From 28e49066c21faff0e56e885fb8f75edba3a40ae2 Mon Sep 17 00:00:00 2001
From: qzmalekuz <qmalekuzzafar1235@gmail.com>
Date: Fri, 20 Mar 2026 01:50:30 +0530
Subject: [PATCH 1/2] Add SBOL to CSV dataset conversion script

---
 example.xml                | 16 ++++++++++++++
 scripts/sbol_to_dataset.py | 44 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+)
 create mode 100644 example.xml
 create mode 100644 scripts/sbol_to_dataset.py

diff --git a/example.xml b/example.xml
new file mode 100644
index 0000000..ebfcf0e
--- /dev/null
+++ b/example.xml
@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<rdf:RDF
+    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+    xmlns:sbol="http://sbols.org/v2#">
+
+  <!-- Define sequence -->
+  <sbol:Sequence rdf:about="http://example.org/seq1">
+    <sbol:elements>ATGCGTACGTAGCTAG</sbol:elements>
+  </sbol:Sequence>
+
+  <!-- Reference sequence from component -->
+  <sbol:ComponentDefinition rdf:about="http://example.org/comp1">
+    <sbol:sequence rdf:resource="http://example.org/seq1"/>
+  </sbol:ComponentDefinition>
+
+</rdf:RDF>
\ No newline at end of file
diff --git a/scripts/sbol_to_dataset.py b/scripts/sbol_to_dataset.py
new file mode 100644
index 0000000..fbacbb2
--- /dev/null
+++ b/scripts/sbol_to_dataset.py
@@ -0,0 +1,44 @@
+from sbol2 import Document
+import pandas as pd
+import argparse
+
+
+def sbol_to_csv(input_file, output_file="dataset.csv"):
+    doc = Document()
+    doc.read(input_file)
+
+    data = []
+
+    for comp in doc.componentDefinitions:
+        seq = None
+
+        try:
+            if comp.sequences:
+                seq_id = comp.sequences[0]
+                sequence_obj = doc.sequences.get(seq_id)
+
+                if sequence_obj:
+                    seq = sequence_obj.elements
+        except Exception:
+            continue
+
+        if seq:
+            data.append({
+                "sequence": seq,
+                "label": "unknown"
+            })
+
+    df = pd.DataFrame(data)
+    df.to_csv(output_file, index=False)
+
+    print(f"✅ Dataset saved to {output_file}")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Convert SBOL to CSV dataset")
+    parser.add_argument("--input", required=True, help="Input SBOL file")
+    parser.add_argument("--output", default="dataset.csv", help="Output CSV file")
+
+    args = parser.parse_args()
+
+    sbol_to_csv(args.input, args.output)
\ No newline at end of file

From c58b32d818f25fb600b481fa15f422d92e22c356 Mon Sep 17 00:00:00 2001
From: qzmalekuz <qmalekuzzafar1235@gmail.com>
Date: Sun, 22 Mar 2026 16:51:06 +0530
Subject: [PATCH 2/2] Remove example.xml from PR

---
 example.xml                | 16 ----------------
 scripts/sbol_to_dataset.py |  2 +-
 2 files changed, 1 insertion(+), 17 deletions(-)
 delete mode 100644 example.xml

diff --git a/example.xml b/example.xml
deleted file mode 100644
index ebfcf0e..0000000
--- a/example.xml
+++ /dev/null
@@ -1,16 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<rdf:RDF
-    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
-    xmlns:sbol="http://sbols.org/v2#">
-
-  <!-- Define sequence -->
-  <sbol:Sequence rdf:about="http://example.org/seq1">
-    <sbol:elements>ATGCGTACGTAGCTAG</sbol:elements>
-  </sbol:Sequence>
-
-  <!-- Reference sequence from component -->
-  <sbol:ComponentDefinition rdf:about="http://example.org/comp1">
-    <sbol:sequence rdf:resource="http://example.org/seq1"/>
-  </sbol:ComponentDefinition>
-
-</rdf:RDF>
\ No newline at end of file
diff --git a/scripts/sbol_to_dataset.py b/scripts/sbol_to_dataset.py
index fbacbb2..a19c5e3 100644
--- a/scripts/sbol_to_dataset.py
+++ b/scripts/sbol_to_dataset.py
@@ -31,7 +31,7 @@ def sbol_to_csv(input_file, output_file="dataset.csv"):
     df = pd.DataFrame(data)
     df.to_csv(output_file, index=False)
 
-    print(f"✅ Dataset saved to {output_file}")
+    print(f"Dataset saved to {output_file}")
 
 
 if __name__ == "__main__":