- Browse by Subject
Browsing by Subject "Insects"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Classifying the Unknown: Identification of Insects by Deep Open-set Bayesian Learning(bioRxiv, 2021-09-17) Badirli, Sarkhan; Picard, Christine J.; Mohler, George; Akata, Zeynep; Dundar, MuratInsects represent a large majority of biodiversity on Earth, yet only 20% of the estimated 5.5 million insect species are currently described (1). While describing new species typically requires specific taxonomic expertise to identify morphological characters that distinguish it from other potential species, DNA-based methods have aided in providing additional evidence of separate species (2). Machine learning (ML) is emerging as a potential new approach in identifying new species, given that this analysis may be more sensitive to subtle differences humans may not process. Existing ML algorithms are limited by image repositories that do not include undescribed species. We developed a Bayesian deep learning method for the open-set classification of species. The proposed approach forms a Bayesian hierarchy of species around corresponding genera and uses deep embeddings of images and barcodes together to identify insects at the lowest level of abstraction possible. To demonstrate proof of concept, we used a database of 32,848 insect instances from 1,040 described species split into training and test data. The test data included 243 species not present in the training data. Our results demonstrate that using DNA sequences and images together, insect instances of described species can be classified with 96.66% accuracy while achieving accuracy of 81.39% in identifying genera of insect instances of undescribed species. The proposed deep open-set Bayesian model demonstrates a powerful new approach that can be used for the gargantuan task of identifying new insect species.Item Comparative genomics of the sheep blow fly Lucilia cuprina(Office of the Vice Chancellor for Research, 2016-04-08) Picard, Christine J.; Andere, Anne A.Insects employ different adaptive strategies in response to selective pressures, such as competition for limited resources. Carrion insects provide the ideal case to study these fundamental processes of adaptive evolution due to the intense selective pressures placed on developing larvae with limited food resources, their widespread and abundant distributions, and the presence of geographically distinct populations with specialized adaptations. One adaptation is facultative ectoparasitism, where the insect strikes a healthy animal and feeds on the living flesh, providing a developmental advantage over competitor fly species, but causing significant harm to the host. Lucilia species, which hybridize in the wild and form geographically distinct subpopulations in other regions, are diverging, meaning that we can observe and quantify early biological adaptive processes that govern speciation as they are occurring over hundreds, instead of millions, of years. The draft genome of a North American male Lucilia cuprina fly (carrion breeder) was assembled using a combination of short and long read sequences. This genome is compared to an existing Australian draft genome (ectoparasite) by elucidating genomic structure in key adaptive processes (i.e. immune system evasion) via high-throughput re-sequencing of parasitic specimens, gene prediction and annotation. The carcass colonized by or animal parasitized by both species, with some geographic overlap, provides a semi-controlled environment within the larger context of the ecosystem to sample a large number of individuals with similar life history strategies, allowing for direct comparative studies to elucidate the correlation between structure and function in the genomes of carrion flies – allowing us to understand biological adaptation and speciation.Item How satellites can help control the spread of diseases such as Zika(The Conversation US, Inc., 2016-02-15) Moreno-Madriñán, Max Jacobo; Environmental Health Science, School of Public Health