Proteins are dynamic, adopting ensembles of conformations. The nature of this conformational heterogenity is imprinted in the raw electron density measurements obtained from X-ray crystallography experiments. Fitting an ensemble of protein structures to these measurements is a challenging, ill-posed inverse problem. We propose a non-i.i.d. ensemble guidance approach to solve this problem using existing protein structure generative models and demonstrate that it accurately recovers complicated multi-modal alternate protein backbone conformations observed in certain single crystal measurements.
@article{arxiv.2412.13223,
title = {Generative modeling of protein ensembles guided by crystallographic electron densities},
author = {Sai Advaith Maddipatla and Nadav Bojan Sellam and Sanketh Vedula and Ailie Marx and Alex Bronstein},
journal= {arXiv preprint arXiv:2412.13223},
year = {2024}
}