debase 0.1.7__tar.gz → 0.1.8__tar.gz

{debase-0.1.7 → debase-0.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.7
+Version: 0.1.8
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.1.7 → debase-0.1.8}/src/debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.7"
+__version__ = "0.1.8"

{debase-0.1.7 → debase-0.1.8}/src/debase/enzyme_lineage_extractor.py

@@ -2005,6 +2005,10 @@ Return ONLY a JSON object mapping lineage variant IDs to sequence variant IDs. I
                         
                         log.info(f"Matched {lineage_id} -> {seq_id} using Gemini")
                 
+                # Log the final state after all matches
+                matched_count = (~df['aa_seq'].isna()).sum()
+                log.info(f"After Gemini matching: {matched_count}/{len(df)} variants have sequences")
+                
             except Exception as e:
                 log.warning(f"Failed to match variants using Gemini: {e}")
 
@@ -2025,6 +2029,12 @@ Return ONLY a JSON object mapping lineage variant IDs to sequence variant IDs. I
     # 5. Sort rows: primary by generation, then by variant_id
     df = df.sort_values(["generation", "variant_id"], kind="mergesort")
 
+    # Debug: Log final merge state
+    seq_count = (~df['aa_seq'].isna()).sum()
+    log.info(f"_merge_lineage_and_sequences returning: {len(df)} variants, {seq_count} with sequences")
+    if seq_count > 0:
+        log.info(f"Sample variant with sequence: {df[~df['aa_seq'].isna()].iloc[0]['variant_id']}")
+
     return df
 
 # --- 8.3  Public API -----------------------------------------------------------
@@ -2053,6 +2063,10 @@ def merge_and_score(
     if missing_rate > 0.5:
         log.warning(">50%% of variants lack sequences (%d / %d)", df["aa_seq"].isna().sum(), len(df))
 
+    # Debug log before returning
+    seq_count = (~df['aa_seq'].isna()).sum() if 'aa_seq' in df else 0
+    log.info(f"merge_and_score returning: {len(df)} variants, {seq_count} with sequences")
+
     return df
 
 # -------------------------------------------------------------------- end 8 ---
@@ -2236,6 +2250,14 @@ def run_pipeline(
         output_csv_path = Path(output_csv)
         # Save final data with sequences using same filename (overwrites lineage-only)
         sequence_path = output_csv_path.parent / "enzyme_lineage_data.csv"
+        
+        # Debug: Log what we're about to save
+        seq_count = (~df_final['aa_seq'].isna()).sum() if 'aa_seq' in df_final else 0
+        log.info(f"About to save CSV: {len(df_final)} variants, {seq_count} with sequences")
+        if seq_count > 0 and 'aa_seq' in df_final:
+            with_seq = df_final[~df_final['aa_seq'].isna()]
+            log.info(f"First variant with sequence: {with_seq.iloc[0]['variant_id']} has {len(with_seq.iloc[0]['aa_seq'])} AA")
+        
         df_final.to_csv(sequence_path, index=False)
         log.info(
             "Overwrote with final results -> %s (%.1f kB)",

{debase-0.1.7 → debase-0.1.8}/src/debase.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.7
+Version: 0.1.8
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team