✨ Add nextflow execution ID tracking

Signed-off-by: zethson <[email protected]>

docs/guide/bulk_rna_seq.ipynb

@@ -317,6 +317,38 @@
     "To make the count matrix queryable by biological entities (genes, experimental metadata, etc.), we can now proceed with: {doc}`docs:bulkrna`"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "429bf863",
+   "metadata": {},
+   "source": [
+    "## Register the Nextflow execution id\n",
+    "\n",
+    "If we want to be able to query LaminDB for Nextflow execution ID, this here is a way to get it:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4c14e053",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# load the nextflow execution id from the execution_report.html and store it in the LaminDB run record\n",
+    "# Regular expression pattern to match the Workflow session ID. We will simplify this in the future.\n",
+    "import re\n",
+    "\n",
+    "pattern = r'Workflow session<\\/dt>\\s*<dd class=\"col-sm-9\"><code>(.*?)<\\/code>'\n",
+    "with open(\"execution_report.html\", \"r\") as file:\n",
+    "    html_content = file.read()\n",
+    "match = re.search(pattern, html_content)\n",
+    "\n",
+    "run = ln.Run.filter(transform__name=\"nf-core rnaseq\").order_by(\"-run_at\").first()\n",
+    "run.reference = match.group(1)\n",
+    "run.reference_type = \"nextflow_id\"\n",
+    "run.save()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "9f607150",
@@ -400,7 +432,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.12"
   },
   "nbproject": {
    "id": "8124Vtle6ZrO",