Determining the structure of a protein has been a decades-long open question. A protein's three-dimensional structure often poses nontrivial computation costs, when classical simulation algorithms are utilized. Advances in the transformer neural network architecture -- such as AlphaFold2 -- achieve significant improvements for this problem, by learning from a large dataset of sequence information and corresponding protein structures. Yet, such methods only focus on sequence information; other available prior knowledge, such as protein crystallography and partial structure of amino acids, could be potentially utilized. To the best of our knowledge, we propose the first transformer-based model that directly utilizes protein crystallography and partial structure information to predict the electron density maps of proteins. Via two new datasets of peptide fragments (2-residue and 15-residue) , we demonstrate our method, dubbed \texttt{CrysFormer}, can achieve accurate predictions, based on a much smaller dataset size and with reduced computation costs.
@article{arxiv.2310.03899,
title = {CrysFormer: Protein Structure Prediction via 3d Patterson Maps and Partial Structure Attention},
author = {Chen Dun and Qiutai Pan and Shikai Jin and Ria Stevens and Mitchell D. Miller and George N. Phillips, and Anastasios Kyrillidis},
journal= {arXiv preprint arXiv:2310.03899},
year = {2023}
}