Breaking

.github/workflows/main.yml

@@ -23,19 +23,12 @@ jobs:
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v4
-      - name: Install poetry
-        run: pipx install poetry
-      - uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
       - name: Free Disk Space (Ubuntu)
         uses: jlumbroso/free-disk-space@main
         with:
           # this might remove tools that are actually needed,
           # if set to "true" but frees about 6 GB
           tool-cache: false
-
           # all of these default to true, but feel free to set to
           # "false" if necessary for your workflow
           android: true
@@ -44,8 +37,13 @@ jobs:
           large-packages: false
           docker-images: true
           swap-storage: false
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
       - name: Install project
-        run: make install
+        run: make virtualenv
         continue-on-error: false
       - name: Run linter
         run: make lint

.github/workflows/release.yml

@@ -24,7 +24,7 @@ jobs:
       - name: Generate Changelog
         run: .github/release_message.sh > release_message.md
       - name: Release
-        uses: softprops/action-gh-release@v2
+        uses: softprops/action-gh-release@v1
         with:
           body_path: release_message.md
 
@@ -38,12 +38,11 @@ jobs:
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v4
-      - name: Install poetry
-        run: pipx install poetry
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
       - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: "poetry"
       - name: Build and publish
         run: |
-          poetry publish -u __token__ -p ${{ secrets.POETRY_TOKEN }} --build
+          uv build && uv publish -u __token__ -p ${{ secrets.POETRY_TOKEN }}

.gitignore

@@ -178,3 +178,35 @@ data/main/bias_sparse.npz
 *.gv
 data/log/
 file.txt
+*.dataset
+*.arrow
+tests/data/step_0__predict_part_0_0.h5ad
+data/human_dcm_hcm_nf/
+data/geneformertest.csv
+clf_omni.pkl
+metrics__*.json
+config/torm.txt
+torm.json
+notebooks/additional/figures/
+notebooks/data/temp/
+data/main/*.parquet
+!data/main/avg_embedding.parquet
+!data/main/biomart_pos.parquet
+data/main/gene_embs/
+data/main/gene_locs/
+step_*.h5ad
+*/.lamindb/
+*.lndb
+notebooks/data/xenium/
+notebooks/data/visium/
+notebooks/scPRINT-2-repro-notebooks/normalize_log/
+notebooks/data/GSE215121/
+notebooks/data/GSE72056/
+metrics_*.json
+notebooks/scPRINT-2-repro-notebooks/benchmark_datasets.tar.gz
+notebooks/scPRINT-2-repro-notebooks/._normalize_log
+figures/umap_*.png
+notebooks/scPRINT-2-repro-notebooks/data/*.png
+data/data.zarr/
+data/*.png
+data/*.tsv

.gitmodules

@@ -1,3 +1,15 @@
-[submodule "RNABERT"]
-path = scprint/tokenizers/RNABERT
-url = https://github.com/jkobject/RNABERT
+[submodule "tools/DeepSEM"]
+path = tools/DeepSEM
+url = https://github.com/jkobject/DeepSEM
+[submodule "tools/SERGIO"]
+path = tools/SERGIO
+url = https://github.com/jkobject/SERGIO
+[submodule "tools/scFoundation"]
+path = tools/scFoundation
+url = https://github.com/biomap-research/scFoundation
+[submodule "tools/scGPT"]
+path = tools/scGPT
+url = https://github.com/jkobject/scGPT
+[submodule "tools/Geneformer"]
+path = tools/Geneformer
+url = https://huggingface.co/ctheodoris/Geneformer/

Dockerfile

@@ -0,0 +1,16 @@
+# Use the specified base image
+FROM openproblems/base_pytorch_nvidia:1
+
+# Install Python packages using pip
+RUN pip install git+https://github.com/cantinilab/scPRINT.git@d8cc270b099c8d5dacf6913acc26f2b696685b2b
+RUN pip install gseapy==1.1.2
+RUN pip install git+https://github.com/jkobject/scDataLoader.git@c67c24a2e5c62399912be39169aae76e29e108aa
+
+RUN lamin init --storage ./main --name main --schema bionty
+RUN lamin load anonymous/main
+
+RUN python -c 'import bionty as bt; bt.base.reset_sources(confirm=True); bt.core.sync_all_sources_to_latest()'
+RUN python -c 'from scdataloader.utils import populate_my_ontology; populate_my_ontology()'
+
+# Set the default command (can be overridden)
+CMD ["scprint", "--help"]