V1 prep

.github/codecov.yml

@@ -1,5 +1,5 @@
 ignore:
-  - "scarf/tests/*"
+  - "tests/*"
   - "setup.py"
 
 github_checks: false

.github/workflows/publish.yml

@@ -7,20 +7,16 @@ on:
 jobs:
   build:
     name: Build distribution
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-26.04
 
     steps:
     - uses: actions/checkout@v4
-    - name: Set up Python
-      uses: actions/setup-python@v5
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
       with:
-        python-version: 3.11.9
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        python -m pip install --upgrade setuptools wheel build
+        python-version: "3.14"
     - name: Build a binary wheel and a source tarball
-      run: python -m build
+      run: uv build
     - name: Store the distribution packages
       uses: actions/upload-artifact@v4
       with:
@@ -31,12 +27,12 @@ jobs:
     name: Publish to PyPI
     needs:
       - build
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-26.04
     environment:
       name: pypi
       url: https://pypi.org/p/scarf
     permissions:
-      id-token: write  # IMPORTANT: mandatory for trusted publishing
+      id-token: write
     steps:
       - name: Download all the dists
         uses: actions/download-artifact@v4

.github/workflows/pytest.yml

@@ -12,27 +12,67 @@ on:
 
 jobs:
   test:
-    runs-on: ${{ matrix.os }}
+    runs-on: ubuntu-26.04
+    env:
+      HNSWLIB_NO_NATIVE: "1"
     strategy:
+      fail-fast: false
       matrix:
-        os: [ubuntu-22.04, windows-2019]
-        python-version: [3.11.9]
+        python-version: ["3.12", "3.13", "3.14"]
+        resolution: [locked]
+        include:
+          - python-version: "3.12"
+            resolution: lowest-direct
     steps:
     - uses: actions/checkout@v4
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+    - name: Install system build dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y build-essential libfftw3-dev libmetis-dev
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
+    - name: Install dependencies (locked)
+      if: matrix.resolution == 'locked'
+      run: uv sync --group profiling --extra test --extra extra
+    - name: Install dependencies (lowest-direct)
+      if: matrix.resolution == 'lowest-direct'
+      run: uv pip install --resolution lowest-direct -e ".[test,extra]" --group profiling
+    - name: Lint and check formatting
+      if: matrix.resolution == 'locked' && matrix.python-version == '3.12'
+      run: |
+        uv run ruff check scarf profiling tests
+        uv run ruff format --check scarf profiling tests
+    - name: Type check
+      if: matrix.resolution == 'locked' && matrix.python-version == '3.12'
+      run: uv run mypy scarf profiling
+    - name: Download test fixtures
       run: |
-        python -m pip install --upgrade pip
-        pip install -r requirements.txt
-        pip install -r requirements_extra.txt
-        pip install pytest pytest-cov topacedo anndata==0.11.4 pcst_fast
-    - name: Test with pytest
+        if [ "${{ matrix.resolution }}" = "lowest-direct" ]; then
+          uv run --no-sync python -m tests.download_fixtures --with-h5ad
+        else
+          uv run python -m tests.download_fixtures --with-h5ad
+        fi
+    - name: Test with pytest (parallel)
       run: |
-        pytest --cov=.
+        if [ "${{ matrix.resolution }}" = "lowest-direct" ]; then
+          uv run --no-sync pytest \
+            -n auto \
+            --dist loadfile \
+            --cov=scarf \
+            --cov-report=xml \
+            --cov-report=term
+        else
+          uv run pytest \
+            -n auto \
+            --dist loadfile \
+            --cov=scarf \
+            --cov-report=xml \
+            --cov-report=term
+        fi
     - name: Upload coverage to Codecov
+      if: matrix.resolution == 'locked' && matrix.python-version == '3.14'
       uses: codecov/codecov-action@v3
       with:
         fail_ci_if_error: false

.gitignore

@@ -3,19 +3,46 @@
 __pycache__
 build
 dist
+*.egg-info
 scarf.egg-info
 scarf_toolkit.egg-info
+.venv
+.venv*/
+.ruff_cache
 dask-worker-space
+# zarr ":memory:" URL materialized as a local directory by older tests
+:memory:
+:memory:/
 *.ipynb_checkpoints
 *.ipynb
+!docs/.jupyter_cache/executed/**/base.ipynb
+docs/.jupyter_cache/_parallel/
+docs/.ipython/
 docs/source/vignettes/README.md
 docs/source/vignettes/scarf_datasets
 docs/source/vignettes/dev
 docs/source/vignettes/*.txt
 docs/source/vignettes/*.mtx
+docs/build/
+docs/_build/
 docs/jupyter_execute
+docs/source/scarf_datasets/
 .coverage
+coverage.xml
+htmlcov/
 .pytest_cache
 interrogate_badge.svg
-scarf/tests/datasets/*
-test_data
+tests/datasets/*
+!tests/datasets/markers_all_clusters.csv
+tests/.env
+tests/.env.*
+benchmarks/.env
+benchmarks/.env.*
+!benchmarks/.env.example
+profiling/.env
+profiling/.env.*
+!profiling/.env.example
+profiling/config.toml
+# Generated / local-only run configs (machine grids). Keep LEARNINGS.md + examples.
+profiling/layouts/
+test_data

.readthedocs.yml

@@ -1,17 +1,17 @@
 version: 2
 
 build:
-  os: ubuntu-22.04
+  os: ubuntu-26.04
   tools:
-    python: "3.11"
+    python: "3.14"
 
 python:
   install:
-    - requirements: requirements.txt
-    - requirements: requirements_extra.txt
-    - requirements: docs/source/requirements.txt
     - method: pip
       path: .
+      extra_requirements:
+        - extra
+        - docs
 
 sphinx:
   configuration: docs/source/conf.py

Dockerfile

@@ -1,28 +1,19 @@
-FROM ubuntu:22.04
+FROM ubuntu:26.04
 
 RUN apt update -y && apt autoremove -y && apt clean -y && apt autoclean -y && apt upgrade -y
-RUN apt install -y wget build-essential git nano
+RUN apt install -y wget build-essential git nano curl libfftw3-dev libmetis-dev libtbb-dev
 
-# The following is done to make sure that tzdata package doesnt prompt for timezone during installation
 ARG TZ="Europe/Stockholm"
 RUN DEBIAN_FRONTEND="noninteractive" TZ=$TZ apt-get -y install tzdata
-RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone &
+RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
 
-#Installing dependencies for sgtsne
-RUN apt install -y libmetis-dev libtbb-dev libfftw3-dev lib32gcc-7-dev libflann-dev libcilkrts5
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
 
-# Installing lastest Miniconda3
-RUN wget -O miniconda_inst "https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh" && \
-	bash miniconda_inst -b && \
-	rm miniconda_inst
+WORKDIR /workspace
+COPY . /workspace
 
-# Exporting PATH and also saving it in bashrc for next session
-# /workspace/bin is so that sgtsne can be found
-RUN echo "export PATH=$PATH:/root/miniconda3/bin:/workspace/bin" >> /root/.bashrc
-ENV PATH=$PATH:/root/miniconda3/bin:/workspace/bin
+RUN uv python install 3.14 && uv sync --extra extra
+ENV PATH="/workspace/.venv/bin:$PATH"
 
-# Installing numpy and pybind11 beforehand because sometimes they don't install so well from requirements.txt
-RUN pip install --upgrade pip
-RUN pip install --no-cache-dir -U numpy pybind11
-
-RUN pip install scarf
+RUN echo "export PATH=/workspace/.venv/bin:/workspace/bin:$PATH" >> /root/.bashrc
+ENV PATH=/workspace/.venv/bin:/workspace/bin:$PATH

LICENSE

@@ -1,6 +1,6 @@
 BSD 3-Clause License
 
-Copyright (c) [2021], [Dhapola P, Karlsson G]
+Copyright (c) 2026, Nygen Analytics AB
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

MANIFEST.in

@@ -7,11 +7,11 @@ exclude .readthedocs.yml
 exclude Dockerfile
 prune scarf_toolkit.egg-info
 prune docs
-prune scarf/tests
+prune tests
+prune profiling
+prune scripts
 prune .circleci
 prune .github
-include requirements.txt
-include requirements_extra.txt
 include VERSION
-include pypi_README.rst
+include README.md
 graft bin

README.md

@@ -0,0 +1,65 @@
+# Scarf
+
+Out-of-core, graph-first workflows for million-cell RNA-seq and CITE-seq.
+
+[![PyPI](https://img.shields.io/pypi/v/scarf.svg)](https://pypi.org/project/scarf)
+[![Docs](https://readthedocs.org/projects/scarf/badge/?version=latest)](https://scarf.readthedocs.io)
+[![Tests](https://github.com/parashardhapola/scarf/actions/workflows/pytest.yml/badge.svg)](https://github.com/parashardhapola/scarf/actions/workflows/pytest.yml)
+[![Coverage](https://codecov.io/gh/parashardhapola/scarf/branch/master/graph/badge.svg?token=ZvJXuYq3pd)](https://codecov.io/gh/parashardhapola/scarf)
+[![Downloads](https://pepy.tech/badge/scarf)](https://pepy.tech/project/scarf)
+
+## Installation
+
+Requires Python 3.12+.
+
+```bash
+pip install scarf[extra]
+```
+
+## Features
+
+- Analyze atlas-scale scRNA-seq on modest hardware (tested up to 4M cells)
+- CITE-seq multimodal analysis with WNN and SNN integration
+- Zarr-backed chunking for low memory use
+- Parallel UMAP and SG-tSNE embeddings
+- Harmony batch correction and partial PCA for merged datasets
+- Cell projection and label transfer across datasets
+- TopACeDo subsampling for representative cell selection
+- Hierarchical clustering with interpretable dendrograms
+
+## Quick start
+
+Convert a Cell Ranger `filtered_feature_bc_matrix.h5` to Zarr, then run a minimal scRNA-seq workflow:
+
+```python
+import scarf
+
+reader = scarf.CrH5Reader("filtered_feature_bc_matrix.h5")
+scarf.CrToZarr(reader, zarr_loc="data.zarr").dump(batch_size=1000)
+
+ds = scarf.DataStore("data.zarr", nthreads=4, min_features_per_cell=10)
+ds.filter_cells(attrs=["RNA_nCounts", "RNA_nFeatures"], highs=[15000, 4000], lows=[1000, 500])
+
+ds.mark_hvgs(min_cells=20, top_n=500)
+ds.make_graph(feat_key="hvgs", k=11, dims=15, n_centroids=100)
+ds.run_umap(n_epochs=250, spread=5, min_dist=1, parallel=True)
+ds.run_leiden_clustering(resolution=0.5)
+
+ds.plot_layout(layout_key="RNA_UMAP", color_by="RNA_leiden_cluster")
+```
+
+## Documentation
+
+- [Installation guide](https://scarf.readthedocs.io/en/latest/install.html)
+- [scRNA-seq tutorial](https://scarf.readthedocs.io/en/latest/vignettes/basic_tutorial_scRNAseq.html)
+- [CITE-seq tutorial](https://scarf.readthedocs.io/en/latest/vignettes/multiple_modalities.html)
+- [Integration guide](https://scarf.readthedocs.io/en/latest/integration_guide.html)
+- [Full API](https://scarf.readthedocs.io/en/latest/api.html)
+
+## Citation
+
+If you use Scarf in your research, please cite [Dhapola et al., Nature Communications (2022)](https://doi.org/10.1038/s41467-022-32097-3).
+
+## Support
+
+Open an [issue on GitHub](https://github.com/parashardhapola/scarf/issues) if you run into problems.

VERSION

@@ -1 +1 @@
-0.32.3
+1.0.0

docs/.jupyter_cache/__version__.txt

@@ -0,0 +1 @@
+1.0.1