pertpy 1.0.1__py3-none-any.whl → 1.0.3__py3-none-any.whl

pertpy/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = "Lukas Heumos"
 __email__ = "lukas.heumos@posteo.net"
-__version__ = "1.0.1"
+__version__ = "1.0.3"
 
 import warnings
 

pertpy/data/_dataloader.py

@@ -17,7 +17,7 @@ def _download(  # pragma: no cover
     url: str,
     output_file_name: str | None = None,
     output_path: str | Path | None = None,
-    block_size: int = 1024,
+    block_size: int = 8192,
     overwrite: bool = False,
     is_zip: bool = False,
     timeout: int = 30,
@@ -74,7 +74,7 @@ def _download(  # pragma: no cover
                     response.raise_for_status()
                     total = int(response.headers.get("content-length", 0))
 
-                    with Progress(refresh_per_second=5) as progress:
+                    with Progress(refresh_per_second=3) as progress:
                         task = progress.add_task("[red]Downloading...", total=total)
                         with Path(temp_file_name).open("wb") as file:
                             for data in response.iter_content(block_size):

pertpy/data/_datasets.py

@@ -43,7 +43,7 @@ def papalexi_2021() -> MuData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/36509460",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/papalexi_2021.h5mu",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -68,7 +68,7 @@ def sc_sim_augur() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/49828902",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/sc_sim_augur.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -98,7 +98,7 @@ def bhattacherjee() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/34526528",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/bhattacher_rna.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -123,7 +123,7 @@ def sciplex3_raw() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/33979517",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/sciplex3.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -141,7 +141,7 @@ def tasccoda_example() -> AnnData:  # pragma: no cover
     The full dataset containing the actual count data can be obtained via smillie_2019().
 
     References:
-        Smillie, Christopher S et al. “Intra- and Inter-cellular Rewiring of the Human Colon during Ulcerative Colitis.”
+        Smillie, Christopher S et al. "Intra- and Inter-cellular Rewiring of the Human Colon during Ulcerative Colitis."
         Cell vol. 178,3 (2019): 714-730.e22. doi:10.1016/j.cell.2019.06.029
 
     Returns:
@@ -151,7 +151,7 @@ def tasccoda_example() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/38648585",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/tasccoda_smillie.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -180,7 +180,7 @@ def frangieh_2021() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/34013717",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/frangieh_2021.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -209,7 +209,7 @@ def frangieh_2021_raw() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/34012565",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/frangieh_2021_raw.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -238,7 +238,7 @@ def dixit_2016_raw() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/34012565",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/dixit_2016_raw.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -267,7 +267,7 @@ def dixit_2016() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/34014608",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/dixit_2016.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -284,8 +284,8 @@ def norman_2019() -> AnnData:  # pragma: no cover
     overexpressing genes alone or in combination
 
     References:
-        Norman, Thomas M et al. “Exploring genetic interaction manifolds constructed from rich
-        single-cell phenotypes.” Science (New York, N.Y.) vol. 365,6455 (2019): 786-793.
+        Norman, Thomas M et al. "Exploring genetic interaction manifolds constructed from rich
+        single-cell phenotypes." Science (New York, N.Y.) vol. 365,6455 (2019): 786-793.
         doi:10.1126/science.aax4438
 
     Returns:
@@ -295,7 +295,7 @@ def norman_2019() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/34027562",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/norman_2019.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -312,8 +312,8 @@ def norman_2019_raw() -> AnnData:  # pragma: no cover
     overexpressing genes alone or in combination
 
     References:
-        Norman, Thomas M et al. “Exploring genetic interaction manifolds constructed from rich
-        single-cell phenotypes.” Science (New York, N.Y.) vol. 365,6455 (2019): 786-793.
+        Norman, Thomas M et al. "Exploring genetic interaction manifolds constructed from rich
+        single-cell phenotypes." Science (New York, N.Y.) vol. 365,6455 (2019): 786-793.
         doi:10.1126/science.aax4438
 
     Returns:
@@ -323,7 +323,7 @@ def norman_2019_raw() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/34002548",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/norman_2019_raw.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -346,7 +346,7 @@ def dialogue_example() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/43462662",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/dialogue_example.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -368,7 +368,7 @@ def distance_example() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/39561379",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/distances_example_data.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -399,7 +399,7 @@ def kang_2018() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/34464122",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/kang_2018.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -428,7 +428,7 @@ def stephenson_2021_subsampled() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/38171703",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/stephenson_2021_subsampled.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -445,7 +445,7 @@ def haber_2017_regions() -> AnnData:  # pragma: no cover
     Some of the cells were also subject to Salmonella or Heligmosomoides polygyrus infection (day 3 and day 10).
 
     References:
-        Haber, Adam L. et al. “A single-cell survey of the small intestinal epithelium” Nature vol. 551 (2017): 333-339
+        Haber, Adam L. et al. "A single-cell survey of the small intestinal epithelium" Nature vol. 551 (2017): 333-339
         doi:10.1038/nature24489
 
     Returns:
@@ -455,7 +455,7 @@ def haber_2017_regions() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/54169301",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/haber_2017_regions.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -482,7 +482,7 @@ def adamson_2016_pilot() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/AdamsonWeissman2016_GSM2406675_10X001.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/adamson_2016_pilot.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -513,7 +513,7 @@ def adamson_2016_upr_epistasis() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/AdamsonWeissman2016_GSM2406677_10X005.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/adamson_2016_upr_epistasis.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -542,7 +542,7 @@ def adamson_2016_upr_perturb_seq() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/AdamsonWeissman2016_GSM2406681_10X010.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/adamson_2016_upr_perturb_seq.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -569,7 +569,7 @@ def aissa_2021() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/AissaBenevolenskaya2021.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/aissa_2021.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -598,7 +598,7 @@ def chang_2021() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/ChangYe2021.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/chang_2021.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -629,7 +629,7 @@ def datlinger_2017() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/DatlingerBock2017.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/datlinger_2017.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -659,7 +659,7 @@ def datlinger_2021() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/DatlingerBock2021.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/datlinger_2021.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -690,7 +690,7 @@ def frangieh_2021_protein() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/FrangiehIzar2021_protein.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/frangieh_2021_protein.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -721,7 +721,7 @@ def frangieh_2021_rna() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/FrangiehIzar2021_RNA.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/frangieh_2021_rna.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -749,7 +749,7 @@ def gasperini_2019_atscale() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/GasperiniShendure2019_atscale.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/gasperini_2019_atscale.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -778,7 +778,7 @@ def gasperini_2019_highmoi() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/GasperiniShendure2019_highMOI.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/gasperini_2019_highmoi.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -807,7 +807,7 @@ def gasperini_2019_lowmoi() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/GasperiniShendure2019_lowMOI.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/gasperini_2019_lowmoi.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -835,7 +835,7 @@ def gehring_2019() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/GehringPachter2019.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/gehring_2019.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -864,7 +864,7 @@ def mcfarland_2020() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/McFarlandTsherniak2020.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/mcfarland_2020.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -893,7 +893,7 @@ def replogle_2022_k562_essential() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/ReplogleWeissman2022_K562_essential.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/gasperini_2019_atscale.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -924,7 +924,7 @@ def replogle_2022_k562_gwps() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/ReplogleWeissman2022_K562_gwps.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/replogle_2022_k562_gwps.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -954,7 +954,7 @@ def replogle_2022_rpe1() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/ReplogleWeissman2022_rpe1.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/replogle_2022_rpe1.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -985,7 +985,7 @@ def schiebinger_2019_16day() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/SchiebingerLander2019_GSE106340.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/schiebinger_2019_16day.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1014,7 +1014,7 @@ def schiebinger_2019_18day() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/SchiebingerLander2019_GSE115943.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/Schiebinger_2019_18day.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1043,7 +1043,7 @@ def schraivogel_2020_tap_screen_chr11() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/SchraivogelSteinmetz2020_TAP_SCREEN__chromosome_11_screen.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/schraivogel_2020_tap_screen_chr11.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1072,7 +1072,7 @@ def schraivogel_2020_tap_screen_chr8() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/SchraivogelSteinmetz2020_TAP_SCREEN__chromosome_8_screen.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/schraivogel_2020_tap_screen_chr8.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1102,7 +1102,7 @@ def shifrut_2018() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/13350497/files/ShifrutMarson2018.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/shifrut_2018.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1133,7 +1133,7 @@ def srivatsan_2020_sciplex2() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/record/10044268/files/SrivatsanTrapnell2020_sciplex2.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/srivatsan_2020_sciplex2.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1162,7 +1162,7 @@ def srivatsan_2020_sciplex3() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/records/13350497/files/SrivatsanTrapnell2020_sciplex3.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/srivatsan_2020_sciplex3.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1194,7 +1194,7 @@ def srivatsan_2020_sciplex4() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/records/10044268/files/SrivatsanTrapnell2020_sciplex4.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/srivatsan_2020_sciplex4.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1226,7 +1226,7 @@ def tian_2019_day7neuron() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/records/10044268/files/TianKampmann2019_day7neuron.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/tian_2019_day7neuron.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1258,7 +1258,7 @@ def tian_2019_ipsc() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/records/10044268/files/TianKampmann2019_iPSC.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/tian_2019_iPad.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1288,7 +1288,7 @@ def tian_2021_crispra() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/records/10044268/files/TianKampmann2021_CRISPRa.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/tian_2021_crispra.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1318,7 +1318,7 @@ def tian_2021_crispri() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/records/10044268/files/TianKampmann2021_CRISPRi.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/tian_2021_crispri.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1345,7 +1345,7 @@ def weinreb_2020() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/records/10044268/files/WeinrebKlein2020.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/weinreb_2020.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1373,7 +1373,7 @@ def xie_2017() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/records/10044268/files/XieHon2017.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/xie_2017.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1403,7 +1403,7 @@ def zhao_2021() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://zenodo.org/records/10044268/files/ZhaoSims2021.h5ad?download=1",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/zhaoSims2021.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1428,7 +1428,7 @@ def cinemaot_example() -> AnnData:  # pragma: no cover:
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/42362796?private_link=270b0d2c7f1ea57c366d",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/cinemaot_example.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1456,7 +1456,7 @@ def dong_2023() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/43068190",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/dong_2023.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1472,7 +1472,7 @@ def smillie_2019() -> AnnData:  # pragma: no cover
     The resulting AnnData when preparing this dataset for processing with tascCODA is available via tasccoda_example().
 
     References:
-        Smillie, Christopher S et al. “Intra- and Inter-cellular Rewiring of the Human Colon during Ulcerative Colitis.”
+        Smillie, Christopher S et al. "Intra- and Inter-cellular Rewiring of the Human Colon during Ulcerative Colitis."
         Cell vol. 178,3 (2019): 714-730.e22. doi:10.1016/j.cell.2019.06.029
 
     Returns:
@@ -1482,7 +1482,7 @@ def smillie_2019() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / Path(output_file_name).with_suffix("")
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/43317285",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/smillie_2019.h5ad.zip",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=True,
@@ -1507,7 +1507,7 @@ def combosciplex() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/44229635",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/combosciplex.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1532,7 +1532,7 @@ def sciplex_gxe1() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/45372454",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/sciPlexGxE_1_GSM7056148.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1564,7 +1564,7 @@ def zhang_2021() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/46457872",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/zhang_2021.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,
@@ -1590,7 +1590,7 @@ def hagai_2018() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/46978846",
+            url="https://scverse-exampledata.s3.eu-west-1.amazonaws.com/pertpy/hagai_2018.h5ad",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,

pertpy/metadata/_cell_line.py

@@ -195,7 +195,9 @@ class CellLine(MetaData):
                 block_size=4096,
                 is_zip=False,
             )
-        df = pd.read_csv(drug_response_prism_file_path, index_col=0)[["depmap_id", "name", "ic50", "ec50", "auc"]]
+        df = pd.read_csv(
+            drug_response_prism_file_path, index_col=0, usecols=["broad_id", "depmap_id", "name", "ic50", "ec50", "auc"]
+        )
         df = df.dropna(subset=["depmap_id", "name"])
         df = df.groupby(["depmap_id", "name"]).mean().reset_index()
         self.drug_response_prism = df
@@ -568,7 +570,9 @@ class CellLine(MetaData):
             verbosity=verbosity,
         )
 
-        old_index_name = "index" if adata.obs.index.name is None else adata.obs.index.name
+        if adata.obs.index.name is None:
+            adata.obs.index.name = "original_index"
+        old_index_name = adata.obs.index.name
         adata.obs = (
             adata.obs.reset_index()
             .set_index([query_id, query_perturbation])
@@ -635,7 +639,9 @@ class CellLine(MetaData):
             verbosity=verbosity,
         )
 
-        old_index_name = "index" if adata.obs.index.name is None else adata.obs.index.name
+        if adata.obs.index.name is None:
+            adata.obs.index.name = "original_index"
+        old_index_name = adata.obs.index.name
         adata.obs = (
             adata.obs.reset_index()
             .set_index([query_id, "perturbation_lower"])

pertpy/metadata/_drug.py

@@ -14,12 +14,14 @@ from ._look_up import LookUp
 from ._metadata import MetaData
 
 if TYPE_CHECKING:
+    from collections.abc import Mapping
+
     from anndata import AnnData
 
 
 def _download_drug_annotation(
     source: Literal["chembl", "dgidb", "pharmgkb"] = "chembl",
-) -> pd.DataFrame | dict[str, dict[str, list[str]]]:
+) -> pd.DataFrame | Mapping[str, Mapping[str, list[str]]]:
     if source == "chembl":
         # Prepared in https://github.com/theislab/pertpy-datasets/blob/main/chembl_data.ipynb
         chembl_path = Path(settings.cachedir) / "chembl.json"
@@ -232,7 +234,7 @@ class Drug(MetaData):
                 self.set()
             return self.dataframe
 
-        def dict(self) -> dict[str, list[str]] | dict[str, dict[str, list[str]]]:
+        def dict(self) -> Mapping[str, list[str]] | Mapping[str, Mapping[str, list[str]]]:
             if not self.loaded:
                 self.set()
             return self.dictionary