Identification of Species by Combining Molecular and Morphological Data Using Convolutional Neural Networks

Genome-wide species delimitation and quantification of the extent of introgression in eriophyoid mite Epitrimerus sabinae complex (Acariformes: Eriophyoidea)

Species complex hinders the exploration of terrestrial species diversity, particularly in small arthropod lineages that are morphologically indistinguishable from each other. The Epitrimerus sabinae complex in the Eriophyoidea provides a valuable case study in species complex delimitation, as they exhibit limited morphological variations. In this study, we obtained thousands of nuclear genomic single-nucleotide polymorphisms via whole-genome sequencing from 55 E. sabinae complex specimens, covering their potential all known distribution ranges. We implemented a framework to infer cryptic speciation, which involved phylogenetic and genetic clustering to identify potential species, followed by population demographic assessment to confirm lineage independence (and thus species status). Our results demonstrate that the E. sabinae complex comprises ten distinct species. These species range from highly divergent, genetically isolated lineages, to differentiated populations involving gene flow. This gene flow is widespread across species boundaries, indicating potential genetic introgression among them. Additionally, demographic analyses revealed that the ten species have followed unique trajectories in size change during the Quaternary period. Time-calibrated phylogenies further showed that speciation in the E. sabinae complex occurred rapidly, resulting in a rapid radiation during the Neogene period. Collectively, parallelism/convergence and recent divergence involving multiple gene flows may explain the homoplasy of E. sabinae complex. Our results highlight the integrated approach in species complex delimitation.

Genus Bithynia: morphological classification to molecular identification

Snails of the genus Bithynia, whose primary habitat is slow-flowing ponds and ditches, serve as the first intermediate hosts of liver fluke. Currently, approximately 200 million individuals worldwide are at risk of liver fluke infection, yet questions still persist regarding the taxonomic identification of Bithynia genus, a crucial player in the transmission of this disease. Accurate taxonomic classification of the Bithynia genus could significantly enhance current understanding of the disease's transmission mechanisms. In this article we comprehensively review the extensive research conducted on Bithynia genus, spanning past inquiries up to the latest findings. The primary emphasis is placed on exploring the taxonomic identification of this genus within various technological settings. We then present a consolidated analysis of the morphological taxonomic identification methods, highlighting their strengths and limitations. We also introduce a novel perspective on the future direction of identification and classification efforts for the members of this genus, emphasizing the crucial role Bithynia plays in the epidemiological cycle of liver fluke transmission. We conclude by urging researchers to prioritize the significance of the members of this genus in the epidemiological cycle of liver fluke transmission and in control measures for disease dissemination, within the context of the vector organisms.

Inferring Taxonomic Affinities and Genetic Distances Using Morphological Features Extracted from Specimen Images: A Case Study with a Bivalve Data Set

Reconstructing the tree of life and understanding the relationships of taxa are core questions in evolutionary and systematic biology. The main advances in this field in the last decades were derived from molecular phylogenetics; however, for most species, molecular data are not available. Here, we explore the applicability of 2 deep learning methods-supervised classification approaches and unsupervised similarity learning-to infer organism relationships from specimen images. As a basis, we assembled an image data set covering 4144 bivalve species belonging to 74 families across all orders and subclasses of the extant Bivalvia, with molecular phylogenetic data being available for all families and a complete taxonomic hierarchy for all species. The suitability of this data set for deep learning experiments was evidenced by an ablation study resulting in almost 80% accuracy for identifications on the species level. Three sets of experiments were performed using our data set. First, we included taxonomic hierarchy and genetic distances in a supervised learning approach to obtain predictions on several taxonomic levels simultaneously. Here, we stimulated the model to consider features shared between closely related taxa to be more critical for their classification than features shared with distantly related taxa, imprinting phylogenetic and taxonomic affinities into the architecture and training procedure. Second, we used transfer learning and similarity learning approaches for zero-shot experiments to identify the higher-level taxonomic affinities of test species that the models had not been trained on. The models assigned the unknown species to their respective genera with approximately 48% and 67% accuracy. Lastly, we used unsupervised similarity learning to infer the relatedness of the images without prior knowledge of their taxonomic or phylogenetic affinities. The results clearly showed similarities between visual appearance and genetic relationships at the higher taxonomic levels. The correlation was 0.6 for the most species-rich subclass (Imparidentia), ranging from 0.5 to 0.7 for the orders with the most images. Overall, the correlation between visual similarity and genetic distances at the family level was 0.78. However, fine-grained reconstructions based on these observed correlations, such as sister-taxa relationships, require further work. Overall, our results broaden the applicability of automated taxon identification systems and provide a new avenue for estimating phylogenetic relationships from specimen images.

A Next Generation of Hierarchical Bayesian Analyses of Hybrid Zones Enables Model-Based Quantification of Variation in Introgression in R

Hybrid zones, where genetically distinct groups of organisms meet and interbreed, offer valuable insights into the nature of species and speciation. Here, we present a new R package, bgchm, for population genomic analyses of hybrid zones. This R package extends and updates the existing bgc software and combines Bayesian analyses of hierarchical genomic clines with Bayesian methods for estimating hybrid indexes, interpopulation ancestry proportions, and geographic clines. Compared to existing software, bgchm offers enhanced efficiency through Hamiltonian Monte Carlo sampling and the ability to work with genotype likelihoods combined with a hierarchical Bayesian approach, enabling inference for diverse types of genetic data sets. The package also facilitates the quantification of introgression patterns across genomes, which is crucial for understanding reproductive isolation and speciation genetics. We first describe the models underlying bgchm and then provide an overview of the R package and illustrate its use through the analysis of simulated and empirical data sets. We show that bgchm generates accurate estimates of model parameters under a variety of conditions, especially when the genetic loci analyzed are highly ancestry informative. This includes relatively robust estimates of genome-wide variability in clines, which has not been the focus of previous models and methods. We also illustrate how both selection and genetic drift contribute to variability in introgression among loci and how additional information can be used to help distinguish these contributions. We conclude by describing the promises and limitations of bgchm, comparing bgchm to other software for genomic cline analyses, and identifying areas for fruitful future development.

The Complete Mitochondrial Genome of the Siberian Scoter Melanitta stejnegeri and Its Phylogenetic Relationship in Anseriformes

The Siberian Scoter (Melanitta stejnegeri) is a medium sea duck distinct from M. deglandi due to the absence of hybridization and differences in morphological characteristics. However, knowledge of its phylogenetic relationships within Anseriformes is limited due to a lack of molecular data. In this study, the complete mitogenome of M. stejnegeri was firstly sequenced, then annotated and used to reconstruct the phylogenetic relationships of 76 Anseriformes species. The complete mitogenome of M. stejnegeri is 16,631 bp and encodes 37 typical genes: 13 protein-coding genes, 2 ribosomal RNAs, 22 transfer RNAs, and 1 non-coding control region. Its mitogenome organization is similar to that of other Anseriformes species. The phylogenetic relationships within the genus Melanitta are initially clarified, with M. americana at the base. M. stejnegeri and M. deglandi are sister groups, clustering with M. fusca and M. perspicillata in order. Phylogenetic analysis suggests that Mareca falcata and M. strepera are sister groups, differing from previous studies. Results firstly indicate that Clangula hyemalis and Somateria mollissima are sister groups, suggesting a potentially skewed phylogenetic relationship may have been overlooked in earlier analyses relying solely on mitochondrial genomes. Our results provide new mitogenome data to support further phylogenetic and taxonomic studies of Anseriformes.

Tracing the genealogy origin of geographic populations based on genomic variation and deep learning

Assigning a query individual animal or plant to its derived population is a prime task in diverse applications related to organismal genealogy. Such endeavors have conventionally relied on short DNA sequences under a phylogenetic framework. These methods naturally show constraints when the inferred population sources are ambiguously phylogenetically structured, a scenario demanding substantially more informative genetic signals. Recent advances in cost-effective production of whole-genome sequences and artificial intelligence have created an unprecedented opportunity to trace the population origin for essentially any given individual, as long as the genome reference data are comprehensive and standardized. Here, we developed a convolutional neural network method to identify population origins using genomic SNPs. Three empirical datasets (an Asian honeybee, a red fire ant, and a chicken datasets) and two simulated populations are used for the proof of concepts. The performance tests indicate that our method can accurately identify the genealogy origin of query individuals, with success rates ranging from  93 % to 100 %. We further showed that the accuracy of the model can be significantly increased by refining the informative sites through FST filtering. Our method is robust to configurations related to batch sizes and epochs, whereas model learning benefits from the setting of a proper preset learning rate. Moreover, we explained the importance score of key sites for algorithm interpretability and credibility, which has been largely ignored. We anticipate that by coupling genomics and deep learning, our method will see broad potential in conservation and management applications that involve natural resources, invasive pests and weeds, and illegal trades of wildlife products.

Species delimitation 4.0: integrative taxonomy meets artificial intelligence

Although species are central units for biological research, recent findings in genomics are raising awareness that what we call species can be ill-founded entities due to solely morphology-based, regional species descriptions. This particularly applies to groups characterized by intricate evolutionary processes such as hybridization, polyploidy, or asexuality. Here, challenges of current integrative taxonomy (genetics/genomics + morphology + ecology, etc.) become apparent: different favored species concepts, lack of universal characters/markers, missing appropriate analytical tools for intricate evolutionary processes, and highly subjective ranking and fusion of datasets. Now, integrative taxonomy combined with artificial intelligence under a unified species concept can enable automated feature learning and data integration, and thus reduce subjectivity in species delimitation. This approach will likely accelerate revising and unraveling eukaryotic biodiversity.

Nonomuraea corallina sp. nov., isolated from coastal sediment in Samila Beach, Thailand: insights into secondary metabolite synthesis as anticancer potential

A novel marine actinomycete, designated strain MCN248T, was isolated from the coastal sediment in Songkhla Province, Thailand. Based on the 16S rRNA gene sequences, the new isolate was closely related to Nonomuraea harbinensis DSM45887T (99.2%) and Nonomuraea ferruginea DSM43553T (98.6%). Phylogenetic analyzes based on the 16S rRNA gene sequences showed that strain MCN248T was clustered with Nonomuraea harbinensis DSM45887T and Nonomuraea ferruginea DSM43553T. However, the digital DNA-DNA hybridization analyzes presented a low relatedness of 40.2% between strain MCN248T and the above closely related strains. This strain contained meso-diaminopimelic acid. The acyl type of the peptidoglycan was acetyl, and mycolic acids were absent. The major menaquinones were MK-9(H2) and MK-9(H4). The whole cell sugars consisted of madurose, ribose, mannose, and glucose. Diphosphatidylglycerol, hydroxyl-phosphatidylethanolamine, phosphatidylethanolamine, phosphatidylinositol, and phosphatidylglycerol were detected as the major phospholipids. The predominant cellular fatty acids were iso-C16:0 (40.4%), 10-methyl-C17:0 (22.1%), and C17:1ω 8c (10.9%). The DNA G + C content of the genomic DNA was 71.7%. With in silico analyzes, the antiSMASH platform uncovered a diverse 29 secondary metabolite biosynthesis arsenal, including non-ribosomal peptide synthetase (NRPS) and polyketide synthase (PKS) of strain MCN248T, with a high prevalence of gene cluster encoding pathways for the production of anticancer and cytotoxic compounds. Consistently, the crude extract could inhibit colorectal HCT-116 cancer cells at a final concentration of 50 μg/mL. Based on the polyphasic approach, strain MCN248 was designated as a novel species of the genus Nonomuraea, for which the name Nonomuraea corallina sp. nov. is proposed. The type strain of the type species is MCN248T (=NBRC115966T = TBRC17110T).

Phylogeny-based assignment of functional traits to DNA barcodes outperforms distance-based, in a comparison of approaches

The full potential for using DNA barcodes for profiling functional trait diversity has yet to be determined in plants and animals; thus, we outline a general framework for quantifying functional trait diversity of insect community DNA and propose and assess the accuracy of three methods for achieving this. We built a novel dataset of traits and DNA barcodes for wild bees in China. An informatics framework was developed for phylogeny-based integration of these data and prediction of traits for any subject barcodes, which was compared with two distance-based methods. For Phylogenetic Assignment, we additionally conducted a species-level analysis of publically available bee trait data. Under the specimen-level dataset, the rate of trait assignment was negatively correlated with distance between the query and the nearest trait-known reference, for all methods. Phylogenetic Assignment was found to perform best under several criteria; particularly, it had the lowest false-positive rate (rarely returning a state prediction where success was unlikely; where the distance from query to the nearest reference was high). For a wider range of compiled traits, conservative life-history traits showed the highest rates of assignment; for example, sociality was predicted with confidence at 53%, parasitism at 44% and nest location at 33%. As outlined herein, automated trait assignment might be applied at scale to either barcodes or metabarcodes. With further compilation and databasing of DNA barcode and trait data, the rate and accuracy of trait assignment is expected to increase to the point of being a widely viable and informative approach.

Rapid Identification of Aphid Species by Headspace GC-MS and Discriminant Analysis

Aphids are a ubiquitous group of pests in agriculture that cause serious losses. For sustainable aphid identification, it is necessary to develop a precise and fast aphid identification tool. A new simple chemotaxonomy approach to rapidly identify aphids was implemented. The method was calibrated in comparison to the established phylogenetic analysis. For chemotaxonomic analysis, aphids were crushed, their headspace compounds were collected through closed-loop stripping (CLS) and analysed using gas chromatography-mass spectrometry (GC-MS). GC-MS data were then subjected to a discriminant analysis using CAP12.exe software, which identified key biomarkers that distinguish aphid species. A dichotomous key taking into account the presence and absence of a set of species-specific biomarkers was derived from the discriminant analysis which enabled rapid and reliable identification of aphid species. As the method overcomes the limits of morphological identification, it works with aphids at all life stages and in both genders. Thus, our method enables entomologists to assign aphids to growth stages and identify the life history of the investigated aphids, i.e., the food plant(s) they fed on. Our experiments clearly showed that the method could be used as a software to automatically identify aphids.

Applying image clustering to phylogenetic analysis: A trial

•Molecular phylogenetic analysis can be supplemented by image clustering analysis that uses pretrained machine learning tools.

Advanced Molecular-Genetic Methods and Prospects for Their Application for the Indication and Identification of <i>Yersinia pestis</i> Strains

The review provides an analysis of the literature data on the use of various modern molecular-genetic methods for the indication and identification of Yersinia pestis strains with different properties and degree of virulence, which is caused by the diverse natural conditions in which they circulate. The methods are also considered from the perspective of their promising application at three levels (territorial, regional and federal) of the system for laboratory diagnosis of infectious diseases at the premises of Rospotrebnadzor organizations to solve the problem of maintaining the sanitary and epidemiological well-being of the country’s population. The main groups of methods considered are as follows: based on the analysis of the lengths of restriction fragments (ribo- and IS-typing, pulse gel electrophoresis); based on the analysis of specific fragments (DFR typing, VNTR typing); based on sequencing (MLST, CRISPR analysis, SNP analysis); PCR methods (including IPCR, SPA); isothermal amplification methods (LAMP, HDA, RPA, SEA, PCA, SHERLOCK); DNA-microarray; methods using aptamer technology; bio- and nano-sensors; DNA origami; methods based on neural networks. We can conclude that the rapid development of molecular diagnostics and genetics is aimed at increasing efficiency, multi-factorial approaches and simplifying the application of techniques with no need for expensive equipment and highly qualified personnel for analysis. At all levels of the system for laboratory diagnosis of infectious diseases at the Rospotrebnadzor organizations, it is possible to use methods based on PCR, isothermal amplification, SHERLOCK, biosensors, and small-sized sequencing devices. At the territorial level, at plague control stations, the use of immuno-PCR and SPA for the indication of Y. pestis is viable. At the regional level, introduction of the technologies based on the use of aptamers and DNA chips looks promising. For the federal level, the use of DNA origami methods and new technologies of whole genome sequencing is a prospect within the framework of advanced identification, molecular typing and sequencing of the genomes of plague agent strains.

Artificial Intelligence Technology Driven Environmental Factors Extraction and Analysis Method in Traditional Clothing Handicraft

The application of artificial intelligence (AI) technology in the field of clothes can provide a good development mode and system under the social context of AI technology development. AI provides help for the development of intelligent clothing. Intelligent clothing is a high-tech product that integrates intelligent technology and clothing. It combines cutting-edge technologies in electronic information technology, sensor technology, textile science, and material science. In the extraction and analysis of environmental factors in clothing handicraft, AI technology has a considerable application prospect and a certain development potential. In order to improve the accuracy of environmental factors extraction in clothing handicraft, this paper uses convolutional neural network (CNN) to extract and analyze environmental factors in traditional clothing handicraft. We carried out experiments on the extraction of environmental factors in clothing handicrafts with pure color, few patterns, patterns, and complex background. The experimental results show that the CNN has a good effect on the extraction of environmental factors in clothing handicraft under different backgrounds. In addition, the model in this paper has good stability, accuracy, and feature extraction speed, which has high practical value and research significance.

Animal Detection and Classification from Camera Trap Images Using Different Mainstream Object Detection Architectures

Simple Summary

The imagery captured by cameras provides important information for wildlife research and conservation. Deep learning technology can assist ecologists in automatically identifying and processing imagery captured from camera traps, improving research capabilities and efficiency. Currently, many general deep learning architectures have been proposed but few have evaluated their applicability for use in real camera trap scenarios. Our study constructed the Northeast Tiger and Leopard National Park wildlife dataset (NTLNP dataset) for the first time and compared the real-world application performance of three currently mainstream object detection models. We hope this study provides a reference on the applicability of the AI technique in wild real-life scenarios and truly help ecologists to conduct wildlife conservation, management, and research more effectively.

Abstract

Camera traps are widely used in wildlife surveys and biodiversity monitoring. Depending on its triggering mechanism, a large number of images or videos are sometimes accumulated. Some literature has proposed the application of deep learning techniques to automatically identify wildlife in camera trap imagery, which can significantly reduce manual work and speed up analysis processes. However, there are few studies validating and comparing the applicability of different models for object detection in real field monitoring scenarios. In this study, we firstly constructed a wildlife image dataset of the Northeast Tiger and Leopard National Park (NTLNP dataset). Furthermore, we evaluated the recognition performance of three currently mainstream object detection architectures and compared the performance of training models on day and night data separately versus together. In this experiment, we selected YOLOv5 series models (anchor-based one-stage), Cascade R-CNN under feature extractor HRNet32 (anchor-based two-stage), and FCOS under feature extractors ResNet50 and ResNet101 (anchor-free one-stage). The experimental results showed that performance of the object detection models of the day-night joint training is satisfying. Specifically, the average result of our models was 0.98 mAP (mean average precision) in the animal image detection and 88% accuracy in the animal video classification. One-stage YOLOv5m achieved the best recognition accuracy. With the help of AI technology, ecologists can extract information from masses of imagery potentially quickly and efficiently, saving much time.