pylocuszoom 0.5.0__tar.gz → 0.6.0__tar.gz

pylocuszoom-0.6.0/.github/workflows/publish.yml

@@ -0,0 +1,108 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    outputs:
+      version: ${{ steps.version.outputs.version }}
+      sha256: ${{ steps.sha256.outputs.sha256 }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Get version
+        id: version
+        run: |
+          VERSION=$(grep '^version = ' pyproject.toml | sed 's/version = "\(.*\)"/\1/')
+          echo "version=$VERSION" >> "$GITHUB_OUTPUT"
+
+      - name: Build package
+        run: uv build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+      - name: Wait for PyPI availability
+        env:
+          PKG_VERSION: ${{ steps.version.outputs.version }}
+        run: |
+          echo "Waiting for pylocuszoom $PKG_VERSION to be available on PyPI..."
+          for i in {1..30}; do
+            if curl -s "https://pypi.org/pypi/pylocuszoom/$PKG_VERSION/json" | grep -q '"version"'; then
+              echo "Package available on PyPI"
+              break
+            fi
+            echo "Attempt $i: Package not yet available, waiting 10s..."
+            sleep 10
+          done
+
+      - name: Get SHA256
+        id: sha256
+        env:
+          PKG_VERSION: ${{ steps.version.outputs.version }}
+        run: |
+          URL="https://pypi.io/packages/source/p/pylocuszoom/pylocuszoom-$PKG_VERSION.tar.gz"
+          SHA256=$(curl -sL "$URL" | sha256sum | cut -d' ' -f1)
+          echo "sha256=$SHA256" >> "$GITHUB_OUTPUT"
+          echo "SHA256: $SHA256"
+
+  update-bioconda:
+    needs: publish
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Update bioconda/meta.yaml
+        env:
+          PKG_VERSION: ${{ needs.publish.outputs.version }}
+          PKG_SHA256: ${{ needs.publish.outputs.sha256 }}
+        run: |
+          # Update version
+          sed -i "s/{% set version = \".*\" %}/{% set version = \"$PKG_VERSION\" %}/" bioconda/meta.yaml
+
+          # Update sha256
+          sed -i "s/sha256: .*/sha256: $PKG_SHA256/" bioconda/meta.yaml
+
+          # Update plotly version requirement
+          sed -i "s/plotly >=5.0.0/plotly >=5.15.0/" bioconda/meta.yaml
+
+          # Add new dependencies if missing
+          if ! grep -q "pydantic" bioconda/meta.yaml; then
+            sed -i '/adjusttext/a\    - pydantic >=2.0.0' bioconda/meta.yaml
+          fi
+          if ! grep -q "requests" bioconda/meta.yaml; then
+            sed -i '/pydantic/a\    - requests >=2.25.0' bioconda/meta.yaml
+          fi
+          if ! grep -q "tqdm" bioconda/meta.yaml; then
+            sed -i '/requests/a\    - tqdm >=4.60.0' bioconda/meta.yaml
+          fi
+
+          cat bioconda/meta.yaml
+
+      - name: Create Pull Request
+        uses: peter-evans/create-pull-request@v6
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: "chore: update bioconda recipe for new release"
+          branch: bioconda-update
+          title: "Update bioconda recipe"
+          body: |
+            Automated update of bioconda/meta.yaml after PyPI release.
+
+            **Next steps:**
+            1. Review this PR
+            2. Merge to main
+            3. Copy `bioconda/meta.yaml` to your fork of bioconda-recipes
+            4. Submit PR to bioconda-recipes
+          labels: |
+            bioconda
+            automated

{pylocuszoom-0.5.0 → pylocuszoom-0.6.0}/CHANGELOG.md

@@ -5,7 +5,29 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [0.6.0] - 2026-01-27
+
+### Added
+- `plot_phewas()` method for phenome-wide association study plots
+- `plot_forest()` method for forest plots (meta-analysis visualization)
+- PheWAS category color palette with 12 distinct colors
+- Forest plot and PheWAS validation utilities
+- Backend methods: `axvline()`, `hbar()`, `errorbar_h()` for new plot types
+- Example plots for PheWAS and forest plots
+- Progress bars (tqdm) for recombination map and liftover chain downloads
+- `requests` and `tqdm` as core dependencies for reliable downloads with progress
+- `pytest-randomly` and `pytest-xdist` as dev dependencies for test randomization and parallel execution
+
+### Changed
+- Bumped minimum Plotly version to 5.15.0 (required for multiple legends feature)
+- eQTL loaders now output `effect_size` column instead of `effect` for plotter compatibility
+- Download functions now use `requests` with streaming and progress bars instead of `urllib`
+
+### Fixed
+- SAIGE loader now prefers SPA-adjusted p-values (`p.value.NA`) over raw p-values when both present
+- BED loader now handles BED12 format and files with more than 6 columns
+- eQTL panel in `plot_stacked()` now filters by chromosome in addition to position
+- Validation errors for non-numeric p-values or positions now show clear "must be numeric" message instead of runtime errors
 
 ## [0.5.0] - 2026-01-27
 
@@ -118,7 +140,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - bokeh >= 3.8.2
 - kaleido >= 0.2.0
 
-[Unreleased]: https://github.com/michael-denyer/pyLocusZoom/compare/v0.5.0...HEAD
+[Unreleased]: https://github.com/michael-denyer/pyLocusZoom/compare/v0.6.0...HEAD
+[0.6.0]: https://github.com/michael-denyer/pyLocusZoom/compare/v0.5.0...v0.6.0
 [0.5.0]: https://github.com/michael-denyer/pyLocusZoom/compare/v0.4.0...v0.5.0
 [0.4.0]: https://github.com/michael-denyer/pyLocusZoom/compare/v0.3.0...v0.4.0
 [0.3.0]: https://github.com/michael-denyer/pyLocusZoom/compare/v0.2.0...v0.3.0

{pylocuszoom-0.5.0 → pylocuszoom-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pylocuszoom
-Version: 0.5.0
+Version: 0.6.0
 Summary: Publication-ready regional association plots with LD coloring, gene tracks, and recombination overlays
 Project-URL: Homepage, https://github.com/michael-denyer/pylocuszoom
 Project-URL: Documentation, https://github.com/michael-denyer/pylocuszoom#readme
@@ -26,13 +26,17 @@ Requires-Dist: loguru>=0.7.0
 Requires-Dist: matplotlib>=3.5.0
 Requires-Dist: numpy>=1.21.0
 Requires-Dist: pandas>=1.4.0
-Requires-Dist: plotly>=5.0.0
+Requires-Dist: plotly>=5.15.0
 Requires-Dist: pydantic>=2.0.0
 Requires-Dist: pyliftover>=0.4
+Requires-Dist: requests>=2.25.0
+Requires-Dist: tqdm>=4.60.0
 Provides-Extra: all
 Requires-Dist: pyspark>=3.0.0; extra == 'all'
 Provides-Extra: dev
 Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
+Requires-Dist: pytest-randomly>=3.0.0; extra == 'dev'
+Requires-Dist: pytest-xdist>=3.0.0; extra == 'dev'
 Requires-Dist: pytest>=7.0.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
 Provides-Extra: spark
@@ -73,9 +77,11 @@ Inspired by [LocusZoom](http://locuszoom.org/) and [locuszoomr](https://github.c
 2. **Stacked plots**: Compare multiple GWAS/phenotypes vertically
 3. **eQTL plot**: Expression QTL data aligned with association plots and gene tracks
 4. **Fine-mapping plots**: Visualize SuSiE credible sets with posterior inclusion probabilities
-5. **Multiple charting libraries**: matplotlib (static), plotly (interactive), bokeh (dashboards)
-6. **Pandas and PySpark support**: Works with both Pandas and PySpark DataFrames for large-scale genomics data
-7. **Convenience data file loaders**: Load and validate common GWAS, eQTL and fine-mapping file formats
+5. **PheWAS plots**: Phenome-wide association study visualization across multiple phenotypes
+6. **Forest plots**: Meta-analysis effect size visualization with confidence intervals
+7. **Multiple charting libraries**: matplotlib (static), plotly (interactive), bokeh (dashboards)
+8. **Pandas and PySpark support**: Works with both Pandas and PySpark DataFrames for large-scale genomics data
+9. **Convenience data file loaders**: Load and validate common GWAS, eQTL and fine-mapping file formats
 
 ## Installation
 
@@ -261,6 +267,48 @@ fig = plotter.plot_stacked(
 
 ![Example fine-mapping plot](examples/finemapping_plot.png)
 
+## PheWAS Plots
+
+Visualize associations of a single variant across multiple phenotypes:
+
+```python
+phewas_df = pd.DataFrame({
+    "phenotype": ["Height", "BMI", "T2D", "CAD", "HDL"],
+    "p_value": [1e-15, 0.05, 1e-8, 1e-3, 1e-10],
+    "category": ["Anthropometric", "Anthropometric", "Metabolic", "Cardiovascular", "Lipids"],
+})
+
+fig = plotter.plot_phewas(
+    phewas_df,
+    variant_id="rs12345",
+    category_col="category",
+)
+```
+
+![Example PheWAS plot](examples/phewas_plot.png)
+
+## Forest Plots
+
+Create forest plots for meta-analysis visualization:
+
+```python
+forest_df = pd.DataFrame({
+    "study": ["Study A", "Study B", "Study C", "Meta-analysis"],
+    "effect": [0.45, 0.52, 0.38, 0.46],
+    "ci_lower": [0.30, 0.35, 0.20, 0.40],
+    "ci_upper": [0.60, 0.69, 0.56, 0.52],
+    "weight": [25, 35, 20, 100],
+})
+
+fig = plotter.plot_forest(
+    forest_df,
+    variant_id="rs12345",
+    weight_col="weight",
+)
+```
+
+![Example forest plot](examples/forest_plot.png)
+
 ## PySpark Support
 
 For large-scale genomics data, pass PySpark DataFrames directly:

{pylocuszoom-0.5.0 → pylocuszoom-0.6.0}/README.md

@@ -32,9 +32,11 @@ Inspired by [LocusZoom](http://locuszoom.org/) and [locuszoomr](https://github.c
 2. **Stacked plots**: Compare multiple GWAS/phenotypes vertically
 3. **eQTL plot**: Expression QTL data aligned with association plots and gene tracks
 4. **Fine-mapping plots**: Visualize SuSiE credible sets with posterior inclusion probabilities
-5. **Multiple charting libraries**: matplotlib (static), plotly (interactive), bokeh (dashboards)
-6. **Pandas and PySpark support**: Works with both Pandas and PySpark DataFrames for large-scale genomics data
-7. **Convenience data file loaders**: Load and validate common GWAS, eQTL and fine-mapping file formats
+5. **PheWAS plots**: Phenome-wide association study visualization across multiple phenotypes
+6. **Forest plots**: Meta-analysis effect size visualization with confidence intervals
+7. **Multiple charting libraries**: matplotlib (static), plotly (interactive), bokeh (dashboards)
+8. **Pandas and PySpark support**: Works with both Pandas and PySpark DataFrames for large-scale genomics data
+9. **Convenience data file loaders**: Load and validate common GWAS, eQTL and fine-mapping file formats
 
 ## Installation
 
@@ -220,6 +222,48 @@ fig = plotter.plot_stacked(
 
 ![Example fine-mapping plot](examples/finemapping_plot.png)
 
+## PheWAS Plots
+
+Visualize associations of a single variant across multiple phenotypes:
+
+```python
+phewas_df = pd.DataFrame({
+    "phenotype": ["Height", "BMI", "T2D", "CAD", "HDL"],
+    "p_value": [1e-15, 0.05, 1e-8, 1e-3, 1e-10],
+    "category": ["Anthropometric", "Anthropometric", "Metabolic", "Cardiovascular", "Lipids"],
+})
+
+fig = plotter.plot_phewas(
+    phewas_df,
+    variant_id="rs12345",
+    category_col="category",
+)
+```
+
+![Example PheWAS plot](examples/phewas_plot.png)
+
+## Forest Plots
+
+Create forest plots for meta-analysis visualization:
+
+```python
+forest_df = pd.DataFrame({
+    "study": ["Study A", "Study B", "Study C", "Meta-analysis"],
+    "effect": [0.45, 0.52, 0.38, 0.46],
+    "ci_lower": [0.30, 0.35, 0.20, 0.40],
+    "ci_upper": [0.60, 0.69, 0.56, 0.52],
+    "weight": [25, 35, 20, 100],
+})
+
+fig = plotter.plot_forest(
+    forest_df,
+    variant_id="rs12345",
+    weight_col="weight",
+)
+```
+
+![Example forest plot](examples/forest_plot.png)
+
 ## PySpark Support
 
 For large-scale genomics data, pass PySpark DataFrames directly:

{pylocuszoom-0.5.0 → pylocuszoom-0.6.0}/bioconda/meta.yaml

@@ -1,5 +1,5 @@
 {% set name = "pylocuszoom" %}
-{% set version = "0.3.0" %}
+{% set version = "0.5.0" %}
 
 package:
   name: {{ name|lower }}
@@ -7,7 +7,7 @@ package:
 
 source:
   url: https://pypi.io/packages/source/{{ name[0] }}/{{ name }}/{{ name }}-{{ version }}.tar.gz
-  sha256: REPLACE_WITH_SHA256_AFTER_PYPI_PUBLISH
+  sha256: 5aa46c51631e2c736867b85144f390da94f813146eeef5f943038a772820022e
 
 build:
   noarch: python

{pylocuszoom-0.5.0 → pylocuszoom-0.6.0}/docs/USER_GUIDE.md

@@ -11,6 +11,8 @@ Comprehensive documentation for pyLocusZoom - regional association plots for GWA
   - [Stacked Plots](#stacked-plots)
   - [eQTL Overlay](#eqtl-overlay)
   - [Fine-mapping Visualization](#fine-mapping-visualization)
+  - [PheWAS Plots](#phewas-plots)
+  - [Forest Plots](#forest-plots)
 - [Backends](#backends)
   - [Matplotlib (Static)](#matplotlib-static)
   - [Plotly (Interactive)](#plotly-interactive)
@@ -19,6 +21,8 @@ Comprehensive documentation for pyLocusZoom - regional association plots for GWA
   - [LocusZoomPlotter](#locuszoomplotter)
   - [plot() Method](#plot-method)
   - [plot_stacked() Method](#plot_stacked-method)
+  - [plot_phewas() Method](#plot_phewas-method)
+  - [plot_forest() Method](#plot_forest-method)
 - [File Loaders](#file-loaders)
   - [GWAS Loaders](#gwas-loaders)
   - [eQTL Loaders](#eqtl-loaders)
@@ -209,6 +213,63 @@ fig = plotter.plot_stacked(
 - Credible sets colored distinctly (CS1 = red, CS2 = blue, etc.)
 - Variants not in credible sets shown in gray
 
+### PheWAS Plots
+
+Visualize associations of a single variant across multiple phenotypes in a phenome-wide association study.
+
+![PheWAS plot](../examples/phewas_plot.png)
+
+```python
+phewas_df = pd.DataFrame({
+    "phenotype": ["Height", "BMI", "T2D", "CAD", "HDL"],
+    "p_value": [1e-15, 0.05, 1e-8, 1e-3, 1e-10],
+    "category": ["Anthropometric", "Anthropometric", "Metabolic", "Cardiovascular", "Lipids"],
+})
+
+fig = plotter.plot_phewas(
+    phewas_df,
+    variant_id="rs12345",
+    category_col="category",
+    significance_threshold=5e-8,
+)
+```
+
+**Features:**
+- Phenotypes grouped and colored by category
+- Genome-wide significance line (red dashed)
+- Optional effect direction markers (triangles for +/-)
+- 12-color palette for distinct categories
+
+### Forest Plots
+
+Create forest plots for meta-analysis visualization showing effect sizes with confidence intervals.
+
+![Forest plot](../examples/forest_plot.png)
+
+```python
+forest_df = pd.DataFrame({
+    "study": ["Study A", "Study B", "Study C", "Meta-analysis"],
+    "effect": [0.45, 0.52, 0.38, 0.46],
+    "ci_lower": [0.30, 0.35, 0.20, 0.40],
+    "ci_upper": [0.60, 0.69, 0.56, 0.52],
+    "weight": [25, 35, 20, 100],  # Optional: affects marker size
+})
+
+fig = plotter.plot_forest(
+    forest_df,
+    variant_id="rs12345",
+    weight_col="weight",
+    null_value=0.0,  # Reference line (0 for beta, 1 for OR)
+    effect_label="Effect Size",
+)
+```
+
+**Features:**
+- Effect sizes as squares with confidence interval whiskers
+- Marker size scaled by study weight (optional)
+- Null effect reference line
+- Study names as y-axis labels
+
 ---
 
 ## Backends
@@ -391,6 +452,66 @@ fig = plotter.plot_stacked(
 | `finemapping_df` | DataFrame | None | Fine-mapping results with `pos` and `pip`. |
 | `finemapping_cs_col` | str | `"cs"` | Column for credible set assignment. |
 
+### plot_phewas() Method
+
+Create a PheWAS (Phenome-Wide Association Study) plot.
+
+```python
+fig = plotter.plot_phewas(
+    phewas_df,                      # Required: PheWAS results
+    variant_id="rs12345",           # Required: variant ID for title
+    phenotype_col="phenotype",      # Phenotype name column
+    p_col="p_value",                # P-value column
+    category_col="category",        # Category for grouping/coloring
+    effect_col=None,                # Effect column for direction markers
+    significance_threshold=5e-8,    # Significance line threshold
+    figsize=(10, 8),                # Figure dimensions
+)
+```
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `phewas_df` | DataFrame | Required | PheWAS results with phenotype and p-value. |
+| `variant_id` | str | Required | Variant ID for plot title. |
+| `phenotype_col` | str | `"phenotype"` | Column with phenotype names. |
+| `p_col` | str | `"p_value"` | Column with p-values. |
+| `category_col` | str | `"category"` | Column for phenotype categories. |
+| `effect_col` | str | None | Column with effect sizes for direction markers. |
+| `significance_threshold` | float | `5e-8` | P-value for significance line. |
+| `figsize` | tuple | `(10, 8)` | Figure dimensions (width, height). |
+
+### plot_forest() Method
+
+Create a forest plot for meta-analysis visualization.
+
+```python
+fig = plotter.plot_forest(
+    forest_df,                      # Required: meta-analysis data
+    variant_id="rs12345",           # Required: variant ID for title
+    study_col="study",              # Study/phenotype name column
+    effect_col="effect",            # Effect size column
+    ci_lower_col="ci_lower",        # Lower CI column
+    ci_upper_col="ci_upper",        # Upper CI column
+    weight_col=None,                # Optional weight column for marker sizes
+    null_value=0.0,                 # Null effect value (0 for beta, 1 for OR)
+    effect_label="Effect Size",     # X-axis label
+    figsize=(8, 6),                 # Figure dimensions
+)
+```
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `forest_df` | DataFrame | Required | Forest plot data with effects and CIs. |
+| `variant_id` | str | Required | Variant ID for plot title. |
+| `study_col` | str | `"study"` | Column with study/phenotype names. |
+| `effect_col` | str | `"effect"` | Column with effect sizes. |
+| `ci_lower_col` | str | `"ci_lower"` | Column with lower confidence interval. |
+| `ci_upper_col` | str | `"ci_upper"` | Column with upper confidence interval. |
+| `weight_col` | str | None | Column with study weights (affects marker size). |
+| `null_value` | float | `0.0` | Reference value for null effect line. |
+| `effect_label` | str | `"Effect Size"` | X-axis label. |
+| `figsize` | tuple | `(8, 6)` | Figure dimensions (width, height). |
+
 ---
 
 ## File Loaders
@@ -568,7 +689,44 @@ gwas_df = pd.DataFrame({
 | `pos` | int | Yes | Variant position. |
 | `p_value` | float | Yes | Association p-value. |
 | `gene` | str | Yes | Target gene symbol. |
-| `effect` | float | No | Effect size for color coding. |
+| `effect_size` | float | No | Effect size for color coding. |
+
+### PheWAS DataFrame
+
+| Column | Type | Required | Description |
+|--------|------|----------|-------------|
+| `phenotype` | str | Yes | Phenotype name. |
+| `p_value` | float | Yes | Association p-value. |
+| `category` | str | No | Phenotype category for grouping/coloring. |
+| `effect_size` | float | No | Effect size for direction markers. |
+
+```python
+phewas_df = pd.DataFrame({
+    "phenotype": ["Height", "BMI", "T2D"],
+    "p_value": [1e-15, 0.05, 1e-8],
+    "category": ["Anthropometric", "Anthropometric", "Metabolic"],
+})
+```
+
+### Forest Plot DataFrame
+
+| Column | Type | Required | Description |
+|--------|------|----------|-------------|
+| `study` | str | Yes | Study or phenotype name. |
+| `effect` | float | Yes | Effect size (beta, OR, HR). |
+| `ci_lower` | float | Yes | Lower confidence interval bound. |
+| `ci_upper` | float | Yes | Upper confidence interval bound. |
+| `weight` | float | No | Study weight (affects marker size). |
+
+```python
+forest_df = pd.DataFrame({
+    "study": ["Study A", "Study B", "Meta-analysis"],
+    "effect": [0.45, 0.52, 0.46],
+    "ci_lower": [0.30, 0.35, 0.40],
+    "ci_upper": [0.60, 0.69, 0.52],
+    "weight": [25, 35, 100],
+})
+```
 
 ---