A deep learning solution for crystallographic structure determination

The general de novo solution of the crystallographic phase problem is difficult and only possible under certain conditions. This paper develops an initial pathway to a deep learning neural network approach for the phase problem in protein crystallography, based on a synthetic dataset of small fragments derived from a large well curated subset of solved structures in the Protein Data Bank (PDB). In particular, electron-density estimates of simple artificial systems are produced directly from corresponding Patterson maps using a convolutional neural network architecture as a proof of concept.

Automated summary

This paper develops an initial pathway to a deep learning neural network approach for solving the phase problem in protein crystallography. It uses a synthetic dataset of small fragments derived from a well curated subset of solved structures in the Protein Data Bank (PDB), and produces electron density estimates of simple artificial systems directly from corresponding Patterson maps using a convolutional neural network architecture as a proof of concept.