cytearc 1.0.0rc1__tar.gz

cytearc-1.0.0rc1/AGENTS.md

@@ -0,0 +1,105 @@
+# Repository instructions
+
+These instructions apply to the whole repository.
+
+## Start here
+
+- Edit package code in `cytearc/`, tests in `tests/`, documentation in `docs/`, profiling tools
+  in `profiling/`, and agent skills in `skills/`.
+- Before analysing data with CyteArc, read the relevant skill in `skills/`, starting with
+  `skills/cytearc-single-cell/SKILL.md`. Read skills only from `skills/`. When a change alters a public
+  API that a skill recipe uses, update the recipe in the same change.
+- Read `docs/AGENTS.md` before executing or publishing documentation.
+- Read `profiling/AGENTS.md` before using profiling tools or cloud resources.
+- Use `docs/source/developers/architecture.md` for code placement and dependency boundaries, and
+  `docs/source/developers/contributing.md` for the human contribution workflow.
+- Biological decision guidance belongs in `docs/source/analysis_with_agents.md`, not in repository
+  instructions.
+
+## CyteArc developer mental model
+
+- CyteArc streams Zarr-backed matrices in bounded blocks. Do not materialize a complete matrix when
+  a blockwise path exists.
+- `DataStore` orchestrates workflows. Reusable computation belongs in its concrete domain package
+  before a thin `datastore._operations` method exposes it.
+- Dependencies flow from `storage`, `matrix`, and `utils`, through data models and domain
+  algorithms, to I/O, datastore orchestration, and plotting.
+- Saved computations are immutable artifacts. `ArtifactRef`, provenance, and durable `PipelineRun`
+  records connect frozen selections, results, reuse, and complete workflow invocations.
+- The lazy public facades are compatibility boundaries. Trace the public call, operation
+  implementation, domain algorithm, persisted result, callers, tests, and documentation before
+  changing a contract.
+- Plotting consumes narrow adapters and must not gain a module-load dependency on `datastore`.
+
+## Source and conventions
+
+- Python 3.12 or newer is required. Use `uv` for every Python command and dependency change.
+- Preserve unrelated working-tree changes. Trace callers and tests before changing a public
+  function or persisted result.
+- Use built-in generics and `X | None`. Do not add `typing.List`,
+  `typing.Optional`, or `from __future__ import annotations`.
+- Pydantic model attributes use camel case.
+- Do not add implicit compatibility branches, ad hoc schema versions, or silent migrations. Make a
+  compatibility policy explicit before implementing it.
+- Do not commit credentials, local object-store endpoints, private bucket names, generated
+  benchmark configs, or result identifiers.
+- Avoid em dashes in public prose, prompts, docstrings, and comments.
+
+## Environment and checks
+
+```bash
+uv sync --group dev --group profiling --extra test --extra extra
+uv run python -m tests.download_fixtures --with-h5ad
+```
+
+Run focused tests without pytest-xdist. Run the quick suite while iterating and the complete suite before handoff:
+
+```bash
+uv run pytest -n 0 tests/test_file.py::test_name
+uv run pytest -m "not slow and not integration"
+uv run pytest
+```
+
+Run the same static checks as CI:
+
+```bash
+uv run ruff check cytearc profiling tests
+uv run ruff format --check cytearc profiling tests
+uv run mypy cytearc profiling
+```
+
+Visual references are intentional artifacts. Regenerate them only when rendering changes:
+
+```bash
+MPLBACKEND=Agg CYTEARC_RUN_VISUAL_REGRESSION=1 \
+  uv run pytest -n 0 -m visual tests/test_plotting_showcase.py
+```
+
+Performance changes to a kernel or stage: run the timed micro-benchmarks on a quiet machine. They
+project each slowdown onto 1M and 10M cells and fail only on a meaningful projected delay:
+
+```bash
+CYTEARC_RUN_BENCHMARKS=1 uv run pytest -n 0 tests/benchmarks
+```
+
+## Troubleshooting router
+
+- Wrong code location or import cycle: read the architecture placement rules and run
+  `uv run pytest -n 0 tests/test_import_architecture.py`.
+- Missing, stale, or incompatible result: inspect the pipeline-run report, artifact status, and
+  lineage before reading private Zarr paths.
+- Public API or persisted contract: inspect the public API reference and the public,
+  compatibility, signature, and frozen-store tests.
+- On-disk layout: read `docs/source/developers/zarr_internals.md`.
+- Documentation cache or build: follow `docs/AGENTS.md`.
+- Profiling, Modal, or benchmark interpretation: follow `profiling/AGENTS.md`.
+- Micro-benchmark regression or baseline update: read the performance benchmarks section of
+  `docs/source/developers/contributing.md`.
+
+## Universal safety
+
+- Execute selected documentation pages in one Modal invocation, with a separate container per
+  page. Do not start another invocation writing the same saved notebooks, or render while those
+  notebooks are being replaced.
+- Never deploy Modal. Deployment is a user action. Ask before any paid or long-running cloud job.
+- Do not publish example datasets or use write credentials unless the user explicitly requests it.

cytearc-1.0.0rc1/LICENSE

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2026, Nygen Analytics AB
+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.

cytearc-1.0.0rc1/MANIFEST.in

@@ -0,0 +1,14 @@
+recursive-exclude * __pycache__
+recursive-exclude * *.pyc
+recursive-exclude * *.pyo
+exclude .gitignore
+exclude .gitattributes
+exclude .readthedocs.yml
+exclude Dockerfile
+prune docs
+prune tests
+prune profiling
+prune scripts
+prune .circleci
+prune .github
+include README.md

cytearc-1.0.0rc1/PKG-INFO

@@ -0,0 +1,183 @@
+Metadata-Version: 2.4
+Name: cytearc
+Version: 1.0.0rc1
+Summary: Out-of-core, graph-first workflows for million-cell RNA-seq and CITE-seq
+Author-email: Parashar Dhapola <parashar.dhapola@gmail.com>
+License-Expression: BSD-3-Clause
+Project-URL: Homepage, https://github.com/NygenAnalytics/CyteArc
+Project-URL: Documentation, https://docs.nygen.io/CyteArc/
+Project-URL: Installation, https://docs.nygen.io/CyteArc/installation
+Project-URL: Issues, https://github.com/NygenAnalytics/CyteArc/issues
+Keywords: single-cell,scRNA-seq,scATAC-seq,CITE-seq,Harmony,WNN,batch-correction,Zarr,memory-efficient
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: h5py>=3.11
+Requires-Dist: hnswlib>=0.8
+Requires-Dist: leidenalg>=0.12
+Requires-Dist: loguru>=0.7
+Requires-Dist: networkx>=3
+Requires-Dist: numba>=0.60
+Requires-Dist: numcodecs>=0.16
+Requires-Dist: numpy>=2
+Requires-Dist: packaging
+Requires-Dist: pandas>=2.2.2
+Requires-Dist: scikit-learn>=1.5
+Requires-Dist: scipy!=1.17.0,>=1.15
+Requires-Dist: statsmodels>=0.14.5
+Requires-Dist: threadpoolctl>=3.5.0
+Requires-Dist: tqdm>=4.60
+Requires-Dist: umap-learn>=0.5.12
+Requires-Dist: zarr>=3.2.0
+Requires-Dist: obstore>=0.5.1
+Requires-Dist: huggingface-hub>=2.0.0
+Requires-Dist: zstandard>=0.25.0
+Requires-Dist: igraph>=1.0.0
+Provides-Extra: cytebase
+Requires-Dist: duckdb>=1.5.5; extra == "cytebase"
+Requires-Dist: httpx>=0.28.1; extra == "cytebase"
+Requires-Dist: matplotlib>=3.9; extra == "cytebase"
+Requires-Dist: pytz>=2026.3.post1; extra == "cytebase"
+Requires-Dist: seaborn>=0.13; extra == "cytebase"
+Provides-Extra: agent
+Requires-Dist: pydantic-ai-slim[openai]>=2.51.0; extra == "agent"
+Provides-Extra: extra
+Requires-Dist: anndata>=0.12; extra == "extra"
+Requires-Dist: kneed>=0.8.1; extra == "extra"
+Requires-Dist: matplotlib>=3.9; extra == "extra"
+Requires-Dist: seaborn>=0.13; extra == "extra"
+Requires-Dist: ipython-autotime>=0.3; extra == "extra"
+Requires-Dist: ipywidgets>=8; extra == "extra"
+Provides-Extra: tsne
+Requires-Dist: sgtsnepi>=0.7; extra == "tsne"
+Provides-Extra: test
+Requires-Dist: pytest>=7.0; extra == "test"
+Requires-Dist: pytest-cov>=4; extra == "test"
+Requires-Dist: pytest-xdist>=3; extra == "test"
+Requires-Dist: anndata>=0.12; extra == "test"
+Requires-Dist: scikit-network>=0.33.1; extra == "test"
+Requires-Dist: rdata>=1.1.0; extra == "test"
+Requires-Dist: pydantic-ai-slim[openai]>=2.51.0; extra == "test"
+Requires-Dist: sgtsnepi>=0.7; (sys_platform == "linux" and platform_machine == "x86_64") and extra == "test"
+Provides-Extra: docs
+Requires-Dist: mystmd>=1.11.0; extra == "docs"
+Requires-Dist: jupytext>=1.19.6; extra == "docs"
+Requires-Dist: ipykernel>=7.3.0; extra == "docs"
+Requires-Dist: nbclient; extra == "docs"
+Requires-Dist: myst-parser; extra == "docs"
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: sphinx_autodoc_typehints; extra == "docs"
+Requires-Dist: sphinx-book-theme; extra == "docs"
+Requires-Dist: sphinx-copybutton; extra == "docs"
+Requires-Dist: sgtsnepi>=0.7; (sys_platform == "linux" and platform_machine == "x86_64") and extra == "docs"
+Dynamic: license-file
+
+# CyteArc
+
+<p align="left">
+  <a href="https://github.com/NygenAnalytics/CyteArc/actions/workflows/pytest.yml"><img src="https://github.com/NygenAnalytics/CyteArc/actions/workflows/pytest.yml/badge.svg" alt="Tests"></a>
+  <a href="https://codecov.io/gh/NygenAnalytics/CyteArc"><img src="https://codecov.io/gh/NygenAnalytics/CyteArc/graph/badge.svg" alt="Coverage"></a>
+  <a href="https://docs.nygen.io/CyteArc/"><img src="https://github.com/NygenAnalytics/CyteArc/actions/workflows/pages.yml/badge.svg" alt="Docs"></a>
+  <a href="https://pypi.org/project/cytearc"><img src="https://img.shields.io/pypi/v/cytearc.svg?color=4c72b0" alt="PyPI"></a>
+  <a href="https://pypi.org/project/cytearc"><img src="https://img.shields.io/badge/python-3.12%20%7C%203.13%20%7C%203.14-4c72b0.svg" alt="Python 3.12, 3.13, and 3.14"></a>
+  <a href="https://pepy.tech/projects/cytearc"><img src="https://static.pepy.tech/personalized-badge/cytearc?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads" alt="Downloads"></a>
+</p>
+
+
+CyteArc is a **fast Python framework for single-cell RNA, ATAC, protein, and multi-omic analysis that scales to 100M+ cells**. In benchmarks, it processed **one million cells within 15 minutes**, from cell filtering through UMAP and clustering to marker gene identification. On **Tahoe-100M**, the same workflow ran in **under 20 hours without any subsampling**.
+
+[Cytebase](https://docs.nygen.io/CyteArc/tutorials/cytebase) is a **ready-to-connect repository of CyteArc datastores**, containing approximately **200 million cells and 1.1 TB of data** on [Hugging Face](https://huggingface.co/buckets/Nygen/cytebase). Mount remote datasets for reanalysis and build or reuse references for mapping new cells, without downloading the complete count matrix. Counts stay remote while you save your own results in a store you control.
+
+CyteArc's **built-in provenance** connects saved results to the exact cells, features, parameters, and upstream computations that produced them, so you can reuse completed work and trace each analysis.
+
+| Problem | How CyteArc solves it | What you get |
+| :-- | :-- | :-- |
+| Your **dataset is larger than RAM** | Out-of-core algorithms, and neighbour search streams from cell-major and gene-major layouts, inside a memory budget you set | Analyse the selected cells with [explicit memory controls](https://docs.nygen.io/CyteArc/concepts/memory-and-execution) |
+| The **data is stored remotely** and requires downloading | Fetches only the chunks an operation touches, and writes results to a store you own | Start analysing immediately, with one authoritative copy |
+| A **single parameter change costs hours** of computation | Each step is fingerprinted by its settings and inputs, so reuse is by content, not by layer name | Only what changed recomputes, and the old version stays for comparison |
+| Sub-population analysis leaves **scattered copies that nobody can trace back** | Subsets are masks in one file, and every result carries the cells and parameters behind it | A year later, a result still explains itself |
+
+## Install
+
+Python 3.12+.
+
+```bash
+uv venv --python 3.12
+uv pip install --python .venv "cytearc[extra]"
+```
+
+Detailed installation instructions [here](https://docs.nygen.io/CyteArc/installation)
+
+## Quick start
+
+```python
+import cytearc
+
+ds = cytearc.DataStore(
+    "s3://bucket/cells.zarr",  # also gs://, hf://, or a local path
+)
+run = ds.pipeline.run()  # durable QC → graph → UMAP → clustering → marker run
+
+ds.plots.embedding(
+    run=run,
+    layout="umap",
+    color_by="clusters",
+)
+```
+
+Read the [scRNA-seq tutorial](https://docs.nygen.io/CyteArc/tutorials/scrna-seq) for a granular workflow, or [remote stores](https://docs.nygen.io/CyteArc/tutorials/remote-stores) for cloud setups.
+
+## Cytebase
+
+Cytebase provides a searchable catalog of public datasets stored as cloud-hosted CyteArc DataStores. Search by study, tissue, disease, or organism, then explore published cell annotations and available embeddings. Public access needs no credentials.
+
+Install the Cytebase extra alongside the analysis extras:
+
+```bash
+uv pip install --python .venv --prerelease allow "cytearc[cytebase,extra]"
+```
+
+```python
+from cytearc import cytebase
+
+catalog = cytebase.Catalog()
+matches = catalog.search("kidney")
+print(matches)
+
+# Open one of the matching datasets for read-only exploration.
+dataset_id = matches[0]["cytebase_id"]
+ds = catalog.open_datastore(dataset_id)
+
+# Create a writable local store for your own analysis, keeping counts remote.
+analysis = catalog.mount_datastore(dataset_id, at="kidney_analysis.zarr")
+```
+
+Use `analysis` with the pipeline shown above to save new results locally. Computation runs in your Python environment, reading count blocks over the network as needed.
+
+Follow the [Cytebase tutorial](https://docs.nygen.io/CyteArc/tutorials/cytebase) for catalog filters, plotting, and example notebooks, or see the [Cytebase API reference](https://docs.nygen.io/CyteArc/api/cytebase.html).
+
+## Documentation
+
+Read workflow vignettes and API references in the **[documentation](https://docs.nygen.io/CyteArc/)**.
+
+## CyteArc's capabilities
+
+| Area | Methods |
+| :-- | :-- |
+| Modalities | scRNA-seq, scATAC-seq, CITE-seq, matched multi-omics |
+| Core workflow | Quality control, feature selection, normalization, PCA and LSI, KNN graph, UMAP, densMAP, t-SNE (optional `tsne` extra), Leiden, Paris, marker search |
+| Integration | Harmony, partial PCA, shared and weighted nearest neighbours, integration metrics |
+| Mapping | Symphony-style reference mapping, label transfer, projection diagnostics |
+| Trajectory | Population Balance Analysis pseudotime, expression dynamics and modules, multi-sink fate probabilities |
+| Also included | Cell-cycle scoring, gene-set activity, graph-diffusion imputation, doublet scores, HTO demultiplexing, pseudobulk export |
+
+## Support
+
+[GitHub issues](https://github.com/NygenAnalytics/CyteArc/issues)
+
+CyteArc is open source software released under the [BSD 3-Clause License](LICENSE) and maintained by [Nygen](https://nygen.io).

cytearc-1.0.0rc1/README.md

@@ -0,0 +1,104 @@
+# CyteArc
+
+<p align="left">
+  <a href="https://github.com/NygenAnalytics/CyteArc/actions/workflows/pytest.yml"><img src="https://github.com/NygenAnalytics/CyteArc/actions/workflows/pytest.yml/badge.svg" alt="Tests"></a>
+  <a href="https://codecov.io/gh/NygenAnalytics/CyteArc"><img src="https://codecov.io/gh/NygenAnalytics/CyteArc/graph/badge.svg" alt="Coverage"></a>
+  <a href="https://docs.nygen.io/CyteArc/"><img src="https://github.com/NygenAnalytics/CyteArc/actions/workflows/pages.yml/badge.svg" alt="Docs"></a>
+  <a href="https://pypi.org/project/cytearc"><img src="https://img.shields.io/pypi/v/cytearc.svg?color=4c72b0" alt="PyPI"></a>
+  <a href="https://pypi.org/project/cytearc"><img src="https://img.shields.io/badge/python-3.12%20%7C%203.13%20%7C%203.14-4c72b0.svg" alt="Python 3.12, 3.13, and 3.14"></a>
+  <a href="https://pepy.tech/projects/cytearc"><img src="https://static.pepy.tech/personalized-badge/cytearc?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads" alt="Downloads"></a>
+</p>
+
+
+CyteArc is a **fast Python framework for single-cell RNA, ATAC, protein, and multi-omic analysis that scales to 100M+ cells**. In benchmarks, it processed **one million cells within 15 minutes**, from cell filtering through UMAP and clustering to marker gene identification. On **Tahoe-100M**, the same workflow ran in **under 20 hours without any subsampling**.
+
+[Cytebase](https://docs.nygen.io/CyteArc/tutorials/cytebase) is a **ready-to-connect repository of CyteArc datastores**, containing approximately **200 million cells and 1.1 TB of data** on [Hugging Face](https://huggingface.co/buckets/Nygen/cytebase). Mount remote datasets for reanalysis and build or reuse references for mapping new cells, without downloading the complete count matrix. Counts stay remote while you save your own results in a store you control.
+
+CyteArc's **built-in provenance** connects saved results to the exact cells, features, parameters, and upstream computations that produced them, so you can reuse completed work and trace each analysis.
+
+| Problem | How CyteArc solves it | What you get |
+| :-- | :-- | :-- |
+| Your **dataset is larger than RAM** | Out-of-core algorithms, and neighbour search streams from cell-major and gene-major layouts, inside a memory budget you set | Analyse the selected cells with [explicit memory controls](https://docs.nygen.io/CyteArc/concepts/memory-and-execution) |
+| The **data is stored remotely** and requires downloading | Fetches only the chunks an operation touches, and writes results to a store you own | Start analysing immediately, with one authoritative copy |
+| A **single parameter change costs hours** of computation | Each step is fingerprinted by its settings and inputs, so reuse is by content, not by layer name | Only what changed recomputes, and the old version stays for comparison |
+| Sub-population analysis leaves **scattered copies that nobody can trace back** | Subsets are masks in one file, and every result carries the cells and parameters behind it | A year later, a result still explains itself |
+
+## Install
+
+Python 3.12+.
+
+```bash
+uv venv --python 3.12
+uv pip install --python .venv "cytearc[extra]"
+```
+
+Detailed installation instructions [here](https://docs.nygen.io/CyteArc/installation)
+
+## Quick start
+
+```python
+import cytearc
+
+ds = cytearc.DataStore(
+    "s3://bucket/cells.zarr",  # also gs://, hf://, or a local path
+)
+run = ds.pipeline.run()  # durable QC → graph → UMAP → clustering → marker run
+
+ds.plots.embedding(
+    run=run,
+    layout="umap",
+    color_by="clusters",
+)
+```
+
+Read the [scRNA-seq tutorial](https://docs.nygen.io/CyteArc/tutorials/scrna-seq) for a granular workflow, or [remote stores](https://docs.nygen.io/CyteArc/tutorials/remote-stores) for cloud setups.
+
+## Cytebase
+
+Cytebase provides a searchable catalog of public datasets stored as cloud-hosted CyteArc DataStores. Search by study, tissue, disease, or organism, then explore published cell annotations and available embeddings. Public access needs no credentials.
+
+Install the Cytebase extra alongside the analysis extras:
+
+```bash
+uv pip install --python .venv --prerelease allow "cytearc[cytebase,extra]"
+```
+
+```python
+from cytearc import cytebase
+
+catalog = cytebase.Catalog()
+matches = catalog.search("kidney")
+print(matches)
+
+# Open one of the matching datasets for read-only exploration.
+dataset_id = matches[0]["cytebase_id"]
+ds = catalog.open_datastore(dataset_id)
+
+# Create a writable local store for your own analysis, keeping counts remote.
+analysis = catalog.mount_datastore(dataset_id, at="kidney_analysis.zarr")
+```
+
+Use `analysis` with the pipeline shown above to save new results locally. Computation runs in your Python environment, reading count blocks over the network as needed.
+
+Follow the [Cytebase tutorial](https://docs.nygen.io/CyteArc/tutorials/cytebase) for catalog filters, plotting, and example notebooks, or see the [Cytebase API reference](https://docs.nygen.io/CyteArc/api/cytebase.html).
+
+## Documentation
+
+Read workflow vignettes and API references in the **[documentation](https://docs.nygen.io/CyteArc/)**.
+
+## CyteArc's capabilities
+
+| Area | Methods |
+| :-- | :-- |
+| Modalities | scRNA-seq, scATAC-seq, CITE-seq, matched multi-omics |
+| Core workflow | Quality control, feature selection, normalization, PCA and LSI, KNN graph, UMAP, densMAP, t-SNE (optional `tsne` extra), Leiden, Paris, marker search |
+| Integration | Harmony, partial PCA, shared and weighted nearest neighbours, integration metrics |
+| Mapping | Symphony-style reference mapping, label transfer, projection diagnostics |
+| Trajectory | Population Balance Analysis pseudotime, expression dynamics and modules, multi-sink fate probabilities |
+| Also included | Cell-cycle scoring, gene-set activity, graph-diffusion imputation, doublet scores, HTO demultiplexing, pseudobulk export |
+
+## Support
+
+[GitHub issues](https://github.com/NygenAnalytics/CyteArc/issues)
+
+CyteArc is open source software released under the [BSD 3-Clause License](LICENSE) and maintained by [Nygen](https://nygen.io).

cytearc-1.0.0rc1/cytearc/__init__.py

@@ -0,0 +1,200 @@
+import warnings as _warnings
+from collections.abc import Callable as _Callable
+from importlib.metadata import PackageNotFoundError as _PackageNotFoundError
+from importlib.metadata import version as _distribution_version
+from pathlib import Path as _Path
+from re import search as _re_search
+from typing import TYPE_CHECKING
+
+from ._facade import lazy_facade as _lazy_facade
+
+if TYPE_CHECKING:
+    from . import cytebase as cytebase
+    from .datastore.datastore import DataStore as DataStore
+    from .datastore.pipeline_run import (
+        PipelineExecutionError as PipelineExecutionError,
+        PipelineRun as PipelineRun,
+    )
+    from .datastore.summary import DataStoreSummary as DataStoreSummary
+    from .storage.lineage import ArtifactLineage as ArtifactLineage
+    from .features.enrichment import (
+        EnrichmentResult as EnrichmentResult,
+        read_gmt as read_gmt,
+    )
+    from .mapping.models import (
+        LabelTransferResult as LabelTransferResult,
+        MappingResult as MappingResult,
+    )
+    from .mapping.reference import MappingReference as MappingReference
+    from .storage.artifacts import ArtifactStatus as ArtifactStatus
+    from .storage.errors import ArtifactResolutionError as ArtifactResolutionError
+    from .storage.refs import ArtifactRef as ArtifactRef
+    from .storage.stores import load_zarr as load_zarr
+    from .merge import (
+        DataStoreMerge as DataStoreMerge,
+    )
+    from .readers import (
+        CSVReader as CSVReader,
+        CrDirReader as CrDirReader,
+        CrH5Reader as CrH5Reader,
+        CrReader as CrReader,
+        H5adInspectResult as H5adInspectResult,
+        H5adReader as H5adReader,
+        MtxReader as MtxReader,
+        SeuratInspectResult as SeuratInspectResult,
+        SeuratReader as SeuratReader,
+        inspect_h5ad as inspect_h5ad,
+        inspect_mtx as inspect_mtx,
+        inspect_seurat as inspect_seurat,
+    )
+    from .trajectory.results import (
+        FateMappingResult as FateMappingResult,
+        PseudotimeAggregationResult as PseudotimeAggregationResult,
+        PseudotimeMarkerResult as PseudotimeMarkerResult,
+        PseudotimeScoreResult as PseudotimeScoreResult,
+    )
+    from .utils import (
+        clean_array as clean_array,
+        configure_output as configure_output,
+        controlled_compute as controlled_compute,
+        logger as logger,
+        permute_into_chunks as permute_into_chunks,
+        rescale_array as rescale_array,
+        rolling_window as rolling_window,
+        set_verbosity as set_verbosity,
+        compute_with_progress as compute_with_progress,
+        tqdmbar as tqdmbar,
+        tqdm_params as tqdm_params,
+    )
+    from .writers import (
+        CSVtoZarr as CSVtoZarr,
+        CrToZarr as CrToZarr,
+        H5adImportResult as H5adImportResult,
+        H5adToZarr as H5adToZarr,
+        MtxToZarr as MtxToZarr,
+        SeuratImportResult as SeuratImportResult,
+        SeuratToZarr as SeuratToZarr,
+        SparseToZarr as SparseToZarr,
+        SubsetZarr as SubsetZarr,
+        create_zarr_count_assay as create_zarr_count_assay,
+        create_zarr_dataset as create_zarr_dataset,
+        create_zarr_obj_array as create_zarr_obj_array,
+        chunked_to_zarr as chunked_to_zarr,
+        subset_assay_zarr as subset_assay_zarr,
+        to_h5ad as to_h5ad,
+        to_mtx as to_mtx,
+        write_renorm_subset_to_zarr as write_renorm_subset_to_zarr,
+    )
+
+_warnings.filterwarnings(
+    "ignore",
+    message=r"The data type .* does not have a Zarr V3 specification\.",
+    module=r"zarr\.core\.dtype\..*",
+)
+
+
+def _resolve_version(
+    distribution_version: _Callable[[str], str] = _distribution_version,
+    version_path: _Path | None = None,
+) -> str:
+    try:
+        return distribution_version("cytearc")
+    except _PackageNotFoundError:
+        path = version_path or _Path(__file__).with_name("_version.py")
+        if not path.is_file():
+            return "unavailable"
+        match = _re_search(
+            r"\bversion\s*=\s*['\"]([^'\"]+)['\"]",
+            path.read_text(encoding="utf-8"),
+        )
+        return match.group(1) if match else "unavailable"
+
+
+__version__ = _resolve_version()
+
+_LAZY_EXPORTS: dict[str, str] = {
+    "ArtifactLineage": ".storage.lineage",
+    "ArtifactRef": ".storage.refs",
+    "ArtifactResolutionError": ".storage.errors",
+    "ArtifactStatus": ".storage.artifacts",
+    "CSVReader": ".readers",
+    "CSVtoZarr": ".writers",
+    "CrDirReader": ".readers",
+    "CrH5Reader": ".readers",
+    "CrReader": ".readers",
+    "CrToZarr": ".writers",
+    "DataStore": ".datastore.datastore",
+    "DataStoreSummary": ".datastore.summary",
+    "DataStoreMerge": ".merge",
+    "EnrichmentResult": ".features.enrichment",
+    "FateMappingResult": ".trajectory.results",
+    "H5adInspectResult": ".readers",
+    "H5adImportResult": ".writers",
+    "H5adReader": ".readers",
+    "H5adToZarr": ".writers",
+    "MtxReader": ".readers",
+    "MtxToZarr": ".writers",
+    "SeuratImportResult": ".writers",
+    "SeuratInspectResult": ".readers",
+    "SeuratReader": ".readers",
+    "SeuratToZarr": ".writers",
+    "LabelTransferResult": ".mapping.models",
+    "MappingReference": ".mapping.reference",
+    "MappingResult": ".mapping.models",
+    "mount_datastore": ".datastore.datastore",
+    "PseudotimeAggregationResult": ".trajectory.results",
+    "PseudotimeMarkerResult": ".trajectory.results",
+    "PseudotimeScoreResult": ".trajectory.results",
+    "PipelineExecutionError": ".datastore.pipeline_run",
+    "PipelineRun": ".datastore.pipeline_run",
+    "SparseToZarr": ".writers",
+    "SubsetZarr": ".writers",
+    "clean_array": ".utils",
+    "configure_output": ".utils",
+    "controlled_compute": ".utils",
+    "create_zarr_count_assay": ".writers",
+    "create_zarr_dataset": ".writers",
+    "create_zarr_obj_array": ".writers",
+    "chunked_to_zarr": ".writers",
+    "inspect_h5ad": ".readers",
+    "inspect_mtx": ".readers",
+    "inspect_seurat": ".readers",
+    "load_zarr": ".storage.stores",
+    "logger": ".utils",
+    "permute_into_chunks": ".utils",
+    "read_gmt": ".features.enrichment",
+    "rescale_array": ".utils",
+    "rolling_window": ".utils",
+    "set_verbosity": ".utils",
+    "compute_with_progress": ".utils",
+    "subset_assay_zarr": ".writers",
+    "to_h5ad": ".writers",
+    "to_mtx": ".writers",
+    "tqdmbar": ".utils",
+    "tqdm_params": ".utils",
+    "write_renorm_subset_to_zarr": ".writers",
+}
+
+__all__ = list(_LAZY_EXPORTS)
+
+__getattr__, __dir__ = _lazy_facade(
+    __name__,
+    _LAZY_EXPORTS,
+    modules=(
+        "assay",
+        "cytebase",
+        "datastore",
+        "embeddings",
+        "features",
+        "mapping",
+        "matrix",
+        "merge",
+        "metadata",
+        "metrics",
+        "quality_control",
+        "readers",
+        "storage",
+        "utils",
+        "writers",
+    ),
+)