Rename sccp to RISE (#489)

* Rename from sccp

* Remove more sccp

* Refactor

---------

Co-authored-by: Aaron Meyer <[email protected]>

Author: aarmey

.github/workflows/test.yml

@@ -20,9 +20,9 @@ jobs:
     - name: Test with pytest
       run: make coverage.xml
     - name: Check formatting
-      run: rye fmt --check sccp
+      run: rye fmt --check RISE
     - name: Check linting
-      run: rye lint sccp
+      run: rye lint RISE
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v4
       with:

sccp/__init__.py renamed to RISE/__init__.py

@@ -68,7 +68,7 @@ def genFigure():
     start = time.time()
     nameOut = "figure" + sys.argv[1]
 
-    exec(f"from sccp.figures.{nameOut} import makeFigure", globals())
+    exec(f"from RISE.figures.{nameOut} import makeFigure", globals())
     ff = makeFigure()  # type: ignore # noqa: F821
 
     if ff is not None:

sccp/data/Thomson/ThomsonCellTypes.csv renamed to RISE/data/Thomson/ThomsonCellTypes.csv

@@ -155,7 +155,7 @@ def plot_ave2genes_per_status(df_total, gene1, gene2, ax):
 
 def plot_toppfun(ax):
     """Plot GSEA results"""
-    df = pd.read_csv("sccp/data/lupus/ToppFun_Cmp14.csv", dtype=str)
+    df = pd.read_csv("RISE/data/lupus/ToppFun_Cmp14.csv", dtype=str)
     df = df.drop(columns=["ID", "Verbose ID"])
     category = df["Category"].to_numpy().astype(str)
 

sccp/data/Thomson/ThomsonDoublets.csv renamed to RISE/data/Thomson/ThomsonDoublets.csv

@@ -16,9 +16,9 @@
 import torch
 from harmonypy import run_harmony
 
-from sccp.factorization import pf2
-from sccp.figures.common import getSetup, subplotLabel
-from sccp.imports import import_lupus
+from RISE.factorization import pf2
+from RISE.figures.common import getSetup, subplotLabel
+from RISE.imports import import_lupus
 
 # Simplified to single-line comments for configuration flags
 RECOMPUTE = False

sccp/data/Thomson/meta.csv renamed to RISE/data/Thomson/meta.csv

@@ -17,7 +17,7 @@ def gateThomsonCellsLeiden(X) -> npt.ArrayLike:
 
 def gateThomsonCells(X) -> npt.ArrayLike:
     """Manually gates cell types for Thomson PaCMAP"""
-    cellTypeDF = pd.read_csv("sccp/data/Thomson/ThomsonCellTypes.csv", index_col=0)
+    cellTypeDF = pd.read_csv("RISE/data/Thomson/ThomsonCellTypes.csv", index_col=0)
     cellTypeDF.index.name = "cell_barcode"
     X.obs = X.obs.join(cellTypeDF, on="cell_barcode", how="inner")
 
@@ -42,7 +42,7 @@ def Thomson_Doublet():
     doublet_score = clf.doublet_score()
     X.obs["doublet"] = doublets
     X.obs["doublet_score"] = doublet_score
-    X.obs["doublet"].to_csv("sccp/data/Thomson/ThomsonDoublets.csv")
+    X.obs["doublet"].to_csv("RISE/data/Thomson/ThomsonDoublets.csv")
 
 
 def getHiResOldLupus(X) -> npt.ArrayLike:

sccp/data/lupus/ToppFun_Cmp14.csv renamed to RISE/data/lupus/ToppFun_Cmp14.csv

@@ -8,7 +8,7 @@
 def import_thomson() -> anndata.AnnData:
     """Import Thompson lab PBMC dataset."""
     # Cell barcodes, sample id of treatment and sample number
-    metafile = pd.read_csv("sccp/data/Thomson/meta.csv", usecols=[0, 1])
+    metafile = pd.read_csv("RISE/data/Thomson/meta.csv", usecols=[0, 1])
     # X = sc.read_10x_mtx(
     #     "/opt/andrew/Thomson/", var_names="gene_symbols", make_unique=True
     # )
@@ -26,7 +26,7 @@ def import_thomson() -> anndata.AnnData:
         }
     )
 
-    doubletDF = pd.read_csv("sccp/data/Thomson/ThomsonDoublets.csv", index_col=0)
+    doubletDF = pd.read_csv("RISE/data/Thomson/ThomsonDoublets.csv", index_col=0)
     doubletDF.index.name = "cell_barcode"
     X.obs = X.obs.join(doubletDF, on="cell_barcode", how="inner")
 

sccp/factorization.py renamed to RISE/factorization.py

@@ -1,15 +1,15 @@
 .PHONY: clean test pyright
 
-flist = $(wildcard sccp/figures/figure*.py)
-allOutput = $(patsubst sccp/figures/figure%.py, output/figure%.svg, $(flist))
+flist = $(wildcard RISE/figures/figure*.py)
+allOutput = $(patsubst RISE/figures/figure%.py, output/figure%.svg, $(flist))
 
 all: $(allOutput)
 
 allThomson: $(filter output/figureThomson%, $(allOutput))
 
 allLupus: $(filter output/figureLupus%, $(allOutput))
 
-output/figure%.svg: sccp/figures/figure%.py
+output/figure%.svg: RISE/figures/figure%.py
 	@ mkdir -p ./output
 	rye run fbuild $*
 
@@ -20,10 +20,10 @@ test: .venv
 	rye sync
 
 coverage.xml: .venv
-	rye run pytest --junitxml=junit.xml --cov=sccp --cov-report xml:coverage.xml
+	rye run pytest --junitxml=junit.xml --cov=RISE --cov-report xml:coverage.xml
 
 pyright: .venv
-	rye run pyright sccp
+	rye run pyright RISE
 
 clean:
 	rm -rf output profile profile.svg

sccp/figures/common.py renamed to RISE/figures/common.py

@@ -1,5 +1,5 @@
 [project]
-name = "sccp"
+name = "RISE"
 version = "0.1.0"
 description = "Single cell analysis across conditions using PARAFAC2."
 authors = [{name = "Andrew Ramirez"}, {name = "Aaron Meyer", email = "[email protected]" }]
@@ -38,8 +38,8 @@ dependencies = [
 readme = "README.md"
 
 [project.scripts]
-fbuild = "sccp.figures.common:genFigure"
-factor = "sccp.imports:factorSave"
+fbuild = "RISE.figures.common:genFigure"
+factor = "RISE.imports:factorSave"
 
 
 [build-system]
@@ -59,7 +59,7 @@ dev-dependencies = [
 allow-direct-references = true
 
 [tool.hatch.build.targets.wheel]
-packages = ["sccp"]
+packages = ["RISE"]
 
 [tool.ruff.lint]
 select = [

sccp/figures/commonFuncs/plotFactors.py renamed to RISE/figures/commonFuncs/plotFactors.py

@@ -26,8 +26,8 @@ anndata==0.11.1
     # via doubletdetection
     # via mudata
     # via parafac2
+    # via rise
     # via scanpy
-    # via sccp
     # via scib
     # via scvi-tools
 annoy==1.17.3
@@ -64,19 +64,19 @@ cycler==0.12.1
 dask==2024.8.2
     # via dask-expr
     # via datashader
-    # via sccp
+    # via rise
 dask-expr==1.1.13
     # via dask
 datashader==0.16.3
-    # via sccp
+    # via rise
 decorator==5.1.1
     # via ipython
 deprecated==1.2.14
     # via scib
 docrep==0.3.2
     # via scvi-tools
 doubletdetection==4.2
-    # via sccp
+    # via rise
 etils==1.11.0
     # via optax
     # via orbax-checkpoint
@@ -108,16 +108,16 @@ geosketch==1.3
 grpcio==1.68.1
     # via tensorboard
 gseapy==1.1.3
-    # via sccp
+    # via rise
 h5netcdf==1.3.0
-    # via sccp
+    # via rise
 h5py==3.11.0
     # via anndata
     # via h5netcdf
     # via scanpy
     # via scib
 harmonypy==0.0.10
-    # via sccp
+    # via rise
 humanize==4.11.0
     # via orbax-checkpoint
 idna==3.8
@@ -167,7 +167,7 @@ legacy-api-wrap==1.4
 leidenalg==0.10.2
     # via doubletdetection
     # via phenograph
-    # via sccp
+    # via rise
     # via scib
 lightning==2.4.0
     # via scvi-tools
@@ -268,9 +268,9 @@ numpy==2.0.2
     # via phenograph
     # via pyarrow
     # via pyro-ppl
+    # via rise
     # via scanorama
     # via scanpy
-    # via sccp
     # via scib
     # via scikit-learn
     # via scikit-misc
@@ -342,7 +342,7 @@ packaging==24.1
     # via xarray
 pacmap==0.7.3
     # via parafac2
-    # via sccp
+    # via rise
 pandas==2.2.2
     # via anndata
     # via dask
@@ -351,16 +351,16 @@ pandas==2.2.2
     # via doubletdetection
     # via gseapy
     # via harmonypy
+    # via rise
     # via scanpy
-    # via sccp
     # via scib
     # via scvi-tools
     # via seaborn
     # via statsmodels
     # via tlviz
     # via xarray
 parafac2 @ git+https://github.com/meyer-lab/parafac2.git@6600c677a77d0f242668babf39559cf7953ff534
-    # via sccp
+    # via rise
 param==2.1.1
     # via datashader
     # via pyct
@@ -439,23 +439,23 @@ rich==13.9.4
     # via flax
     # via scvi-tools
 scanorama==1.7.4
-    # via sccp
+    # via rise
 scanpy==1.10.4
     # via doubletdetection
-    # via sccp
+    # via rise
     # via scib
 scib==1.1.5
-    # via sccp
+    # via rise
 scikit-learn==1.6.0
     # via geosketch
     # via harmonypy
     # via pacmap
     # via parafac2
     # via phenograph
     # via pynndescent
+    # via rise
     # via scanorama
     # via scanpy
-    # via sccp
     # via scib
     # via scvi-tools
     # via umap-learn
@@ -472,9 +472,9 @@ scipy==1.14.1
     # via parafac2
     # via phenograph
     # via pynndescent
+    # via rise
     # via scanorama
     # via scanpy
-    # via sccp
     # via scib
     # via scikit-learn
     # via scvi-tools
@@ -484,10 +484,10 @@ scipy==1.14.1
     # via tlviz
     # via umap-learn
 scvi-tools==1.2.2.post1
-    # via sccp
+    # via rise
 seaborn==0.13.2
+    # via rise
     # via scanpy
-    # via sccp
     # via scib
 session-info==1.0.0
     # via scanpy
@@ -513,8 +513,8 @@ sparse==0.15.4
 stack-data==0.6.3
     # via ipython
 statsmodels==0.14.2
+    # via rise
     # via scanpy
-    # via sccp
     # via tlviz
 stdlib-list==0.10.0
     # via session-info
@@ -526,7 +526,7 @@ tensorboard-data-server==0.7.2
     # via tensorboard
 tensorly==0.8.1
     # via parafac2
-    # via sccp
+    # via rise
 tensorstore==0.1.71
     # via flax
     # via orbax-checkpoint
@@ -536,7 +536,7 @@ threadpoolctl==3.5.0
     # via scikit-learn
 tlviz==0.1.1
     # via parafac2
-    # via sccp
+    # via rise
 toolz==0.12.1
     # via chex
     # via dask
@@ -559,8 +559,8 @@ tqdm==4.66.5
     # via parafac2
     # via pyro-ppl
     # via pytorch-lightning
+    # via rise
     # via scanpy
-    # via sccp
     # via scvi-tools
     # via umap-learn
 traitlets==5.14.3