debase 0.1.3__tar.gz → 0.1.5__tar.gz

{debase-0.1.3 → debase-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.3
+Version: 0.1.5
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team
@@ -61,14 +61,70 @@ Enzyme lineage analysis and sequence extraction package with advanced parallel p
 
 ## Installation
 
+### Quick Install (PyPI)
 ```bash
 pip install debase
 ```
+
+### Development Setup with Conda (Recommended)
+
+1. **Clone the repository**
+```bash
+git clone https://github.com/YuemingLong/DEBase.git
+cd DEBase
+```
+
+2. **Create conda environment from provided file**
+```bash
+conda env create -f environment.yml
+conda activate debase
+```
+
+3. **Install DEBase in development mode**
+```bash
+pip install -e .
+```
+
+### Manual Setup
+
+If you prefer to set up the environment manually:
+
+```bash
+# Create new conda environment
+conda create -n debase python=3.9
+conda activate debase
+
+# Install conda packages
+conda install -c conda-forge pandas numpy matplotlib seaborn jupyter jupyterlab openpyxl biopython requests tqdm
+
+# Install RDKit (optional - used for SMILES canonicalization)
+conda install -c conda-forge rdkit
+
+# Install pip-only packages
+pip install PyMuPDF google-generativeai debase
+```
+
+**Note about RDKit**: RDKit is optional and only used for canonicalizing SMILES strings in the output. If not installed, DEBase will still function normally but SMILES strings won't be standardized.
+
 ## Requirements
 
 - Python 3.8 or higher
 - A Gemini API key (set as environment variable `GEMINI_API_KEY`)
 
+### Setting up Gemini API Key
+
+```bash
+# Option 1: Export in your shell
+export GEMINI_API_KEY="your-api-key-here"
+
+# Option 2: Add to ~/.bashrc or ~/.zshrc for persistence
+echo 'export GEMINI_API_KEY="your-api-key-here"' >> ~/.bashrc
+source ~/.bashrc
+
+# Option 3: Create .env file in project directory
+echo 'GEMINI_API_KEY=your-api-key-here' > .env
+```
+
 ## Recent Updates
 
 - **Campaign-Aware Extraction**: Automatically detects and processes multiple directed evolution campaigns in a single paper

{debase-0.1.3 → debase-0.1.5}/README.md

@@ -4,14 +4,70 @@ Enzyme lineage analysis and sequence extraction package with advanced parallel p
 
 ## Installation
 
+### Quick Install (PyPI)
 ```bash
 pip install debase
 ```
+
+### Development Setup with Conda (Recommended)
+
+1. **Clone the repository**
+```bash
+git clone https://github.com/YuemingLong/DEBase.git
+cd DEBase
+```
+
+2. **Create conda environment from provided file**
+```bash
+conda env create -f environment.yml
+conda activate debase
+```
+
+3. **Install DEBase in development mode**
+```bash
+pip install -e .
+```
+
+### Manual Setup
+
+If you prefer to set up the environment manually:
+
+```bash
+# Create new conda environment
+conda create -n debase python=3.9
+conda activate debase
+
+# Install conda packages
+conda install -c conda-forge pandas numpy matplotlib seaborn jupyter jupyterlab openpyxl biopython requests tqdm
+
+# Install RDKit (optional - used for SMILES canonicalization)
+conda install -c conda-forge rdkit
+
+# Install pip-only packages
+pip install PyMuPDF google-generativeai debase
+```
+
+**Note about RDKit**: RDKit is optional and only used for canonicalizing SMILES strings in the output. If not installed, DEBase will still function normally but SMILES strings won't be standardized.
+
 ## Requirements
 
 - Python 3.8 or higher
 - A Gemini API key (set as environment variable `GEMINI_API_KEY`)
 
+### Setting up Gemini API Key
+
+```bash
+# Option 1: Export in your shell
+export GEMINI_API_KEY="your-api-key-here"
+
+# Option 2: Add to ~/.bashrc or ~/.zshrc for persistence
+echo 'export GEMINI_API_KEY="your-api-key-here"' >> ~/.bashrc
+source ~/.bashrc
+
+# Option 3: Create .env file in project directory
+echo 'GEMINI_API_KEY=your-api-key-here' > .env
+```
+
 ## Recent Updates
 
 - **Campaign-Aware Extraction**: Automatically detects and processes multiple directed evolution campaigns in a single paper

{debase-0.1.3 → debase-0.1.5}/src/debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.3"
+__version__ = "0.1.5"

{debase-0.1.3 → debase-0.1.5}/src/debase/enzyme_lineage_extractor.py

@@ -800,15 +800,36 @@ def identify_evolution_locations(
                         _dump(f"=== CAMPAIGN MAPPING PROMPT ===\nLocation: {location_str}\n{'='*80}\n\n{mapping_prompt}", mapping_file)
                     
                     response = model.generate_content(mapping_prompt)
-                    campaign_id = _extract_text(response).strip().strip('"')
+                    response_text = _extract_text(response).strip()
+                    
+                    # Extract just the campaign_id from the response
+                    # Look for the campaign_id pattern in the response
+                    campaign_id = None
+                    for campaign in campaigns:
+                        if hasattr(campaign, 'campaign_id') and campaign.campaign_id in response_text:
+                            campaign_id = campaign.campaign_id
+                            break
+                    
+                    # If not found, try to extract the last line or quoted string
+                    if not campaign_id:
+                        # Try to find quoted string
+                        quoted_match = re.search(r'"([^"]+)"', response_text)
+                        if quoted_match:
+                            campaign_id = quoted_match.group(1)
+                        else:
+                            # Take the last non-empty line
+                            lines = [line.strip() for line in response_text.split('\n') if line.strip()]
+                            if lines:
+                                campaign_id = lines[-1].strip('"')
                     
                     # Save mapping response to debug if provided
                     if debug_dir:
                         response_file = debug_path / f"campaign_mapping_response_{location_str.replace(' ', '_')}_{int(time.time())}.txt"
-                        _dump(f"=== CAMPAIGN MAPPING RESPONSE ===\nLocation: {location_str}\nMapped to: {campaign_id}\n{'='*80}\n\n{_extract_text(response)}", response_file)
+                        _dump(f"=== CAMPAIGN MAPPING RESPONSE ===\nLocation: {location_str}\nFull response:\n{response_text}\nExtracted campaign_id: {campaign_id}\n{'='*80}", response_file)
                     
                     # Add campaign_id to location
-                    loc['campaign_id'] = campaign_id
+                    if campaign_id:
+                        loc['campaign_id'] = campaign_id
                     log.info(f"Mapped {location_str} to campaign: {campaign_id}")
                 except Exception as exc:
                     log.warning(f"Failed to map location to campaign: {exc}")
@@ -1003,6 +1024,38 @@ IMPORTANT: Only extract variants that belong to this specific campaign.
 
 # ---- 6.3  Helper for location-based extraction -----------------------------
 
+def _is_toc_entry(text: str, position: int, pattern: str) -> bool:
+    """Check if a found pattern is likely a table of contents entry."""
+    # Find the line containing this position
+    line_start = text.rfind('\n', 0, position)
+    line_end = text.find('\n', position)
+    
+    if line_start == -1:
+        line_start = 0
+    else:
+        line_start += 1
+        
+    if line_end == -1:
+        line_end = len(text)
+        
+    line = text[line_start:line_end]
+    
+    # TOC indicators:
+    # 1. Line contains dots (...) followed by page number
+    # 2. Line ends with just a page number
+    # 3. Line has "Table S12:" or similar followed by title and page
+    if '...' in line or re.search(r'\.\s*\d+\s*$', line) or re.search(r':\s*[^:]+\s+\d+\s*$', line):
+        return True
+        
+    # Check if this is in a contents/TOC section
+    # Look backwards up to 500 chars for "Contents" or "Table of Contents"
+    context_start = max(0, position - 500)
+    context = text[context_start:position].lower()
+    if 'contents' in context or 'table of contents' in context:
+        return True
+        
+    return False
+
 def _extract_text_at_locations(text: str, locations: List[Union[str, dict]], context_chars: int = 5000, validate_sequences: bool = False) -> str:
     """Extract text around identified locations."""
     if not locations:
@@ -1061,11 +1114,25 @@ def _extract_text_at_locations(text: str, locations: List[Union[str, dict]], con
         pos = -1
         used_pattern = None
         for pattern in page_patterns:
-            temp_pos = text_lower.find(pattern.lower())
-            if temp_pos != -1:
+            search_pos = 0
+            while search_pos < len(text_lower):
+                temp_pos = text_lower.find(pattern.lower(), search_pos)
+                if temp_pos == -1:
+                    break
+                    
+                # Check if this is a TOC entry
+                if _is_toc_entry(text, temp_pos, pattern):
+                    log.debug("Skipping TOC entry for pattern '%s' at position %d", pattern, temp_pos)
+                    search_pos = temp_pos + len(pattern)
+                    continue
+                    
+                # Found non-TOC entry
                 pos = temp_pos
                 used_pattern = pattern
-                log.debug("Found pattern '%s' at position %d", pattern, pos)
+                log.debug("Found pattern '%s' at position %d (not TOC)", pattern, pos)
+                break
+                
+            if pos != -1:
                 break
         
         if pos != -1:
@@ -1254,7 +1321,9 @@ def get_lineage(
                 
             # Use text-based extraction (works for tables and text sections)
             # Extract from full text, not caption text - use only primary location
-            focused_text = _extract_text_at_locations(full_text, [primary_location])
+            # Use more context for tables since they often span multiple pages
+            context_size = 15000 if location_type == 'table' else 5000
+            focused_text = _extract_text_at_locations(full_text, [primary_location], context_chars=context_size)
             log.info("Reduced text from %d to %d chars using primary location %s for campaign %s", 
                      len(full_text), len(focused_text), 
                      primary_location.get('location', 'Unknown') if isinstance(primary_location, dict) else 'Unknown',
@@ -2038,8 +2107,15 @@ def run_pipeline(
     sequences = get_sequences(full_text, model, pdf_paths=pdf_paths, debug_dir=debug_dir)
     
     # 4a. Try PDB extraction if no sequences found -----------------------------
-    if not sequences or all(s.aa_seq is None for s in sequences):
-        log.info("No sequences found in paper, attempting PDB extraction...")
+    # Check if we need PDB sequences (no sequences or only partial sequences)
+    MIN_PROTEIN_LENGTH = 50  # Most proteins are >50 AA
+    needs_pdb = (not sequences or 
+                 all(s.aa_seq is None or (s.aa_seq and len(s.aa_seq) < MIN_PROTEIN_LENGTH) 
+                     for s in sequences))
+    
+    if needs_pdb:
+        log.info("No full-length sequences found in paper (only partial sequences < %d AA), attempting PDB extraction...", 
+                 MIN_PROTEIN_LENGTH)
         
         # Extract PDB IDs from all PDFs
         pdb_ids = []

{debase-0.1.3 → debase-0.1.5}/src/debase.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.3
+Version: 0.1.5
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team
@@ -61,14 +61,70 @@ Enzyme lineage analysis and sequence extraction package with advanced parallel p
 
 ## Installation
 
+### Quick Install (PyPI)
 ```bash
 pip install debase
 ```
+
+### Development Setup with Conda (Recommended)
+
+1. **Clone the repository**
+```bash
+git clone https://github.com/YuemingLong/DEBase.git
+cd DEBase
+```
+
+2. **Create conda environment from provided file**
+```bash
+conda env create -f environment.yml
+conda activate debase
+```
+
+3. **Install DEBase in development mode**
+```bash
+pip install -e .
+```
+
+### Manual Setup
+
+If you prefer to set up the environment manually:
+
+```bash
+# Create new conda environment
+conda create -n debase python=3.9
+conda activate debase
+
+# Install conda packages
+conda install -c conda-forge pandas numpy matplotlib seaborn jupyter jupyterlab openpyxl biopython requests tqdm
+
+# Install RDKit (optional - used for SMILES canonicalization)
+conda install -c conda-forge rdkit
+
+# Install pip-only packages
+pip install PyMuPDF google-generativeai debase
+```
+
+**Note about RDKit**: RDKit is optional and only used for canonicalizing SMILES strings in the output. If not installed, DEBase will still function normally but SMILES strings won't be standardized.
+
 ## Requirements
 
 - Python 3.8 or higher
 - A Gemini API key (set as environment variable `GEMINI_API_KEY`)
 
+### Setting up Gemini API Key
+
+```bash
+# Option 1: Export in your shell
+export GEMINI_API_KEY="your-api-key-here"
+
+# Option 2: Add to ~/.bashrc or ~/.zshrc for persistence
+echo 'export GEMINI_API_KEY="your-api-key-here"' >> ~/.bashrc
+source ~/.bashrc
+
+# Option 3: Create .env file in project directory
+echo 'GEMINI_API_KEY=your-api-key-here' > .env
+```
+
 ## Recent Updates
 
 - **Campaign-Aware Extraction**: Automatically detects and processes multiple directed evolution campaigns in a single paper