Haruspex: A Neural Network for the Automatic Identification of Oligonucleotides and Protein Secondary Structure in Cryo‐Electron Microscopy Maps. Issue 35 (11th May 2020)

• Record Type: Journal Article
• Authors: Mostosi, Philipp; Schindelin, Hermann; Kollmannsberger, Philip; Thorn, Andrea
• Is Part Of: Angewandte Chemie international edition. Volume 59:Issue 35(2020)
• Page Start: 14788
• Page End: 14795
• Publication Date: 2020-05-11
• Subjects: DNA structures -- electron microscopy -- neural networks -- protein structures -- RNA structures; Chemistry -- Periodicals; 540
• DOI: 10.1002/anie.202000421
• Languages: English
• ISSNs: 1433-7851

Abstract

Abstract: In recent years, three‐dimensional density maps reconstructed from single particle images obtained by electron cryo‐microscopy (cryo‐EM) have reached unprecedented resolution. However, map interpretation can be challenging, in particular if the constituting structures require de‐novo model building or are very mobile. Herein, we demonstrate the potential of convolutional neural networks for the annotation of cryo‐EM maps: our network Haruspex has been trained on a carefully curated set of 293 experimentally derived reconstruction maps to automatically annotate RNA/DNA as well as protein secondary structure elements. It can be straightforwardly applied to newly reconstructed maps in order to support domain placement or as a starting point for main‐chain placement. Due to its high recall and precision rates of 95.1 % and 80.3 %, respectively, on an independent test set of 122 maps, it can also be used for validation during model building. The trained network will be available as part of the CCP‐EM suite. Abstract : Haruspex is a new tool to identify secondary structure and RNA/DNA in cryo‐EM reconstruction maps. It uses a neural network which has been trained on a carefully curated set of 293 experimentally derived reconstructions and can be straightforwardly applied to newly reconstructed maps to support model building and validation.