SFCalculator

This is the code repo related to manuscript SFCalculator: connecting deep generative models and crystallography

Structure Factor Calculator implemented in tensorflow2, pytorch and jax.

A differentiable pipeline connecting the protein atomic models and experimental structure factors, featuring a differentiable bulk solvent correction.

The symmetry-related nitty-gritty in both real space and reciprocal space are included.

Source codes

Source codes in three popular deep learning frameworks are provided in the following submodule repositories:

1. SFcalculator_torch, pytorch implementation.

2. SFcalculator_jax, jax implementation.

3. SFcalculator_tf, tensorflow2 implementation.

Note

The pytorch version is currently in active development, making it several versions ahead and the preferred choice.

Authors

Minhuan Li, minhuanli@flatironinstitute.org

Doeke R. Hekstra, doeke_hekstra@harvard.edu

Installation

Pytorch version

1. Create a python environment with package manager you like (mambaforge recommended).

2. Install Pytorch

3. Install SFcalculator-torch

   pip install SFcalculator-torch

Jax version

1. Create a python environment with package manager you like (mambaforge recommended).

2. Install Jax

3. Install SFcalculator-jax

   pip install SFcalculator-jax

Tensorflow 2 version

1. Create a python environment with package manager you like (mambaforge recommended).

2. Install Tensorflow2

3. Install SFcalculator-tf:

   pip install SFcalculator-tf

Tutorial

Here is a walkthrough tutorial page for PyTorch version: https://hekstra-lab.github.io/SFcalculator_torch/

Citation

@article{li2025sfcalculator,
  title={SFCalculator: connecting deep generative models and crystallography},
  author={Li, Minhuan and Dalton, Kevin M and Hekstra, Doeke Romke},
  journal={bioRxiv},
  pages={2025--01},
  year={2025},
  publisher={Cold Spring Harbor Laboratory}
}

Archive

A short version has been presented as Towards automated crystallographic structure refinement with a differentiable pipeline on Machine Learning in Structural Biology Workshop at NeurIPS 2022.