debase 0.1.16__py3-none-any.whl → 0.1.18__py3-none-any.whl

debase/PIPELINE_FLOW.md

@@ -0,0 +1,100 @@
+# DEBase Pipeline Flow
+
+## Overview
+The DEBase pipeline extracts enzyme engineering data from chemistry papers through a series of modular steps.
+
+## Pipeline Architecture
+
+```
+┌─────────────────────┐     ┌─────────────────────┐
+│   Manuscript PDF    │     │       SI PDF        │
+└──────────┬──────────┘     └──────────┬──────────┘
+           │                           │
+           └───────────┬───────────────┘
+                       │
+                       ▼
+         ┌─────────────────────────────┐
+         │ 1. enzyme_lineage_extractor │
+         │   - Extract enzyme variants │
+         │   - Parse mutations         │
+         │   - Get basic metadata      │
+         └─────────────┬───────────────┘
+                       │
+                       ▼
+         ┌─────────────────────────────┐
+         │    2. cleanup_sequence      │
+         │   - Validate sequences      │
+         │   - Fix formatting issues   │
+         │   - Generate full sequences │
+         └─────────────┬───────────────┘
+                       │
+           ┌───────────┴───────────────┐
+           │                           │
+           ▼                           ▼
+┌─────────────────────────┐ ┌─────────────────────────┐
+│ 3a. reaction_info       │ │ 3b. substrate_scope     │
+│     _extractor          │ │     _extractor          │
+│ - Performance metrics   │ │ - Substrate variations  │
+│ - Model reaction        │ │ - Additional variants   │
+│ - Conditions            │ │ - Scope data            │
+└───────────┬─────────────┘ └───────────┬─────────────┘
+            │                           │
+            └───────────┬───────────────┘
+                        │
+                        ▼
+          ┌─────────────────────────────┐
+          │    4. lineage_format_o3     │
+          │   - Merge all data          │
+          │   - Fill missing sequences  │
+          │   - Format final output     │
+          └─────────────┬───────────────┘
+                        │
+                        ▼
+                ┌─────────────┐
+                │ Final CSV   │
+                └─────────────┘
+```
+
+## Module Details
+
+### 1. enzyme_lineage_extractor.py
+- **Input**: Manuscript PDF, SI PDF
+- **Output**: CSV with enzyme variants and mutations
+- **Function**: Extracts enzyme identifiers, mutation lists, and basic metadata
+
+### 2. cleanup_sequence.py  
+- **Input**: Enzyme lineage CSV
+- **Output**: CSV with validated sequences
+- **Function**: Validates protein sequences, generates full sequences from mutations
+
+### 3a. reaction_info_extractor.py
+- **Input**: PDFs + cleaned enzyme CSV
+- **Output**: CSV with reaction performance data
+- **Function**: Extracts yield, TTN, selectivity, reaction conditions
+
+### 3b. substrate_scope_extractor.py
+- **Input**: PDFs + cleaned enzyme CSV  
+- **Output**: CSV with substrate scope entries
+- **Function**: Extracts substrate variations tested with different enzymes
+
+### 4. lineage_format_o3.py
+- **Input**: Reaction CSV + Substrate scope CSV
+- **Output**: Final formatted CSV
+- **Function**: Merges data, fills missing sequences, applies consistent formatting
+
+## Key Features
+
+1. **Modular Design**: Each step can be run independently
+2. **Parallel Extraction**: Steps 3a and 3b run independently 
+3. **Error Recovery**: Pipeline can resume from any step
+4. **Clean Interfaces**: Each module has well-defined inputs/outputs
+
+## Usage
+
+```bash
+# Full pipeline
+python -m debase.wrapper_clean manuscript.pdf --si si.pdf --output results.csv
+
+# With intermediate files kept for debugging  
+python -m debase.wrapper_clean manuscript.pdf --si si.pdf --keep-intermediates
+```

debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.16"
+__version__ = "0.1.18"

debase/enzyme_lineage_extractor.py

@@ -823,7 +823,14 @@ def identify_evolution_locations(
 
 def _parse_variants(data: Dict[str, Any], campaign_id: Optional[str] = None) -> List[Variant]:
     """Convert raw JSON to a list[Variant] with basic validation."""
-    variants_json = data.get("variants", []) if isinstance(data, dict) else []
+    if isinstance(data, list):
+        # Direct array of variants
+        variants_json = data
+    elif isinstance(data, dict):
+        # Object with "variants" key
+        variants_json = data.get("variants", [])
+    else:
+        variants_json = []
     parsed: List[Variant] = []
     for item in variants_json:
         try:
@@ -1283,13 +1290,40 @@ def get_lineage(
         log.info(f"Identified {len(campaigns)} distinct campaigns")
         for camp in campaigns:
             log.info(f"  - {camp.campaign_name}: {camp.description}")
+    else:
+        log.warning("No campaigns identified, creating default campaign for enzyme characterization")
+        # Create a default campaign when none are found
+        default_campaign = Campaign(
+            campaign_id="default_characterization",
+            campaign_name="Enzyme Characterization Study",
+            description="Default campaign for papers that characterize existing enzyme variants without describing new directed evolution",
+            model_substrate="Unknown",
+            model_product="Unknown",
+            data_locations=["Full manuscript text"]
+        )
+        campaigns = [default_campaign]
+        log.info(f"Created default campaign: {default_campaign.campaign_name}")
     
     # Use captions for identification - they're concise and focused
     locations = identify_evolution_locations(caption_text, model, debug_dir=debug_dir, campaigns=None, pdf_paths=pdf_paths)
     
     all_variants = []
     
-    if locations and campaigns:
+    if campaigns:
+        # If we have campaigns but no specific locations, use general extraction
+        if not locations:
+            log.info("No specific lineage locations found, extracting from full text with campaign context")
+            # Extract lineage for each campaign using full text
+            for campaign in campaigns:
+                log.info(f"Processing campaign: {campaign.campaign_id}")
+                campaign_variants = extract_campaign_lineage(
+                    full_text, model, campaign_id=campaign.campaign_id, 
+                    debug_dir=debug_dir, pdf_paths=pdf_paths,
+                    campaign_info=campaign
+                )
+                all_variants.extend(campaign_variants)
+            return all_variants, campaigns
+        # Original logic for when we have both locations and campaigns
         # Log location information
         location_summary = []
         for loc in locations[:5]:
@@ -1939,6 +1973,173 @@ def fetch_pdb_sequences(pdb_id: str) -> Dict[str, str]:
         log.warning(f"Failed to fetch PDB {pdb_id}: {e}")
         return {}
 
+def extract_enzyme_info_with_gemini(
+    text: str,
+    variants: List[Variant],
+    model,
+) -> Dict[str, str]:
+    """Use Gemini to extract enzyme names or sequences when PDB IDs are not available.
+    
+    Returns:
+        Dict mapping variant IDs to sequences
+    """
+    # Build variant info for context
+    variant_info = []
+    for v in variants[:10]:  # Limit to first 10 variants for context
+        info = {
+            "id": v.variant_id,
+            "mutations": v.mutations[:5] if v.mutations else [],  # Limit mutations shown
+            "parent": v.parent_id,
+            "generation": v.generation
+        }
+        variant_info.append(info)
+    
+    prompt = f"""You are analyzing a scientific paper about enzyme engineering. No PDB IDs were found in the paper, and I need to obtain protein sequences for the enzyme variants described.
+
+Here are the variants found in the paper:
+{json.dumps(variant_info, indent=2)}
+
+Please analyze the paper text and:
+1. Identify the common name of the enzyme being studied (e.g., "P450 BM3", "cytochrome P450 BM3", "CYP102A1")
+2. If possible, extract or find the wild-type sequence
+3. Provide any UniProt IDs or accession numbers mentioned
+
+Paper text (first 5000 characters):
+{text[:5000]}
+
+Return your response as a JSON object with this structure:
+{{
+    "enzyme_name": "common name of the enzyme",
+    "systematic_name": "systematic name if applicable (e.g., CYP102A1)",
+    "uniprot_id": "UniProt ID if found",
+    "wild_type_sequence": "sequence if found in paper or if you know it",
+    "additional_names": ["list", "of", "alternative", "names"]
+}}
+
+If you cannot determine certain fields, set them to null.
+"""
+    
+    try:
+        response = model.generate_content(prompt)
+        text_response = _extract_text(response).strip()
+        
+        # Parse JSON response
+        if text_response.startswith("```"):
+            text_response = text_response.split("```")[1].strip()
+            if text_response.startswith("json"):
+                text_response = text_response[4:].strip()
+            text_response = text_response.split("```")[0].strip()
+        
+        enzyme_info = json.loads(text_response)
+        log.info(f"Gemini extracted enzyme info: {enzyme_info.get('enzyme_name', 'Unknown')}")
+        
+        sequences = {}
+        
+        # If Gemini provided a sequence directly, use it
+        if enzyme_info.get("wild_type_sequence"):
+            # Clean the sequence
+            seq = enzyme_info["wild_type_sequence"].upper().replace(" ", "").replace("\n", "")
+            # Validate it looks like a protein sequence
+            if seq and all(c in "ACDEFGHIKLMNPQRSTVWY" for c in seq) and len(seq) > 50:
+                # Map to the first variant or wild-type
+                wt_variant = next((v for v in variants if "WT" in v.variant_id.upper() or v.generation == 0), None)
+                if wt_variant:
+                    sequences[wt_variant.variant_id] = seq
+                else:
+                    sequences[variants[0].variant_id] = seq
+                log.info(f"Using sequence from Gemini: {len(seq)} residues")
+        
+        # If no sequence but we have names, try to fetch from UniProt
+        if not sequences:
+            names_to_try = []
+            if enzyme_info.get("enzyme_name"):
+                names_to_try.append(enzyme_info["enzyme_name"])
+            if enzyme_info.get("systematic_name"):
+                names_to_try.append(enzyme_info["systematic_name"])
+            if enzyme_info.get("uniprot_id"):
+                names_to_try.append(enzyme_info["uniprot_id"])
+            if enzyme_info.get("additional_names"):
+                names_to_try.extend(enzyme_info["additional_names"])
+            
+            # Try each name with UniProt
+            for name in names_to_try:
+                if name:
+                    uniprot_seqs = fetch_sequence_by_name(name)
+                    if uniprot_seqs:
+                        # Map the first sequence to appropriate variant
+                        seq = list(uniprot_seqs.values())[0]
+                        wt_variant = next((v for v in variants if "WT" in v.variant_id.upper() or v.generation == 0), None)
+                        if wt_variant:
+                            sequences[wt_variant.variant_id] = seq
+                        else:
+                            sequences[variants[0].variant_id] = seq
+                        log.info(f"Found sequence via UniProt search for '{name}': {len(seq)} residues")
+                        break
+        
+        return sequences
+        
+    except Exception as e:
+        log.warning(f"Failed to extract enzyme info with Gemini: {e}")
+        return {}
+
+
+def fetch_sequence_by_name(enzyme_name: str) -> Dict[str, str]:
+    """Fetch protein sequences from UniProt by enzyme name or ID.
+    
+    Args:
+        enzyme_name: Name, ID, or accession of the enzyme
+    
+    Returns:
+        Dict mapping identifiers to sequences
+    """
+    import requests
+    
+    clean_name = enzyme_name.strip()
+    
+    # First try as accession number
+    if len(clean_name) <= 10 and (clean_name[0].isalpha() and clean_name[1:].replace("_", "").isalnum()):
+        # Looks like a UniProt accession
+        url = f"https://rest.uniprot.org/uniprotkb/{clean_name}"
+        try:
+            response = requests.get(url, timeout=10)
+            if response.status_code == 200:
+                data = response.json()
+                sequence = data.get('sequence', {}).get('value', '')
+                if sequence:
+                    return {clean_name: sequence}
+        except:
+            pass
+    
+    # Try search API
+    url = "https://rest.uniprot.org/uniprotkb/search"
+    params = {
+        "query": f'(protein_name:"{clean_name}" OR gene:"{clean_name}" OR id:"{clean_name}")',
+        "format": "json",
+        "size": "5",
+        "fields": "accession,id,protein_name,gene_names,sequence"
+    }
+    
+    try:
+        response = requests.get(url, params=params, timeout=10)
+        response.raise_for_status()
+        data = response.json()
+        
+        results = data.get('results', [])
+        sequences = {}
+        
+        for result in results[:1]:  # Just take the first match
+            sequence = result.get('sequence', {}).get('value', '')
+            if sequence:
+                sequences[clean_name] = sequence
+                break
+        
+        return sequences
+        
+    except Exception as e:
+        log.warning(f"Failed to fetch sequence for '{enzyme_name}': {e}")
+        return {}
+
+
 def match_pdb_to_variants(
     pdb_sequences: Dict[str, str],
     variants: List[Variant],
@@ -2110,16 +2311,23 @@ def _merge_lineage_and_sequences(
         for v in lineage
     ])
 
-    df_seq = pd.DataFrame([
-        {
-            "variant_id": s.variant_id,
-            "aa_seq": s.aa_seq,
-            "dna_seq": s.dna_seq,
-            "seq_confidence": s.confidence,
-            "truncated": s.truncated,
-        }
-        for s in seqs
-    ])
+    if seqs:
+        df_seq = pd.DataFrame([
+            {
+                "variant_id": s.variant_id,
+                "aa_seq": s.aa_seq,
+                "dna_seq": s.dna_seq,
+                "seq_confidence": s.confidence,
+                "truncated": s.truncated,
+                "seq_source": s.metadata.get("source", None) if s.metadata else None,
+            }
+            for s in seqs
+        ])
+    else:
+        # Create empty DataFrame with correct columns for merging
+        df_seq = pd.DataFrame(columns=[
+            "variant_id", "aa_seq", "dna_seq", "seq_confidence", "truncated", "seq_source"
+        ])
     
     # Log sequence data info
     if len(df_seq) > 0:
@@ -2397,7 +2605,7 @@ def run_pipeline(
         early_df = _lineage_to_dataframe(lineage)
         output_csv_path = Path(output_csv)
         # Save lineage-only data with specific filename
-        lineage_path = output_csv_path.parent / "enzyme_lineage_data.csv"
+        lineage_path = output_csv_path.parent / "enzyme_lineage_name.csv"
         early_df.to_csv(lineage_path, index=False)
         log.info(
             "Saved lineage-only CSV -> %s",
@@ -2461,6 +2669,36 @@ def run_pipeline(
                     log.warning(f"No sequences found in PDB {pdb_id}")
         else:
             log.warning("No PDB IDs found in paper")
+            
+        # 4b. If still no sequences, try Gemini extraction as last resort
+        if not sequences or all(not s.aa_seq for s in sequences):
+            log.info("No sequences from PDB, attempting Gemini-based extraction...")
+            
+            gemini_sequences = extract_enzyme_info_with_gemini(full_text, lineage, model)
+            
+            if gemini_sequences:
+                # Convert to SequenceBlock objects
+                gemini_seq_blocks = []
+                for variant_id, seq in gemini_sequences.items():
+                    # Find the matching variant
+                    variant = next((v for v in lineage if v.variant_id == variant_id), None)
+                    if variant:
+                        seq_block = SequenceBlock(
+                            variant_id=variant.variant_id,
+                            aa_seq=seq,
+                            dna_seq=None,
+                            confidence=0.9,  # High confidence but slightly lower than PDB
+                            truncated=False,
+                            metadata={"source": "Gemini/UniProt"}
+                        )
+                        gemini_seq_blocks.append(seq_block)
+                        log.info(f"Added sequence for {variant.variant_id} via Gemini/UniProt: {len(seq)} residues")
+                
+                if gemini_seq_blocks:
+                    sequences = gemini_seq_blocks
+                    log.info(f"Successfully extracted {len(gemini_seq_blocks)} sequences via Gemini")
+            else:
+                log.warning("Failed to extract sequences via Gemini")
 
     # 5. Merge & score (Section 8) --------------------------------------------
     doi = extract_doi(manuscript)

debase/lineage_format.py

@@ -188,11 +188,17 @@ class VariantRecord:
     # Reaction-related -------------------------------------------------------------
     def substrate_iupac(self) -> List[str]:
         raw = str(self.row.get("substrate_iupac_list", "")).strip()
-        return _split_list(raw)
+        result = _split_list(raw)
+        if not result and raw and raw.lower() != 'nan':
+            log.debug(f"substrate_iupac_list for {self.eid}: raw='{raw}', parsed={result}")
+        return result
 
     def product_iupac(self) -> List[str]:
         raw = str(self.row.get("product_iupac_list", "")).strip()
-        return _split_list(raw)
+        result = _split_list(raw)
+        if not result and raw and raw.lower() != 'nan':
+            log.debug(f"product_iupac_list for {self.eid}: raw='{raw}', parsed={result}")
+        return result
 
 
     def ttn_or_yield(self) -> Optional[float]:
@@ -377,6 +383,53 @@ def _nt_mut(parent_aa: str, child_aa: str, parent_nt: str = "", child_nt: str =
 
 # === 6. SMILES CONVERSION HELPERS ==================================================
 
+def search_smiles_with_gemini(compound_name: str, model=None) -> Optional[str]:
+    """
+    Use Gemini to search for SMILES strings of complex compounds.
+    Returns SMILES string if found, None otherwise.
+    """
+    if not compound_name or compound_name.lower() in ['nan', 'none', '']:
+        return None
+        
+    if not model:
+        try:
+            # Import get_model from enzyme_lineage_extractor
+            import sys
+            from pathlib import Path
+            sys.path.append(str(Path(__file__).parent))
+            from enzyme_lineage_extractor import get_model
+            model = get_model()
+        except Exception as e:
+            log.warning(f"Could not load Gemini model: {e}")
+            return None
+    
+    prompt = f"""Search for the SMILES string representation of this chemical compound:
+"{compound_name}"
+
+IMPORTANT: 
+- Do NOT generate or create a SMILES string
+- Only provide SMILES that you can find in chemical databases or literature
+- For deuterated compounds, search for the specific isotope-labeled SMILES
+- If you cannot find the exact SMILES, say "NOT FOUND"
+
+Return ONLY the SMILES string if found, or "NOT FOUND" if not found.
+No explanation or additional text."""
+    
+    try:
+        response = model.generate_content(prompt)
+        result = response.text.strip()
+        
+        if result and result != "NOT FOUND" and not result.startswith("I"):
+            # Basic validation that it looks like SMILES
+            if any(c in result for c in ['C', 'c', 'N', 'O', 'S', 'P', '[', ']', '(', ')']):
+                log.info(f"Gemini found SMILES for '{compound_name}': {result}")
+                return result
+        return None
+    except Exception as e:
+        log.debug(f"Gemini SMILES search failed for '{compound_name}': {e}")
+        return None
+
+
 def _split_list(raw: str) -> List[str]:
     if not raw or str(raw).lower() == 'nan':
         return []
@@ -429,7 +482,12 @@ def _name_to_smiles(name: str, is_substrate: bool) -> str:
     except FileNotFoundError:
         pass  # OPSIN not installed
 
-    # 3. PubChem PUG REST (online) ---------------------------------------------
+    # 3. Gemini search (for complex compounds) ---------------------------------
+    gemini_smiles = search_smiles_with_gemini(name)
+    if gemini_smiles:
+        return gemini_smiles
+    
+    # 4. PubChem PUG REST (online) ---------------------------------------------
     try:
         import requests
 
@@ -538,13 +596,23 @@ def _root_enzyme_id(eid: str, idmap: Dict[str, Dict[str, str]], lineage_roots: D
 
 def _generate_lineage_roots(df: pd.DataFrame) -> Dict[str, str]:
     """Infer lineage roots using generation numbers and simple sequence similarity."""
-    idmap: Dict[str, Dict[str, str]] = {str(r["enzyme_id"]): r for _, r in df.iterrows()}
+    # Create idmap, handling missing enzyme_id gracefully
+    idmap: Dict[str, Dict[str, str]] = {}
+    for _, r in df.iterrows():
+        eid = r.get("enzyme_id")
+        if pd.isna(eid) or str(eid).strip() == "":
+            continue
+        idmap[str(eid)] = r
     roots: Dict[str, str] = {}
     # Look for generation 0 as the root
-    gen0 = {r["enzyme_id"] for _, r in df.iterrows() if str(r.get("generation", "")).strip() == "0"}
+    gen0 = {r["enzyme_id"] for _, r in df.iterrows() 
+            if str(r.get("generation", "")).strip() == "0" 
+            and not pd.isna(r.get("enzyme_id"))}
     # If no gen0 found, fall back to gen1
     if not gen0:
-        gen0 = {r["enzyme_id"] for _, r in df.iterrows() if str(r.get("generation", "")).strip() == "1"}
+        gen0 = {r["enzyme_id"] for _, r in df.iterrows() 
+                if str(r.get("generation", "")).strip() == "1" 
+                and not pd.isna(r.get("enzyme_id"))}
 
     def _seq_sim(a: str, b: str) -> float:
         if not a or not b:
@@ -553,7 +621,9 @@ def _generate_lineage_roots(df: pd.DataFrame) -> Dict[str, str]:
         return matches / max(len(a), len(b))
 
     for _, row in df.iterrows():
-        eid = row["enzyme_id"]
+        eid = row.get("enzyme_id")
+        if pd.isna(eid) or str(eid).strip() == "":
+            continue
         if eid in gen0:
             roots[eid] = eid
             continue
@@ -593,6 +663,9 @@ def _generate_lineage_roots(df: pd.DataFrame) -> Dict[str, str]:
 
 def flatten_dataframe(df: pd.DataFrame) -> pd.DataFrame:
     """Main public API: returns a DataFrame in the flat output format."""
+    log.info(f"Starting flatten_dataframe with {len(df)} input rows")
+    log.info(f"Input columns: {list(df.columns)}")
+    
     # Apply column aliases to the dataframe
     for alias, canonical in COLUMN_ALIASES.items():
         if alias in df.columns and canonical not in df.columns:
@@ -621,8 +694,29 @@ def flatten_dataframe(df: pd.DataFrame) -> pd.DataFrame:
     # _save_pickle(SUBSTRATE_CACHE, SUBSTRATE_CACHE_FILE)
 
     # 3. Flatten rows ---------------------------------------------------------
-    idmap = {str(r["enzyme_id"]): r.to_dict() for _, r in df.iterrows()}
+    # Create idmap for parent lookups, but note this will only keep last occurrence of duplicates
+    idmap = {}
+    for _, r in df.iterrows():
+        eid = str(r["enzyme_id"])
+        if eid in idmap:
+            log.debug(f"Overwriting duplicate enzyme_id in idmap: {eid}")
+        idmap[eid] = r.to_dict()
+    
+    # Check for duplicate enzyme_ids
+    enzyme_ids = [str(r["enzyme_id"]) for _, r in df.iterrows()]
+    unique_ids = set(enzyme_ids)
+    if len(enzyme_ids) != len(unique_ids):
+        log.warning(f"Found duplicate enzyme_ids! Total: {len(enzyme_ids)}, Unique: {len(unique_ids)}")
+        from collections import Counter
+        id_counts = Counter(enzyme_ids)
+        duplicates = {k: v for k, v in id_counts.items() if v > 1}
+        log.warning(f"Duplicate enzyme_ids: {duplicates}")
+        log.info("Note: All rows will still be processed, but parent lookups may use the last occurrence of duplicate IDs")
+    
     output_rows: List[Dict[str, str]] = []
+    skipped_count = 0
+    processed_count = 0
+    
     for idx, (_, row) in enumerate(df.iterrows()):
         rec = VariantRecord(row.to_dict())
         eid = rec.eid
@@ -632,13 +726,19 @@ def flatten_dataframe(df: pd.DataFrame) -> pd.DataFrame:
         prods = rec.product_iupac()
         data_type = rec.row.get("data_type", "")
         
-        if not subs or not prods:
-            # Skip entries without reaction info unless it's marked as lineage only
+        if not prods:
+            # Skip entries without product info unless it's marked as lineage only
             if data_type == "lineage":
                 subs, prods = [""], [""]  # placeholders
             else:
-                log.debug("Skipping %s due to missing reaction data", eid)
+                log.info(f"Skipping enzyme_id={eid} (row {idx}) due to missing product data. prods={prods}, data_type={data_type}")
+                skipped_count += 1
                 continue
+        
+        # If no substrates but we have products, use empty substrate list
+        if not subs:
+            log.debug(f"Empty substrate list for enzyme_id={eid}, using empty placeholder")
+            subs = [""]
 
         sub_smiles = [sub_cache.get(s, "") for s in subs]
         prod_smiles = [prod_cache.get(p, "") for p in prods]
@@ -712,7 +812,9 @@ def flatten_dataframe(df: pd.DataFrame) -> pd.DataFrame:
             additional_information=additional_information,
         )
         output_rows.append(flat.as_dict())
+        processed_count += 1
 
+    log.info(f"Flattening complete: {processed_count} rows processed, {skipped_count} rows skipped")
     out_df = pd.DataFrame(output_rows, columns=OUTPUT_COLUMNS)
     return out_df
 

debase/reaction_info_extractor.py

@@ -761,6 +761,15 @@ Ignore locations that contain data for other campaigns.
                 return line
         return page[:800]
 
+    def _ensure_rgb_pixmap(self, pix: fitz.Pixmap) -> fitz.Pixmap:
+        """Ensure pixmap is in RGB colorspace for PIL compatibility."""
+        if pix.alpha:  # RGBA -> RGB
+            pix = fitz.Pixmap(fitz.csRGB, pix)
+        elif pix.colorspace and pix.colorspace.name not in ["DeviceRGB", "DeviceGray"]:
+            # Convert unsupported colorspaces (CMYK, LAB, etc.) to RGB
+            pix = fitz.Pixmap(fitz.csRGB, pix)
+        return pix
+
     # ---- NEW: Page image helper for both figures and tables ----
     def _extract_page_png(self, ref: str, extract_figure_only: bool = True) -> Optional[str]:
         """Export the page containing the reference as PNG.
@@ -802,14 +811,14 @@ Ignore locations that contain data for other campaigns.
                             if img_rect.y1 < cap_rect.y0:  # fully above caption
                                 # Extract image bytes
                                 pix = fitz.Pixmap(doc, xref)
-                                if pix.alpha:  # RGBA -> RGB
-                                    pix = fitz.Pixmap(fitz.csRGB, pix)
+                                pix = self._ensure_rgb_pixmap(pix)
                                 img_bytes = pix.tobytes("png")
                                 return b64encode(img_bytes).decode()
                 else:
                     # Extract the entire page as an image
                     mat = fitz.Matrix(2.0, 2.0)  # 2x zoom for better quality
                     pix = page.get_pixmap(matrix=mat)
+                    pix = self._ensure_rgb_pixmap(pix)
                     img_bytes = pix.tobytes("png")
                     return b64encode(img_bytes).decode()
         return None
@@ -842,11 +851,13 @@ Ignore locations that contain data for other campaigns.
             # Add the current page
             mat = fitz.Matrix(2.0, 2.0)  # 2x zoom for better quality
             pix = doc.load_page(page_num).get_pixmap(matrix=mat)
+            pix = self._ensure_rgb_pixmap(pix)
             all_images.append(pix)
             
             # If this is the last page with the reference, also add the next page
             if i == len(pages) - 1 and page_num + 1 < doc.page_count:
                 next_pix = doc.load_page(page_num + 1).get_pixmap(matrix=mat)
+                next_pix = self._ensure_rgb_pixmap(next_pix)
                 all_images.append(next_pix)
                 LOGGER.info(f"Added next page: page {page_num + 2}")  # +2 because page numbers are 1-based for users
         
@@ -855,14 +866,16 @@ Ignore locations that contain data for other campaigns.
             
         # If only one page, return it directly
         if len(all_images) == 1:
-            return b64encode(all_images[0].tobytes("png")).decode()
+            pix = self._ensure_rgb_pixmap(all_images[0])
+            return b64encode(pix.tobytes("png")).decode()
             
         # Combine multiple pages vertically
         if not all_images:
             return None
             
         if len(all_images) == 1:
-            return b64encode(all_images[0].tobytes("png")).decode()
+            pix = self._ensure_rgb_pixmap(all_images[0])
+            return b64encode(pix.tobytes("png")).decode()
             
         # Calculate dimensions for combined image
         total_height = sum(pix.height for pix in all_images)
@@ -903,6 +916,7 @@ Ignore locations that contain data for other campaigns.
         # Convert the page to a pixmap
         mat = fitz.Matrix(2.0, 2.0)  # 2x zoom for quality
         combined_pix = page.get_pixmap(matrix=mat)
+        combined_pix = self._ensure_rgb_pixmap(combined_pix)
         
         # Convert to PNG and return
         img_bytes = combined_pix.tobytes("png")
@@ -947,8 +961,9 @@ Ignore locations that contain data for other campaigns.
             LOGGER.info("Gemini Vision: extracting metrics for %d enzymes from %s…", len(enzyme_list), ref)
             tag = f"extract_metrics_batch_vision"
         else:
-            # Add enzyme names to prompt for batch extraction
-            prompt = campaign_context + PROMPT_EXTRACT_METRICS + f"\n\nExtract performance data for ALL these enzyme variants:\n{enzyme_names}\n\n=== CONTEXT ===\n" + snippet[:4000]
+            # Add enzyme names to prompt for batch extraction with explicit format requirement
+            format_example = '{"enzyme1": {"yield": "99.0%", "ttn": null, ...}, "enzyme2": {"yield": "85.0%", ...}}'
+            prompt = campaign_context + PROMPT_EXTRACT_METRICS + f"\n\nExtract performance data for ALL these enzyme variants:\n{enzyme_names}\n\nReturn a JSON object with enzyme names as keys, each containing the metrics.\nExample format: {format_example}\n\n=== CONTEXT ===\n" + snippet[:4000]
             LOGGER.info("Gemini: extracting metrics for %d enzymes from %s…", len(enzyme_list), ref)
             tag = f"extract_metrics_batch"
 

debase/wrapper.py

@@ -46,101 +46,333 @@ def run_sequence_cleanup(input_csv: Path, output_csv: Path) -> Path:
     """
     Step 2: Clean and validate protein sequences
     Calls: cleanup_sequence.py
+    Returns output path even if cleanup fails (copies input file)
     """
     logger.info(f"Cleaning sequences from {input_csv.name}")
     
-    from .cleanup_sequence import main as cleanup_sequences
-    cleanup_sequences([str(input_csv), str(output_csv)])
-    
-    logger.info(f"Sequence cleanup complete: {output_csv}")
-    return output_csv
+    try:
+        from .cleanup_sequence import main as cleanup_sequences
+        cleanup_sequences([str(input_csv), str(output_csv)])
+        
+        logger.info(f"Sequence cleanup complete: {output_csv}")
+        return output_csv
+        
+    except Exception as e:
+        logger.warning(f"Sequence cleanup failed: {e}")
+        logger.info("Copying original file to continue pipeline...")
+        
+        # Copy the input file as-is to continue pipeline
+        import shutil
+        shutil.copy2(input_csv, output_csv)
+        
+        logger.info(f"Original file copied: {output_csv}")
+        return output_csv
 
 
 def run_reaction_extraction(manuscript: Path, si: Path, lineage_csv: Path, output: Path, debug_dir: Path = None) -> Path:
     """
     Step 3a: Extract reaction performance metrics
     Calls: reaction_info_extractor.py
+    Returns output path even if extraction fails (creates empty file)
     """
     logger.info(f"Extracting reaction info for enzymes in {lineage_csv.name}")
     
-    from .reaction_info_extractor import ReactionExtractor, Config
-    import pandas as pd
-    
-    # Load enzyme data
-    enzyme_df = pd.read_csv(lineage_csv)
-    
-    # Initialize extractor and run
-    cfg = Config()
-    extractor = ReactionExtractor(manuscript, si, cfg, debug_dir=debug_dir)
-    df_metrics = extractor.run(enzyme_df)
-    
-    # Save results
-    df_metrics.to_csv(output, index=False)
-    logger.info(f"Reaction extraction complete: {output}")
-    return output
+    try:
+        from .reaction_info_extractor import ReactionExtractor, Config
+        import pandas as pd
+        
+        # Load enzyme data
+        enzyme_df = pd.read_csv(lineage_csv)
+        
+        # Initialize extractor and run
+        cfg = Config()
+        extractor = ReactionExtractor(manuscript, si, cfg, debug_dir=debug_dir)
+        df_metrics = extractor.run(enzyme_df)
+        
+        # Save results
+        df_metrics.to_csv(output, index=False)
+        logger.info(f"Reaction extraction complete: {output}")
+        return output
+        
+    except Exception as e:
+        logger.warning(f"Reaction extraction failed: {e}")
+        logger.info("Creating empty reaction info file to continue pipeline...")
+        
+        # Create empty reaction CSV with basic columns
+        import pandas as pd
+        empty_df = pd.DataFrame(columns=[
+            'enzyme', 'substrate', 'product', 'yield_percent', 'ee_percent',
+            'conversion_percent', 'reaction_type', 'reaction_conditions', 'notes'
+        ])
+        empty_df.to_csv(output, index=False)
+        
+        logger.info(f"Empty reaction file created: {output}")
+        return output
 
 
 def run_substrate_scope_extraction(manuscript: Path, si: Path, lineage_csv: Path, output: Path, debug_dir: Path = None) -> Path:
     """
     Step 3b: Extract substrate scope data (runs in parallel with reaction extraction)
     Calls: substrate_scope_extractor.py
+    Returns output path even if extraction fails (creates empty file)
     """
     logger.info(f"Extracting substrate scope for enzymes in {lineage_csv.name}")
     
-    from .substrate_scope_extractor import run_pipeline
+    try:
+        from .substrate_scope_extractor import run_pipeline
+        
+        # Run substrate scope extraction
+        run_pipeline(
+            manuscript=manuscript,
+            si=si,
+            lineage_csv=lineage_csv,
+            output_csv=output,
+            debug_dir=debug_dir
+        )
+        
+        logger.info(f"Substrate scope extraction complete: {output}")
+        return output
+        
+    except Exception as e:
+        logger.warning(f"Substrate scope extraction failed: {e}")
+        logger.info("Creating empty substrate scope file to continue pipeline...")
+        
+        # Create empty substrate scope CSV with proper headers
+        import pandas as pd
+        empty_df = pd.DataFrame(columns=[
+            'enzyme', 'substrate', 'product', 'yield_percent', 'ee_percent', 
+            'conversion_percent', 'selectivity', 'reaction_conditions', 'notes'
+        ])
+        empty_df.to_csv(output, index=False)
+        
+        logger.info(f"Empty substrate scope file created: {output}")
+        return output
+
+
+def match_enzyme_variants_with_gemini(lineage_enzymes: list, data_enzymes: list, model=None) -> dict:
+    """
+    Use Gemini to match enzyme variant IDs between different datasets.
+    Returns a mapping of data_enzyme_id -> lineage_enzyme_id.
+    """
+    import json
     
-    # Run substrate scope extraction
-    run_pipeline(
-        manuscript=manuscript,
-        si=si,
-        lineage_csv=lineage_csv,
-        output_csv=output,
-        debug_dir=debug_dir
-    )
+    if not model:
+        try:
+            from .enzyme_lineage_extractor import get_model
+            model = get_model()
+        except:
+            logger.warning("Could not load Gemini model for variant matching")
+            return {}
     
-    logger.info(f"Substrate scope extraction complete: {output}")
-    return output
+    prompt = f"""Match enzyme variant IDs between two lists from the same scientific paper.
+
+These lists come from different sections or analyses of the same study, but may use different naming conventions.
+
+List 1 (from lineage/sequence data):
+{json.dumps(lineage_enzymes)}
+
+List 2 (from experimental data):
+{json.dumps(data_enzymes)}
+
+Analyze the patterns and match variants that refer to the same enzyme.
+Return ONLY a JSON object mapping IDs from List 2 to their corresponding IDs in List 1.
+Format: {{"list2_id": "list1_id", ...}}
+Only include matches you are confident about based on the naming patterns.
+"""
+    
+    try:
+        response = model.generate_content(prompt)
+        mapping_text = response.text.strip()
+        
+        # Extract JSON from response
+        if '```json' in mapping_text:
+            mapping_text = mapping_text.split('```json')[1].split('```')[0].strip()
+        elif '```' in mapping_text:
+            mapping_text = mapping_text.split('```')[1].split('```')[0].strip()
+        
+        mapping = json.loads(mapping_text)
+        logger.info(f"Gemini matched {len(mapping)} enzyme variants")
+        for k, v in mapping.items():
+            logger.info(f"  Matched '{k}' -> '{v}'")
+        return mapping
+    except Exception as e:
+        logger.warning(f"Failed to match variants with Gemini: {e}")
+        return {}
 
 
 def run_lineage_format(reaction_csv: Path, substrate_scope_csv: Path, cleaned_csv: Path, output_csv: Path) -> Path:
     """
     Step 4: Format and merge all data into final CSV
-    Calls: lineage_format.py
+    Creates comprehensive format merging all available data, even if some extraction steps failed
     """
     logger.info(f"Formatting and merging data into final output")
     
-    from .lineage_format import run_pipeline
-    import pandas as pd
-    
-    # First, we need to merge the protein sequences into the reaction data
-    df_reaction = pd.read_csv(reaction_csv)
-    df_sequences = pd.read_csv(cleaned_csv)
-    
-    # Merge sequences into reaction data
-    # Include generation and parent info for proper mutation calculation
-    sequence_cols = ['protein_sequence', 'dna_seq', 'seq_confidence', 'truncated', 'flag', 
-                     'generation', 'parent_enzyme_id', 'mutations']
-    sequence_data = df_sequences[['enzyme_id'] + [col for col in sequence_cols if col in df_sequences.columns]]
-    
-    # Merge on enzyme_id or variant_id
-    if 'enzyme_id' in df_reaction.columns:
-        df_reaction = df_reaction.merge(sequence_data, on='enzyme_id', how='left', suffixes=('', '_seq'))
-    elif 'enzyme' in df_reaction.columns:
-        sequence_data = sequence_data.rename(columns={'enzyme_id': 'enzyme'})
-        df_reaction = df_reaction.merge(sequence_data, on='enzyme', how='left', suffixes=('', '_seq'))
-    
-    # Save the merged reaction data
-    df_reaction.to_csv(reaction_csv, index=False)
-    
-    # Run the formatting pipeline
-    df_final = run_pipeline(
-        reaction_csv=reaction_csv,
-        substrate_scope_csv=substrate_scope_csv,
-        output_csv=output_csv
-    )
-    
-    logger.info(f"Final formatting complete: {output_csv}")
-    return output_csv
+    try:
+        import pandas as pd
+        
+        # Read all available data files
+        logger.info("Reading enzyme lineage data...")
+        df_lineage = pd.read_csv(cleaned_csv)
+        
+        logger.info("Reading reaction data...")
+        try:
+            df_reaction = pd.read_csv(reaction_csv)
+            has_reaction_data = len(df_reaction) > 0 and not df_reaction.empty
+        except:
+            df_reaction = pd.DataFrame()
+            has_reaction_data = False
+        
+        logger.info("Reading substrate scope data...")
+        try:
+            df_scope = pd.read_csv(substrate_scope_csv)
+            has_scope_data = len(df_scope) > 0 and not df_scope.empty
+        except:
+            df_scope = pd.DataFrame()
+            has_scope_data = False
+        
+        # Start with lineage data as base
+        df_final = df_lineage.copy()
+        
+        # Ensure consistent enzyme ID column
+        if 'variant_id' in df_final.columns and 'enzyme_id' not in df_final.columns:
+            df_final = df_final.rename(columns={'variant_id': 'enzyme_id'})
+        
+        # Merge reaction data if available
+        if has_reaction_data:
+            logger.info(f"Merging reaction data ({len(df_reaction)} records)")
+            # Match on enzyme_id or enzyme
+            merge_key = 'enzyme_id' if 'enzyme_id' in df_reaction.columns else 'enzyme'
+            if merge_key in df_reaction.columns:
+                df_final = df_final.merge(df_reaction, left_on='enzyme_id', right_on=merge_key, how='left', suffixes=('', '_reaction'))
+        else:
+            logger.info("No reaction data available")
+        
+        # Merge substrate scope data if available
+        if has_scope_data:
+            logger.info(f"Merging substrate scope data ({len(df_scope)} records)")
+            merge_key = 'enzyme_id' if 'enzyme_id' in df_scope.columns else 'enzyme'
+            
+            if merge_key in df_scope.columns:
+                # First try direct merge
+                df_test_merge = df_final.merge(df_scope, left_on='enzyme_id', right_on=merge_key, how='left', suffixes=('', '_scope'))
+                
+                # Check if any matches were found
+                matched_count = df_test_merge[merge_key + '_scope'].notna().sum() if merge_key + '_scope' in df_test_merge.columns else 0
+                
+                if matched_count == 0:
+                    logger.info("No direct matches found, using Gemini to match enzyme variants...")
+                    
+                    # Get unique enzyme IDs from both datasets
+                    lineage_enzymes = df_final['enzyme_id'].dropna().unique().tolist()
+                    scope_enzymes = df_scope[merge_key].dropna().unique().tolist()
+                    
+                    # Get mapping from Gemini
+                    mapping = match_enzyme_variants_with_gemini(lineage_enzymes, scope_enzymes)
+                    
+                    if mapping:
+                        # Apply mapping to scope data
+                        df_scope_mapped = df_scope.copy()
+                        df_scope_mapped[merge_key] = df_scope_mapped[merge_key].map(lambda x: mapping.get(x, x))
+                        df_final = df_final.merge(df_scope_mapped, left_on='enzyme_id', right_on=merge_key, how='left', suffixes=('', '_scope'))
+                    else:
+                        logger.warning("Could not match enzyme variants between datasets")
+                        df_final = df_test_merge
+                else:
+                    df_final = df_test_merge
+                    logger.info(f"Direct merge matched {matched_count} records")
+        else:
+            logger.info("No substrate scope data available")
+        
+        # Add comprehensive column structure for missing data
+        essential_columns = [
+            'enzyme_id', 'parent_id', 'generation', 'mutations', 'campaign_id', 'notes',
+            'aa_seq', 'dna_seq', 'seq_confidence', 'truncated', 'seq_source', 'doi',
+            'substrate_list', 'substrate_iupac_list', 'product_list', 'product_iupac_list',
+            'cofactor_list', 'cofactor_iupac_list', 'yield', 'ee', 'ttn',
+            'reaction_temperature', 'reaction_ph', 'reaction_buffer', 'reaction_other_conditions',
+            'data_location'
+        ]
+        
+        # Add missing columns with NaN
+        for col in essential_columns:
+            if col not in df_final.columns:
+                df_final[col] = None
+        
+        # Clean up duplicate columns from merging
+        columns_to_keep = []
+        seen_base_names = set()
+        for col in df_final.columns:
+            base_name = col.split('_reaction')[0].split('_scope')[0]
+            if base_name not in seen_base_names:
+                columns_to_keep.append(col)
+                seen_base_names.add(base_name)
+            elif col.endswith('_scope') or col.endswith('_reaction'):
+                # Prefer scope or reaction data over base lineage data for certain columns
+                if base_name in ['substrate_list', 'product_list', 'yield', 'ee', 'reaction_temperature']:
+                    columns_to_keep.append(col)
+                    # Remove the base column if it exists
+                    if base_name in columns_to_keep:
+                        columns_to_keep.remove(base_name)
+                    seen_base_names.add(base_name)
+        
+        df_final = df_final[columns_to_keep]
+        
+        # Rename merged columns back to standard names
+        rename_map = {}
+        for col in df_final.columns:
+            if col.endswith('_scope') or col.endswith('_reaction'):
+                base_name = col.split('_scope')[0].split('_reaction')[0]
+                rename_map[col] = base_name
+        df_final = df_final.rename(columns=rename_map)
+        
+        # Save the comprehensive final output
+        df_final.to_csv(output_csv, index=False)
+        
+        logger.info(f"Final comprehensive format complete: {output_csv}")
+        logger.info(f"Final output contains {len(df_final)} variants with {len(df_final.columns)} data columns")
+        
+        # Log what data was successfully merged
+        if has_reaction_data:
+            logger.info("✓ Reaction performance data merged")
+        if has_scope_data:
+            logger.info("✓ Substrate scope data merged")
+        
+        # Now run the actual lineage format to produce plate-based format
+        logger.info("\nRunning lineage format to produce plate-based output...")
+        try:
+            from .lineage_format import flatten_dataframe
+            
+            # Create the plate-based output filename
+            plate_output = output_csv.parent / (output_csv.stem + "_plate_format.csv")
+            
+            # Flatten the dataframe to plate format
+            df_flattened = flatten_dataframe(df_final)
+            
+            # Save the flattened output
+            df_flattened.to_csv(plate_output, index=False)
+            
+            logger.info(f"✓ Plate-based format saved to: {plate_output}")
+            logger.info(f"  Contains {len(df_flattened)} rows with plate/well assignments")
+            
+            # Update the final output path to be the plate format
+            output_csv = plate_output
+            
+        except Exception as e:
+            logger.warning(f"Could not generate plate-based format: {e}")
+            logger.info("Comprehensive format will be used as final output")
+        
+        return output_csv
+        
+    except Exception as e:
+        logger.warning(f"Final formatting failed: {e}")
+        logger.info("Using cleaned sequence data as final output...")
+        
+        # Copy the cleaned CSV as the final output
+        import shutil
+        shutil.copy2(cleaned_csv, output_csv)
+        
+        logger.info(f"Cleaned sequence file used as final output: {output_csv}")
+        return output_csv
 
 
 def run_pipeline(
@@ -206,7 +438,7 @@ def run_pipeline(
         
         # Step 4: Format and merge
         logger.info("\n[Step 4/5] Formatting and merging data...")
-        run_lineage_format(reaction_csv, substrate_csv, cleaned_csv, output_path)
+        final_output = run_lineage_format(reaction_csv, substrate_csv, cleaned_csv, output_path)
         
         # Step 5: Finalize
         logger.info("\n[Step 5/5] Finalizing...")
@@ -219,11 +451,13 @@ def run_pipeline(
         
         logger.info("\n" + "="*60)
         logger.info("PIPELINE COMPLETED SUCCESSFULLY")
-        logger.info(f"Output: {output_path}")
+        logger.info(f"Comprehensive output: {output_path}")
+        if final_output != output_path:
+            logger.info(f"Plate-based output: {final_output}")
         logger.info(f"Runtime: {elapsed:.1f} seconds")
         logger.info("="*60)
         
-        return output_path
+        return final_output
         
     except Exception as e:
         logger.error(f"Pipeline failed: {str(e)}")

{debase-0.1.16.dist-info → debase-0.1.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.16
+Version: 0.1.18
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

debase-0.1.18.dist-info/RECORD

@@ -0,0 +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=Qd1kKsssesKE5FvJnDdAuZsx_BrxTSJJyt68SK99D54,50
+debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
+debase/cleanup_sequence.py,sha256=QyhUqvTBVFTGM7ebAHmP3tif3Jq-8hvoLApYwAJtpH4,32702
+debase/enzyme_lineage_extractor.py,sha256=xbNKkIMRCM2dYHsX24vWX1EsQINaGSWBj-iTX10B8Mw,117057
+debase/lineage_format.py,sha256=IS9ig-Uv7KxtI9enZKM6YgQ7sitqwOo4cdXbOy38J3s,34232
+debase/reaction_info_extractor.py,sha256=W9CS0puFTdhJ_T2Fpy931EgnjOCsHHjbtU6RdnzDlhw,113140
+debase/substrate_scope_extractor.py,sha256=9XDF-DxOqB63AwaVceAMvg7BcjoTQXE_pG2c_seM_DA,100698
+debase/wrapper.py,sha256=V9bs8ZiyCpJHMM5VuN74kiKdkQRVU6vyvLKCrO1BUB8,20890
+debase-0.1.18.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.1.18.dist-info/METADATA,sha256=XvSrveJ0Y40c53JYUfiveaQNJ3qoEkxaQ61n3_--1cQ,10790
+debase-0.1.18.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.1.18.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.1.18.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.1.18.dist-info/RECORD,,

debase-0.1.16.dist-info/RECORD

@@ -1,16 +0,0 @@
-debase/__init__.py,sha256=YeKveGj_8fwuu5ozoK2mUU86so_FjiCwsvg1d_lYVZU,586
-debase/__main__.py,sha256=LbxYt2x9TG5Ced7LpzzX_8gkWyXeZSlVHzqHfqAiPwQ,160
-debase/_version.py,sha256=l25FRqoNjxB5d3qBHsLMMA_9YWsIZ7nJ5BiTLj0qYE8,50
-debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
-debase/cleanup_sequence.py,sha256=QyhUqvTBVFTGM7ebAHmP3tif3Jq-8hvoLApYwAJtpH4,32702
-debase/enzyme_lineage_extractor.py,sha256=jNxNCh8VF0dUFxUlTall0w1-oQojXRXLnWcuPFs5ij8,106879
-debase/lineage_format.py,sha256=mACni9M1RXA_1tIyDZJpStQoutd_HLG2qQMAORTusZs,30045
-debase/reaction_info_extractor.py,sha256=9DkEZh7TgsxKpFkKbLyUhS_w0Z84LczkDFv-v_NEHE4,112174
-debase/substrate_scope_extractor.py,sha256=9XDF-DxOqB63AwaVceAMvg7BcjoTQXE_pG2c_seM_DA,100698
-debase/wrapper.py,sha256=lTx375a57EVuXcZ_roXaj5UDj8HjRcb5ViNaSgPN4Ik,10352
-debase-0.1.16.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
-debase-0.1.16.dist-info/METADATA,sha256=7sv2OcIuHaoOImkBdoEtRzyOjp9Kuoz2ZmgK4tosaUc,10790
-debase-0.1.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-debase-0.1.16.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
-debase-0.1.16.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
-debase-0.1.16.dist-info/RECORD,,