debase 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl

debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.6"
+__version__ = "0.1.8"

debase/enzyme_lineage_extractor.py

@@ -1944,7 +1944,13 @@ def _merge_lineage_and_sequences(
     df = pd.merge(df_lin, df_seq, on="variant_id", how="left")
 
     # 2a. If we have unmatched sequences and a model, use Gemini to match them
+    log.info(f"Model available: {model is not None}, Sequences found: {len(df_seq)}")
     if model and len(df_seq) > 0:
+        # Log initial state
+        log.info(f"Merge attempt: {len(df_lin)} lineage entries, {len(df_seq)} sequences")
+        log.info(f"Lineage IDs: {df_lin['variant_id'].tolist()[:5]}...")
+        log.info(f"Sequence IDs: {df_seq['variant_id'].tolist()[:5]}...")
+        
         # Find lineage entries without sequences
         missing_seq = df['aa_seq'].isna() & df['dna_seq'].isna()
         unmatched_lineage = df[missing_seq]['variant_id'].tolist()
@@ -1999,6 +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}")
 
@@ -2019,6 +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 -----------------------------------------------------------
@@ -2047,6 +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 ---
@@ -2230,6 +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-0.1.6.dist-info → debase-0.1.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.6
+Version: 0.1.8
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.1.6.dist-info → debase-0.1.8.dist-info}/RECORD

@@ -1,17 +1,17 @@
 debase/PIPELINE_FLOW.md,sha256=S4nQyZlX39-Bchw1gQWPK60sHiFpB1eWHqo5GR9oTY8,4741
 debase/__init__.py,sha256=YeKveGj_8fwuu5ozoK2mUU86so_FjiCwsvg1d_lYVZU,586
 debase/__main__.py,sha256=LbxYt2x9TG5Ced7LpzzX_8gkWyXeZSlVHzqHfqAiPwQ,160
-debase/_version.py,sha256=0-ypEiBe2kUuZ71tMon-TVN7tQNbXA_-yM2NzlyMWuk,49
+debase/_version.py,sha256=pU1LNmYqDA6wql-sQ9H8cktGdOqOUTonX-sx1fgYV2Y,49
 debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
 debase/cleanup_sequence.py,sha256=QyhUqvTBVFTGM7ebAHmP3tif3Jq-8hvoLApYwAJtpH4,32702
-debase/enzyme_lineage_extractor.py,sha256=_kVsuOXOR8qhrOIy3mKNJuac3joK6goke628nAJoj88,94183
+debase/enzyme_lineage_extractor.py,sha256=k62qIp37ONYJBWT8D7ROh7ooYhz871BlCXJmAduq8js,95764
 debase/lineage_format.py,sha256=mACni9M1RXA_1tIyDZJpStQoutd_HLG2qQMAORTusZs,30045
 debase/reaction_info_extractor.py,sha256=6wWj4IyUNSugNjxpwMGjABSAp68yHABaz_7ZRjh9GEk,112162
 debase/substrate_scope_extractor.py,sha256=dbve8q3K7ggA3A6EwB-KK9L19BnMNgPZMZ05G937dSY,82262
 debase/wrapper.py,sha256=lTx375a57EVuXcZ_roXaj5UDj8HjRcb5ViNaSgPN4Ik,10352
-debase-0.1.6.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
-debase-0.1.6.dist-info/METADATA,sha256=mLzMY4LQx3SoOsirAiKhcqMofiMZ_D7jjB68ohUplFI,10789
-debase-0.1.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-debase-0.1.6.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
-debase-0.1.6.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
-debase-0.1.6.dist-info/RECORD,,
+debase-0.1.8.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.1.8.dist-info/METADATA,sha256=uGoC1Ebi663KiWpLbzkbcpKHYFxKjTJXoU1lV4cbVJ8,10789
+debase-0.1.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.1.8.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.1.8.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.1.8.dist-info/RECORD,,