debase 0.1.8__py3-none-any.whl → 0.1.11__py3-none-any.whl

debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.8"
+__version__ = "0.1.11"

debase/enzyme_lineage_extractor.py

@@ -1562,11 +1562,24 @@ TEXT (may be truncated):
 ```
 """.strip()
 
-def extract_sequences(text: str, model, *, debug_dir: str | Path | None = None) -> list[SequenceBlock]:
+def extract_sequences(text: str, model, *, debug_dir: str | Path | None = None, lineage_context: str = None) -> list[SequenceBlock]:
     """Prompt Gemini and convert its JSON reply into SequenceBlock objects."""
-    prompt = _SEQ_EXTRACTION_PROMPT.format(
+    base_prompt = _SEQ_EXTRACTION_PROMPT.format(
         schema=_SEQUENCE_SCHEMA_HINT, text=text[:MAX_CHARS]
     )
+    
+    # Add lineage context if available
+    if lineage_context:
+        prompt = f"""{base_prompt}
+
+IMPORTANT CONTEXT - Known variants from lineage extraction:
+{lineage_context}
+
+Match sequences to these known variants when possible. Variants may be labeled differently in different sections (e.g., "5295" might also appear as "ʟ-G0", "ʟ-ApPgb-αEsA-G0", or "ʟ-ApPgb-αEsA-G0 (5295)").
+"""
+    else:
+        prompt = base_prompt
+    
     data = generate_json_with_retry(model, prompt, _SEQUENCE_SCHEMA_HINT, debug_dir=debug_dir, tag="sequences")
     return _parse_sequences(data)
 
@@ -1620,7 +1633,7 @@ def _parse_sequences(raw: list[dict]) -> list[SequenceBlock]:
     return blocks
 
 # --- 7.5  Convenience wrapper -------------------------------------------------
-def get_sequences(text: str, model, *, pdf_paths: List[Path] = None, debug_dir: str | Path | None = None) -> list[SequenceBlock]:
+def get_sequences(text: str, model, *, pdf_paths: List[Path] = None, debug_dir: str | Path | None = None, lineage_variants: List[Variant] = None) -> list[SequenceBlock]:
     # Phase 1: Identify where sequences might be located
     locations = identify_sequence_locations(text, model, debug_dir=debug_dir)
     
@@ -1685,14 +1698,36 @@ def get_sequences(text: str, model, *, pdf_paths: List[Path] = None, debug_dir:
             if focused_text and len(focused_text) < len(text):
                 log.info("Reduced text from %d to %d chars using validated location", 
                          len(text), len(focused_text))
-                return extract_sequences(focused_text, model, debug_dir=debug_dir)
+                # Build lineage context if available
+                lineage_context = None
+                if lineage_variants:
+                    variant_info = []
+                    for v in lineage_variants[:20]:  # Limit to first 20
+                        info = f"- {v.variant_id} (Gen {v.generation})"
+                        if v.mutations:
+                            info += f" [{', '.join(v.mutations[:3])}{'...' if len(v.mutations) > 3 else ''}]"
+                        variant_info.append(info)
+                    lineage_context = "\n".join(variant_info)
+                
+                return extract_sequences(focused_text, model, debug_dir=debug_dir, lineage_context=lineage_context)
         else:
             log.warning("Location validation failed or returned invalid location: %s", 
                        validation.get("reason", "Unknown"))
     
     # Fallback to full text
     log.info("Using full text for sequence extraction")
-    return extract_sequences(text, model, debug_dir=debug_dir)
+    # Build lineage context if available
+    lineage_context = None
+    if lineage_variants:
+        variant_info = []
+        for v in lineage_variants[:20]:  # Limit to first 20
+            info = f"- {v.variant_id} (Gen {v.generation})"
+            if v.mutations:
+                info += f" [{', '.join(v.mutations[:3])}{'...' if len(v.mutations) > 3 else ''}]"
+            variant_info.append(info)
+        lineage_context = "\n".join(variant_info)
+    
+    return extract_sequences(text, model, debug_dir=debug_dir, lineage_context=lineage_context)
 
 # === 7.6 PDB SEQUENCE EXTRACTION === -----------------------------------------
 """When no sequences are found in the paper, attempt to fetch them from PDB."""
@@ -1989,21 +2024,55 @@ Return ONLY a JSON object mapping lineage variant IDs to sequence variant IDs. I
                         text = text[4:].strip()
                 
                 matches = json.loads(text)
+                log.info(f"Gemini returned matches: {matches}")
+                
+                # Debug: Log what sequences we actually have
+                log.info(f"Available sequence variant IDs: {unmatched_seqs['variant_id'].tolist()}")
                 
                 # 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]
+                    if lineage_id in unmatched_lineage:
+                        # Find the sequence data - be flexible with matching
+                        seq_data = None
                         
-                        # 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']
+                        # First try exact match
+                        seq_matches = unmatched_seqs[unmatched_seqs['variant_id'] == seq_id]
+                        if len(seq_matches) > 0:
+                            seq_data = seq_matches.iloc[0]
+                        else:
+                            # Try to find by checking various matching strategies
+                            for idx, row in unmatched_seqs.iterrows():
+                                variant_id = row['variant_id']
+                                # Check if one is contained in the other
+                                if seq_id in variant_id or variant_id in seq_id:
+                                    seq_data = row
+                                    break
+                                # Check if they share the same core identifier (e.g., G0, G1, etc.)
+                                seq_id_parts = re.findall(r'G\d+(?:-\d+)?', seq_id)
+                                variant_id_parts = re.findall(r'G\d+(?:-\d+)?', variant_id)
+                                if seq_id_parts and variant_id_parts and seq_id_parts[0] == variant_id_parts[0]:
+                                    seq_data = row
+                                    break
                         
-                        log.info(f"Matched {lineage_id} -> {seq_id} using Gemini")
+                        if seq_data is not None:
+                            # Update the dataframe
+                            mask = df['variant_id'] == lineage_id
+                            if mask.any():
+                                # Log before update
+                                log.debug(f"Before update: df row for {lineage_id} has aa_seq={df.loc[mask, 'aa_seq'].iloc[0]}")
+                                
+                                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.get('seq_confidence', None)
+                                df.loc[mask, 'truncated'] = seq_data.get('truncated', False)
+                                
+                                # Log after update
+                                log.debug(f"After update: df row for {lineage_id} has aa_seq={df.loc[mask, 'aa_seq'].iloc[0][:50] if df.loc[mask, 'aa_seq'].iloc[0] else 'None'}")
+                                log.info(f"Matched {lineage_id} -> {seq_id} using Gemini (populated sequence of length {len(seq_data['aa_seq']) if seq_data['aa_seq'] else 0})")
+                            else:
+                                log.warning(f"No rows found in dataframe for lineage_id {lineage_id}")
+                        else:
+                            log.warning(f"Could not find sequence data for {seq_id} in unmatched sequences")
                 
                 # Log the final state after all matches
                 matched_count = (~df['aa_seq'].isna()).sum()
@@ -2184,7 +2253,7 @@ def run_pipeline(
         )
 
     # 4. Extract sequences (Section 7) ----------------------------------------
-    sequences = get_sequences(full_text, model, pdf_paths=pdf_paths, debug_dir=debug_dir)
+    sequences = get_sequences(full_text, model, pdf_paths=pdf_paths, debug_dir=debug_dir, lineage_variants=lineage)
     
     # 4a. Try PDB extraction if no sequences found -----------------------------
     # Check if we need PDB sequences (no sequences or only partial sequences)

{debase-0.1.8.dist-info → debase-0.1.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.8
+Version: 0.1.11
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.1.8.dist-info → debase-0.1.11.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=pU1LNmYqDA6wql-sQ9H8cktGdOqOUTonX-sx1fgYV2Y,49
+debase/_version.py,sha256=L4sqaU-oAJRWrcboH-vA95jHfUiXr5-fAsrF7lqZSyQ,50
 debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
 debase/cleanup_sequence.py,sha256=QyhUqvTBVFTGM7ebAHmP3tif3Jq-8hvoLApYwAJtpH4,32702
-debase/enzyme_lineage_extractor.py,sha256=k62qIp37ONYJBWT8D7ROh7ooYhz871BlCXJmAduq8js,95764
+debase/enzyme_lineage_extractor.py,sha256=at4OYHdXtgMku1FR_6AsHWk64UKInWkGQL9m3H6cKIQ,99809
 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-0.1.8.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,,
+debase-0.1.11.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.1.11.dist-info/METADATA,sha256=ZSR0Yl36Al_rQm9Ht9jut7om3xQT8yqyobIjEUH_Xfo,10790
+debase-0.1.11.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.1.11.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.1.11.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.1.11.dist-info/RECORD,,