torchref 0.4.2

Pytorch based crystallographic refinement

TorchRef

A PyTorch-based crystallographic refinement library

TorchRef is a crystallographic refinement package built entirely on PyTorch. By leveraging PyTorch's automatic differentiation and GPU acceleration, TorchRef enables seamless integration with machine learning workflows and provides a flexible, extensible framework for crystallographic structure refinement.

Key Features

• Native PyTorch Integration: Built on PyTorch's nn.Module architecture, TorchRef integrates naturally with the PyTorch ecosystem, including machine learning models, optimizers, and GPU acceleration.

• Automatic Differentiation: Dynamic computational graphs eliminate the need for manually implemented gradient calculations. Define new refinement targets directly—PyTorch handles the derivatives automatically.

• Modular Architecture: Following PyTorch's module pattern, components are easily composable and extensible. Add custom targets, restraints, or optimizers without modifying core code.

• GPU Acceleration: Leverage CUDA for structure factor calculations, scaling, and optimization—achieving significant speedups for large structures.

• FFT-based Structure Factors: Efficient structure factor calculation using Fast Fourier Transform (FFT) methods, enabling rapid F_calc computation even for large unit cells.

• State Management: Full state_dict support enables saving and loading complete refinement states, including model parameters, scaler settings, and restraints.

Getting Started

Notebook	Description
	Basic Usage - Getting started tutorial
	Code Examples - Common patterns and recipes
	Target Exploration - Exploring refinement targets
	Structure Factor Calculation - FFT-based F_calc

Installation

pip install torchref

Local installation for development

clone the repository

git clone https://github.com/HatPdotS/TorchRef.git cd torchref

Install with pip

pip install -e .

Or install with development dependencies

pip install -e ".[dev]"

Dependencies

• Python ≥ 3.10
• PyTorch ≥ 2.40
• NumPy ≥ 2.0
• Gemmi ≥ 0.5
• reciprocalspaceship ≥ 0.9
• SciPy ≥ 1.7

Testing

# Run all tests
pytest tests/

# Run with coverage
pytest tests/ --cov=torchref

# Run specific test categories
pytest tests/unit/           # Fast unit tests
pytest tests/integration/    # Integration tests
pytest tests/functional/     # Full workflow tests

Contributing

Contributions are welcome! Please follow these guidelines:

1. Follow the NumPy docstring style
2. Add tests for new functionality
3. Ensure all tests pass before submitting

License

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