batch subset update based on review

broadinstitute · Jan 30, 2025 · de49617 · de49617
1 parent 6744c90
commit de49617
Showing 1 changed file with 9 additions and 5 deletions.
diff --git a/scripts/notebooks/SampleQC.ipynb b/scripts/notebooks/SampleQC.ipynb
@@ -1642,7 +1642,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<div class=\"alert alert-block alert-success\"><b>Optional</b>: If you wish to only include a subset of batches out of the ones listed above, you can filter <tt>sample_set_tbl</tt> to only include them using the cell below. Ensure that all batches you expect are included.</div>"
+    "<div class=\"alert alert-block alert-success\"><b>Optional</b>: If you wish to only include a subset of batches out of the ones listed above, you can filter <tt>sample_set_tbl</tt> to only include them using the cell below. Ensure that all batches you expect are included by running the following cell to display them.</div>"
    ]
   },
   {
@@ -1651,10 +1651,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Optionally filter to only include a subset of batches from sample_set_tbl and update the saved file. For example:\n",
-    "sample_set_tbl = sample_set_tbl[sample_set_tbl['entity:sample_set_id'].str.contains('KJ_EvidenceQC_Updates')]\n",
-    "file_path = generate_file_path(TLD_PATH, 'artifacts', 'sample_sets_qc.tsv')\n",
-    "save_df(WS_BUCKET, file_path, sample_set_tbl)"
+    "# Optionally filter to only include a subset of batches from sample_set_tbl and update the saved file\n",
+    "# For example, to select batches based on a shared sample_set_id substring, set SUBSTRING below\n",
+    "SUBSTRING = None\n",
+    "if SUBSTRING is not None:\n",
+    "    sample_set_tbl = sample_set_tbl[sample_set_tbl['entity:sample_set_id'].str.contains(SUBSTRING)]\n",
+    "    \n",
+    "    file_path = generate_file_path(TLD_PATH, 'artifacts', 'sample_sets_qc.tsv')\n",
+    "    save_df(WS_BUCKET, file_path, sample_set_tbl)"
    ]
   },
   {