debase 0.1.5__py3-none-any.whl → 0.1.7__py3-none-any.whl

debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.5"
+__version__ = "0.1.7"

debase/enzyme_lineage_extractor.py

@@ -1912,7 +1912,7 @@ def _infer_generations(variants: List[Variant]) -> None:
 
 
 def _merge_lineage_and_sequences(
-    lineage: List[Variant], seqs: List[SequenceBlock], doi: Optional[str]
+    lineage: List[Variant], seqs: List[SequenceBlock], doi: Optional[str], model=None
 ) -> pd.DataFrame:
     """Return a tidy DataFrame with one row per variant."""
 
@@ -1943,6 +1943,71 @@ def _merge_lineage_and_sequences(
     # 2. Outer merge keeps every lineage entry and adds sequence cols when present
     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()
+        
+        # Find sequences that weren't matched
+        matched_seq_ids = df[~missing_seq]['variant_id'].tolist()
+        unmatched_seqs = df_seq[~df_seq['variant_id'].isin(matched_seq_ids)]
+        
+        if len(unmatched_lineage) > 0 and len(unmatched_seqs) > 0:
+            log.info(f"Found {len(unmatched_lineage)} lineage entries without sequences and {len(unmatched_seqs)} unmatched sequences")
+            log.info(f"Using Gemini to match variants")
+            
+            # Build prompt for Gemini to match variants
+            prompt = f"""Match enzyme variant IDs between two lists. The same variant may be labeled differently in different parts of the paper.
+
+Lineage variant IDs (need sequences):
+{json.dumps(unmatched_lineage)}
+
+Sequence variant IDs (have sequences):
+{json.dumps(unmatched_seqs['variant_id'].tolist())}
+
+These lists contain variant identifiers from the same paper but may use different naming conventions.
+Match each lineage variant ID to its corresponding sequence variant ID based on any patterns or relationships you can identify.
+
+Return ONLY a JSON object mapping lineage variant IDs to sequence variant IDs. Include only matches you are confident about.
+"""
+            
+            try:
+                response = model.generate_content(prompt)
+                text = _extract_text(response).strip()
+                
+                # Parse JSON response
+                if text.startswith("```"):
+                    text = text.split("```")[1].strip()
+                    if text.startswith("json"):
+                        text = text[4:].strip()
+                
+                matches = json.loads(text)
+                
+                # Apply the matches
+                for lineage_id, seq_id in matches.items():
+                    if lineage_id in unmatched_lineage and seq_id in unmatched_seqs['variant_id'].values:
+                        # Get the sequence data
+                        seq_data = unmatched_seqs[unmatched_seqs['variant_id'] == seq_id].iloc[0]
+                        
+                        # Update the dataframe
+                        mask = df['variant_id'] == lineage_id
+                        df.loc[mask, 'aa_seq'] = seq_data['aa_seq']
+                        df.loc[mask, 'dna_seq'] = seq_data['dna_seq']
+                        df.loc[mask, 'seq_confidence'] = seq_data['seq_confidence']
+                        df.loc[mask, 'truncated'] = seq_data['truncated']
+                        
+                        log.info(f"Matched {lineage_id} -> {seq_id} using Gemini")
+                
+            except Exception as e:
+                log.warning(f"Failed to match variants using Gemini: {e}")
+
     # 3. If generation missing after user input, try inference
     if df["generation"].isna().any():
         _infer_generations(lineage)  # mutates in place
@@ -1968,6 +2033,7 @@ def merge_and_score(
     lineage: List[Variant],
     seqs: List[SequenceBlock],
     doi: Optional[str] = None,
+    model=None,
 ) -> pd.DataFrame:
     """User-facing helper imported by the pipeline orchestrator.
 
@@ -1980,7 +2046,7 @@ def merge_and_score(
         raise ValueError("merge_and_score(): `lineage` list is empty; nothing to merge")
 
     # If no sequences found, still build a DataFrame so caller can decide what to do.
-    df = _merge_lineage_and_sequences(lineage, seqs, doi)
+    df = _merge_lineage_and_sequences(lineage, seqs, doi, model)
 
     # Basic sanity: warn if many missing sequences
     missing_rate = df["aa_seq"].isna().mean() if "aa_seq" in df else 1.0
@@ -2163,7 +2229,7 @@ def run_pipeline(
 
     # 5. Merge & score (Section 8) --------------------------------------------
     doi = extract_doi(manuscript)
-    df_final = merge_and_score(lineage, sequences, doi)
+    df_final = merge_and_score(lineage, sequences, doi, model)
 
     # 6. Write FINAL CSV -------------------------------------------------------
     if output_csv:

{debase-0.1.5.dist-info → debase-0.1.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.5
+Version: 0.1.7
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.1.5.dist-info → debase-0.1.7.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=Bj9n2sI-8fEKj8LGa2ZU_dV7G5OnubUV9yK63_ZmeUU,49
+debase/_version.py,sha256=vPJKuOkG3cFKZEVbwdNnidjitp6bll8M7nfNUPqx6YA,49
 debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
 debase/cleanup_sequence.py,sha256=QyhUqvTBVFTGM7ebAHmP3tif3Jq-8hvoLApYwAJtpH4,32702
-debase/enzyme_lineage_extractor.py,sha256=kn3pfPWctiaWC-oaynEOike9MQ-63ApAK1cmoHbTPzU,91159
+debase/enzyme_lineage_extractor.py,sha256=7RWogFelrFcwAUup1MgJuiozjEbBc3ri2F2UV3eTEig,94544
 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-0.1.5.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
-debase-0.1.5.dist-info/METADATA,sha256=1vMeMX3yGLXnnvnp9lN3mTRDCsdqFklE0puYlBemfyE,10789
-debase-0.1.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-debase-0.1.5.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
-debase-0.1.5.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
-debase-0.1.5.dist-info/RECORD,,
+debase-0.1.7.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.1.7.dist-info/METADATA,sha256=Dj6i6WqC3QFJxXZyPQT7e27Aq8Hrrclu-44KadmYQJ0,10789
+debase-0.1.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.1.7.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.1.7.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.1.7.dist-info/RECORD,,