debase 0.4.1__py3-none-any.whl → 0.4.3__py3-none-any.whl

debase/wrapper.py

@@ -120,25 +120,36 @@ def run_sequence_cleanup(input_csv: Path, output_csv: Path) -> Path:
 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
+    Calls: reaction_info_extractor.py main function to get full functionality including campaign CSV saving
     Returns output path even if extraction fails (creates empty file)
     """
     logger.info(f"Extracting reaction info for enzymes in {lineage_csv.name}")
     
     try:
-        from .reaction_info_extractor import ReactionExtractor, Config
-        import pandas as pd
+        import sys
+        
+        # Call reaction_info_extractor.main() directly in same process for token tracking
+        old_argv = sys.argv
+        sys.argv = [
+            "reaction_info_extractor",
+            "--manuscript", str(manuscript),
+            "--lineage-csv", str(lineage_csv),
+            "--output", str(output)
+        ]
+        
+        # Add optional arguments
+        if si:
+            sys.argv.extend(["--si", str(si)])
+        if debug_dir:
+            sys.argv.extend(["--debug-dir", str(debug_dir)])
         
-        # Load enzyme data
-        enzyme_df = pd.read_csv(lineage_csv)
+        # Import and call main() directly
+        from .reaction_info_extractor import main
+        main()
         
-        # Initialize extractor and run
-        cfg = Config()
-        extractor = ReactionExtractor(manuscript, si, cfg, debug_dir=debug_dir)
-        df_metrics = extractor.run(enzyme_df)
+        # Restore original argv
+        sys.argv = old_argv
         
-        # Save results
-        df_metrics.to_csv(output, index=False)
         logger.info(f"Reaction extraction complete: {output}")
         return output
         
@@ -156,6 +167,21 @@ def run_reaction_extraction(manuscript: Path, si: Path, lineage_csv: Path, outpu
         
         logger.info(f"Empty reaction file created: {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:

{debase-0.4.1.dist-info → debase-0.4.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.4.1
+Version: 0.4.3
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

debase-0.4.3.dist-info/RECORD

@@ -0,0 +1,16 @@
+debase/__init__.py,sha256=YeKveGj_8fwuu5ozoK2mUU86so_FjiCwsvg1d_lYVZU,586
+debase/__main__.py,sha256=LbxYt2x9TG5Ced7LpzzX_8gkWyXeZSlVHzqHfqAiPwQ,160
+debase/_version.py,sha256=r0b4fvQcrrvOScFMddjVgWAGNt17iQxCJH2xYW06jio,49
+debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
+debase/cleanup_sequence.py,sha256=4qZrSXInyJKEJqcgcONp4IX24ALEj5lf7E0XaOZVxZ0,40329
+debase/enzyme_lineage_extractor.py,sha256=tFyrcWkNKKr8T9xq0tIXUDNfcX0tbdWGrLhgo5m7lmA,129804
+debase/lineage_format.py,sha256=Q6kpqKPUxJsMYpb0Yt8IbVlp6VDYX2vkITuGhT9MEbw,47056
+debase/reaction_info_extractor.py,sha256=q-iHgfVLXP4r2Se8yA9I0AvtnAhHBltTztrXspl3EKU,151949
+debase/substrate_scope_extractor.py,sha256=eaVimhxmmaRj-9dRN6RKK4yStCmZAuX8xBaarsIsmUo,114212
+debase/wrapper.py,sha256=r0xxoiBvmMIktiGPOD4w9hne8m0SLzZ03WeWnBuDW0A,25236
+debase-0.4.3.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.4.3.dist-info/METADATA,sha256=UT8ymX3oothXvgA9ayr74_Bd-St7I0Pj7CoEg8LlKg8,10789
+debase-0.4.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.4.3.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.4.3.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.4.3.dist-info/RECORD,,

debase-0.4.1.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=qJBDmAhFTv4pYwvc3Umy_Lwc_v8doVBVCiysT7Eoh3E,49
-debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
-debase/cleanup_sequence.py,sha256=ngxb_tPekjCWvampAjyuFqK4wLk_meFSj_TwfvOxheQ,33978
-debase/enzyme_lineage_extractor.py,sha256=laIw9A5AuJ_kJe9h6Fp_WzMh_ctCN31bo2b2-RKrFd4,124019
-debase/lineage_format.py,sha256=IS9ig-Uv7KxtI9enZKM6YgQ7sitqwOo4cdXbOy38J3s,34232
-debase/reaction_info_extractor.py,sha256=xRyYoQKqSzer-k8FZwg55nDd0D-6QBc0F-HAyfvisG0,150368
-debase/substrate_scope_extractor.py,sha256=JLXHEEeMDFiFQRt8gVCnnhimrxDF23-z0jq3N4-3gn8,101469
-debase/wrapper.py,sha256=TGU5eq0qWTrkRR35ztsp8WMb1E9Nt64BdbHuYHROmYA,24279
-debase-0.4.1.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
-debase-0.4.1.dist-info/METADATA,sha256=kSH58QfBv6WGb8Ds3mcei-DUmWQormuSyPHNOmpbcQ8,10789
-debase-0.4.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-debase-0.4.1.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
-debase-0.4.1.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
-debase-0.4.1.dist-info/RECORD,,