Merge branch 'master' into integration-improvements

theislab · Jan 16, 2025 · 7931c8c · 7931c8c
2 parents cceb006 + 53ae3e4
commit 7931c8c
Show file tree

Hide file tree

Showing 34 changed files with 314 additions and 385 deletions.
diff --git a/.github/workflows/build_book.yml b/.github/workflows/build_book.yml
@@ -4,7 +4,7 @@ on: [push, pull_request]
 
 jobs:
   build-book:
-    runs-on: ubuntu-22-04
+    runs-on: ubuntu-22.04
     steps:
       - uses: actions/checkout@v4
 
@@ -34,7 +34,7 @@ jobs:
         run: make
 
   pdfhtml:
-    runs-on: ubuntu-22-04
+    runs-on: ubuntu-22.04
 
     steps:
       - uses: actions/checkout@v4

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -2,18 +2,20 @@ fail_fast: false
 default_language_version:
   python: python3
 default_stages:
-  - commit
-  - push
+  - pre-commit
+  - pre-push
 minimum_pre_commit_version: 2.16.0
 repos:
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: v2.5.1
     hooks:
       - id: prettier
-  - repo: https://github.com/psf/black
-    rev: 22.3.0
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.6
     hooks:
-      - id: black-jupyter
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix, --unsafe-fixes]
+      - id: ruff-format
         exclude: |
           (?x)^(
               jupyter-book/conditions/differential_gene_expression.ipynb|

diff --git a/jupyter-book/air_repertoire/clonotype.ipynb b/jupyter-book/air_repertoire/clonotype.ipynb
@@ -73,12 +73,11 @@
     ")\n",
     "warnings.simplefilter(action=\"ignore\", category=FutureWarning)\n",
     "\n",
-    "from palmotif import compute_motif, svg_logo\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
     "import scanpy as sc\n",
     "import scirpy as ir\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import seaborn as sb\n",
+    "from palmotif import compute_motif, svg_logo\n",
     "\n",
     "warnings.simplefilter(action=\"ignore\", category=pd.errors.DtypeWarning)"
    ]
@@ -1698,18 +1697,13 @@
     ")\n",
     "warnings.simplefilter(action=\"ignore\", category=FutureWarning)\n",
     "\n",
-    "from palmotif import compute_motif, svg_logo\n",
-    "import scanpy as sc\n",
     "import dandelion as ddl\n",
-    "import scirpy as ir\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import seaborn as sb\n",
-    "\n",
-    "import os\n",
-    "\n",
     "import matplotlib as mpl\n",
     "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import scanpy as sc\n",
+    "import scirpy as ir\n",
+    "from palmotif import compute_motif, svg_logo\n",
     "\n",
     "warnings.simplefilter(action=\"ignore\", category=pd.errors.DtypeWarning)"
    ]

diff --git a/jupyter-book/air_repertoire/ir_profiling.ipynb b/jupyter-book/air_repertoire/ir_profiling.ipynb
@@ -225,11 +225,10 @@
     ")\n",
     "warnings.simplefilter(action=\"ignore\", category=FutureWarning)\n",
     "\n",
+    "import pandas as pd\n",
     "import scanpy as sc\n",
     "import scirpy as ir\n",
     "\n",
-    "import pandas as pd\n",
-    "\n",
     "warnings.simplefilter(action=\"ignore\", category=pd.errors.DtypeWarning)"
    ]
   },

diff --git a/jupyter-book/air_repertoire/multimodal_integration.ipynb b/jupyter-book/air_repertoire/multimodal_integration.ipynb
@@ -52,11 +52,10 @@
     "warnings.simplefilter(action=\"ignore\", category=FutureWarning)\n",
     "warnings.simplefilter(action=\"ignore\", category=UserWarning)\n",
     "\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
     "import scanpy as sc\n",
     "import scirpy as ir\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import seaborn as sb\n",
     "\n",
     "warnings.simplefilter(action=\"ignore\", category=pd.errors.DtypeWarning)"
    ]
@@ -424,8 +423,8 @@
     }
    ],
    "source": [
-    "from palmotif import compute_pal_motif, mpl_logo, svg_logo\n",
     "from IPython.display import SVG\n",
+    "from palmotif import compute_pal_motif, svg_logo\n",
     "\n",
     "df_sequences = adata_tc[~adata_tc.obs[\"IR_VDJ_1_junction_aa\"].isna()].obs[\n",
     "    [\"IR_VDJ_1_junction_aa\", \"elevated_IFNG\"]\n",
@@ -1017,8 +1016,8 @@
     "    \"tcr\": f\"{path_tmp}/TESSA_tcrs.csv\",\n",
     "    \"exp\": f\"{path_tmp}/TESSA_gex.csv\",\n",
     "    # TESSA models\n",
-    "    \"model\": f\"TESSA/BriseisEncoder/TrainedEncoder.h5\",\n",
-    "    \"embeding_vectors\": f\"TESSA/BriseisEncoder/Atchley_factors.csv\",\n",
+    "    \"model\": \"TESSA/BriseisEncoder/TrainedEncoder.h5\",\n",
+    "    \"embeding_vectors\": \"TESSA/BriseisEncoder/Atchley_factors.csv\",\n",
     "    # Output files\n",
     "    \"output_TCR\": f\"{path_res}/TESSA_tcr_embedding.csv\",\n",
     "    \"output_log\": f\"{path_res}/TESSA_log.log\",\n",
@@ -1270,8 +1269,6 @@
    },
    "outputs": [],
    "source": [
-    "import conga\n",
-    "\n",
     "df_tcr = pd.read_csv(\n",
     "    f\"{path_data}/TCR_00_read_aligned.csv\",\n",
     "    # index_col='barcode',\n",
@@ -1418,7 +1415,7 @@
     "\n",
     "import tcr_embedding.utils_training as utils\n",
     "from tcr_embedding.models.model_selection import run_model_selection\n",
-    "from tcr_embedding.utils_preprocessing import group_shuffle_split, encode_tcr"
+    "from tcr_embedding.utils_preprocessing import encode_tcr, group_shuffle_split"
    ]
   },
   {

diff --git a/jupyter-book/air_repertoire/specificity.ipynb b/jupyter-book/air_repertoire/specificity.ipynb
@@ -66,11 +66,11 @@
     "    \".*IProgress not found*\",\n",
     ")\n",
     "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
     "import scanpy as sc\n",
     "import scirpy as ir\n",
-    "import pandas as pd\n",
-    "import seaborn as sb\n",
-    "import matplotlib.pyplot as plt"
+    "import seaborn as sb"
    ]
   },
   {
@@ -924,8 +924,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from tcrdist.repertoire import TCRrep\n",
-    "from tcrdist.tree import TCRtree"
+    "from tcrdist.repertoire import TCRrep"
    ]
   },
   {
@@ -1230,8 +1229,8 @@
     }
    ],
    "source": [
-    "import scipy.spatial as sp\n",
     "import scipy.cluster.hierarchy as hc\n",
+    "import scipy.spatial as sp\n",
     "from matplotlib import rcParams\n",
     "\n",
     "rcParams[\"figure.figsize\"] = (20, 20)\n",
@@ -1294,7 +1293,6 @@
     "\n",
     "\n",
     "def add_dists(adata, df_dist_alpha, df_dist_beta, name, cutoff):\n",
-    "\n",
     "    adata.uns[f\"ir_dist_aa_{name}\"] = {\n",
     "        \"params\": {\"metric\": f\"{name}\", \"sequence\": \"aa\", \"cutoff\": cutoff}\n",
     "    }\n",

diff --git a/jupyter-book/cellular_structure/annotation.ipynb b/jupyter-book/cellular_structure/annotation.ipynb
@@ -49,8 +49,7 @@
     "\n",
     "warnings.filterwarnings(\"ignore\", category=DeprecationWarning)\n",
     "\n",
-    "import numba\n",
-    "from numba.core.errors import NumbaDeprecationWarning, NumbaPendingDeprecationWarning\n",
+    "from numba.core.errors import NumbaDeprecationWarning\n",
     "\n",
     "warnings.simplefilter(\"ignore\", category=NumbaDeprecationWarning)"
    ]
@@ -84,17 +83,18 @@
     }
    ],
    "source": [
-    "import scanpy as sc\n",
-    "import pandas as pd\n",
+    "import urllib.request\n",
+    "from pathlib import Path\n",
+    "\n",
+    "import celltypist\n",
+    "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
-    "import os\n",
-    "from scipy.sparse import csr_matrix\n",
+    "import pandas as pd\n",
+    "import scanpy as sc\n",
+    "import scarches as sca\n",
     "import seaborn as sns\n",
-    "import matplotlib.pyplot as plt\n",
-    "import celltypist\n",
     "from celltypist import models\n",
-    "import scarches as sca\n",
-    "import urllib.request"
+    "from scipy.sparse import csr_matrix"
    ]
   },
   {
@@ -305,9 +305,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "marker_genes_in_data = dict()\n",
+    "marker_genes_in_data = {}\n",
     "for ct, markers in marker_genes.items():\n",
-    "    markers_found = list()\n",
+    "    markers_found = []\n",
     "    for marker in markers:\n",
     "        if marker in adata.var.index:\n",
     "            markers_found.append(marker)\n",
@@ -2105,9 +2105,9 @@
    "outputs": [],
    "source": [
     "# loading model.pt from figshare\n",
-    "if not os.path.exists(\"./reference_model\"):\n",
-    "    os.mkdir(\"./reference_model\")\n",
-    "elif not os.path.exists(\"./reference_model/model.pt\"):\n",
+    "if not Path(\"./reference_model\").exists():\n",
+    "    Path(\"./reference_model\").mkdir()\n",
+    "elif not Path(\"./reference_model/model.pt\").exists():\n",
     "    urllib.request.urlretrieve(\n",
     "        \"https://figshare.com/ndownloader/files/41436648\",\n",
     "        filename=\"reference_model/model.pt\",\n",
@@ -2198,7 +2198,7 @@
     }
    ],
    "source": [
-    "scarches_model.train(max_epochs=500, plan_kwargs=dict(weight_decay=0.0))"
+    "scarches_model.train(max_epochs=500, plan_kwargs={\"weight_decay\": 0.0})"
    ]
   },
   {
@@ -2777,9 +2777,9 @@
    "outputs": [],
    "source": [
     "adata.obs[\"transf_cell_type_certain\"] = adata.obs.transf_cell_type.tolist()\n",
-    "adata.obs.loc[\n",
-    "    adata.obs.transf_cell_type_unc > 0.2, \"transf_cell_type_certain\"\n",
-    "] = \"Unknown\""
+    "adata.obs.loc[adata.obs.transf_cell_type_unc > 0.2, \"transf_cell_type_certain\"] = (\n",
+    "    \"Unknown\"\n",
+    ")"
    ]
   },
   {

diff --git a/jupyter-book/cellular_structure/integration.ipynb b/jupyter-book/cellular_structure/integration.ipynb
@@ -130,20 +130,17 @@
    ],
    "source": [
     "# Python packages\n",
-    "import scanpy as sc\n",
-    "import scvi\n",
+    "import anndata2ri\n",
     "import bbknn\n",
-    "import scib\n",
+    "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "import matplotlib.pyplot as plt\n",
-    "import matplotlib\n",
+    "import scanpy as sc\n",
+    "import scib\n",
+    "import scvi\n",
     "\n",
     "# R interface\n",
     "from rpy2.robjects import pandas2ri\n",
-    "from rpy2.robjects import r\n",
-    "import rpy2.rinterface_lib.callbacks\n",
-    "import anndata2ri\n",
     "\n",
     "pandas2ri.activate()\n",
     "anndata2ri.activate()\n",
@@ -932,7 +929,6 @@
     "sc.pp.highly_variable_genes(\n",
     "    adata, n_top_genes=2000, flavor=\"cell_ranger\", batch_key=batch_key\n",
     ")\n",
-    "adata\n",
     "adata.var"
    ]
   },

diff --git a/jupyter-book/chromatin_accessibility/quality_control.ipynb b/jupyter-book/chromatin_accessibility/quality_control.ipynb
@@ -75,22 +75,19 @@
    ],
    "source": [
     "# Single-cell packages\n",
-    "import scanpy as sc\n",
+    "import anndata2ri\n",
+    "import matplotlib.pyplot as plt\n",
     "import muon as mu\n",
-    "from muon import atac as ac  # the module containing function for scATAC data processing\n",
+    "import numpy as np\n",
     "\n",
     "# General helpful packages for data analysis and visualization\n",
-    "import os\n",
     "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
+    "import scanpy as sc\n",
     "import seaborn as sns\n",
+    "from muon import atac as ac  # the module containing function for scATAC data processing\n",
     "\n",
     "# Packages enabling to run R code\n",
-    "import rpy2.rinterface_lib.callbacks\n",
-    "import logging\n",
     "from rpy2.robjects import pandas2ri\n",
-    "import anndata2ri\n",
     "\n",
     "pandas2ri.activate()  # Automatically convert rpy2 outputs to pandas DataFrames\n",
     "anndata2ri.activate()\n",