Use pt.ds instead of pt.dt

augur.ipynb

@@ -68,7 +68,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "adata = pt.dt.sc_sim_augur()\n",
+    "adata = pt.ds.sc_sim_augur()\n",
     "\n",
     "ag_rfc = pt.tl.Augur(\"random_forest_classifier\")\n",
     "loaded_data = ag_rfc.load(adata)"
@@ -388,7 +388,7 @@
    },
    "outputs": [],
    "source": [
-    "bhattacherjee_adata = pt.dt.bhattacherjee()\n",
+    "bhattacherjee_adata = pt.ds.bhattacherjee()\n",
     "ag_rfc = pt.tl.Augur(\"random_forest_classifier\")"
    ]
   },

cinemaot.ipynb

@@ -77,7 +77,7 @@
    },
    "outputs": [],
    "source": [
-    "adata = pt.dt.cinemaot_example()"
+    "adata = pt.ds.cinemaot_example()"
    ]
   },
   {
@@ -536,7 +536,7 @@
     }
    ],
    "source": [
-    "adata_extended = pt.dt.dong_2023()"
+    "adata_extended = pt.ds.dong_2023()"
    ]
   },
   {

dialogue.ipynb

@@ -92,7 +92,7 @@
     }
    ],
    "source": [
-    "adata = pt.dt.dialogue_example()\n",
+    "adata = pt.ds.dialogue_example()\n",
     "adata"
    ]
   },

differential_gene_expression.ipynb

@@ -90,7 +90,7 @@
    },
    "outputs": [],
    "source": [
-    "adata = pt.dt.zhang_2021()"
+    "adata = pt.ds.zhang_2021()"
    ]
   },
   {

distance_tests.ipynb

@@ -47,7 +47,7 @@
    "source": [
     "Here we use an example dataset, which is a subsetted and already preprocessed\n",
     "version of data from the original Perturb-seq paper (Dixit et al., 2016). The full dataset can be accessed using \n",
-    "`pt.dt.dixit_2016()`.\n",
+    "`pt.ds.dixit_2016()`.\n",
     "\n",
     "__Note__ that most distances are computed in PCA space to avoid the curse of dimensionality or to speed up computation.\n",
     "When using your own dataset __run__ `scanpy.pp.pca` __first__, prior to using the distance methods. \n",
@@ -60,7 +60,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "adata = pt.dt.distance_example()\n",
+    "adata = pt.ds.distance_example()\n",
     "obs_key = \"perturbation\"  # defines groups to test\n",
     "contrast = \"control\""
    ]

distances.ipynb

@@ -60,7 +60,7 @@
    "metadata": {},
    "source": [
     "Here, we use an example dataset, which is a subset and already preprocessed version of data from the original Perturb-seq paper ([Dixit et al., 2016](https://www.sciencedirect.com/science/article/pii/S0092867416316105?via%3Dihub)).\n",
-    "The full dataset can be accessed using  `pt.dt.dixit_2016()`.\n",
+    "The full dataset can be accessed using  `pt.ds.dixit_2016()`.\n",
     "\n",
     "__Note__ that most distances are computed in PCA space to avoid the curse of dimensionality or to speed up computation.\n",
     "When using your own dataset __run__ `scanpy.pp.pca` __first__, prior to using the distance methods. \n",
@@ -78,7 +78,7 @@
    },
    "outputs": [],
    "source": [
-    "adata = pt.dt.distance_example()\n",
+    "adata = pt.ds.distance_example()\n",
     "obs_key = \"perturbation\"  # defines groups to test"
    ]
   },

guide_rna_assignment.ipynb

@@ -484,7 +484,7 @@
     }
    ],
    "source": [
-    "mdata = pt.dt.papalexi_2021()\n",
+    "mdata = pt.ds.papalexi_2021()\n",
     "# seems like an error in the original data\n",
     "mdata.mod[\"gdo\"].X = scipy.sparse.csr_matrix(mdata.mod[\"gdo\"].X.toarray() - 1)\n",
     "mdata.push_obs(columns=[\"gdo:guide_ID\"], mods=\"gdo\")\n",

mcfarland_use_case.ipynb

@@ -85,7 +85,7 @@
     }
    ],
    "source": [
-    "adata = pt.dt.mcfarland_2020()\n",
+    "adata = pt.ds.mcfarland_2020()\n",
     "adata"
    ]
   },

metadata_annotation.ipynb

@@ -75,7 +75,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "adata = pt.dt.mcfarland_2020()"
+    "adata = pt.ds.mcfarland_2020()"
    ]
   },
   {

milo.ipynb

@@ -96,7 +96,7 @@
    },
    "outputs": [],
    "source": [
-    "adata = pt.dt.stephenson_2021_subsampled()"
+    "adata = pt.ds.stephenson_2021_subsampled()"
    ]
   },
   {
@@ -2284,7 +2284,7 @@
    "outputs": [],
    "source": [
     "# Load a dataset with raw counts and prepare the Milo object\n",
-    "adata_de = pt.dt.kang_2018()\n",
+    "adata_de = pt.ds.kang_2018()\n",
     "sc.pp.subsample(adata_de, n_obs=10000, random_state=0)  # subsample for a fast demo\n",
     "adata_de.layers[\"counts\"] = adata_de.X.copy()\n",
     "adata_de.obs[\"sample\"] = adata_de.obs[\"replicate\"].astype(str) + \"_\" + adata_de.obs[\"label\"].astype(str)\n",

norman_use_case.ipynb

@@ -95,7 +95,7 @@
     }
    ],
    "source": [
-    "adata = pt.dt.norman_2019()\n",
+    "adata = pt.ds.norman_2019()\n",
     "adata"
    ]
   },

perturbation_efficacy.ipynb

@@ -179,7 +179,7 @@
     }
    ],
    "source": [
-    "mdata = pt.dt.papalexi_2021()\n",
+    "mdata = pt.ds.papalexi_2021()\n",
     "gene_target_data = mdata.obs[\"gene_target\"].copy()\n",
     "mdata.push_obs(columns=[\"replicate\", \"phase\", \"perturbation\", \"NT\"], mods=[\"rna\"])\n",
     "mdata[\"rna\"].obs[\"gene_target\"] = gene_target_data\n",

perturbation_space.ipynb

@@ -125,7 +125,7 @@
     }
    ],
    "source": [
-    "adata = pt.dt.norman_2019()\n",
+    "adata = pt.ds.norman_2019()\n",
     "adata"
    ]
   },
@@ -2688,7 +2688,7 @@
     }
    ],
    "source": [
-    "sciplex = pt.dt.srivatsan_2020_sciplex2()\n",
+    "sciplex = pt.ds.srivatsan_2020_sciplex2()\n",
     "sc.pp.normalize_total(sciplex, target_sum=1e4)\n",
     "sc.pp.log1p(sciplex)\n",
     "sc.pp.pca(sciplex)\n",

sccoda.ipynb

@@ -238,7 +238,7 @@
     }
    ],
    "source": [
-    "haber_cells = pt.dt.haber_2017_regions()\n",
+    "haber_cells = pt.ds.haber_2017_regions()\n",
     "haber_cells.obs"
    ]
   },

sccoda_extended.ipynb

@@ -104,7 +104,7 @@
     }
    ],
    "source": [
-    "haber_cells = pt.dt.haber_2017_regions()\n",
+    "haber_cells = pt.ds.haber_2017_regions()\n",
     "\n",
     "# Convert data to mudata object\n",
     "sccoda_model = pt.tl.Sccoda()\n",

sccoda_tasccoda_case_study.ipynb

@@ -86,7 +86,7 @@
     }
    ],
    "source": [
-    "haber_cells = pt.dt.haber_2017_regions()\n",
+    "haber_cells = pt.ds.haber_2017_regions()\n",
     "\n",
     "sccoda_model = pt.tl.Sccoda()\n",
     "sccoda_data = sccoda_model.load(\n",

scgen_perturbation_prediction.ipynb

@@ -78,7 +78,7 @@
    },
    "outputs": [],
    "source": [
-    "train = pt.dt.kang_2018()"
+    "train = pt.ds.kang_2018()"
    ]
   },
   {

tasccoda.ipynb

@@ -341,7 +341,7 @@
     }
    ],
    "source": [
-    "smillie_counts = pt.dt.smillie_2019()\n",
+    "smillie_counts = pt.ds.smillie_2019()\n",
     "smillie_counts.obs"
    ]
   },

zhang_use_case.ipynb

@@ -78,7 +78,7 @@
     }
    ],
    "source": [
-    "adata = pt.dt.zhang_2021()\n",
+    "adata = pt.ds.zhang_2021()\n",
     "adata"
    ]
   },