Biology subjects

Vos, R. A.

Publications and source records attributed to Vos, R. A..

5 recordsLinked to original sources

bioRxiv2018

Taxonomic Classification of Ants (Formicidae) from Images using Deep Learning

The well-documented, species-rich, and diverse group of ants (Formicidae) are important ecological bioindicators for species richness, ecosystem health, and biodiversity, but ant species identification is complex and requires specific knowledge. In the past few years, insect identification from images has seen increasing interest and success, with processing speed improving and costs lowering. Here we propose deep learning (in the form of a convolutional neural network (CNN)) to classify ants at species level using AntWeb images. We used an Inception-ResNet-V2-based CNN to classify ant images, and three shot types with 10,204 images for 97 species, in addition to a multi-view approach, for training and testing the CNN while also testing a worker-only set and an AntWeb protocol-deviant test set. Top 1 accuracy reached 62% - 81%, top 3 accuracy 80% - 92%, and genus accuracy 79% - 95% on species classification for different shot type approaches. The head shot type outperformed other shot type approaches. Genus accuracy was broadly similar to top 3 accuracy. Removing reproductives from the test data improved accuracy only slightly. Accuracy on AntWeb protocol-deviant data was very low. In addition, we make recommendations for future work concerning image threshold, distribution, and quality, multi-view approaches, metadata, and on protocols; potentially leading to higher accuracy with less computational effort.

bioinformatics↗

bioRxiv2018

Image analysis for taxonomic identification of Javanese butterflies

Taxonomic experts classify millions of specimens, but this is very time-consuming and therefore expensive. Image analysis is a way to automate identification and was previously done at Naturalis Biodiversity Center for slipper orchids (Cypripedioideae) by the program OrchID. This program operated by extracting a pre-defined number of features from images, and these features were used to train artificial neural networks (ANN) to classify out-of-sample images. This program was extended to work for a collection of Javanese butterflies, donated to Naturalis by the Van Groenendael-Krijger Foundation. Originally, for the orchids, an image was divided into a pre-defined number of horizontal and vertical bins and the mean blue-green-red values of each bin were calculated (BGR method) to obtain image features. In the extended implementation, characteristic image features were extracted using the SURF algorithm implemented in OpenCV and clustered with the BagOfWords method (SURF-BOW method). In addition, a combination of BGR- and SURF-BOW was implemented to extract both types of features in a single dataset (BGR-SURF method). A selection of the butterfly and orchid images was made to create datasets with at least 5 and at most 50 specimens per species. The SURF-BOW and BGR-SURF methods were applied to both selected datasets, and the original BGR method was applied to the selected butterfly dataset. PCA plots were made to inspect visually how well the applied methods discriminated among the species. For the butterflies, both genus and species appeared to cluster together in the plots of the SURF-BOW method. However, no obvious clustering was noticeable for the orchid plots. The performance of the ANNs was validated by a stratified k-fold cross validation. For the butterflies, the BGR-SURF method scored best with an accuracy of 77%, against 71% for the SURF-BOW method and 66% for the BGR method, all for chained genus and species prediction with k = 10. The new methods could not improve the accuracy of the orchid classification with k = 10, which was 75% on genus, 52% on genus and section and 48% on genus, section and species in the original framework and now less than 25% for all. The validation results also showed that at least about 15 specimens per species were necessary for a good prediction with the SURF-BOW method. The BGR-SURF method was found to be the best of these methods for butterflies, but the original BGR method was best for the slipper orchids. In the future these methods may be tested with other datasets, for example with mosquitoes. In addition, other classifiers may be tested for better performance, like support vector machines.

bioinformatics↗

bioRxiv2018

TreeBASEdmp: A Toolkit for Phyloinformatic Research

Over the last 20 years, TreeBASE has acquired a substantial body of phylogenetic data, including more than 20,000 published phylogenies. Given latency issues and limited options when it comes to querying the database remotely, a simplified and consolidated version of the database, here called TreeBASEdmp, is made available for download, allowing biologists to design custom analyses of the data on their local computers. The database is indexed to support searching for phylogenetic topologies using nested sets and closure tables. Here we propose a new approach to find broadly-defined phylogenetic patterns, a method we call Generic Topological Querying, which allows the user to find hypotheses of relationship without being constrained to use particular sets of specific taxa. Additionally, we normalize as many leaf nodes as possible to an equivalent species rank identifier to assist in supertree synthesis. Our example script rapidly assembles sets of trees and generates a matrix representation of them for subsequent supertree generation.

evolutionary biology↗

bioRxiv2017

Evolutionary dynamics of mycorrhizal symbiosis in land plant diversification

Mycorrhizal symbiosis between soil fungi and land plants is one of the most widespread and ecologically important mutualisms on earth. It has long been hypothesized that the Glomeromycotina, the mycorrhizal symbionts of the majority of plants, facilitated colonization of land by plants in the Ordovician. This view was recently challenged by the discovery of mycorrhizal associations with Mucoromycotina in several early diverging lineages of land plants. Utilizing a large, species-level database of plants mycorrhizal associations and a Bayesian approach to state transition dynamics we here show that the recruitment of Mucoromycotina is the best supported transition from a non-mycorrhizal state. We further found that transitions between different combinations of either or both of Mucoromycotina and Glomeromycotina occur at high rates and found similar promiscuity among combinations that include either or both of Glomeromycotina and Ascomycota with a nearly fixed association with Basidiomycota. Our results demonstrate that under the most likely scenario symbiosis with Mucoromycotina enabled the establishment of early land plants.

evolutionary biology↗

bioRxiv2017

The Bio::Phylo libraries for phylogenetic data analysis, version 2.0

MotivationPhylogenetic analysis is a broad and expanding field that requires versatile programming toolkits to manage the various data types, file formats, and needs for scalability, simulation, visualization, and data exploration.\n\nResultsWe present version 2.0 of the Bio::Phylo libraries for phylogenetic data analysis. This new release represents a rewrite of the architecture, allowing for extensions that improve speed and persistence, as well as increased functionality in terms of analysis, data reading and writing, and visualization.\n\nAvailabilityThe package is released as open source software under the same terms as Perl itself and available from the comprehensive Perl archive network as well as directly from the source code repository.\n\nContactrutger.vos@naturalis.nl\n\nSupplementary informationSupplementary data are available as doi:10.5281/zenodo.1039210

bioinformatics↗