README.md

metadata

title: Microbial Susceptibility Analyzer
emoji: 👁
colorFrom: blue
colorTo: indigo
sdk: streamlit
sdk_version: 1.43.2
app_file: app.py
pinned: false
license: mit
thumbnail: >-
  https://cdn-uploads.huggingface.co/production/uploads/64774490312e3909019550f0/JWfMLBEIsP543Hu2G5yAR.jpeg

Microbial Susceptibility Analyzer

Overview

The Microbial Susceptibility Analyzer is a Streamlit-based web application that combines machine learning and rule-based decision making to predict antibiotic resistance patterns. The application provides:

• Susceptibility predictions for organism-antibiotic combinations
• Rule-based guidance for treatment decisions
• AI-powered explanations and recommendations
• Batch prediction capabilities for CSV datasets

Installation

1. Clone the repository:

git clone https://github.com/yourusername/microbial-susceptibility-analyzer.git
cd microbial-susceptibility-analyzer

2. Create a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows use: venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

4. Set up environment variables: Create a .streamlit/secrets.toml file with your API keys:

OPENAI_API_KEY = "your_openai_api_key"
OPENAI_BASE_URL = "https://api.openai.com/v1"

Usage

Run the application:

streamlit run app.py

The application provides several pages:

• Home: Project overview and introduction
• Susceptibility Analysis: Single prediction interface
• AI Assistant: Expert system for detailed explanations
• Data Upload: Batch prediction for CSV files
• About: Project information and contact details

File Structure

microbial-susceptibility-analyzer/
├── app.py                 # Main application file
├── prediction.py          # Prediction logic
├── ai_assistant.py        # AI integration
├── utils.py               # Utility functions
├── config.py              # Configuration settings
├── requirements.txt       # Python dependencies
├── README.md              # This documentation
├── label_encoders/        # Label encoding files
│   ├── organism_label_encoder.json
│   ├── antibiotic_label_encoder.json
│   └── ...
├── models/                # Trained models
│   ├── best_model.pkl
│   └── best_model_1.pkl
└── data/                  # Data files
    ├── implied_susceptibility_rules.csv
    └── microbiology_cultures_implied_susceptibility.csv

Configuration

The application requires the following configuration:

1. Model Path: Set in config.py
2. Encoder Directory: Set in config.py
3. OpenAI API: Configure in .streamlit/secrets.toml

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contact

For questions or support, contact:
Chukwuebuka Anulunko
[email protected]