%0 Journal Article %1 mostosi_haruspex_nodate %A Mostosi, Philipp %A Schindelin, Hermann %A Kollmannsberger, Philip %A Thorn, Andrea %D 2020 %J Angewandte Chemie International Edition %K cctb computationalimageanalysis imported philipkollmannsberger %N n/a %R 10.1002/anie.202000421 %T Haruspex: A Neural Network for the Automatic Identification of Oligonucleotides and Protein Secondary Structure in Cryo-Electron Microscopy Maps %U https://onlinelibrary.wiley.com/doi/abs/10.1002/anie.202000421 %V n/a %X 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.

@article{mostosi_haruspex_nodate, 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.}, added-at = {2020-06-05T16:14:26.000+0200}, author = {Mostosi, Philipp and Schindelin, Hermann and Kollmannsberger, Philip and Thorn, Andrea}, biburl = {https://www.bibsonomy.org/bibtex/27345e85ac4705c1f0ee6eff4b5a50c34/philipk}, copyright = {© 2020 The Authors. Published by Wiley-VCH Verlag GmbH \& Co. KGaA.}, doi = {10.1002/anie.202000421}, file = {Full Text PDF:/Users/philip/Zotero/storage/5IDXG6C5/Mostosi et al. - Haruspex A Neural Network for the Automatic Ident.pdf:application/pdf;Snapshot:/Users/philip/Zotero/storage/3GDPGHII/anie.html:text/html}, interhash = {a146fc9c38775f6a79aa0f94f5328a50}, intrahash = {7345e85ac4705c1f0ee6eff4b5a50c34}, issn = {1521-3773}, journal = {Angewandte Chemie International Edition}, keywords = {cctb computationalimageanalysis imported philipkollmannsberger}, language = {en}, note = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/anie.202000421}, number = {n/a}, shorttitle = {Haruspex}, timestamp = {2020-06-05T16:14:26.000+0200}, title = {Haruspex: {A} {Neural} {Network} for the {Automatic} {Identification} of {Oligonucleotides} and {Protein} {Secondary} {Structure} in {Cryo}-{Electron} {Microscopy} {Maps}}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/anie.202000421}, urldate = {2020-06-05}, volume = {n/a}, year = 2020 }