debase 0.6.1__tar.gz → 0.7.0__tar.gz

{debase-0.6.1/src/debase.egg-info → debase-0.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.6.1
+Version: 0.7.0
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.6.1 → debase-0.7.0}/src/debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.6.1"
+__version__ = "0.7.0"

{debase-0.6.1 → debase-0.7.0}/src/debase/caption_pattern.py

@@ -8,15 +8,20 @@ formats found in scientific papers, including:
 - Other types: Scheme 1, Chart 1
 - Page headers: S14 Table 5
 - Various punctuation: Figure 1. Figure 1: Figure 1 |
+- Inline captions: ...text Table 1. Caption text...
 """
 
 import re
 
 # Universal caption pattern that handles all common formats
+# Now includes both start-of-line and inline caption patterns
 UNIVERSAL_CAPTION_PATTERN = re.compile(
     r"""
-    ^                                      # Start of line
-    [^\n]{0,20}?                          # Up to 20 chars of any content (page headers, etc.)
+    (?:                                    # Non-capturing group for position
+        ^[^\n]{0,20}?                      # Start of line with up to 20 chars before
+    |                                      # OR
+        (?<=[a-zA-Z0-9\s])                # Look-behind for alphanumeric or space (for inline)
+    )
     (                                      # Start capture group
         (?:Extended\s+Data\s+)?           # Optional "Extended Data" prefix
         (?:ED\s+)?                        # Optional "ED" prefix

{debase-0.6.1 → debase-0.7.0}/src/debase/cleanup_sequence.py

@@ -1016,13 +1016,38 @@ Return ONLY valid JSON with information about the SINGLE BEST seed enzyme.
                         
                         if source_enzyme_id:
                             # Find the source enzyme's sequence in the dataframe
+                            # Prefer sequences from OTHER campaigns (not the current empty campaign)
                             source_rows = df[df['enzyme_id'] == source_enzyme_id]
                             if source_rows.empty:
                                 log.warning(f"Source enzyme {source_enzyme_id} not found in dataframe")
                             else:
-                                source_sequence = str(source_rows.iloc[0]['protein_sequence']).strip()
-                                if not source_sequence or source_sequence.lower() in ["nan", "none", ""]:
-                                    log.warning(f"Source enzyme {source_enzyme_id} has no sequence")
+                                # Look for a row with a sequence, preferring other campaigns
+                                source_sequence = None
+                                source_row_idx = None
+                                
+                                # First, try to find a row with sequence from a different campaign
+                                for idx, row in source_rows.iterrows():
+                                    seq = str(row['protein_sequence']).strip()
+                                    if seq and seq.lower() not in ["nan", "none", ""]:
+                                        # Check if this is from a different campaign
+                                        if row['campaign_id'] != campaign_id:
+                                            source_sequence = seq
+                                            source_row_idx = idx
+                                            log.info(f"Found source sequence for {source_enzyme_id} from campaign {row['campaign_id']}")
+                                            break
+                                
+                                # If not found in other campaigns, try any row with sequence
+                                if not source_sequence:
+                                    for idx, row in source_rows.iterrows():
+                                        seq = str(row['protein_sequence']).strip()
+                                        if seq and seq.lower() not in ["nan", "none", ""]:
+                                            source_sequence = seq
+                                            source_row_idx = idx
+                                            log.info(f"Found source sequence for {source_enzyme_id} from same campaign {row['campaign_id']}")
+                                            break
+                                
+                                if not source_sequence:
+                                    log.warning(f"Source enzyme {source_enzyme_id} has no sequence in any campaign")
                                 else:
                                     # Find the target enzyme in our empty list
                                     seed_found = False
@@ -1031,7 +1056,8 @@ Return ONLY valid JSON with information about the SINGLE BEST seed enzyme.
                                             if relationship_type == "EXACT_MATCH":
                                                 # Exact match - copy sequence directly
                                                 df.at[entry['idx'], 'protein_sequence'] = source_sequence
-                                                df.at[entry['idx'], 'flag'] = df.at[entry['idx'], 'flag'] + " gemini_cross_campaign_seed_exact"
+                                                current_flag = str(df.at[entry['idx'], 'flag']) if pd.notna(df.at[entry['idx'], 'flag']) else ""
+                                                df.at[entry['idx'], 'flag'] = current_flag + " gemini_cross_campaign_seed_exact"
                                                 log.info(f"Set seed sequence for {target_enzyme_id} from exact match {source_enzyme_id} (length: {len(source_sequence)})")
                                                 seed_found = True
                                                 
@@ -1045,7 +1071,8 @@ Return ONLY valid JSON with information about the SINGLE BEST seed enzyme.
                                                     
                                                     if success:
                                                         df.at[entry['idx'], 'protein_sequence'] = mutated_sequence
-                                                        df.at[entry['idx'], 'flag'] = df.at[entry['idx'], 'flag'] + " gemini_cross_campaign_seed_parent"
+                                                        current_flag = str(df.at[entry['idx'], 'flag']) if pd.notna(df.at[entry['idx'], 'flag']) else ""
+                                                        df.at[entry['idx'], 'flag'] = current_flag + " gemini_cross_campaign_seed_parent"
                                                         log.info(f"Set seed sequence for {target_enzyme_id} by applying mutations {target_mutations} to parent {source_enzyme_id} (length: {len(mutated_sequence)})")
                                                         seed_found = True
                                                     else:
@@ -1053,7 +1080,8 @@ Return ONLY valid JSON with information about the SINGLE BEST seed enzyme.
                                                 else:
                                                     # No mutations - use parent sequence directly
                                                     df.at[entry['idx'], 'protein_sequence'] = source_sequence
-                                                    df.at[entry['idx'], 'flag'] = df.at[entry['idx'], 'flag'] + " gemini_cross_campaign_seed_parent_no_mutations"
+                                                    current_flag = str(df.at[entry['idx'], 'flag']) if pd.notna(df.at[entry['idx'], 'flag']) else ""
+                                                    df.at[entry['idx'], 'flag'] = current_flag + " gemini_cross_campaign_seed_parent_no_mutations"
                                                     log.info(f"Set seed sequence for {target_enzyme_id} from parent {source_enzyme_id} (no mutations, length: {len(source_sequence)})")
                                                     seed_found = True
                                             break