Read outlines or masks from segmentation_file_regex parameter (#25)

* add shrink data script and duckdb * add example images * read outlines, masks from segmentation_file_regex * Create BR00143976_shrunken.parquet * updated lockfile * update notebook
WayScience · Nov 12, 2024 · e3e3962 · e3e3962
1 parent 25fac60
commit e3e3962
Show file tree

Hide file tree

Showing 18 changed files with 442 additions and 85 deletions.
diff --git a/docs/src/examples/cytodataframe_at_a_glance.ipynb b/docs/src/examples/cytodataframe_at_a_glance.ipynb
diff --git a/docs/src/examples/cytodataframe_at_a_glance.py b/docs/src/examples/cytodataframe_at_a_glance.py
@@ -28,6 +28,9 @@
 jump_data_path = "../../../tests/data/cytotable/JUMP_plate_BR00117006"
 nf1_cellpainting_path = "../../../tests/data/cytotable/NF1_cellpainting_data_shrunken/"
 nuclear_speckles_path = "../../../tests/data/cytotable/nuclear_speckles"
+pediatric_cancer_atlas_path = (
+    "../../../tests/data/cytotable/pediatric_cancer_atlas_profiling"
+)
 # -
 # %%time
 # view JUMP plate BR00117006 with images
@@ -107,3 +110,22 @@
         "Image_FileName_GOLD",
     ]
 ][:3]
+
+# %%time
+# view ALSF pediatric cancer atlas plate BR00143976 with images
+CytoDataFrame(
+    data=f"{pediatric_cancer_atlas_path}/BR00143976_shrunken.parquet",
+    data_context_dir=f"{pediatric_cancer_atlas_path}/images/orig",
+    data_outline_context_dir=f"{pediatric_cancer_atlas_path}/images/outlines",
+    segmentation_file_regex={
+        r"CellsOutlines_BR(\d+)_C(\d{2})_\d+\.tiff": r".*ch3.*\.tiff",
+        r"NucleiOutlines_BR(\d+)_C(\d{2})_\d+\.tiff": r".*ch5.*\.tiff",
+    },
+)[
+    [
+        "Metadata_ImageNumber",
+        "Metadata_Nuclei_Number_Object_Number",
+        "Image_FileName_OrigAGP",
+        "Image_FileName_OrigDNA",
+    ]
+][:3]
diff --git a/media/coverage-badge.svg b/media/coverage-badge.svg
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -54,6 +54,7 @@ jupytext = "^1.16.4"
 black = "^24.10.0"
 isort = "^5.13.2"
 jupyterlab-code-formatter = "^3.0.2"
+duckdb = "^1.1.3"
 
 [tool.poetry.group.docs.dependencies]
 # used for rendering docs into docsite