Comparing Modlyn & Scanpy feature selection methods .md

!pip install 'modlyn[dev]'
!lamin init --storage test-modlyn
Hide code cell output 
Requirement already satisfied: modlyn[dev] in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (0.0.7)
Requirement already satisfied: anndata>=0.12.0rc1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (0.12.10)
Requirement already satisfied: scikit-learn in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (1.9.0)
Requirement already satisfied: matplotlib in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (3.11.1)

Requirement already satisfied: lightning in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (2.6.5)
Requirement already satisfied: lamindb[jupyter] in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (2.8.1)
Requirement already satisfied: seaborn in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (0.13.2)
Requirement already satisfied: scanpy>=1.10 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (1.12.2)
Requirement already satisfied: pre-commit in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (4.6.1)
Requirement already satisfied: nox in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (2025.2.9)
Requirement already satisfied: pytest>=6.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (9.1.1)
Requirement already satisfied: pytest-cov in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (7.1.0)
Requirement already satisfied: nbproject_test in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from modlyn[dev]) (0.6.0)
Requirement already satisfied: array-api-compat>=1.7.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from anndata>=0.12.0rc1->modlyn[dev]) (1.15.0)
Requirement already satisfied: h5py>=3.8 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from anndata>=0.12.0rc1->modlyn[dev]) (3.16.0)
Requirement already satisfied: legacy-api-wrap in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from anndata>=0.12.0rc1->modlyn[dev]) (1.5)
Requirement already satisfied: natsort in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from anndata>=0.12.0rc1->modlyn[dev]) (8.4.0)
Requirement already satisfied: numpy>=1.26 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from anndata>=0.12.0rc1->modlyn[dev]) (2.4.6)
Requirement already satisfied: packaging>=24.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from anndata>=0.12.0rc1->modlyn[dev]) (26.2)
Requirement already satisfied: pandas!=2.1.2,<3,>=2.1.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from anndata>=0.12.0rc1->modlyn[dev]) (2.3.3)
Requirement already satisfied: scipy!=1.17.0,>=1.12 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from anndata>=0.12.0rc1->modlyn[dev]) (1.16.3)
Requirement already satisfied: zarr!=3.0.*,>=2.18.7 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from anndata>=0.12.0rc1->modlyn[dev]) (3.2.1)
Requirement already satisfied: python-dateutil>=2.8.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pandas!=2.1.2,<3,>=2.1.0->anndata>=0.12.0rc1->modlyn[dev]) (2.9.0.post0)
Requirement already satisfied: pytz>=2020.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pandas!=2.1.2,<3,>=2.1.0->anndata>=0.12.0rc1->modlyn[dev]) (2026.2)
Requirement already satisfied: tzdata>=2022.7 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pandas!=2.1.2,<3,>=2.1.0->anndata>=0.12.0rc1->modlyn[dev]) (2026.3)
Requirement already satisfied: iniconfig>=1.0.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pytest>=6.0->modlyn[dev]) (2.3.0)
Requirement already satisfied: pluggy<2,>=1.5 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pytest>=6.0->modlyn[dev]) (1.6.0)
Requirement already satisfied: pygments>=2.7.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pytest>=6.0->modlyn[dev]) (2.20.0)
Requirement already satisfied: six>=1.5 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas!=2.1.2,<3,>=2.1.0->anndata>=0.12.0rc1->modlyn[dev]) (1.17.0)
Requirement already satisfied: certifi in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (2026.7.22)
Requirement already satisfied: fast-array-utils>=1.4 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from fast-array-utils[accel,sparse]>=1.4->scanpy>=1.10->modlyn[dev]) (1.5)
Requirement already satisfied: joblib in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (1.5.3)
Requirement already satisfied: networkx>=2.8.8 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (3.6.1)
Requirement already satisfied: numba>=0.60 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (0.66.0)
Requirement already satisfied: patsy in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (1.0.2)
Requirement already satisfied: pynndescent>=0.5.13 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (0.6.0)
Requirement already satisfied: scverse-misc>=0.0.6 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (0.1.3)
Requirement already satisfied: session-info2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (0.4.1)
Requirement already satisfied: statsmodels>=0.14.5 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (0.14.6)
Requirement already satisfied: tqdm in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (4.69.0)
Requirement already satisfied: typing-extensions in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (4.16.0)
Requirement already satisfied: umap-learn>=0.5.12 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scanpy>=1.10->modlyn[dev]) (0.5.12)

Requirement already satisfied: contourpy>=1.0.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from matplotlib->modlyn[dev]) (1.3.3)
Requirement already satisfied: cycler>=0.10 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from matplotlib->modlyn[dev]) (0.12.1)
Requirement already satisfied: fonttools>=4.28.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from matplotlib->modlyn[dev]) (4.63.0)
Requirement already satisfied: kiwisolver>=1.3.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from matplotlib->modlyn[dev]) (1.5.0)
Requirement already satisfied: pillow>=9 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from matplotlib->modlyn[dev]) (12.3.0)
Requirement already satisfied: pyparsing>=3 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from matplotlib->modlyn[dev]) (3.3.2)
Requirement already satisfied: llvmlite<0.49,>=0.48.0dev0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from numba>=0.60->scanpy>=1.10->modlyn[dev]) (0.48.0)
Requirement already satisfied: narwhals>=2.0.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scikit-learn->modlyn[dev]) (2.24.0)
Requirement already satisfied: threadpoolctl>=3.5.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from scikit-learn->modlyn[dev]) (3.6.0)

Requirement already satisfied: donfig>=0.8 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from zarr!=3.0.*,>=2.18.7->anndata>=0.12.0rc1->modlyn[dev]) (0.8.1.post1)
Requirement already satisfied: google-crc32c>=1.5 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from zarr!=3.0.*,>=2.18.7->anndata>=0.12.0rc1->modlyn[dev]) (1.8.0)
Requirement already satisfied: numcodecs>=0.14 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from zarr!=3.0.*,>=2.18.7->anndata>=0.12.0rc1->modlyn[dev]) (0.16.5)
Requirement already satisfied: pyyaml in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from donfig>=0.8->zarr!=3.0.*,>=2.18.7->anndata>=0.12.0rc1->modlyn[dev]) (6.0.3)
WARNING: lamindb 2.8.1 does not provide the extra 'jupyter'
Requirement already satisfied: lamindb-core==2.8.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.8.1)
Requirement already satisfied: lamin_utils==0.16.4 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.16.4)
Requirement already satisfied: lamin_cli==1.19.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.19.1)
Requirement already satisfied: lamindb_setup==1.25.5 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.25.5)
Requirement already satisfied: psycopg2-binary in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.9.12)
Requirement already satisfied: rich-click>=1.7 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamin_cli==1.19.1->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.9.8)
Requirement already satisfied: bionty<3,>=2.3.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.4.2)
Requirement already satisfied: pertdb<3,>=2.2.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.2.0)
Requirement already satisfied: jupytext in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.19.5)
Requirement already satisfied: nbconvert>=7.2.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (7.17.1)
Requirement already satisfied: nbproject==0.11.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.11.1)
Requirement already satisfied: pyarrow in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (25.0.0)
Requirement already satisfied: pandera>=0.24.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.32.1)
Requirement already satisfied: graphviz in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.21)

Requirement already satisfied: python-dotenv in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.2.2)
Requirement already satisfied: django<5.3,>=5.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (5.2.16)
Requirement already satisfied: dj_database_url<3.0.0,>=1.3.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.3.0)
Requirement already satisfied: django-pgtrigger in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.17.0)
Requirement already satisfied: pydantic-settings in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.14.2)
Requirement already satisfied: platformdirs<5.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.11.0)
Requirement already satisfied: httpx_retries<1.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.6.0)
Requirement already satisfied: requests in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.34.2)
Requirement already satisfied: universal_pathlib==0.3.10 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.3.10)
Requirement already satisfied: botocore<2.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.43.46)
Requirement already satisfied: supabase<=2.24.0,>=2.20.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.24.0)
Requirement already satisfied: websockets>=13.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (15.0.1)
Requirement already satisfied: pyjwt<3.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.13.0)
Requirement already satisfied: psutil in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (7.2.2)
Requirement already satisfied: aiobotocore<4.0.0,>=2.12.4 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.8.0)
Requirement already satisfied: s3fs!=2024.10.0,<=2026.1.0,>=2023.12.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2026.1.0)
Requirement already satisfied: boto3 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.43.46)
Requirement already satisfied: pydantic>=2.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbproject==0.11.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.13.4)
Requirement already satisfied: orjson in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbproject==0.11.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.11.9)
Requirement already satisfied: importlib-metadata in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbproject==0.11.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (9.0.0)
Requirement already satisfied: fsspec>=2024.5.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from universal_pathlib==0.3.10->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2026.1.0)
Requirement already satisfied: pathlib-abc<0.6.0,>=0.5.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from universal_pathlib==0.3.10->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.5.2)
Requirement already satisfied: aiohttp<4.0.0,>=3.12.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.14.3)
Requirement already satisfied: aioitertools<1.0.0,>=0.5.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.13.0)
Requirement already satisfied: jmespath<2.0.0,>=0.7.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.1.0)
Requirement already satisfied: multidict<7.0.0,>=6.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (6.7.1)
Requirement already satisfied: wrapt<3.0.0,>=1.10.10 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.2.2)
WARNING: aiobotocore 3.8.0 does not provide the extra 'boto3'
Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.12.0->aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.7.1)
Requirement already satisfied: aiosignal>=1.4.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.12.0->aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.4.0)
Requirement already satisfied: attrs>=17.3.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.12.0->aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (26.1.0)
Requirement already satisfied: frozenlist>=1.1.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.12.0->aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.8.0)
Requirement already satisfied: propcache>=0.2.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.12.0->aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.5.2)
Requirement already satisfied: yarl<2.0,>=1.17.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.12.0->aiobotocore<4.0.0,>=2.12.4->aiobotocore[boto3]<4.0.0,>=2.12.4; extra == "aws"->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.24.5)
Requirement already satisfied: urllib3!=2.2.0,<3,>=1.25.4 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from botocore<2.0.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.7.0)

Requirement already satisfied: asgiref>=3.8.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from django<5.3,>=5.2->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.12.1)
Requirement already satisfied: sqlparse>=0.3.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from django<5.3,>=5.2->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.5.5)
Requirement already satisfied: httpx>=0.20.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from httpx_retries<1.0.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.28.1)
Requirement already satisfied: realtime==2.24.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.24.0)
Requirement already satisfied: supabase-functions==2.24.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.24.0)
Requirement already satisfied: storage3==2.24.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.24.0)
Requirement already satisfied: supabase-auth==2.24.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.24.0)
Requirement already satisfied: postgrest==2.24.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.24.0)
Requirement already satisfied: deprecation>=2.1.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from postgrest==2.24.0->supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.1.0)
Requirement already satisfied: strenum>=0.4.15 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from supabase-functions==2.24.0->supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.4.15)
Requirement already satisfied: anyio in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from httpx>=0.20.0->httpx_retries<1.0.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.14.2)
Requirement already satisfied: httpcore==1.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from httpx>=0.20.0->httpx_retries<1.0.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.0.9)

Requirement already satisfied: idna in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from httpx>=0.20.0->httpx_retries<1.0.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.18)
Requirement already satisfied: h11>=0.16 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from httpcore==1.*->httpx>=0.20.0->httpx_retries<1.0.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.16.0)
Requirement already satisfied: h2<5,>=3 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from httpx[http2]<0.29,>=0.26->postgrest==2.24.0->supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.3.0)
Requirement already satisfied: hyperframe<7,>=6.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from h2<5,>=3->httpx[http2]<0.29,>=0.26->postgrest==2.24.0->supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (6.1.0)
Requirement already satisfied: hpack<5,>=4.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from h2<5,>=3->httpx[http2]<0.29,>=0.26->postgrest==2.24.0->supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.2.0)
Requirement already satisfied: annotated-types>=0.6.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pydantic>=2.0.0->nbproject==0.11.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.7.0)
Requirement already satisfied: pydantic-core==2.46.4 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pydantic>=2.0.0->nbproject==0.11.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.46.4)
Requirement already satisfied: typing-inspection>=0.4.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pydantic>=2.0.0->nbproject==0.11.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.4.2)

Requirement already satisfied: beautifulsoup4 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.15.0)
Requirement already satisfied: bleach!=5.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from bleach[css]!=5.0.0->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (6.4.0)
Requirement already satisfied: defusedxml in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.7.1)
Requirement already satisfied: jinja2>=3.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.1.6)
Requirement already satisfied: jupyter-core>=4.7 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (5.9.1)
Requirement already satisfied: jupyterlab-pygments in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.3.0)
Requirement already satisfied: markupsafe>=2.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.0.3)
Requirement already satisfied: mistune<4,>=2.0.3 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.3.4)
Requirement already satisfied: nbclient>=0.5.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.11.0)
Requirement already satisfied: nbformat>=5.7 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (5.10.4)
Requirement already satisfied: pandocfilters>=1.4.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.5.1)
Requirement already satisfied: traitlets>=5.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (5.15.1)
Requirement already satisfied: webencodings in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from bleach!=5.0.0->bleach[css]!=5.0.0->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.5.1)
Requirement already satisfied: tinycss2>=1.1.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from bleach[css]!=5.0.0->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.5.1)
Requirement already satisfied: jupyter-client>=7.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbclient>=0.5.0->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (8.9.1)
Requirement already satisfied: pyzmq>=25.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from jupyter-client>=7.0.0->nbclient>=0.5.0->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (27.1.0)
Requirement already satisfied: tornado>=6.4.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from jupyter-client>=7.0.0->nbclient>=0.5.0->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (6.5.7)
Requirement already satisfied: fastjsonschema>=2.15 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbformat>=5.7->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.21.2)
Requirement already satisfied: jsonschema>=2.6 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbformat>=5.7->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.26.0)

Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from jsonschema>=2.6->nbformat>=5.7->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2025.9.1)
Requirement already satisfied: referencing>=0.28.4 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from jsonschema>=2.6->nbformat>=5.7->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.37.0)
Requirement already satisfied: rpds-py>=0.25.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from jsonschema>=2.6->nbformat>=5.7->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2026.6.3)
Requirement already satisfied: typeguard in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pandera>=0.24.0->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.5.2)
Requirement already satisfied: typing_inspect>=0.6.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pandera>=0.24.0->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.9.0)
Requirement already satisfied: cryptography>=3.4.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pyjwt[crypto]>=2.10.1->supabase-auth==2.24.0->supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (49.0.0)
Requirement already satisfied: cffi>=2.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cryptography>=3.4.0->pyjwt[crypto]>=2.10.1->supabase-auth==2.24.0->supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.1.0)
Requirement already satisfied: pycparser in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cffi>=2.0.0->cryptography>=3.4.0->pyjwt[crypto]>=2.10.1->supabase-auth==2.24.0->supabase<=2.24.0,>=2.20.0->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.0)
Requirement already satisfied: click>=8 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from rich-click>=1.7->lamin_cli==1.19.1->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (8.4.2)
Requirement already satisfied: rich>=12 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from rich-click>=1.7->lamin_cli==1.19.1->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (15.0.0)
Requirement already satisfied: markdown-it-py>=2.2.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from rich>=12->rich-click>=1.7->lamin_cli==1.19.1->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.2.0)
Requirement already satisfied: mdurl~=0.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=12->rich-click>=1.7->lamin_cli==1.19.1->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.1.2)

Requirement already satisfied: mypy-extensions>=0.3.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from typing_inspect>=0.6.0->pandera>=0.24.0->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (1.1.0)
Requirement already satisfied: soupsieve>=1.6.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from beautifulsoup4->nbconvert>=7.2.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (2.9.1)
Requirement already satisfied: s3transfer<0.20.0,>=0.19.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from boto3->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.19.2)

Requirement already satisfied: zipp>=3.20 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from importlib-metadata->nbproject==0.11.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (4.1.0)
Requirement already satisfied: mdit-py-plugins in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from jupytext->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (0.6.1)
Requirement already satisfied: lightning-utilities<2.0,>=0.10.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lightning->modlyn[dev]) (0.15.3)
Requirement already satisfied: torch<4.0,>=2.1.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lightning->modlyn[dev]) (2.13.0)
Requirement already satisfied: torchmetrics<3.0,>0.7.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lightning->modlyn[dev]) (1.9.0)
Requirement already satisfied: pytorch-lightning in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from lightning->modlyn[dev]) (2.6.5)

Requirement already satisfied: filelock in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from torch<4.0,>=2.1.0->lightning->modlyn[dev]) (3.32.0)
Requirement already satisfied: setuptools>=77.0.3 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from torch<4.0,>=2.1.0->lightning->modlyn[dev]) (83.0.0)
Requirement already satisfied: sympy>=1.13.3 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from torch<4.0,>=2.1.0->lightning->modlyn[dev]) (1.14.0)
Requirement already satisfied: cuda-toolkit==13.0.3 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (13.0.3.0)
Requirement already satisfied: cuda-bindings<14,>=13.0.3 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from torch<4.0,>=2.1.0->lightning->modlyn[dev]) (13.3.1)
Requirement already satisfied: nvidia-cudnn-cu13==9.20.0.48 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from torch<4.0,>=2.1.0->lightning->modlyn[dev]) (9.20.0.48)
Requirement already satisfied: nvidia-cusparselt-cu13==0.8.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from torch<4.0,>=2.1.0->lightning->modlyn[dev]) (0.8.1)
Requirement already satisfied: nvidia-nccl-cu13==2.29.7 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from torch<4.0,>=2.1.0->lightning->modlyn[dev]) (2.29.7)
Requirement already satisfied: nvidia-nvshmem-cu13==3.4.5 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from torch<4.0,>=2.1.0->lightning->modlyn[dev]) (3.4.5)
Requirement already satisfied: triton==3.7.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from torch<4.0,>=2.1.0->lightning->modlyn[dev]) (3.7.1)
Requirement already satisfied: nvidia-cublas==13.1.1.3.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (13.1.1.3)
Requirement already satisfied: nvidia-cuda-nvrtc==13.0.88.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (13.0.88)
Requirement already satisfied: nvidia-cuda-runtime==13.0.96.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (13.0.96)
Requirement already satisfied: nvidia-cufft==12.0.0.61.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (12.0.0.61)
Requirement already satisfied: nvidia-nvjitlink<14,>=13.0.88 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (13.3.33)
Requirement already satisfied: nvidia-cufile==1.15.1.6.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (1.15.1.6)
Requirement already satisfied: nvidia-cuda-cupti==13.0.85.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (13.0.85)
Requirement already satisfied: nvidia-curand==10.4.0.35.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (10.4.0.35)
Requirement already satisfied: nvidia-cusolver==12.0.4.66.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (12.0.4.66)

Requirement already satisfied: nvidia-cusparse==12.6.3.3.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (12.6.3.3)
Requirement already satisfied: nvidia-nvtx==13.0.85.* in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-toolkit[cublas,cudart,cufft,cufile,cupti,curand,cusolver,cusparse,nvjitlink,nvrtc,nvtx]==13.0.3; platform_system == "Linux"->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (13.0.85)
Requirement already satisfied: cuda-pathfinder>=1.4.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from cuda-bindings<14,>=13.0.3->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (1.6.0)

Requirement already satisfied: mpmath<1.4,>=1.1.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from sympy>=1.13.3->torch<4.0,>=2.1.0->lightning->modlyn[dev]) (1.3.0)

Requirement already satisfied: ipykernel in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nbproject_test->modlyn[dev]) (7.3.0)
Requirement already satisfied: comm>=0.1.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipykernel->nbproject_test->modlyn[dev]) (0.2.3)
Requirement already satisfied: debugpy>=1.6.5 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipykernel->nbproject_test->modlyn[dev]) (1.8.21)
Requirement already satisfied: ipython>=7.23.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipykernel->nbproject_test->modlyn[dev]) (9.15.0)
Requirement already satisfied: matplotlib-inline>=0.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipykernel->nbproject_test->modlyn[dev]) (0.2.2)
Requirement already satisfied: nest-asyncio2>=1.7.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipykernel->nbproject_test->modlyn[dev]) (1.7.2)
Requirement already satisfied: decorator>=5.1.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (5.3.1)
Requirement already satisfied: ipython-pygments-lexers>=1.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (1.1.1)
Requirement already satisfied: jedi>=0.18.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (0.20.0)
Requirement already satisfied: pexpect>4.6 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (4.9.0)
Requirement already satisfied: prompt_toolkit<3.1.0,>=3.0.41 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (3.0.52)
Requirement already satisfied: stack_data>=0.6.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (0.6.3)
Requirement already satisfied: wcwidth in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from prompt_toolkit<3.1.0,>=3.0.41->ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (0.8.2)
Requirement already satisfied: parso<0.9.0,>=0.8.6 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from jedi>=0.18.2->ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (0.8.7)

Requirement already satisfied: ptyprocess>=0.5 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pexpect>4.6->ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (0.7.0)
Requirement already satisfied: executing>=1.2.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from stack_data>=0.6.0->ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (2.2.1)
Requirement already satisfied: asttokens>=2.1.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from stack_data>=0.6.0->ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (3.0.2)
Requirement already satisfied: pure-eval in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from stack_data>=0.6.0->ipython>=7.23.1->ipykernel->nbproject_test->modlyn[dev]) (0.2.3)
Requirement already satisfied: argcomplete<4,>=1.9.4 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nox->modlyn[dev]) (3.7.0)
Requirement already satisfied: colorlog<7,>=2.6.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nox->modlyn[dev]) (6.11.0)
Requirement already satisfied: dependency-groups>=1.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nox->modlyn[dev]) (1.3.1)
Requirement already satisfied: virtualenv>=20.14.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from nox->modlyn[dev]) (21.7.0)

Requirement already satisfied: distlib<1,>=0.3.7 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from virtualenv>=20.14.1->nox->modlyn[dev]) (0.4.3)
Requirement already satisfied: python-discovery>=1.4.2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from virtualenv>=20.14.1->nox->modlyn[dev]) (1.5.0)
Requirement already satisfied: cfgv>=2.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pre-commit->modlyn[dev]) (3.5.0)
Requirement already satisfied: identify>=1.0.0 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pre-commit->modlyn[dev]) (2.6.19)
Requirement already satisfied: nodeenv>=0.11.1 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from pre-commit->modlyn[dev]) (1.10.0)

Requirement already satisfied: coverage>=7.10.6 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from coverage[toml]>=7.10.6->pytest-cov->modlyn[dev]) (7.15.2)
Requirement already satisfied: charset_normalizer<4,>=2 in /opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages (from requests->lamindb_setup==1.25.5->lamindb_setup[aws]==1.25.5->lamindb-core==2.8.1->lamindb-core[full]==2.8.1->lamindb[jupyter]; extra == "dev"->modlyn[dev]) (3.4.9)

→ initialized lamindb: anonymous/test-modlyn

import lamindb as ln
import modlyn as mn
import scanpy as sc
import pandas as pd
import seaborn as sns

sns.set_theme()
%config InlineBackend.figure_formats = ['svg']
Hide code cell output 
→ connected lamindb: anonymous/test-modlyn

ln.track()
Hide code cell output 
→ created Transform('cMfGmSHmiInu0000', key='quickstart.ipynb'), started new Run('mmhhkAv83GkVZtqc') at 2026-07-23 11:05:33 UTC

→ notebook imports: lamindb-core==2.8.1 modlyn==0.0.7 pandas==2.3.3 scanpy==1.12.2 seaborn==0.13.2

• tip: to identify the notebook across renames, pass the uid: ln.track("cMfGmSHmiInu")

Prepare dataset

artifact = ln.Artifact.using("laminlabs/arrayloader-benchmarks").get(
    "JNaxQe8zbljesdbK0000"
)
adata = artifact.load()
sc.pp.log1p(adata)
adata
Hide code cell output 
/tmp/ipykernel_3396/2273553885.py:1: DeprecationWarning: Use connect instead of using, using will be removed in the future.
  artifact = ln.Artifact.using("laminlabs/arrayloader-benchmarks").get(

→ transferred: Artifact(uid='JNaxQe8zbljesdbK0000'), Storage(uid='LCfy7WeXbvKN')

AnnData object with n_obs × n_vars = 1000 × 100
    obs: 'sample', 'gene_count', 'tscp_count', 'mread_count', 'drugname_drugconc', 'drug', 'cell_line', 'sublibrary', 'BARCODE', 'pcnt_mito', 'S_score', 'G2M_score', 'phase', 'pass_filter', 'cell_name', 'plate'
    uns: 'log1p'

keep = adata.obs["cell_line"].value_counts().loc[lambda x: x > 3].index
adata = adata[adata.obs["cell_line"].isin(keep)].copy()
adata
Hide code cell output 
AnnData object with n_obs × n_vars = 992 × 100
    obs: 'sample', 'gene_count', 'tscp_count', 'mread_count', 'drugname_drugconc', 'drug', 'cell_line', 'sublibrary', 'BARCODE', 'pcnt_mito', 'S_score', 'G2M_score', 'phase', 'pass_filter', 'cell_name', 'plate'
    uns: 'log1p'

adata.obs["cell_line"].value_counts().tail()
Hide code cell output 
cell_line
CVCL_0099    8
CVCL_1693    8
CVCL_1239    8
CVCL_0028    4
CVCL_1125    4
Name: count, dtype: int64

Train LogReg with Modlyn

logreg = mn.models.SimpleLogReg(
    adata=adata,
    label_column="cell_line",
    learning_rate=1e-1,
    weight_decay=1e-3,
)
logreg.fit(
    adata_train=adata,
    adata_val=adata[:20],
    train_dataloader_kwargs={"batch_size": 128, "drop_last": True, "num_workers": 4},
    max_epochs=5,
)
Hide code cell output 
GPU available: False, used: False

TPU available: False, using: 0 TPU cores

/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/logger_connector.py:76: Starting from v1.9.0, `tensorboardX` has been removed as a dependency of the `lightning.pytorch` package, due to potential conflicts with other packages in the ML ecosystem. For this reason, `logger=True` will use `CSVLogger` as the default logger, unless the `tensorboard` or `tensorboardX` packages are found. Please `pip install lightning[extra]` or one of them to enable TensorBoard support by default
💡 Tip: For seamless cloud logging and experiment tracking, try installing [litlogger](https://pypi.org/project/litlogger/) to enable LitLogger, which logs metrics and artifacts automatically to the Lightning Experiments platform.

💡 Tip: For seamless cloud uploads and versioning, try installing [litmodels](https://pypi.org/project/litmodels/) to enable LitModelCheckpoint, which syncs automatically with the Lightning model registry.

┏━━━┳━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━┳━━━━━━━┓
┃   ┃ Name          ┃ Type             ┃ Params ┃ Mode  ┃ FLOPs ┃
┡━━━╇━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━╇━━━━━━━┩
│ 0 │ linear        │ Linear           │  4.5 K │ train │     0 │
│ 1 │ train_metrics │ MetricCollection │      0 │ train │     0 │
│ 2 │ val_metrics   │ MetricCollection │      0 │ train │     0 │
└───┴───────────────┴──────────────────┴────────┴───────┴───────┘

Trainable params: 4.5 K                                                                                            
Non-trainable params: 0                                                                                            
Total params: 4.5 K                                                                                                
Total estimated model params size (MB): 0.018                                                                      
Modules in train mode: 7                                                                                           
Modules in eval mode: 0                                                                                            
Total FLOPs: 0                                                                                                     

/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py:21: `isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.

/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/rich/live.py:260: UserWarning: install 
"ipywidgets" for Jupyter support
  warnings.warn('install "ipywidgets" for Jupyter support')

/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py:21: `isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:434: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=3` in the `DataLoader` to improve performance.

`Trainer.fit` stopped: `max_epochs=5` reached.













logreg.plot_losses()










Hide code cell output



_images/57c969fd0a744a8c1b37849600e40be9598362c0fadd25bbc33777af358d37d4.svg
Final training loss: 3.2961
Final validation loss: 4.2149















logreg.plot_classification_report(adata)










Hide code cell output




Weighted F1: 0.098





/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/sklearn/metrics/_classification.py:1879: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, f"{metric.capitalize()} is", result.shape[0])
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/sklearn/metrics/_classification.py:1879: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, f"{metric.capitalize()} is", result.shape[0])
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/sklearn/metrics/_classification.py:1879: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, f"{metric.capitalize()} is", result.shape[0])




_images/bf317ac90ef274e8fc1f1e07bdb95ea071d8ac02e638ee61fbbbe42220f50cda.svg










Get features scores of different methods






df_modlyn_logreg = logreg.get_weights()
df_modlyn_logreg.head()










Hide code cell output








  
    

      gene_name
      PIM2
      ECHS1
      LINC03049
      RPL27AP5
      ENSG00000274769
      ENSG00000277770
      CTF1
      Y_RNA-586
      LINC01312
      XRCC6P2
      ...
      HMOX1
      KRT8P28
      ENSG00000271945
      CHRND
      ADAM7-AS2
      ENSG00000272384
      IMP4
      PSMC1P8
      HOMER3
      AIFM3
    

  
  
    

      CVCL_0023
      -0.422666
      -0.506160
      -0.002956
      0.010464
      0.007372
      0.011887
      -0.010289
      0.011620
      -0.039496
      0.003184
      ...
      -0.100679
      0.003845
      0.601916
      0.000430
      0.010069
      -0.006843
      -0.434854
      -0.011490
      0.435216
      -0.060732
    

    

      CVCL_0028
      -0.095305
      0.469816
      -0.006349
      -0.004729
      -0.012226
      0.004879
      0.004470
      0.010267
      -0.019992
      0.004431
      ...
      -0.138809
      -0.006756
      0.000416
      0.002522
      0.009235
      0.007154
      -0.112344
      -0.012179
      -0.044331
      0.007553
    

    

      CVCL_0069
      0.903953
      -0.345842
      -0.005748
      0.005704
      -0.009512
      -0.002293
      -0.011909
      0.005523
      -0.033314
      0.008082
      ...
      -0.307831
      0.008610
      -0.066037
      -0.003863
      0.006472
      0.006525
      -0.259674
      -0.003985
      -0.176322
      -0.040104
    

    

      CVCL_0099
      -0.211742
      -0.161015
      -0.008330
      -0.009837
      -0.009997
      -0.006892
      0.018938
      0.007052
      -0.033342
      -0.011921
      ...
      -0.234590
      0.008841
      -0.021167
      0.007888
      -0.006830
      -0.007106
      -0.219199
      0.009113
      -0.061126
      -0.009620
    

    

      CVCL_0131
      -0.042574
      0.669554
      0.005480
      -0.005993
      0.007165
      -0.004007
      0.001241
      -0.010810
      -0.021955
      0.009477
      ...
      -0.189909
      0.009038
      -0.206123
      0.002917
      -0.007139
      0.011839
      -0.582050
      0.008407
      -0.288258
      -0.031270
    

  



5 rows × 100 columns












sc.tl.rank_genes_groups(adata, "cell_line", method="logreg", key_added="sc_logreg")
df_scanpy_logreg = sc.get.rank_genes_groups_df(
    adata, group=None, key="sc_logreg"
).pivot(index="group", columns="names", values="scores")
df_scanpy_logreg.attrs["method_name"] = "scanpy_logreg"
df_scanpy_logreg.head()










Hide code cell output








  
    

      names
      ACOT9
      ADAM7-AS2
      AGGF1P9
      AIFM3
      ARHGAP23P1
      ARID5A
      ATP5PB
      ATRIP
      BAG4
      BLVRB
      ...
      RPL32P23
      RPL7P6
      SNORD115-2
      TLDC2
      TSPAN9
      UBE2L3
      UBE2V1P8
      XRCC6P2
      XXYLT1-AS2
      Y_RNA-586
    

    

      group
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    

  
  
    

      CVCL_0023
      0.659618
      0.0
      0.0
      -0.031030
      0.0
      0.231701
      -0.597661
      -0.293584
      -0.548324
      -0.266297
      ...
      0.0
      0.0
      0.0
      -0.100346
      -0.296451
      -0.581786
      0.0
      0.0
      -0.026877
      0.0
    

    

      CVCL_0028
      -0.242723
      0.0
      0.0
      -0.004131
      0.0
      -0.056369
      -0.127508
      -0.051344
      -0.118967
      -0.154228
      ...
      0.0
      0.0
      0.0
      -0.009306
      -0.237152
      0.332722
      0.0
      0.0
      -0.005290
      0.0
    

    

      CVCL_0069
      -0.660634
      0.0
      0.0
      -0.016867
      0.0
      -0.187452
      -0.364053
      0.430800
      -0.362276
      0.079544
      ...
      0.0
      0.0
      0.0
      -0.029943
      -0.612790
      -0.662974
      0.0
      0.0
      -0.017092
      0.0
    

    

      CVCL_0099
      0.580846
      0.0
      0.0
      -0.012110
      0.0
      -0.107890
      -0.227720
      1.138230
      -0.206624
      -0.275042
      ...
      0.0
      0.0
      0.0
      -0.028184
      -0.400412
      -0.420857
      0.0
      0.0
      -0.009776
      0.0
    

    

      CVCL_0131
      1.401364
      0.0
      0.0
      -0.031490
      0.0
      -0.405170
      0.233426
      0.091139
      0.118451
      -0.426097
      ...
      0.0
      0.0
      0.0
      -0.241476
      0.822093
      -0.169690
      0.0
      0.0
      -0.035441
      0.0
    

  



5 rows × 100 columns












sc.tl.rank_genes_groups(adata, "cell_line", method="wilcoxon", key_added="sc_wilcoxon")
df_scanpy_wilcoxon = sc.get.rank_genes_groups_df(
    adata, group=None, key="sc_wilcoxon"
).pivot(index="group", columns="names", values="scores")
df_scanpy_wilcoxon.attrs["method_name"] = "scanpy_wilcoxon"
df_scanpy_wilcoxon.head()










Hide code cell output




/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:459: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "names"] = self.var_names[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:461: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "scores"] = scores[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:464: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals"] = pvals[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:474: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "pvals_adj"] = pvals_adj[global_indices]
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/scanpy/tools/_rank_genes_groups.py:485: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`
  self.stats[group_name, "logfoldchanges"] = np.log2(









  
    

      names
      ACOT9
      ADAM7-AS2
      AGGF1P9
      AIFM3
      ARHGAP23P1
      ARID5A
      ATP5PB
      ATRIP
      BAG4
      BLVRB
      ...
      RPL32P23
      RPL7P6
      SNORD115-2
      TLDC2
      TSPAN9
      UBE2L3
      UBE2V1P8
      XRCC6P2
      XXYLT1-AS2
      Y_RNA-586
    

    

      group
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    

  
  
    

      CVCL_0023
      0.332005
      0.0
      0.0
      -0.018388
      0.0
      0.144039
      -0.533252
      -0.193074
      -0.478088
      -0.299997
      ...
      0.0
      0.0
      0.0
      -0.045970
      -0.571730
      -0.687506
      0.0
      0.0
      -0.018388
      0.0
    

    

      CVCL_0028
      -0.409188
      0.0
      0.0
      -0.006995
      0.0
      -0.073444
      -0.202846
      -0.073444
      -0.181862
      -0.241316
      ...
      0.0
      0.0
      0.0
      -0.017487
      -0.356728
      0.466895
      0.0
      0.0
      -0.006995
      0.0
    

    

      CVCL_0069
      -0.796838
      0.0
      0.0
      -0.013621
      0.0
      -0.143022
      -0.395014
      0.307384
      -0.354150
      -0.024064
      ...
      0.0
      0.0
      0.0
      -0.034053
      -0.694680
      -0.755975
      0.0
      0.0
      -0.013621
      0.0
    

    

      CVCL_0099
      0.629415
      0.0
      0.0
      -0.009912
      0.0
      -0.104077
      -0.287449
      1.125018
      -0.257713
      -0.341966
      ...
      0.0
      0.0
      0.0
      -0.024780
      -0.505515
      -0.550119
      0.0
      0.0
      -0.009912
      0.0
    

    

      CVCL_0131
      2.103801
      0.0
      0.0
      -0.022238
      0.0
      -0.233502
      0.201855
      0.049323
      -0.014255
      -0.467575
      ...
      0.0
      0.0
      0.0
      -0.055596
      1.118188
      -0.118889
      0.0
      0.0
      -0.022238
      0.0
    

  



5 rows × 100 columns












Compare feature selection results






compare = mn.eval.CompareScoresJaccard(
    [df_modlyn_logreg, df_scanpy_logreg, df_scanpy_wilcoxon], n_top_values=[5, 10, 25]
)













compare.plot_heatmaps()










Hide code cell output



_images/4f77c975c9c4036f29cf0721f1d36e56b0d5a757d8292c6b1539f4f2b62d0d81.svg










compare.compute_jaccard_comparison()
compare.plot_jaccard_comparison()










Hide code cell output



_images/e813e6b637a22794c67dfa8febf2898820364e2fde4e170cdbc4c2793d603562.svg










ln.finish()










Hide code cell output




! calling anonymously, will miss private instances





→ finished Run('mmhhkAv83GkVZtqc') after 29s at 2026-07-23 11:06:02 UTC