Automated interpretation of Cryo-EM density maps with convolutional neural networks

Philipp Mostosi, Hermann Schindelin, Philip Kollmannsberger, Andrea Thorn

Jul 24, 2019

Received Date: 4th July 19

Haruspex is a fully convolutional neural network that automatically annotates both protein secondary structure and nucleotides in experimentally derived Cryo-EM maps. The network was trained on a carefully curated dataset of EMDB (Electron Microscopy Data Bank) entries. Haruspex enables users to identify folds and can be used to guide model building as well as validate structures.

Read in full at bioRxiv.

This is an abstract of a preprint hosted on an independent third party site. It has not been peer reviewed but is currently under consideration at Nature Communications.

Nature Communications

Nature Research, Springer Nature