normalize strings

Author: scottgigante-immunai

openproblems/api/hash.py

@@ -46,8 +46,10 @@ def docker_token(image_name):
             [
                 "curl",
                 "--silent",
-                f"https://auth.docker.io/token?scope=repository:{image_name}:"
-                "pull&service=registry.docker.io",
+                (
+                    f"https://auth.docker.io/token?scope=repository:{image_name}:"
+                    "pull&service=registry.docker.io"
+                ),
             ]
         )
     )
@@ -88,8 +90,8 @@ def docker_hash(image_name):
             return docker_labels_from_api(image_name)["bio.openproblems.hash"]
     except Exception:  # pragma: nocover
         warnings.warn(
-            "Failed to access docker or the docker API; docker image hash failed. "
-            f"All jobs using {image_name} will not be cached."
+            "Failed to access docker or the docker API; docker image hash failed. All"
+            f" jobs using {image_name} will not be cached."
         )
         return str(random.getrandbits(256))
 

openproblems/data/tabula_muris_senis.py

@@ -29,8 +29,8 @@ def check_unknown_organs(datasets, organ_list):
     unknown_organs = set(organ_list) - known_organs
     if unknown_organs:
         raise ValueError(
-            f"Unknown organs provided in `organ_list': {', '.join(unknown_organs)}. "
-            f"Known organs are {', '.join(known_organs)}"
+            f"Unknown organs provided in `organ_list': {', '.join(unknown_organs)}."
+            f" Known organs are {', '.join(known_organs)}"
         )
 
 
@@ -107,8 +107,8 @@ def load_tabula_muris_senis(test=False, method_list=None, organ_list=None):
     unknown_methods = set(method_list) - set(["facs", "droplet"])
     if unknown_methods:
         raise ValueError(
-            f"Unknown methods provided in `method_list': {','.join(unknown_methods)}. "
-            "Known methods are `facs' and `droplet'"
+            f"Unknown methods provided in `method_list': {','.join(unknown_methods)}."
+            " Known methods are `facs' and `droplet'"
         )
 
     datasets_path = f"/curation/v1/collections/{COLLECTION_ID}"

openproblems/patch.py

@@ -52,7 +52,7 @@ def _download_aftp(
     if timeout:
         wget_command_list += ["-T", str(timeout)]
 
-    log.debug("Running: %s" % (" ".join(wget_command_list)))
+    log.debug("Running: %s" % " ".join(wget_command_list))
     subprocess.call(wget_command_list)
     return tmp_path
 

openproblems/tasks/_batch_integration/_common/datasets/immune.py

@@ -9,9 +9,10 @@
     dataset_name="Immune (by batch)",
     data_url=load_immune.metadata["data_url"],
     data_reference=load_immune.metadata["data_reference"],
-    dataset_summary="Human immune cells from peripheral blood and bone marrow "
-    "taken from 5 datasets comprising 10 batches across technologies (10X, "
-    "Smart-seq2).",
+    dataset_summary=(
+        "Human immune cells from peripheral blood and bone marrow taken from 5 datasets"
+        " comprising 10 batches across technologies (10X, Smart-seq2)."
+    ),
     image="openproblems",
 )
 def immune_batch(

openproblems/tasks/_batch_integration/_common/datasets/lung.py

@@ -9,8 +9,10 @@
     dataset_name="Lung (Viera Braga et al.)",
     data_url=load_lung.metadata["data_url"],
     data_reference=load_lung.metadata["data_reference"],
-    dataset_summary="Human lung scRNA-seq data from 3 datasets with 32,472 cells. "
-    "From Vieira Braga et al. Technologies: 10X and Drop-seq.",
+    dataset_summary=(
+        "Human lung scRNA-seq data from 3 datasets with 32,472 cells. From Vieira Braga"
+        " et al. Technologies: 10X and Drop-seq."
+    ),
     image="openproblems",
 )
 def lung_batch(

openproblems/tasks/_batch_integration/_common/datasets/pancreas.py

@@ -9,9 +9,10 @@
     dataset_name="Pancreas (by batch)",
     data_url=load_pancreas.metadata["data_url"],
     data_reference=load_pancreas.metadata["data_reference"],
-    dataset_summary="Human pancreatic islet scRNA-seq data from 6 datasets "
-    "across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, "
-    "and SMARTER-seq).",
+    dataset_summary=(
+        "Human pancreatic islet scRNA-seq data from 6 datasets across technologies"
+        " (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq)."
+    ),
     image="openproblems",
 )
 def pancreas_batch(

openproblems/tasks/_cell_cell_communication/cell_cell_communication_ligand_target/datasets/tnbc_wu2021.py

@@ -10,11 +10,12 @@
     "Triple negative breast cancer atlas",
     data_url=load_tnbc_data.metadata["data_url"],
     data_reference=load_tnbc_data.metadata["data_reference"],
-    dataset_summary="Human breast cancer atlas (Wu et al., 2021), "
-    "with cytokine activities, inferred using a multivariate "
-    "linear model with cytokine-focused signatures, as assumed true "
-    "cell-cell communication (Dimitrov et al., 2022). "
-    "42512 cells x 28078 features with 29 cell types from 10 patients",
+    dataset_summary=(
+        "Human breast cancer atlas (Wu et al., 2021), with cytokine activities,"
+        " inferred using a multivariate linear model with cytokine-focused signatures,"
+        " as assumed true cell-cell communication (Dimitrov et al., 2022). 42512 cells"
+        " x 28078 features with 29 cell types from 10 patients"
+    ),
     image="openproblems-r-extras",
 )
 def tnbc_data(test=False):

openproblems/tasks/_cell_cell_communication/cell_cell_communication_source_target/datasets/allen_brain_atlas.py

@@ -7,11 +7,12 @@
     "Mouse brain atlas",
     data_url=load_mouse_brain_atlas.metadata["data_url"],
     data_reference=load_mouse_brain_atlas.metadata["data_reference"],
-    dataset_summary="A murine brain atlas with adjacent cell types as assumed "
-    "benchmark truth, inferred from deconvolution proportion "
-    "correlations using matching 10x Visium slides "
-    "(see Dimitrov et al., 2022). "
-    "14249 cells x 34617 features with 23 cell type labels.",
+    dataset_summary=(
+        "A murine brain atlas with adjacent cell types as assumed benchmark truth,"
+        " inferred from deconvolution proportion correlations using matching 10x Visium"
+        " slides (see Dimitrov et al., 2022). 14249 cells x 34617 features with 23 cell"
+        " type labels."
+    ),
     image="openproblems-r-extras",
 )
 def mouse_brain_atlas(test=False):

openproblems/tasks/denoising/datasets/pancreas.py

@@ -7,10 +7,11 @@
     dataset_name="Pancreas (inDrop)",
     data_url=load_pancreas.metadata["data_url"],
     data_reference=load_pancreas.metadata["data_reference"],
-    dataset_summary="Human pancreatic islet scRNA-seq data from 6 datasets "
-    "across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, "
-    "and SMARTER-seq). Here we just use the inDrop1 batch, which includes"
-    "1937 cells × 15502 genes.",
+    dataset_summary=(
+        "Human pancreatic islet scRNA-seq data from 6 datasets across technologies"
+        " (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Here"
+        " we just use the inDrop1 batch, which includes1937 cells × 15502 genes."
+    ),
     image="openproblems-python-pytorch",
 )
 def pancreas(test=False):

openproblems/tasks/denoising/datasets/pbmc.py

@@ -8,8 +8,8 @@
     data_url=load_tenx_1k_pbmc.metadata["data_url"],
     data_reference=load_tenx_1k_pbmc.metadata["data_reference"],
     dataset_summary=(
-        "1k Peripheral Blood Mononuclear Cells (PBMCs) from a healthy donor. "
-        "Sequenced on 10X v3 chemistry in November 2018 by 10X Genomics."
+        "1k Peripheral Blood Mononuclear Cells (PBMCs) from a healthy donor. Sequenced"
+        " on 10X v3 chemistry in November 2018 by 10X Genomics."
     ),
     image="openproblems-python-pytorch",
 )