Name annotation downloads by assembly, record, and segment coordinates

app.py

@@ -1,6 +1,7 @@
 """A small Hugging Face Space for exploring genome annotations by accession."""
 from pathlib import Path
 import os
+import re
 import tempfile
 
 # Shared compute hosts can have /tmp/gradio owned by a different user.
@@ -55,8 +56,14 @@ def build_app(catalog=None):
     def export(index):
         if index is None:
             raise gr.Error("Choose a segment first.")
-        target = Path(tempfile.mkdtemp(prefix="genbank-export-")) / "annotation.parquet"
-        pq.write_table(catalog.segment_table(index), target, compression="zstd")
+        table = catalog.segment_table(index)
+        assembly = re.sub(r"[^A-Za-z0-9._-]", "_", table["assembly_accession"][0].as_py())
+        record = re.sub(r"[^A-Za-z0-9._-]", "_", table["record_name"][0].as_py())
+        start = table["segment_start_bp"][0].as_py()
+        end = table["segment_end_bp"][0].as_py()
+        filename = f"{assembly}__{record}__{start}-{end}.parquet"
+        target = Path(tempfile.mkdtemp(prefix="genbank-export-")) / filename
+        pq.write_table(table, target, compression="zstd")
         return str(target)
 
     with gr.Blocks(title="GenBank Annotation Explorer", delete_cache=(3600, 3600)) as demo: