feat(seaborn): implement sequence-logo-basic (#4614)

## Implementation: `sequence-logo-basic` - seaborn

Implements the **seaborn** version of `sequence-logo-basic`.

**File:** `plots/sequence-logo-basic/implementations/seaborn.py`

**Parent Issue:** #4421

---
:robot: *[impl-generate
workflow](https://github.com/MarkusNeusinger/pyplots/actions/runs/22780524945)*

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Author: github-actions[bot]

plots/sequence-logo-basic/implementations/seaborn.py

@@ -0,0 +1,149 @@
+""" pyplots.ai
+sequence-logo-basic: Sequence Logo for Motif Visualization
+Library: seaborn 0.13.2 | Python 3.14.3
+Quality: 92/100 | Created: 2026-03-06
+"""
+
+import matplotlib.pyplot as plt
+import matplotlib.transforms as mtransforms
+import numpy as np
+import pandas as pd
+import seaborn as sns
+from matplotlib.font_manager import FontProperties
+from matplotlib.patches import PathPatch
+from matplotlib.textpath import TextPath
+
+
+# Data - DNA transcription factor binding site motif (10 positions)
+bases = ["A", "C", "G", "T"]
+
+frequencies = np.array(
+    [
+        [0.05, 0.80, 0.10, 0.05],  # pos 1: strong C
+        [0.70, 0.10, 0.10, 0.10],  # pos 2: strong A
+        [0.05, 0.05, 0.85, 0.05],  # pos 3: strong G
+        [0.10, 0.10, 0.10, 0.70],  # pos 4: strong T
+        [0.25, 0.25, 0.25, 0.25],  # pos 5: no preference
+        [0.60, 0.15, 0.15, 0.10],  # pos 6: moderate A
+        [0.05, 0.05, 0.05, 0.85],  # pos 7: strong T
+        [0.90, 0.03, 0.04, 0.03],  # pos 8: very strong A
+        [0.10, 0.60, 0.20, 0.10],  # pos 9: moderate C
+        [0.05, 0.05, 0.80, 0.10],  # pos 10: strong G
+    ]
+)
+
+n_positions = frequencies.shape[0]
+
+# Calculate information content (bits) per position
+# IC = log2(4) + sum(f * log2(f)) = 2 + sum(f * log2(f))
+info_content = np.zeros(n_positions)
+for i in range(n_positions):
+    entropy = sum(f * np.log2(f) for f in frequencies[i] if f > 0)
+    info_content[i] = 2.0 + entropy
+
+# Standard DNA color scheme via seaborn palette management
+base_color_list = ["#3AA655", "#4169E1", "#F5A623", "#E74C3C"]
+base_palette = sns.color_palette(base_color_list)
+base_colors = dict(zip(bases, base_palette, strict=True))
+
+# Build frequency DataFrame for heatmap
+freq_df = pd.DataFrame(frequencies.T, index=bases, columns=range(1, n_positions + 1))
+
+# Plot setup with seaborn context and style
+sns.set_context("talk", font_scale=1.0)
+sns.set_style("white")
+fig, (ax_logo, ax_heat) = plt.subplots(2, 1, figsize=(16, 9), height_ratios=[3.5, 1], gridspec_kw={"hspace": 0.45})
+
+# --- Top panel: Sequence Logo ---
+fp = FontProperties(family="monospace", weight="bold")
+letter_width = 0.78
+
+for pos in range(n_positions):
+    ic = info_content[pos]
+    letter_heights = frequencies[pos] * ic
+    sorted_indices = np.argsort(letter_heights)
+    y_offset = 0.0
+
+    for idx in sorted_indices:
+        height = letter_heights[idx]
+        if height < 0.01:
+            continue
+
+        letter = bases[idx]
+        color = base_colors[letter]
+        x_center = pos
+        x_left = x_center - letter_width / 2
+
+        tp = TextPath((0, 0), letter, size=1, prop=fp)
+        bbox = tp.get_extents()
+        if bbox.width == 0 or bbox.height == 0:
+            continue
+
+        scale_x = letter_width / bbox.width
+        scale_y = height / bbox.height
+        tx = x_left - bbox.x0 * scale_x
+        ty = y_offset - bbox.y0 * scale_y
+
+        transform = mtransforms.Affine2D().scale(scale_x, scale_y).translate(tx, ty) + ax_logo.transData
+        patch = PathPatch(tp, facecolor=color, edgecolor="none", transform=transform)
+        ax_logo.add_patch(patch)
+        y_offset += height
+
+# Logo axis styling
+ax_logo.set_xlim(-0.6, n_positions - 0.4)
+ax_logo.set_ylim(0, 2.1)
+ax_logo.set_xticks(range(n_positions))
+ax_logo.set_xticklabels(range(1, n_positions + 1))
+ax_logo.set_xlabel("Position", fontsize=20)
+ax_logo.set_ylabel("Information content (bits)", fontsize=20)
+ax_logo.set_title("sequence-logo-basic \u00b7 seaborn \u00b7 pyplots.ai", fontsize=24, fontweight="medium", pad=15)
+ax_logo.tick_params(axis="both", labelsize=16)
+sns.despine(ax=ax_logo, top=True, right=True)
+ax_logo.yaxis.grid(True, alpha=0.15, linewidth=0.5, color="#cccccc")
+ax_logo.set_axisbelow(True)
+
+# Highlight the most conserved position
+max_ic_pos = int(np.argmax(info_content))
+ax_logo.axvspan(max_ic_pos - 0.42, max_ic_pos + 0.42, color="#ffd700", alpha=0.12, zorder=0)
+
+# Conservation annotation
+ax_logo.annotate(
+    f"Most conserved\n({info_content[max_ic_pos]:.1f} bits)",
+    xy=(max_ic_pos, info_content[max_ic_pos]),
+    xytext=(max_ic_pos - 2.5, 1.90),
+    fontsize=13,
+    fontstyle="italic",
+    color="#444444",
+    arrowprops={"arrowstyle": "->", "color": "#888888", "lw": 1.3, "connectionstyle": "arc3,rad=-0.2"},
+    ha="center",
+    va="center",
+)
+
+# --- Bottom panel: Frequency heatmap using seaborn ---
+sns.heatmap(
+    freq_df,
+    ax=ax_heat,
+    cmap=sns.light_palette("#306998", as_cmap=True),
+    annot=True,
+    fmt=".2f",
+    annot_kws={"fontsize": 12, "fontweight": "medium"},
+    linewidths=1.5,
+    linecolor="white",
+    cbar_kws={"label": "Frequency", "shrink": 0.8, "aspect": 15, "pad": 0.02},
+    vmin=0,
+    vmax=1,
+    square=False,
+)
+ax_heat.set_xlabel("Position", fontsize=16)
+ax_heat.set_ylabel("", fontsize=16)
+ax_heat.tick_params(axis="both", labelsize=14)
+ax_heat.tick_params(axis="y", rotation=0)
+
+# Color the y-axis base labels to match the logo colors
+for tick_label in ax_heat.get_yticklabels():
+    base = tick_label.get_text()
+    if base in base_colors:
+        tick_label.set_color(base_colors[base])
+        tick_label.set_fontweight("bold")
+
+plt.savefig("plot.png", dpi=300, bbox_inches="tight")

plots/sequence-logo-basic/metadata/seaborn.yaml

@@ -0,0 +1,234 @@
+library: seaborn
+specification_id: sequence-logo-basic
+created: '2026-03-06T20:26:36Z'
+updated: '2026-03-06T20:58:49Z'
+generated_by: claude-opus-4-5-20251101
+workflow_run: 22780524945
+issue: 4421
+python_version: 3.14.3
+library_version: 0.13.2
+preview_url: https://storage.googleapis.com/pyplots-images/plots/sequence-logo-basic/seaborn/plot.png
+preview_thumb: https://storage.googleapis.com/pyplots-images/plots/sequence-logo-basic/seaborn/plot_thumb.png
+preview_html: null
+quality_score: 92
+review:
+  strengths:
+  - Excellent two-panel design combining sequence logo with frequency heatmap for
+    complementary views
+  - Properly rendered letter glyphs using TextPath/PathPatch (correct technique for
+    sequence logos)
+  - Strong data storytelling with highlighted most-conserved position and annotation
+    arrow
+  - Colored heatmap y-axis labels matching logo colors — thoughtful design touch
+  - Well-chosen data showing full range of conservation levels including uniform position
+  weaknesses:
+  - Minor colorblind concern with green-red pairing (though this is the standard bioinformatics
+    convention)
+  image_description: 'The plot features a two-panel layout on a white background.
+    The top panel is a sequence logo showing 10 positions of a DNA transcription factor
+    binding site. Letters (A in green, C in blue, G in orange, T in red) are stacked
+    vertically at each position, with height proportional to information content in
+    bits (y-axis, 0–2). Position 8 has the tallest stack (~1.4 bits, dominated by
+    a large green "A") and is highlighted with a pale yellow vertical band and an
+    italic annotation "Most conserved (1.4 bits)" with a curved arrow. Position 5
+    is nearly empty (uniform distribution). The title reads "sequence-logo-basic ·
+    seaborn · pyplots.ai" in medium weight at the top. Top and right spines are removed;
+    a very subtle horizontal grid is visible. The bottom panel is a seaborn heatmap
+    showing the raw frequency matrix (4 rows: A, C, G, T × 10 columns) with annotated
+    values (.2f format), colored from white to dark blue. Y-axis labels are colored
+    to match their respective base colors (green A, blue C, orange G, red T). A "Frequency"
+    colorbar appears on the right. Both panels share "Position" as the x-axis label.'
+  criteria_checklist:
+    visual_quality:
+      score: 29
+      max: 30
+      items:
+      - id: VQ-01
+        name: Text Legibility
+        score: 8
+        max: 8
+        passed: true
+        comment: 'All font sizes explicitly set: title 24pt, labels 20pt, ticks 16pt,
+          heatmap annotations 12pt'
+      - id: VQ-02
+        name: No Overlap
+        score: 6
+        max: 6
+        passed: true
+        comment: No overlapping text or elements; annotation well-positioned
+      - id: VQ-03
+        name: Element Visibility
+        score: 6
+        max: 6
+        passed: true
+        comment: Letter glyphs properly scaled and clearly visible at all positions
+      - id: VQ-04
+        name: Color Accessibility
+        score: 3
+        max: 4
+        passed: true
+        comment: Standard DNA colors; green-red pairing is mild colorblind concern
+          but established convention
+      - id: VQ-05
+        name: Layout & Canvas
+        score: 4
+        max: 4
+        passed: true
+        comment: Two-panel layout with 3.5:1 ratio gives proper emphasis; good use
+          of 16x9 canvas
+      - id: VQ-06
+        name: Axis Labels & Title
+        score: 2
+        max: 2
+        passed: true
+        comment: Position and Information content (bits) with units
+    design_excellence:
+      score: 16
+      max: 20
+      items:
+      - id: DE-01
+        name: Aesthetic Sophistication
+        score: 6
+        max: 8
+        passed: true
+        comment: Custom DNA palette, two-panel layout, colored heatmap y-labels, annotation
+          with curved arrow
+      - id: DE-02
+        name: Visual Refinement
+        score: 5
+        max: 6
+        passed: true
+        comment: Spines removed, subtle grid alpha=0.15, white linecolor in heatmap,
+          generous panel spacing
+      - id: DE-03
+        name: Data Storytelling
+        score: 5
+        max: 6
+        passed: true
+        comment: Yellow highlight on most conserved position with annotation; heatmap
+          provides complementary detail
+    spec_compliance:
+      score: 15
+      max: 15
+      items:
+      - id: SC-01
+        name: Plot Type
+        score: 5
+        max: 5
+        passed: true
+        comment: Correct sequence logo with vertically stacked letters scaled by information
+          content
+      - id: SC-02
+        name: Required Features
+        score: 4
+        max: 4
+        passed: true
+        comment: 'All spec features: stacked letters, IC scaling, standard colors,
+          scaled glyphs'
+      - id: SC-03
+        name: Data Mapping
+        score: 3
+        max: 3
+        passed: true
+        comment: X-axis positions 1-10, Y-axis IC in bits 0-2 range
+      - id: SC-04
+        name: Title & Legend
+        score: 3
+        max: 3
+        passed: true
+        comment: Correct title format; letters self-identify by color and shape
+    data_quality:
+      score: 15
+      max: 15
+      items:
+      - id: DQ-01
+        name: Feature Coverage
+        score: 6
+        max: 6
+        passed: true
+        comment: 'Full range: strong conservation (pos 3,7,8), moderate (pos 2,6,9),
+          none (pos 5)'
+      - id: DQ-02
+        name: Realistic Context
+        score: 5
+        max: 5
+        passed: true
+        comment: DNA transcription factor binding site motif — real bioinformatics
+          context
+      - id: DQ-03
+        name: Appropriate Scale
+        score: 4
+        max: 4
+        passed: true
+        comment: IC values 0-1.4 bits realistic for DNA; frequencies sum to 1 per
+          position
+    code_quality:
+      score: 10
+      max: 10
+      items:
+      - id: CQ-01
+        name: KISS Structure
+        score: 3
+        max: 3
+        passed: true
+        comment: 'Linear flow: imports, data, IC calculation, logo rendering, heatmap,
+          save'
+      - id: CQ-02
+        name: Reproducibility
+        score: 2
+        max: 2
+        passed: true
+        comment: Fully deterministic hardcoded frequency data
+      - id: CQ-03
+        name: Clean Imports
+        score: 2
+        max: 2
+        passed: true
+        comment: All imports used
+      - id: CQ-04
+        name: Code Elegance
+        score: 2
+        max: 2
+        passed: true
+        comment: Clean, well-structured; TextPath/PathPatch is correct technique
+      - id: CQ-05
+        name: Output & API
+        score: 1
+        max: 1
+        passed: true
+        comment: Saves as plot.png, dpi=300, bbox_inches=tight, no deprecated API
+    library_mastery:
+      score: 7
+      max: 10
+      items:
+      - id: LM-01
+        name: Idiomatic Usage
+        score: 4
+        max: 5
+        passed: true
+        comment: Good use of sns.set_context, set_style, despine, heatmap, color_palette,
+          light_palette
+      - id: LM-02
+        name: Distinctive Features
+        score: 3
+        max: 5
+        passed: true
+        comment: sns.heatmap with annotations, sns.light_palette for custom cmap,
+          sns.despine
+  verdict: APPROVED
+impl_tags:
+  dependencies: []
+  techniques:
+  - subplots
+  - annotations
+  - patches
+  - manual-ticks
+  - colorbar
+  patterns:
+  - data-generation
+  - iteration-over-groups
+  dataprep: []
+  styling:
+  - grid-styling
+  - custom-colormap
+  - edge-highlighting