🧪 ABD-Model

Atom and Bond Detection for Molecular Images

A YOLO-based deep learning model for detecting atoms and bonds in 2D molecular structure images.

---

📖 Overview

ABD-Model is a YOLO-based deep learning model designed to detect atoms (e.g., C, O, H, N) and bond types (single, double, triple) in molecular structure images. It extracts structured, machine-readable data from 2D molecular representations — making it a useful building block for computational chemistry pipelines, cheminformatics tools, and automated structure recognition workflows.

---

✨ Features

Feature	Description
🔬 Atom Detection	Detects atoms such as Carbon (C), Oxygen (O), Nitrogen (N), and Hydrogen (H) in molecular images
⚛️ Bond Detection	Identifies single, double, and triple bonds between atoms
🖼️ Versatility	Works across a wide variety of molecular structure image styles
⚡ YOLO-Based	Fast, accurate, single-pass object detection
🌍 Open Source	Easy to integrate, extend, and customize for your own projects

---

📦 Requirements

• Python 3.x
• PyTorch
• OpenCV (for image processing)
• NumPy
• Additional dependencies listed in requirements.txt

Install all dependencies with:

pip install -r requirements.txt

---

🚀 Installation

1. Clone this repository

git clone https://github.com/Safi-ullah-majid/ABD-model.git
cd ABD-model

2. Install dependencies

pip install -r requirements.txt

3. Download the model weights

Download the ABD.pt model file and place it in the correct directory (see project structure below).

---

🧠 Usage

Run predictions using the predict.py script:

python predict.py --input_path path/to/image.png

Before running, make sure:

• ✅ The input image is in .png format
• ✅ The model file (ABD.pt) is present and loads correctly
• ✅ The input image is a valid .png file representing a molecular structure

Example

python predict.py --input_path examples/aspirin.png

---

🗂️ Project Structure

ABD-model/
├── ABD.pt              # Pretrained model weights
├── predict.py           # Inference script
├── requirements.txt      # Python dependencies
├── LICENSE               # MIT License
└── README.md             # Project documentation

---

🤝 Contributing

Contributions, issues, and feature requests are welcome! Feel free to check the issues page or open a pull request.

---

📄 License

This repository is licensed under the MIT License — see the LICENSE file for details.

---

Made with 🧪 by Safi Ullah Majid