genome-spy-python 0.7.0__tar.gz → 0.8.0__tar.gz

genome_spy_python-0.8.0/.agents/skills/contribute-genomespy/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: contribute-genomespy
+description: Use whenever work in genome-spy-python requires creating or updating an upstream GenomeSpy PR, including feature, fix, documentation and workflow changes.
+---
+
+# Contribute to GenomeSpy
+
+1. Keep Python-specific work here. Put reusable engine behavior upstream when
+   the existing native API cannot cover it cleanly.
+2. Locate the intended GenomeSpy checkout and verify its Git remotes and branch;
+   do not assume a temporary clone is current. Read its `AGENTS.md`.
+3. Use that checkout's `.agents/skills/plan-genomespy-change/SKILL.md` before
+   implementation and before opening or updating any upstream PR. If code is
+   already written, run its architecture-fit check before PR preparation.
+   Use `.agents/skills/prepare-genomespy-change/SKILL.md` for commits and PR
+   preparation. Follow those upstream workflows rather than copying them here.
+   If either skill is absent, locate the current instructions before proceeding.
+4. Keep upstream edits separate from Python integration work and coordinate file
+   ownership with active chats when authorized. Preserve the agreed release/source
+   dependency; do not silently ship a local unreleased Core build.
+5. Report the upstream PR/commit, verification and remaining integration dependency.

{genome_spy_python-0.7.0 → genome_spy_python-0.8.0}/.github/workflows/ci.yml

@@ -4,8 +4,22 @@ on:
   push:
     branches: [main]
   pull_request:
+  workflow_dispatch:
+    inputs:
+      full_scanpy:
+        description: Run all Scanpy references, browsers and workflows
+        type: boolean
+        default: false
   # Reused by the release workflow as a pre-publish gate.
   workflow_call:
+    inputs:
+      full_scanpy:
+        type: boolean
+        default: false
+
+concurrency:
+  group: ci-${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
 
 jobs:
   test:
@@ -34,7 +48,7 @@ jobs:
         run: uv run mypy src/
       - name: Run package tests
         run: >-
-          uv run pytest tests/ -x
+          uv run pytest tests/ -x --ignore=tests/integrations/scanpy
           -m "not docs and not codegen"
           --durations=10
       - run: node --test tests/*.test.mjs
@@ -71,6 +85,94 @@ jobs:
           --with "$GITHUB_WORKSPACE"/dist/*.whl
           python -c "from importlib.resources import files; import genome_spy as gs; package = files('genome_spy'); assert package.joinpath('schema/genome-spy-schema.json').is_file(); assert package.joinpath('schema/capabilities.json').is_file(); assert package.joinpath('static/widget.js').is_file(); assert package.joinpath('static/genome-spy.js').is_file(); assert package.joinpath('static/controls.js').is_file(); assert package.joinpath('static/inspector.js').is_file(); chart = gs.Chart([{'x': 1}]).mark_point().encode(x='x:Q'); spec = chart.to_dict(); assert spec['mark'] == 'point'; assert spec['encoding']['x']['field'] == 'x'; assert spec[chr(36) + 'schema'].endswith('/schema.json')"
 
+  scanpy:
+    runs-on: ubuntu-latest
+    timeout-minutes: 75
+    strategy:
+      fail-fast: false
+      matrix:
+        python: ${{ fromJSON((github.ref == 'refs/heads/main' || inputs.full_scanpy) && '["3.11", "3.12", "3.13"]' || '["3.11"]') }}
+    env:
+      MPLBACKEND: Agg
+    steps:
+      - uses: actions/checkout@v7
+      - uses: astral-sh/setup-uv@v9.0.0
+        with:
+          enable-cache: true
+          python-version: ${{ matrix.python }}
+      - run: uv sync --locked --dev --extra scanpy --group scanpy-test
+      - name: Fast Scanpy checks
+        if: github.ref != 'refs/heads/main' && !inputs.full_scanpy
+        run: >-
+          uv run --no-sync pytest tests/integrations/scanpy
+          --ignore=tests/integrations/scanpy/browser
+          -m "not reference and not workflow" -q --durations=10
+      - name: Full Scanpy checks
+        if: github.ref == 'refs/heads/main' || inputs.full_scanpy
+        run: >-
+          uv run --no-sync pytest tests/integrations/scanpy
+          --ignore=tests/integrations/scanpy/browser -q --durations=10
+      # The renderer is JavaScript; repeat it once, rather than for each Python.
+      - if: matrix.python == '3.11'
+        run: uv run --no-sync python -m playwright install --with-deps chromium
+      - name: Browser smoke checks
+        if: matrix.python == '3.11' && github.ref != 'refs/heads/main' && !inputs.full_scanpy
+        run: >-
+          uv run --no-sync pytest tests/integrations/scanpy/browser -m smoke -q
+          --basetemp="${{ runner.temp }}/scanpy-browser"
+      - name: Full browser checks
+        if: matrix.python == '3.11' && (github.ref == 'refs/heads/main' || inputs.full_scanpy)
+        run: >-
+          uv run --no-sync pytest tests/integrations/scanpy/browser -q
+          --basetemp="${{ runner.temp }}/scanpy-browser"
+      - name: Render the workflow notebooks in JupyterLab
+        if: matrix.python == '3.11' && (github.ref == 'refs/heads/main' || inputs.full_scanpy)
+        run: |
+          uv run --no-sync python tools/check_notebook_rendering.py integrations/scanpy/notebooks/scanpy_umap.ipynb --screenshot "${{ runner.temp }}/scanpy-browser/umap-notebook.png"
+          uv run --no-sync python tools/check_notebook_rendering.py integrations/scanpy/notebooks/scanpy_expression.ipynb --screenshot "${{ runner.temp }}/scanpy-browser/expression-notebook.png"
+      - uses: actions/upload-artifact@v7
+        if: always() && matrix.python == '3.11'
+        with:
+          name: scanpy-browser
+          path: ${{ runner.temp }}/scanpy-browser
+          if-no-files-found: ignore
+
+  scanpy-compatibility:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    env:
+      MPLBACKEND: Agg
+    steps:
+      - uses: actions/checkout@v7
+      - uses: astral-sh/setup-uv@v9.0.0
+        with:
+          python-version: "3.12"
+      - name: Install current Scanpy separately from the reference environment
+        run: |
+          uv venv --python 3.12 "$RUNNER_TEMP/scanpy-compat"
+          uv pip install --python "$RUNNER_TEMP/scanpy-compat/bin/python" \
+            -e '.[scanpy]' 'scanpy==1.12.4' pytest pillow playwright pyarrow
+      - name: Fast compatibility checks
+        if: github.ref != 'refs/heads/main' && !inputs.full_scanpy
+        run: >-
+          "$RUNNER_TEMP/scanpy-compat/bin/python" -m pytest
+          tests/integrations/scanpy --ignore=tests/integrations/scanpy/browser
+          -m "not reference and not workflow" -q --durations=10
+      - name: Full compatibility checks
+        if: github.ref == 'refs/heads/main' || inputs.full_scanpy
+        run: >-
+          "$RUNNER_TEMP/scanpy-compat/bin/python" -m pytest
+          tests/integrations/scanpy --ignore=tests/integrations/scanpy/browser -q
+      - if: github.ref == 'refs/heads/main' || inputs.full_scanpy
+        run: '"$RUNNER_TEMP/scanpy-compat/bin/python" -m playwright install --with-deps chromium'
+      - name: Check native interactions with current Scanpy
+        if: github.ref == 'refs/heads/main' || inputs.full_scanpy
+        run: >-
+          "$RUNNER_TEMP/scanpy-compat/bin/python" -m pytest
+          tests/integrations/scanpy/browser/test_grid_interactions.py::TestGridInteractions
+          tests/integrations/scanpy/browser/test_linked_embeddings.py
+          -q --basetemp="${{ runner.temp }}/scanpy-compat-browser"
+
   codegen:
     runs-on: ubuntu-latest
     steps:
@@ -134,6 +236,16 @@ jobs:
           "$RUNNER_TEMP/notebook-env/bin/python" tools/check_notebook_rendering.py \
             notebooks/edit_sequence.ipynb --workflow sequence \
             --screenshot "$RUNNER_TEMP/edit-sequence.png"
+      - name: Verify the agent guide notebook roundtrip
+        run: |
+          "$RUNNER_TEMP/notebook-env/bin/python" tools/check_notebook_rendering.py \
+            docs/agents/embed-api.md --workflow agent-embed \
+            --screenshot "$RUNNER_TEMP/agent-embed.png"
+      - name: Exercise Python-linked chart widgets
+        run: |
+          "$RUNNER_TEMP/notebook-env/bin/python" tools/check_notebook_rendering.py \
+            notebooks/penguin_python_roundtrip.ipynb --workflow python-rows \
+            --screenshot "$RUNNER_TEMP/python-rows.png"
       - uses: actions/upload-artifact@v7
         if: always()
         with:

{genome_spy_python-0.7.0 → genome_spy_python-0.8.0}/.github/workflows/docs.yml

@@ -31,6 +31,8 @@ jobs:
       # Example modules that back the gallery need the example runtime
       # (pandas/numpy) plus the docs toolchain.
       - run: uv sync --locked --group docs --group dev
+      - name: Prepare Scanpy guide data
+        run: uv run integrations/scanpy/prepare_guide_data.py
       # Render real chart screenshots for the gallery cards.
       - name: Render gallery thumbnails
         run: |

{genome_spy_python-0.7.0 → genome_spy_python-0.8.0}/.github/workflows/release.yml

@@ -23,6 +23,8 @@ concurrency:
 jobs:
   check:
     uses: ./.github/workflows/ci.yml
+    with:
+      full_scanpy: true
 
   build:
     needs: check

{genome_spy_python-0.7.0 → genome_spy_python-0.8.0}/.gitignore

@@ -54,6 +54,11 @@ coverage.xml
 .pytest_cache/
 cover/
 
+# Generated test images stay local or in temporary CI artifacts.
+/tests/**/*.png
+# Scanpy downloads this count dataset on first use; it is never vendored.
+**/data/pbmc3k_raw.h5ad
+
 # Translations
 *.mo
 *.pot
@@ -251,3 +256,6 @@ scripts/_fetch_reference.py
 
 # Local recording demos and working files
 /demos/
+
+# Generated Scanpy benchmark observations are not reference fixtures.
+tests/integrations/scanpy/fixtures/*performance*.json

{genome_spy_python-0.7.0 → genome_spy_python-0.8.0}/.pre-commit-config.yaml

@@ -1,6 +1,13 @@
 repos:
+  - repo: local
+    hooks:
+      - id: no-test-artifacts
+        name: keep generated test artifacts out of Git
+        language: fail
+        entry: Generated test media and benchmark reports belong in temporary directories, not Git.
+        files: '(?i)^tests/.*(?:\.(?:png|jpe?g|gif|webp|svg|pdf|mp4|webm|mov|avi|bmp|tiff?|avif|html|h5ad|h5|parquet|arrow|feather|npz|npy|pkl|pickle)|performance[^/]*\.json)$'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.0
+    rev: v0.15.19
     hooks:
       - id: ruff
         args: [--fix]

genome_spy_python-0.8.0/AGENTS.md

@@ -0,0 +1,101 @@
+# Repository instructions
+
+`genome-spy-python` wraps GenomeSpy in an idiomatic Python API, as Altair wraps
+Vega-Lite. Users author compatible specs, serialize JSON, and render in notebooks.
+Treat it as a library with a clean public API. Build the reusable Core grammar
+before app-specific concepts. Notebook rendering is first-class; prefer `anywidget`.
+
+## Layout
+
+| Path | Purpose |
+| --- | --- |
+| `src/genome_spy/` | Installable library |
+| `src/genome_spy/integrations/<library>/` | Optional integration implementations |
+| `tests/` | pytest suite |
+| `integrations/` | Tracked integration plans and per-library workflow notebooks |
+| `scripts/` | Helpers run via `uv run` |
+| `plans/` | Plans, context, and implementation notes |
+| `material/` | Local reference documents; not committed |
+| `tmp/` | External reference code/repos; not committed |
+
+## Working rules
+
+- Think before coding: state assumptions and tradeoffs; push back when warranted.
+- Apply YAGNI and the [Ponytail rules](https://github.com/DietrichGebert/ponytail/blob/main/.agents/rules/ponytail.md):
+  complete the task with the least new code. Avoid unrequested features,
+  wrappers, conversions, options, and speculative abstractions. If 200 lines
+  could be 50, rewrite them.
+- Prefer existing repository code, then standard-library/platform features,
+  then installed dependencies, then minimal new code. Do not add a dependency
+  for a few lines of functionality.
+- Before editing, trace affected callers, tests, fixtures, configuration, and
+  exports. Fix shared root causes once and complete every affected part.
+- Make surgical changes: match existing style, remove imports/variables orphaned
+  by your edits, preserve existing layers and native value forms, and leave
+  unrelated code alone. Keep validation and error handling when moving code.
+- Prefer equally small solutions that handle edge cases. Preserve security,
+  accessibility, trust-boundary checks, and required hardware calibration.
+- Keep comments to one-line explanations of why. Document deliberate shortcuts
+  as `shortcut: <the limit>, <when to upgrade>`.
+- Set verifiable goals and give a brief plan for multi-step work.
+- When work requires an upstream GenomeSpy PR, use
+  [contribute-genomespy](.agents/skills/contribute-genomespy/SKILL.md).
+- Keep core logic pure Python; isolate I/O and integration at the edges.
+- Follow the linked [language, docstring, formatting, and gallery standards](docs/contributing/standards.md).
+  Read the relevant sections before Python or gallery edits; they are requirements.
+
+## Testing and handoff
+
+Use pytest. Add or update tests for behavior changes, with fixed seeds for random
+behavior. Keep tests small and focused on one behavior. Apply the "Suspicious
+Check": tighten any test that could pass for the wrong reason.
+
+Never commit or push generated test artifacts, including reference images,
+screenshots, overlays, recordings and chart exports. Generate them in temporary
+directories or ignored local caches; track test source, generators and deliberate
+text fixtures. Keep committed notebooks free of execution outputs and widget
+state. Check outgoing commit history before pushing: deleting artifacts from the
+current tree does not remove old blobs.
+
+Use `uv` for environments and dependencies. Before handoff, run targeted tests for
+changed behavior and lint. Format before finalizing non-trivial edits; type-check
+when public Python code changes. End the handoff with any skipped or unvalidated
+work and material risks.
+Ruff is the formatting/lint authority; fix issues rather than suppressing them by
+default.
+
+| Task | Command |
+| --- | --- |
+| Sync environment | `uv sync --dev` |
+| Run tests | `uv run pytest tests/ -x` |
+| Lint | `uv run ruff check .` |
+| Format | `uv run ruff format .` |
+| Type-check | `uv run mypy src/` |
+| Install hooks | `uv run pre-commit install` |
+
+Make small, thematic commits. Use conventional commits:
+`<type>(<scope>): <description>` when a scope helps. Do not rewrite history unless
+explicitly asked.
+
+## Plans and references
+
+| Document | Read when |
+| --- | --- |
+| `integrations/README.md` | Integration layout, plan lifecycle, and clearance rules |
+| `integrations/<library>/STATUS.md` | Current implementation, next slice, blockers, and retained evidence |
+| `integrations/<library>/PLAN.md` | Planning or extending a library integration; update status with implementation |
+| `plans/` | Optional ignored local context; may be absent. Tracked integration plans and status own current scope and delivery. |
+
+## GitHub review evidence
+
+- For PR/issue screenshots and recordings, use the authenticated GitHub CLI's
+  native `--attach` support; it does not require a browser login. Check
+  `gh pr comment --help` before assuming the installed CLI supports uploads.
+- The default `gh` on this machine is older. A working official CLI is cached at
+  `tmp/github-cli-2.103.2/gh_2.103.2_macOS_arm64/bin/gh` in this repository. Use
+  that binary when present, or a newer official CLI with `--attach` support.
+- Write multiline comment text to a temporary file, then run the capable binary:
+  `gh pr comment NUMBER --repo OWNER/REPO --body-file /private/tmp/comment.md --attach /absolute/demo.webm`.
+  The upload becomes a playable GitHub attachment. Verify the posted comment
+  contains its `github.com/user-attachments/assets/` URL. Keep media out of Git,
+  reuse configured CLI authentication, and never print tokens.

{genome_spy_python-0.7.0 → genome_spy_python-0.8.0}/CHANGELOG.md

@@ -5,6 +5,32 @@ 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).
 
+## [0.8.0] - 2026-10-29
+
+### Added
+
+- Optional Scanpy plotting integration through
+  `import genome_spy.integrations.scanpy as gsc`, preserving supported plotting
+  names and arguments while Scanpy continues to own analysis.
+- Interactive embeddings, PCA diagnostics, dotplots, matrixplots, heatmaps,
+  clustermaps, expression tracks, ranked-gene summaries, quality checks,
+  time-series, DPT and PAGA plots. Unsupported plots and options fail explicitly.
+- `EmbeddingSummary` for linked cell selections, expression summaries,
+  histograms and marker tracks, with optional cell counts and selection retrieval
+  in Python.
+- Scanpy guides with live examples, downloadable notebooks, installation and
+  export instructions, and documented coverage limits.
+
+### Changed
+
+- Support Scanpy >=1.11.5,<1.13, tested with 1.11.5 and 1.12.4, while keeping
+  the reference environment pinned independently.
+
+### Fixed
+
+- Follow Scanpy 1.12's swapped-dotplot scaling and report its unavailable
+  automatic PAGA tree layouts without substituting another layout.
+
 ## [0.7.0] - 2026-10-20
 
 ### Added
@@ -181,6 +207,7 @@ First public alpha release, targeting GenomeSpy Core 0.87.0.
 - Packaged example datasets, documentation, tutorials, and an interactive
   visualization gallery.
 
+[0.8.0]: https://github.com/genome-spy/genome-spy-python/compare/v0.7.0...v0.8.0
 [0.7.0]: https://github.com/genome-spy/genome-spy-python/compare/v0.6.0...v0.7.0
 [0.6.0]: https://github.com/genome-spy/genome-spy-python/compare/v0.5.0...v0.6.0
 [0.5.0]: https://github.com/genome-spy/genome-spy-python/compare/v0.4.0...v0.5.0

genome_spy_python-0.8.0/LICENSES/SCANPY-BSD-3-Clause.txt

@@ -0,0 +1,30 @@
+BSD 3-Clause License
+
+Copyright (c) 2025 scverse
+Copyright (c) 2017 F. Alexander Wolf, P. Angerer, Theis Lab
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

{genome_spy_python-0.7.0 → genome_spy_python-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: genome-spy-python
-Version: 0.7.0
+Version: 0.8.0
 Summary: genome-spy-python is a declarative genomics visualization library for Python, built on top of the genome-spy JSON specification.
 Project-URL: Homepage, https://github.com/genome-spy/genome-spy-python
 Project-URL: Documentation, https://genomespy.app/genome-spy-python/
@@ -16,6 +16,7 @@ License-File: LICENSES/CC0-1.0.txt
 License-File: LICENSES/DATA-SOURCE-REPOSITORIES-MIT.txt
 License-File: LICENSES/GENOMESPY-MIT.txt
 License-File: LICENSES/LATO-OFL-1.1.txt
+License-File: LICENSES/SCANPY-BSD-3-Clause.txt
 License-File: LICENSES/VEGA-BSD-3-Clause.txt
 License-File: LICENSES/VEGA-LITE-BSD-3-Clause.txt
 License-File: THIRD_PARTY_NOTICES.md
@@ -37,6 +38,8 @@ Provides-Extra: anndata
 Requires-Dist: anndata>=0.11.0; extra == 'anndata'
 Provides-Extra: arrow
 Requires-Dist: pyarrow>=18.0.0; extra == 'arrow'
+Provides-Extra: scanpy
+Requires-Dist: scanpy[paga]<1.13,>=1.11.5; extra == 'scanpy'
 Description-Content-Type: text/markdown
 
 <p align="center">
@@ -71,6 +74,13 @@ The project is under active development. The current focus is the reusable
 GenomeSpy Core grammar and notebook rendering; GenomeSpy App-specific features
 will come later.
 
+Optional library integrations keep upstream analysis workflows and replace
+supported plotting calls. The [integration workspace](integrations/README.md)
+links each implementation, tracked plan, workflow notebooks, tests, and user guide.
+The Scanpy integration is implemented in
+[`src/genome_spy/integrations/scanpy/`](src/genome_spy/integrations/scanpy/), exposed as
+`import genome_spy.integrations.scanpy as gsc` and `gsc.pl.umap(...)`.
+
 ## Installation
 
 The package requires Python 3.11 or newer.
@@ -81,6 +91,12 @@ From PyPI:
 pip install genome-spy-python
 ```
 
+For Scanpy plotting:
+
+```bash
+pip install --upgrade 'genome-spy-python[scanpy]'
+```
+
 From source:
 
 ```bash

{genome_spy_python-0.7.0 → genome_spy_python-0.8.0}/README.md

@@ -30,6 +30,13 @@ The project is under active development. The current focus is the reusable
 GenomeSpy Core grammar and notebook rendering; GenomeSpy App-specific features
 will come later.
 
+Optional library integrations keep upstream analysis workflows and replace
+supported plotting calls. The [integration workspace](integrations/README.md)
+links each implementation, tracked plan, workflow notebooks, tests, and user guide.
+The Scanpy integration is implemented in
+[`src/genome_spy/integrations/scanpy/`](src/genome_spy/integrations/scanpy/), exposed as
+`import genome_spy.integrations.scanpy as gsc` and `gsc.pl.umap(...)`.
+
 ## Installation
 
 The package requires Python 3.11 or newer.
@@ -40,6 +47,12 @@ From PyPI:
 pip install genome-spy-python
 ```
 
+For Scanpy plotting:
+
+```bash
+pip install --upgrade 'genome-spy-python[scanpy]'
+```
+
 From source:
 
 ```bash

{genome_spy_python-0.7.0 → genome_spy_python-0.8.0}/THIRD_PARTY_NOTICES.md

@@ -108,6 +108,13 @@ selection, formatting and example contributions.
 
 ## PBMC marker expression
 
+The Scanpy documentation also displays `scanpy.datasets.pbmc68k_reduced()` from
+Scanpy 1.11.5. This packaged subset contains 700 cells from the
+[10x Genomics PBMC68k dataset](https://www.10xgenomics.com/datasets/fresh-68-k-pbm-cs-donor-a-1-standard-1-1-0),
+licensed CC BY 4.0. Credit 10x Genomics and Scanpy's preprocessing contributors;
+the examples retain the supplied UMAP coordinates, expression and annotations.
+The source H5AD is loaded from Scanpy and is not vendored in this repository.
+
 `pbmc_markers.json.gz` contains selected markers from 2,638 cells in Scanpy's processed
 PBMC3k fixture, obtained from [cellxgene revision
 68dfbcc](https://github.com/chanzuckerberg/cellxgene/blob/68dfbcc2eb675e96c6a5e2a6b7a0d3465ccf46bc/example-dataset/pbmc3k.h5ad).
@@ -119,6 +126,48 @@ Euclidean group tree, and plotting coordinates. `tools/prepare_pbmc_gallery_data
 the source checksum is retained in the bundle. The CC BY 4.0 text is in
 `LICENSES/CC-BY-4.0.txt`.
 
+The Scanpy data-check guide uses the full raw PBMC3k counts loaded through
+`scanpy.datasets.pbmc3k()` (2,700 cells × 32,738 genes). Scanpy prepares the
+normalization, variable-gene statistics and Scrublet results explicitly.
+
+## Expression Atlas ovarian cortex example
+
+The UMAP guide uses the public [E-MTAB-8381 study](https://www.ebi.ac.uk/gxa/sc/experiments/E-MTAB-8381)
+from EMBL-EBI Single Cell Expression Atlas: 36,785 cells × 23,772 genes in the
+download accessed on 27 October 2026. Credit Wagner, Yoshihara, Douagi et al.,
+[Single-cell analysis of human ovarian cortex identifies distinct cell populations
+but no oogonial stem cells](https://doi.org/10.1038/s41467-020-14936-3),
+Nature Communications 11, 1147 (2020), and the Atlas contributors.
+The publication is CC BY 4.0; the public Atlas download is provided under the
+[EMBL-EBI terms of use](https://www.ebi.ac.uk/about/terms-of-use/), which impose
+no additional restrictions beyond those of the data owner and require attribution.
+
+Scanpy loads the study, normalizes/log-transforms counts, selects 2,000 variable
+genes for PCA, and computes neighbors and UMAP with seed 0. All Atlas cells are
+retained. The chart shows normalized VWF expression (ENSG00000110799), with the
+color range capped at the 99th percentile. This plotting example does not
+reproduce the paper's filtering, integration or biological analysis. Downloads and
+prepared H5AD files stay in ignored caches; no dataset is added to Git.
+
+## Scanpy simulation examples
+
+The profiles guide displays Scanpy 1.11.5's packaged `krumsiek11()` simulation
+(640 samples × 11 genes, four runs of 160 samples), based on
+[Krumsiek et al. (2011)](https://doi.org/10.1371/journal.pone.0022649).
+Credit the model authors and Scanpy's simulation contributors. The stored
+simulation is loaded without rerunning it; five genes are shown. Sample names
+are made unique and integer highlight keys are stored as strings for H5AD,
+without changing values or row order. Scanpy explicitly prepares neighbors,
+diffusion components and DPT annotations for the later examples.
+The source table is supplied by Scanpy and is not vendored here. Its repository's
+copyright notice and BSD-3-Clause terms are retained in
+`LICENSES/SCANPY-BSD-3-Clause.txt`, including in the published documentation.
+
+The PAGA guide reuses the PBMC68k subset credited above. Scanpy explicitly
+prepares PAGA, graph positions and pseudotime; supplied UMAP coordinates and
+expression snapshots are retained. No new biological trajectory is claimed
+by the example's chosen group order.
+
 ## Bundled TCGA example tables
 
 | Files | Source and processing |