chore: changes to add uns metadata for spatial

backend/common/utils/cxg_generation_utils.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import pickle
 
 import numpy as np
 import pandas as pd
@@ -31,6 +32,32 @@
             metadata_array.meta[key] = value
 
 
+def convert_uns_to_cxg_group(cxg_container, metadata_dict, group_metadata_name="cxg_group_metadata", ctx=None):
+
+    array_name = f"{cxg_container}/{group_metadata_name}"
+
+    tiledb.from_numpy(array_name, np.zeros((1,)))
+
+    def iterate_over_dict(metadata_dict):
+        with tiledb.open(array_name, mode="w", ctx=ctx) as metadata_array:
+            for key, value in metadata_dict.items():
+                if not key.startswith("spatial"):
+                    continue
+                print(f"key: {key}, type:{type(value)}, value: {value}")
+                if isinstance(value, dict):
+                    try:
+                        metadata_array.meta[key] = pickle.dumps(value)
+                    except Exception as e:
+                        logging.error(f"Error adding metadata {key} to {array_name}: {e}")
+                else:
+                    try:
+                        metadata_array.meta[key] = value
+                    except Exception as e:
+                        logging.error(f"Error adding metadata {key} to {array_name}: {e}")
+
+    iterate_over_dict(metadata_dict)
+
+
 def convert_dataframe_to_cxg_array(cxg_container, dataframe_name, dataframe, index_column_name, ctx):
     """
     Saves the contents of the dataframe to the CXG output directory specified.

backend/layers/processing/h5ad_data_file.py

@@ -18,6 +18,7 @@
     convert_dictionary_to_cxg_group,
     convert_matrices_to_cxg_arrays,
     convert_ndarray_to_cxg_dense_array,
+    convert_uns_to_cxg_group,
 )
 from backend.common.utils.matrix_utils import is_matrix_sparse
 from backend.common.utils.tiledb import consolidation_buffer_size
@@ -79,6 +80,9 @@ def to_cxg(self, output_cxg_directory, sparse_threshold, convert_anndata_colors_
         convert_dataframe_to_cxg_array(output_cxg_directory, "var", self.var, self.var_index_column_name, ctx)
         logging.info("\t...dataset var dataframe saved")
 
+        convert_uns_to_cxg_group(output_cxg_directory, self.anndata.uns, "uns", ctx)
+        logging.info("\t...dataset uns dataframe saved")
+
         self.write_anndata_embeddings_to_cxg(output_cxg_directory, ctx)
         logging.info("\t...dataset embeddings saved")
 

make_cxg.ipynb

@@ -0,0 +1,61 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from backend.layers.processing.h5ad_data_file import H5ADDataFile\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def make_cxg(local_filename):\n",
+    "    \"\"\"\n",
+    "    Convert the uploaded H5AD file to the CXG format servicing the cellxgene Explorer.\n",
+    "    \"\"\"\n",
+    "\n",
+    "    cxg_output_container = local_filename.replace(\".h5ad\", \".cxg\")\n",
+    "    try:\n",
+    "        h5ad_data_file = H5ADDataFile(local_filename, var_index_column_name=\"feature_name\")\n",
+    "        h5ad_data_file.to_cxg(cxg_output_container, sparse_threshold=25.0)\n",
+    "    except Exception as ex:\n",
+    "        # TODO use a specialized exception\n",
+    "        msg = \"CXG conversion failed.\"\n",
+    "\n",
+    "        raise RuntimeError(msg) from ex\n",
+    "        raise ex\n",
+    "\n",
+    "    return cxg_output_container\n",
+    "\n",
+    "make_cxg(\"UXR_0bb15784-1cea-47e1-9a00-57dcd127746c.h5ad\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}