debase 0.1.0__py3-none-any.whl → 0.1.2__py3-none-any.whl

debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.0"
+__version__ = "0.1.2"

debase/reaction_info_extractor.py

@@ -685,7 +685,7 @@ Ignore locations that contain data for other campaigns.
             'confidence': 95
         }
     
-    def find_lineage_model_reaction(self, location: str, group_context: str) -> Dict[str, Any]:
+    def find_lineage_model_reaction(self, location: str, group_context: str, model_reaction_locations: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
         """Find the model reaction for a specific lineage group."""
         # Gather relevant text near this location
         page_text = self._page_with_reference(location) or ""
@@ -693,6 +693,7 @@ Ignore locations that contain data for other campaigns.
         # Also check manuscript introduction for model reaction info
         intro_text = "\n\n".join(self.ms_pages[:3]) if self.ms_pages else ""
         
+        # Build the prompt with location and context
         prompt = PROMPT_FIND_LINEAGE_MODEL_REACTION.format(
             location=location,
             group_context=group_context
@@ -700,6 +701,22 @@ Ignore locations that contain data for other campaigns.
         prompt += f"\n\nText near {location}:\n{page_text[:3000]}"
         prompt += f"\n\nManuscript introduction:\n{intro_text[:3000]}"
         
+        # If we have model reaction locations, include text from those locations too
+        if model_reaction_locations:
+            # Add text from model reaction location
+            if model_reaction_locations.get("model_reaction_location", {}).get("location"):
+                model_loc = model_reaction_locations["model_reaction_location"]["location"]
+                model_text = self._get_text_around_location(model_loc)
+                if model_text:
+                    prompt += f"\n\nText from {model_loc} (potential model reaction location):\n{model_text[:3000]}"
+            
+            # Add text from conditions location (often contains reaction details)
+            if model_reaction_locations.get("conditions_location", {}).get("location"):
+                cond_loc = model_reaction_locations["conditions_location"]["location"]
+                cond_text = self._get_text_around_location(cond_loc)
+                if cond_text:
+                    prompt += f"\n\nText from {cond_loc} (reaction conditions):\n{cond_text[:3000]}"
+        
         try:
             data = generate_json_with_retry(
                 self.model,
@@ -1790,8 +1807,16 @@ TEXT FROM MANUSCRIPT:
             if location.get('caption'):
                 location_context += f"\nCaption: {location['caption']}"
             
-            # Try to find model reaction for this specific lineage
-            location_model_reaction = self.find_lineage_model_reaction(location['location'], location_context)
+            # First find model reaction locations for this campaign/enzyme group
+            location_enzymes = df_location['enzyme'].unique().tolist()
+            model_reaction_locations = self.find_model_reaction_locations(location_enzymes)
+            
+            # Try to find model reaction for this specific lineage, passing the locations
+            location_model_reaction = self.find_lineage_model_reaction(
+                location['location'], 
+                location_context,
+                model_reaction_locations
+            )
             
             # Get full model reaction info with IUPAC names
             if location_model_reaction.get('substrate_ids') or location_model_reaction.get('product_ids'):
@@ -1799,7 +1824,6 @@ TEXT FROM MANUSCRIPT:
             else:
                 # Fall back to general model reaction extraction
                 # Pass the enzyme variants from this location
-                location_enzymes = df_location['enzyme'].unique().tolist()
                 model_info = self.gather_model_reaction_info(location_enzymes)
             
             # Add model reaction info to all enzymes from this location
@@ -1891,7 +1915,16 @@ TEXT FROM MANUSCRIPT:
             if group.get('caption'):
                 location_context += f"\nCaption: {group['caption']}"
             
-            location_model_reaction = self.find_lineage_model_reaction(group_location, location_context)
+            # First find model reaction locations for this enzyme group
+            location_enzymes = df_location['enzyme'].unique().tolist() if 'enzyme' in df_location.columns else all_enzyme_ids
+            model_reaction_locations = self.find_model_reaction_locations(location_enzymes)
+            
+            # Try to find model reaction for this specific lineage, passing the locations
+            location_model_reaction = self.find_lineage_model_reaction(
+                group_location, 
+                location_context,
+                model_reaction_locations
+            )
             
             # Get full model reaction info with IUPAC names
             if location_model_reaction.get('substrate_ids') or location_model_reaction.get('product_ids'):
@@ -1899,7 +1932,6 @@ TEXT FROM MANUSCRIPT:
             else:
                 # Try to extract model reaction from this specific location
                 # Pass the enzyme variants that have data in this location
-                location_enzymes = df_location['enzyme'].unique().tolist() if 'enzyme' in df_location.columns else all_enzyme_ids
                 model_info = self.gather_model_reaction_info(location_enzymes)
             
             # Add model reaction info to all enzymes from this location

debase/wrapper.py

@@ -35,9 +35,7 @@ def run_lineage_extraction(manuscript: Path, si: Path, output: Path, debug_dir:
     """
     logger.info(f"Extracting enzyme lineage from {manuscript.name}")
     
-    import sys
-    sys.path.insert(0, str(Path(__file__).parent.parent.parent))
-    from src.debase.enzyme_lineage_extractor import run_pipeline
+    from .enzyme_lineage_extractor import run_pipeline
     run_pipeline(manuscript=manuscript, si=si, output_csv=output, debug_dir=debug_dir)
     
     logger.info(f"Lineage extraction complete: {output}")
@@ -51,7 +49,7 @@ def run_sequence_cleanup(input_csv: Path, output_csv: Path) -> Path:
     """
     logger.info(f"Cleaning sequences from {input_csv.name}")
     
-    from src.debase.cleanup_sequence import main as cleanup_sequences
+    from .cleanup_sequence import main as cleanup_sequences
     cleanup_sequences([str(input_csv), str(output_csv)])
     
     logger.info(f"Sequence cleanup complete: {output_csv}")
@@ -65,7 +63,7 @@ def run_reaction_extraction(manuscript: Path, si: Path, lineage_csv: Path, outpu
     """
     logger.info(f"Extracting reaction info for enzymes in {lineage_csv.name}")
     
-    from src.debase.reaction_info_extractor import ReactionExtractor, Config
+    from .reaction_info_extractor import ReactionExtractor, Config
     import pandas as pd
     
     # Load enzyme data
@@ -89,7 +87,7 @@ def run_substrate_scope_extraction(manuscript: Path, si: Path, lineage_csv: Path
     """
     logger.info(f"Extracting substrate scope for enzymes in {lineage_csv.name}")
     
-    from src.debase.substrate_scope_extractor import run_pipeline
+    from .substrate_scope_extractor import run_pipeline
     
     # Run substrate scope extraction
     run_pipeline(
@@ -111,7 +109,7 @@ def run_lineage_format(reaction_csv: Path, substrate_scope_csv: Path, cleaned_cs
     """
     logger.info(f"Formatting and merging data into final output")
     
-    from src.debase.lineage_format import run_pipeline
+    from .lineage_format import run_pipeline
     import pandas as pd
     
     # First, we need to merge the protein sequences into the reaction data

{debase-0.1.0.dist-info → debase-0.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.0
+Version: 0.1.2
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team
@@ -64,13 +64,6 @@ Enzyme lineage analysis and sequence extraction package with advanced parallel p
 ```bash
 pip install debase
 ```
-
-For full functionality with chemical SMILES support:
-
-```bash
-pip install debase[rdkit]
-```
-
 ## Requirements
 
 - Python 3.8 or higher
@@ -139,13 +132,6 @@ debase --manuscript paper.pdf --si si.pdf --use-optimized-reaction --reaction-ba
 debase --manuscript paper.pdf --si si.pdf  # Default method
 ```
 
-## Performance Comparison
-
-| Method | Total Time | API Calls | Accuracy | Best For |
-|--------|------------|-----------|----------|----------|
-| Sequential | ~45 min | 44 calls | Highest | Small datasets |
-| **Parallel Individual** | **~12 min** | **44 calls** | **High** | **Recommended** |
-| Batch Processing | ~8 min | ~8 calls | Good | Speed-critical |
 
 ## Advanced Usage
 
@@ -169,31 +155,6 @@ python -m debase.substrate_scope_extractor_parallel \
   --manuscript paper.pdf --si si.pdf --lineage-csv lineage.csv \
   --max-workers 5 --output substrate_scope.csv
 ```
-
-## Python API
-
-```python
-from debase.wrapper import run_pipeline
-
-# Run full pipeline with parallel processing
-run_pipeline(
-    manuscript_path="paper.pdf",
-    si_path="si.pdf", 
-    output="output.csv",
-    use_parallel_individual=True,
-    max_workers=5
-)
-
-# For individual steps
-from debase.reaction_info_extractor_parallel import extract_reaction_info_parallel
-from debase.enzyme_lineage_extractor import setup_gemini_api
-
-model = setup_gemini_api()
-reaction_data = extract_reaction_info_parallel(
-    model, manuscript_path, si_path, enzyme_csv_path, max_workers=5
-)
-```
-
 ## Pipeline Architecture
 
 The DEBase pipeline consists of 5 main steps:
@@ -222,9 +183,6 @@ The DEBase pipeline consists of 5 main steps:
 - **External database integration:** Automatic sequence fetching from PDB and UniProt
 - **AI-powered matching:** Uses Gemini to intelligently match database entries to enzyme variants
 - **Smart filtering:** Automatically excludes non-enzyme entries (buffers, controls, etc.)
-- **Progress tracking:** Real-time status updates
-- **Flexible output:** CSV format with comprehensive chemical and performance data
-- **Caching:** PDF encoding cache for improved performance
 - **Vision capabilities:** Extracts data from both text and images in PDFs
 
 ## Complete Command Reference
@@ -234,7 +192,6 @@ The DEBase pipeline consists of 5 main steps:
 --manuscript PATH           # Required: Path to manuscript PDF
 --si PATH                  # Optional: Path to supplementary information PDF
 --output PATH              # Output file path (default: manuscript_name_debase.csv)
---queries N                # Number of consensus queries (default: 2)
 ```
 
 ### Performance Options
@@ -279,21 +236,5 @@ The DEBase pipeline consists of 5 main steps:
 3. **Use batch processing** only when speed is critical and some accuracy loss is acceptable
 4. **Skip validation** (`--skip-validation`) for faster processing in production
 5. **Keep intermediates** (`--keep-intermediates`) for debugging and incremental runs
-6. **Check external databases** - Many sequences can be automatically fetched from PDB/UniProt
-7. **Verify enzyme entries** - The system automatically filters out buffers and controls
-
-## Troubleshooting
-
-### No sequences found
-- The extractor will automatically search PDB and UniProt databases
-- Check the logs for which database IDs were found and attempted
-- Sequences with PDB structures will be fetched with high confidence
-
-### Incorrect enzyme extraction
-- Non-enzyme entries (buffers, controls, media) are automatically filtered
-- Check the log for entries marked as "Filtering out non-enzyme entry"
+6. 
 
-### PDB matching issues
-- The system uses AI to match PDB IDs to specific enzyme variants
-- Increased context extraction ensures better matching accuracy
-- Check logs for "Gemini PDB matching" entries to see the matching process

{debase-0.1.0.dist-info → debase-0.1.2.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=HnfC_TWAA2mfjIbkXT0ipZEqElS5wLaMzSj1DkE1F88,49
+debase/_version.py,sha256=rPOdIIhUKYST-L457GFA8SWkOdMGZQAiiaWLSYHnVwc,49
 debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
 debase/cleanup_sequence.py,sha256=QyhUqvTBVFTGM7ebAHmP3tif3Jq-8hvoLApYwAJtpH4,32702
 debase/enzyme_lineage_extractor.py,sha256=1GcgHA-lQPRf9-bNDlvQIP8p-KsP3D2WhIuOtCVJ_ME,87276
 debase/lineage_format.py,sha256=mACni9M1RXA_1tIyDZJpStQoutd_HLG2qQMAORTusZs,30045
-debase/reaction_info_extractor.py,sha256=euw-4NHFuOPxpF99PJxTMLYYG0WryBDUCpoANB-SPPM,109655
+debase/reaction_info_extractor.py,sha256=vgXE4eFSmRUU_RPsW7E0vbP5mU0tjrhwk7UVqz_98yM,111469
 debase/substrate_scope_extractor.py,sha256=dbve8q3K7ggA3A6EwB-KK9L19BnMNgPZMZ05G937dSY,82262
-debase/wrapper.py,sha256=UlUBxxIXBnVtSIT9lZXkQeImlCABiUuof1CVZNKv9N4,10482
-debase-0.1.0.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
-debase-0.1.0.dist-info/METADATA,sha256=3s1NGPGYOb2bbP5PD5OoWBcJ7UeZ2OTQiOQ-SE5uqoM,11509
-debase-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-debase-0.1.0.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
-debase-0.1.0.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
-debase-0.1.0.dist-info/RECORD,,
+debase/wrapper.py,sha256=lTx375a57EVuXcZ_roXaj5UDj8HjRcb5ViNaSgPN4Ik,10352
+debase-0.1.2.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.1.2.dist-info/METADATA,sha256=t5JrPGNEtLsF3qXrSpHvn02_rlNGlkYv-NDubaXZa2w,9382
+debase-0.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.1.2.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.1.2.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.1.2.dist-info/RECORD,,