debase 0.1.0__py3-none-any.whl → 0.1.1__py3-none-any.whl

debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.0"
+__version__ = "0.1.1"

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-0.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.0
+Version: 0.1.1
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.1.0.dist-info → debase-0.1.1.dist-info}/RECORD

@@ -1,17 +1,16 @@
-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=f_aADPF4S4TQJIdnkbAgxIqnOWgZS6TJ3X9EDBZt_OM,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/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-0.1.1.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.1.1.dist-info/METADATA,sha256=GI8WvSNVIllw_ZKLqlhy-rqtVHBun3ZG1hahEvO_BMo,11509
+debase-0.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.1.1.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.1.1.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.1.1.dist-info/RECORD,,

debase/PIPELINE_FLOW.md

@@ -1,100 +0,0 @@
-# DEBase Pipeline Flow
-
-## Overview
-The DEBase pipeline extracts enzyme engineering data from chemistry papers through a series of modular steps.
-
-## Pipeline Architecture
-
-```
-┌─────────────────────┐     ┌─────────────────────┐
-│   Manuscript PDF    │     │       SI PDF        │
-└──────────┬──────────┘     └──────────┬──────────┘
-           │                           │
-           └───────────┬───────────────┘
-                       │
-                       ▼
-         ┌─────────────────────────────┐
-         │ 1. enzyme_lineage_extractor │
-         │   - Extract enzyme variants │
-         │   - Parse mutations         │
-         │   - Get basic metadata      │
-         └─────────────┬───────────────┘
-                       │
-                       ▼
-         ┌─────────────────────────────┐
-         │    2. cleanup_sequence      │
-         │   - Validate sequences      │
-         │   - Fix formatting issues   │
-         │   - Generate full sequences │
-         └─────────────┬───────────────┘
-                       │
-           ┌───────────┴───────────────┐
-           │                           │
-           ▼                           ▼
-┌─────────────────────────┐ ┌─────────────────────────┐
-│ 3a. reaction_info       │ │ 3b. substrate_scope     │
-│     _extractor          │ │     _extractor          │
-│ - Performance metrics   │ │ - Substrate variations  │
-│ - Model reaction        │ │ - Additional variants   │
-│ - Conditions            │ │ - Scope data            │
-└───────────┬─────────────┘ └───────────┬─────────────┘
-            │                           │
-            └───────────┬───────────────┘
-                        │
-                        ▼
-          ┌─────────────────────────────┐
-          │    4. lineage_format_o3     │
-          │   - Merge all data          │
-          │   - Fill missing sequences  │
-          │   - Format final output     │
-          └─────────────┬───────────────┘
-                        │
-                        ▼
-                ┌─────────────┐
-                │ Final CSV   │
-                └─────────────┘
-```
-
-## Module Details
-
-### 1. enzyme_lineage_extractor.py
-- **Input**: Manuscript PDF, SI PDF
-- **Output**: CSV with enzyme variants and mutations
-- **Function**: Extracts enzyme identifiers, mutation lists, and basic metadata
-
-### 2. cleanup_sequence.py  
-- **Input**: Enzyme lineage CSV
-- **Output**: CSV with validated sequences
-- **Function**: Validates protein sequences, generates full sequences from mutations
-
-### 3a. reaction_info_extractor.py
-- **Input**: PDFs + cleaned enzyme CSV
-- **Output**: CSV with reaction performance data
-- **Function**: Extracts yield, TTN, selectivity, reaction conditions
-
-### 3b. substrate_scope_extractor.py
-- **Input**: PDFs + cleaned enzyme CSV  
-- **Output**: CSV with substrate scope entries
-- **Function**: Extracts substrate variations tested with different enzymes
-
-### 4. lineage_format_o3.py
-- **Input**: Reaction CSV + Substrate scope CSV
-- **Output**: Final formatted CSV
-- **Function**: Merges data, fills missing sequences, applies consistent formatting
-
-## Key Features
-
-1. **Modular Design**: Each step can be run independently
-2. **Parallel Extraction**: Steps 3a and 3b run independently 
-3. **Error Recovery**: Pipeline can resume from any step
-4. **Clean Interfaces**: Each module has well-defined inputs/outputs
-
-## Usage
-
-```bash
-# Full pipeline
-python -m debase.wrapper_clean manuscript.pdf --si si.pdf --output results.csv
-
-# With intermediate files kept for debugging  
-python -m debase.wrapper_clean manuscript.pdf --si si.pdf --keep-intermediates
-```