debase 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.2"
+__version__ = "0.1.4"

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}")
@@ -1297,6 +1318,8 @@ _SEQUENCE_SCHEMA_HINT = """
 _SEQ_LOC_PROMPT = """
 Find where FULL-LENGTH protein or DNA sequences are located in this document.
 
+PRIORITY: Protein/amino acid sequences are preferred over DNA sequences.
+
 Look for table of contents entries or section listings that mention sequences.
 Return a JSON array where each element has:
 - "section": the section heading or description
@@ -1305,6 +1328,7 @@ Return a JSON array where each element has:
 Focus on:
 - Table of contents or entries about "Sequence Information" or "Nucleotide and amino acid sequences"
 - Return the EXACT notation as shown.
+- Prioritize sections that mention "protein" or "amino acid" sequences
 
 Return [] if no sequence sections are found.
 Absolutely don't include nucleotides or primer sequences, it is better to return nothing then incomplete sequence, use your best judgement.
@@ -1465,10 +1489,16 @@ def validate_sequence_locations(text: str, locations: list, model, *, pdf_paths:
 # --- 7.3  Main extraction prompt ---------------------------------------------
 _SEQ_EXTRACTION_PROMPT = """
 Extract EVERY distinct enzyme-variant sequence you can find in the text.
+
+IMPORTANT: Prioritize amino acid (protein) sequences over DNA sequences:
+- If an amino acid sequence exists for a variant, extract ONLY the aa_seq (set dna_seq to null)
+- Only extract dna_seq if NO amino acid sequence is available for that variant
+- This reduces redundancy since protein sequences are usually more relevant
+
 For each variant return:
   * variant_id  - the label used in the paper (e.g. "R4-10")
   * aa_seq      - amino-acid sequence (uppercase), or null
-  * dna_seq     - DNA sequence (A/C/G/T), or null
+  * dna_seq     - DNA sequence (A/C/G/T), or null (ONLY if no aa_seq exists)
 
 Respond ONLY with **minified JSON** that matches the schema below.
 NO markdown, no code fences, no commentary.
@@ -2029,8 +2059,15 @@ 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/reaction_info_extractor.py

@@ -1055,7 +1055,20 @@ Different campaigns may use different model reactions.
         """Extract text around a given location identifier."""
         location_lower = location.lower()
         
-        # Search in all pages
+        # Handle compound locations like "Figure 2 caption and Section I"
+        # Extract the first figure/table/scheme reference
+        figure_match = re.search(r"(figure|scheme|table)\s*\d+", location_lower)
+        if figure_match:
+            primary_location = figure_match.group(0)
+            # Try to find this primary location first
+            for page_text in self.all_pages:
+                if primary_location in page_text.lower():
+                    idx = page_text.lower().index(primary_location)
+                    start = max(0, idx - 500)
+                    end = min(len(page_text), idx + 3000)
+                    return page_text[start:end]
+        
+        # Search in all pages for exact match
         for page_text in self.all_pages:
             if location_lower in page_text.lower():
                 # Find the location and extract context around it

{debase-0.1.2.dist-info → debase-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.2
+Version: 0.1.4
 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-0.1.2.dist-info → debase-0.1.4.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=rPOdIIhUKYST-L457GFA8SWkOdMGZQAiiaWLSYHnVwc,49
+debase/_version.py,sha256=mcDHWqAxAKwMNAAyHmpWVDTK-zafQ1kQjmiwnsZbUD4,49
 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/enzyme_lineage_extractor.py,sha256=s1kPOomvJjfMSN5odxeyXNmxiaOzXyOZICr4YUWU6j8,89288
 debase/lineage_format.py,sha256=mACni9M1RXA_1tIyDZJpStQoutd_HLG2qQMAORTusZs,30045
-debase/reaction_info_extractor.py,sha256=vgXE4eFSmRUU_RPsW7E0vbP5mU0tjrhwk7UVqz_98yM,111469
+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-0.1.2.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,,
+debase-0.1.4.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.1.4.dist-info/METADATA,sha256=fZwXCP1i1s0VNq7Ds5bd2ys3pONgaV1XCe_edUkQdRU,10789
+debase-0.1.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.1.4.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.1.4.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.1.4.dist-info/RECORD,,