TY - JOUR A1 - Mostosi, Philipp A1 - Schindelin, Hermann A1 - Kollmannsberger, Philip A1 - Thorn, Andrea T1 - Haruspex: A Neural Network for the Automatic Identification of Oligonucleotides and Protein Secondary Structure in Cryo‐Electron Microscopy Maps JF - Angewandte Chemie International Edition N2 - 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. KW - DNA structures KW - electron microscopy KW - neural networks KW - protein structures KW - RNA structures Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-214763 VL - 59 IS - 35 SP - 14788 EP - 14795 ER - TY - JOUR A1 - Hagge, Jonas A1 - Müller, Jörg A1 - Birkemoe, Tone A1 - Buse, Jörn A1 - Christensen, Rune Haubo Bojesen A1 - Gossner, Martin M. A1 - Gruppe, Axel A1 - Heibl, Christoph A1 - Jarzabek‐Müller, Andrea A1 - Seibold, Sebastian A1 - Siitonen, Juha A1 - Soutinho, João Gonçalo A1 - Sverdrup‐Thygeson, Anne A1 - Thorn, Simon A1 - Drag, Lukas T1 - What does a threatened saproxylic beetle look like? Modelling extinction risk using a new morphological trait database JF - Journal of Animal Ecology N2 - The extinction of species is a non‐random process, and understanding why some species are more likely to go extinct than others is critical for conservation efforts. Functional trait‐based approaches offer a promising tool to achieve this goal. In forests, deadwood‐dependent (saproxylic) beetles comprise a major part of threatened species, but analyses of their extinction risk have been hindered by the availability of suitable morphological traits. To better understand the mechanisms underlying extinction in insects, we investigated the relationships between morphological features and the extinction risk of saproxylic beetles. Specifically, we hypothesised that species darker in colour, with a larger and rounder body, a lower mobility, lower sensory perception and more robust mandibles are at higher risk. We first developed a protocol for morphological trait measurements and present a database of 37 traits for 1,157 European saproxylic beetle species. Based on 13 selected, independent traits characterising aspects of colour, body shape, locomotion, sensory perception and foraging, we used a proportional‐odds multiple linear mixed‐effects model to model the German Red List categories of 744 species as an ordinal index of extinction risk. Six out of 13 traits correlated significantly with extinction risk. Larger species as well as species with a broad and round body had a higher extinction risk than small, slim and flattened species. Species with short wings had a higher extinction risk than those with long wings. On the contrary, extinction risk increased with decreasing wing load and with higher mandibular aspect ratio (shorter and more robust mandibles). Our study provides new insights into how morphological traits, beyond the widely used body size, determine the extinction risk of saproxylic beetles. Moreover, our approach shows that the morphological characteristics of beetles can be comprehensively represented by a selection of 13 traits. We recommend them as a starting point for functional analyses in the rapidly growing field of ecological and conservation studies of deadwood. KW - deadwood KW - extinction risk KW - forest biodiversity KW - forestry KW - functional traits KW - morphometry KW - red lists KW - saproxylic beetles Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-244717 VL - 90 IS - 8 SP - 1934 EP - 1947 ER -