debase 0.1.7__tar.gz → 0.1.9__tar.gz

{debase-0.1.7 → debase-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.7
+Version: 0.1.9
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.1.7 → debase-0.1.9}/src/debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.7"
+__version__ = "0.1.9"

{debase-0.1.7 → debase-0.1.9}/src/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."""
@@ -2005,6 +2040,10 @@ 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 +2064,12 @@ 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 +2098,10 @@ 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 ---
@@ -2170,7 +2219,7 @@ 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)
@@ -2236,6 +2285,14 @@ 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-0.1.9}/src/debase.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.7
+Version: 0.1.9
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team