → save
• CQ-02: Reproducibility (3/3) - np.random.seed(42) set
• CQ-03: Clean Imports (2/2) - Only numpy, pandas, lets_plot used
• CQ-04: No Deprecated API (1/1) - Current lets-plot API
• CQ-05: Output Correct (0/1) - Saves to "plot.png" but uses path="." parameter

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Good use of ggplot grammar, scale_x_continuous with custom breaks/labels, theme customization, but could use more advanced lets-plot features

Strengths

• Excellent Manhattan plot structure with proper cumulative genomic positions and chromosome labeling
• Effective use of alternating blue/gray colors for chromosome distinction
• Significant SNPs highlighted in red above genome-wide threshold line
• Both genome-wide (dashed red) and suggestive (dotted gray) threshold lines included
• Good data generation with realistic GWAS patterns including peaks on specific chromosomes

Weaknesses

• Chromosome labels on x-axis could be slightly larger for better readability at full resolution

Verdict: APPROVED