debase 0.1.0__tar.gz → 0.1.1__tar.gz

{debase-0.1.0 → debase-0.1.1}/PKG-INFO

@@ -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 → debase-0.1.1}/src/debase/_version.py

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

{debase-0.1.0 → debase-0.1.1}/src/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 → debase-0.1.1}/src/debase.egg-info/PKG-INFO

@@ -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 → debase-0.1.1}/src/debase.egg-info/SOURCES.txt

@@ -1,15 +1,8 @@
-.gitignore
-CONTRIBUTING.md
 LICENSE
 MANIFEST.in
 README.md
-environment.yml
 pyproject.toml
 setup.py
-docs/README.md
-docs/examples/README.md
-src/__init__.py
-src/debase/PIPELINE_FLOW.md
 src/debase/__init__.py
 src/debase/__main__.py
 src/debase/_version.py

debase-0.1.0/.gitignore

@@ -1,177 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-.python-version
-
-# pipenv
-Pipfile.lock
-
-# poetry
-poetry.lock
-
-# pdm
-.pdm.toml
-
-# PEP 582
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-.idea/
-
-# VS Code
-.vscode/
-
-# macOS
-.DS_Store
-.AppleDouble
-.LSOverride
-
-# Windows
-Thumbs.db
-Thumbs.db:encryptable
-ehthumbs.db
-ehthumbs_vista.db
-*.stackdump
-[Dd]esktop.ini
-$RECYCLE.BIN/
-*.cab
-*.msi
-*.msix
-*.msm
-*.msp
-*.lnk
-
-# Linux
-*~
-
-# Temporary files
-*.tmp
-*.temp
-*.log
-.temp_*/
-.cache/
-
-# DEBase specific
-enzyme_pipeline*.log
-temp_merged_input.csv
-*.egg-info/
-
-# Project data and examples
-data/
-examples/
-!examples/test.csv  # Keep test.csv as example output
-
-# Cache files
-*.pkl
-*_cache.pkl
-
-# Large database files
-*.db
-
-# PDFs and Excel files
-*.pdf
-*.xlsx
-
-# Backup files
-*_backup.py
-lineage_format_backup.py
-
-# Temporary directories
-.temp_*
-enzyme_analysis_*

debase-0.1.0/CONTRIBUTING.md

@@ -1,61 +0,0 @@
-# Contributing to DEBase
-
-Thank you for your interest in contributing to DEBase!
-
-## Development Setup
-
-1. Clone the repository:
-```bash
-git clone https://github.com/yourusername/debase.git
-cd debase
-```
-
-2. Create a virtual environment:
-```bash
-python -m venv venv
-source venv/bin/activate  # On Windows: venv\Scripts\activate
-```
-
-3. Install in development mode:
-```bash
-pip install -e ".[dev]"
-```
-
-## Running Tests
-
-```bash
-pytest tests/
-```
-
-## Code Style
-
-We use Black for code formatting:
-```bash
-black src/ tests/
-```
-
-And isort for import sorting:
-```bash
-isort src/ tests/
-```
-
-## Project Structure
-
-```
-debase/
-├── src/debase/           # Main package source code
-├── tests/               # Test suite
-├── docs/               # Documentation
-├── examples/           # Example outputs and usage
-├── data/              # Research data (PDFs)
-└── scripts/           # Utility scripts
-```
-
-## Submitting Changes
-
-1. Fork the repository
-2. Create a feature branch
-3. Make your changes
-4. Add tests if applicable
-5. Run the test suite
-6. Submit a pull request

debase-0.1.0/docs/README.md

@@ -1,19 +0,0 @@
-# DEBase Documentation
-
-This directory contains comprehensive documentation for the DEBase enzyme analysis pipeline.
-
-## Directory Structure
-
-- `api/` - API documentation and reference
-- `examples/` - Usage examples and tutorials  
-- `tutorials/` - Step-by-step guides
-
-## Quick Start
-
-See the main [README.md](../README.md) for installation and basic usage.
-
-## Contents
-
-1. [Installation Guide](tutorials/installation.md)
-2. [API Reference](api/README.md)
-3. [Usage Examples](examples/README.md)

debase-0.1.0/docs/examples/README.md

@@ -1,24 +0,0 @@
-# DEBase Examples
-
-This directory contains example outputs and usage demonstrations for the DEBase pipeline.
-
-## Example Outputs
-
-The `../../examples/` directory contains sample results from successful pipeline runs:
-
-- `trpb_complete_pipeline.csv` - Complete TrpB enzyme dataset with sequences, mutations, and reactions
-- `carbene_complete_pipeline.csv` - Carbene transfer enzyme data with SMILES and conditions  
-- `REFINED_ENZYME_SEQUENCES.csv` - Refined sequence extraction results
-
-## Data Format
-
-Each CSV contains:
-- Full-length protein sequences (200-400+ amino acids)
-- Complete mutation lineage tracking
-- Chemical reaction SMILES strings
-- Experimental conditions and metadata
-- Performance metrics (yield, TTN, enantioselectivity)
-
-## Usage
-
-These files demonstrate the expected output format and can be used as reference for pipeline validation.

debase-0.1.0/environment.yml

@@ -1,21 +0,0 @@
-name: debase
-channels:
-  - conda-forge
-  - defaults
-dependencies:
-  - python=3.9
-  - pandas>=1.0.0
-  - numpy>=1.19.0
-  - matplotlib>=3.3.0
-  - seaborn>=0.11.0
-  - jupyter>=1.0.0
-  - jupyterlab>=3.0.0
-  - openpyxl>=3.0.0
-  - biopython>=1.78
-  - requests>=2.25.0
-  - tqdm>=4.60.0
-  - rdkit>=2020.03.1
-  - pip
-  - pip:
-    - PyMuPDF>=1.18.0
-    - google-generativeai>=0.3.0

debase-0.1.0/src/__init__.py

@@ -1 +0,0 @@
-

debase-0.1.0/src/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
-```