Phenomics in Livestock Research: Bottlenecks and Promises of Digital Phenotyping and Other Quantification Techniques on a Global Scale

Bottlenecks in moving genomics to real-life applications also include phenomics. This is true not only for genomics medicine and public health genomics but also in ecology and livestock phenomics. This expert narrative review explores the intricate relationship between genetic makeup and observable phenotypic traits across various biological levels in the context of livestock research. We unpack and emphasize the significance of precise phenotypic data in selective breeding outcomes and examine the multifaceted applications of phenomics, ranging from improvement to assessing welfare, reproductive traits, and environmental adaptation in livestock. As phenotypic traits exhibit strong correlations, their measurement alongside specific biological outcomes provides insights into performance, overall health, and clinical endpoints like morbidity and disease. In addition, automated assessment of livestock holds potential for monitoring the dynamic phenotypic traits across various species, facilitating a deeper comprehension of how they adapt to their environment and attendant stressors. A key challenge in genetic improvement in livestock is predicting individuals with optimal fitness without direct measurement. Temporal predictions from unmanned aerial systems can surpass genomic predictions, offering in-depth data on livestock. In the near future, digital phenotyping and digital biomarkers may further unravel the genetic intricacies of stress tolerance, adaptation and welfare aspects of animals enabling the selection of climate-resilient and productive livestock. This expert review thus delves into challenges associated with phenotyping and discusses technological advancements shaping the future of biological research concerning livestock.

A Review of Recent Hardware and Software Advances in GPU-Accelerated Edge-Computing Single-Board Computers (SBCs) for Computer Vision

Computer Vision (CV) has become increasingly important for Single-Board Computers (SBCs) due to their widespread deployment in addressing real-world problems. Specifically, in the context of smart cities, there is an emerging trend of developing end-to-end video analytics solutions designed to address urban challenges such as traffic management, disaster response, and waste management. However, deploying CV solutions on SBCs presents several pressing challenges (e.g., limited computation power, inefficient energy management, and real-time processing needs) hindering their use at scale. Graphical Processing Units (GPUs) and software-level developments have emerged recently in addressing these challenges to enable the elevated performance of SBCs; however, it is still an active area of research. There is a gap in the literature for a comprehensive review of such recent and rapidly evolving advancements on both software and hardware fronts. The presented review provides a detailed overview of the existing GPU-accelerated edge-computing SBCs and software advancements including algorithm optimization techniques, packages, development frameworks, and hardware deployment specific packages. This review provides a subjective comparative analysis based on critical factors to help applied Artificial Intelligence (AI) researchers in demonstrating the existing state of the art and selecting the best suited combinations for their specific use-case. At the end, the paper also discusses potential limitations of the existing SBCs and highlights the future research directions in this domain.

DiasMorph: a dataset of morphological traits and images of Central European diaspores

We present DiasMorph, a dataset of images and traits of diaspores from 1,442 taxa in 519 genera, and 96 families from Central Europe, totalling 94,214 records. The dataset was constructed following a standardised and reproducible image analysis method. The image dataset consists of diaspores against a high-contrast background, enabling a simple and efficient segmentation process. The quantitative traits records go beyond traditional morphometric measurements, and include colour and contour features, which are made available for the first time in a large dataset. These measurements correspond to individual diaspores, an input currently unavailable in traits databases, and allow for several approaches to explore the morphological traits of these species. Additionally, information regarding the presence and absence of appendages and structures both in the images and diaspores of the assessed taxa is also included. By making these data available, we aim to encourage initiatives to advance on new tools for diaspore identification, further our understanding of morphological traits functions, and provide means for the continuous development of image analyses applications.

Automated monitoring of brush use in dairy cattle

Access to brushes allows for natural scratching behaviors in cattle, especially in confined indoor settings. Cattle are motivated to use brushes, but brush use varies with multiple factors including social hierarchy and health. Brush use might serve an indicator of cow health or welfare, but practical application of these measures requires accurate and automated monitoring tools. This study describes a machine learning approach to monitor brush use by dairy cattle. We aimed to capture the daily brush use by integrating data on the rotation of a mechanical brush with data on cow identify derived from either 1) low-frequency radio frequency identification or 2) a computer vision system using fiducial markers. We found that the computer vision system outperformed the RFID system in accuracy, and that the machine learning algorithms enhanced the precision of the brush use estimates. This study presents the first description of a fiducial marker-based computer vision system for monitoring individual cattle behavior in a group setting; this approach could be applied to develop automated measures of other behaviors with the potential to better assess welfare and improve the care for farm animals.

Towards a standardized framework for AI-assisted, image-based monitoring of nocturnal insects

Automated sensors have potential to standardize and expand the monitoring of insects across the globe. As one of the most scalable and fastest developing sensor technologies, we describe a framework for automated, image-based monitoring of nocturnal insects-from sensor development and field deployment to workflows for data processing and publishing. Sensors comprise a light to attract insects, a camera for collecting images and a computer for scheduling, data storage and processing. Metadata is important to describe sampling schedules that balance the capture of relevant ecological information against power and data storage limitations. Large data volumes of images from automated systems necessitate scalable and effective data processing. We describe computer vision approaches for the detection, tracking and classification of insects, including models built from existing aggregations of labelled insect images. Data from automated camera systems necessitate approaches that account for inherent biases. We advocate models that explicitly correct for bias in species occurrence or abundance estimates resulting from the imperfect detection of species or individuals present during sampling occasions. We propose ten priorities towards a step-change in automated monitoring of nocturnal insects, a vital task in the face of rapid biodiversity loss from global threats. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

How many specimens make a sufficient training set for automated three-dimensional feature extraction?

Deep learning has emerged as a robust tool for automating feature extraction from three-dimensional images, offering an efficient alternative to labour-intensive and potentially biased manual image segmentation methods. However, there has been limited exploration into the optimal training set sizes, including assessing whether artficial expansion by data augmentation can achieve consistent results in less time and how consistent these benefits are across different types of traits. In this study, we manually segmented 50 planktonic foraminifera specimens from the genus Menardella to determine the minimum number of training images required to produce accurate volumetric and shape data from internal and external structures. The results reveal unsurprisingly that deep learning models improve with a larger number of training images with eight specimens being required to achieve 95% accuracy. Furthermore, data augmentation can enhance network accuracy by up to 8.0%. Notably, predicting both volumetric and shape measurements for the internal structure poses a greater challenge compared with the external structure, owing to low contrast differences between different materials and increased geometric complexity. These results provide novel insight into optimal training set sizes for precise image segmentation of diverse traits and highlight the potential of data augmentation for enhancing multivariate feature extraction from three-dimensional images.

A gentle introduction to computer vision-based specimen classification in ecological datasets

Classifying specimens is a critical component of ecological research, biodiversity monitoring and conservation. However, manual classification can be prohibitively time-consuming and expensive, limiting how much data a project can afford to process. Computer vision, a form of machine learning, can help overcome these problems by rapidly, automatically and accurately classifying images of specimens. Given the diversity of animal species and contexts in which images are captured, there is no universal classifier for all species and use cases. As such, ecologists often need to train their own models. While numerous software programs exist to support this process, ecologists need a fundamental understanding of how computer vision works to select appropriate model workflows based on their specific use case, data types, computing resources and desired performance capabilities. Ecologists may also face characteristic quirks of ecological datasets, such as long-tail distributions, 'unknown' species, similarity between species and polymorphism within species, which impact the efficacy of computer vision. Despite growing interest in computer vision for ecology, there are few resources available to help ecologists face the challenges they are likely to encounter. Here, we present a gentle introduction for species classification using computer vision. In this manuscript and associated GitHub repository, we demonstrate how to prepare training data, basic model training procedures, and methods for model evaluation and selection. Throughout, we explore specific considerations ecologists should make when training classification models, such as data domains, feature extractors and class imbalances. With these basics, ecologists can adjust their workflows to achieve research goals and/or account for uncertainty in downstream analysis. Our goal is to provide guidance for ecologists for getting started in or improving their use of machine learning for visual classification tasks.

Drift on holey landscapes as a dominant evolutionary process

An organism's phenotype has been shaped by evolution but the specific processes have to be indirectly inferred for most species. For example, correlations among traits imply the historical action of correlated selection and, more generally, the expression and distribution of traits is expected to be reflective of the adaptive landscapes that have shaped a population. However, our expectations about how quantitative traits-like most behaviors, physiological processes, and life-history traits-should be distributed under different evolutionary processes are not clear. Here, we show that genetic variation in quantitative traits is not distributed as would be expected under dominant evolutionary models. Instead, we found that genetic variation in quantitative traits across six phyla and 60 species (including both Plantae and Animalia) is consistent with evolution across high-dimensional "holey landscapes." This suggests that the leading conceptualizations and modeling of the evolution of trait integration fail to capture how phenotypes are shaped and that traits are integrated in a manner contrary to predictions of dominant evolutionary theory. Our results demonstrate that our understanding of how evolution has shaped phenotypes remains incomplete and these results provide a starting point for reassessing the relevance of existing evolutionary models.

Chasing the mechanisms of ecologically adaptive salinity tolerance

Plants adapted to challenging environments offer fascinating models of evolutionary change. Importantly, they also give information to meet our pressing need to develop resilient, low-input crops. With mounting environmental fluctuation-including temperature, rainfall, and soil salinity and degradation-this is more urgent than ever. Happily, solutions are hiding in plain sight: the adaptive mechanisms from natural adapted populations, once understood, can then be leveraged. Much recent insight has come from the study of salinity, a widespread factor limiting productivity, with estimates of 20% of all cultivated lands affected. This is an expanding problem, given increasing climate volatility, rising sea levels, and poor irrigation practices. We therefore highlight recent benchmark studies of ecologically adaptive salt tolerance in plants, assessing macro- and microevolutionary mechanisms, and the recently recognized role of ploidy and the microbiome on salinity adaptation. We synthesize insight specifically on naturally evolved adaptive salt-tolerance mechanisms, as these works move substantially beyond traditional mutant or knockout studies, to show how evolution can nimbly "tweak" plant physiology to optimize function. We then point to future directions to advance this field that intersect evolutionary biology, abiotic-stress tolerance, breeding, and molecular plant physiology.

Phenomics as an approach to Comparative Developmental Physiology

The dynamic nature of developing organisms and how they function presents both opportunity and challenge to researchers, with significant advances in understanding possible by adopting innovative approaches to their empirical study. The information content of the phenotype during organismal development is arguably greater than at any other life stage, incorporating change at a broad range of temporal, spatial and functional scales and is of broad relevance to a plethora of research questions. Yet, effectively measuring organismal development, and the ontogeny of physiological regulations and functions, and their responses to the environment, remains a significant challenge. "Phenomics", a global approach to the acquisition of phenotypic data at the scale of the whole organism, is uniquely suited as an approach. In this perspective, we explore the synergies between phenomics and Comparative Developmental Physiology (CDP), a discipline of increasing relevance to understanding sensitivity to drivers of global change. We then identify how organismal development itself provides an excellent model for pushing the boundaries of phenomics, given its inherent complexity, comparably smaller size, relative to adult stages, and the applicability of embryonic development to a broad suite of research questions using a diversity of species. Collection, analysis and interpretation of whole organismal phenotypic data are the largest obstacle to capitalising on phenomics for advancing our understanding of biological systems. We suggest that phenomics within the context of developing organismal form and function could provide an effective scaffold for addressing grand challenges in CDP and phenomics.

Enabling interpretable machine learning for biological data with reliability scores

Machine learning tools have proven useful across biological disciplines, allowing researchers to draw conclusions from large datasets, and opening up new opportunities for interpreting complex and heterogeneous biological data. Alongside the rapid growth of machine learning, there have also been growing pains: some models that appear to perform well have later been revealed to rely on features of the data that are artifactual or biased; this feeds into the general criticism that machine learning models are designed to optimize model performance over the creation of new biological insights. A natural question arises: how do we develop machine learning models that are inherently interpretable or explainable? In this manuscript, we describe the SWIF(r) reliability score (SRS), a method building on the SWIF(r) generative framework that reflects the trustworthiness of the classification of a specific instance. The concept of the reliability score has the potential to generalize to other machine learning methods. We demonstrate the utility of the SRS when faced with common challenges in machine learning including: 1) an unknown class present in testing data that was not present in training data, 2) systemic mismatch between training and testing data, and 3) instances of testing data that have missing values for some attributes. We explore these applications of the SRS using a range of biological datasets, from agricultural data on seed morphology, to 22 quantitative traits in the UK Biobank, and population genetic simulations and 1000 Genomes Project data. With each of these examples, we demonstrate how the SRS can allow researchers to interrogate their data and training approach thoroughly, and to pair their domain-specific knowledge with powerful machine-learning frameworks. We also compare the SRS to related tools for outlier and novelty detection, and find that it has comparable performance, with the advantage of being able to operate when some data are missing. The SRS, and the broader discussion of interpretable scientific machine learning, will aid researchers in the biological machine learning space as they seek to harness the power of machine learning without sacrificing rigor and biological insight.

Comparing ant morphology measurements from microscope and online AntWeb.org 2D z-stacked images

Unprecedented technological advances in digitization and the steadily expanding open-access digital repositories are yielding new opportunities to quickly and efficiently measure morphological traits without transportation and advanced/expensive microscope machinery. A prime example is the AntWeb.org database, which allows researchers from all over the world to study taxonomic, ecological, or evolutionary questions on the same ant specimens with ease. However, the reproducibility and reliability of morphometric data deduced from AntWeb compared to traditional microscope measurements has not yet been tested. Here, we compared 12 morphological traits of 46 Temnothorax ant specimens measured either directly by stereomicroscope on physical specimens or via the widely used open-access software tpsDig utilizing AntWeb digital images. We employed a complex statistical framework to test several aspects of reproducibility and reliability between the methods. We estimated (i) the agreement between the measurement methods and (ii) the trait value dependence of the agreement, then (iii) compared the coefficients of variation produced by the different methods, and finally, (iv) tested for systematic bias between the methods in a mixed modeling-based statistical framework. The stereomicroscope measurements were extremely precise. Our comparisons showed that agreement between the two methods was exceptionally high, without trait value dependence. Furthermore, the coefficients of variation did not differ between the methods. However, we found systematic bias in eight traits: apart from one trait where software measurements overestimated the microscopic measurements, the former underestimated the latter. Our results shed light on the fact that relying solely on the level of agreement between methods can be highly misleading. In our case, even though the software measurements predicted microscope measurements very well, replacing traditional microscope measurements with software measurements, and especially mixing data collected by the different methods, might result in erroneous conclusions. We provide guidance on the best way to utilize virtual specimens (2D z-stacked images) as a source of morphometric data, emphasizing the method's limitations in certain fields and applications.

Using pose estimation to identify regions and points on natural history specimens

A key challenge in mobilising growing numbers of digitised biological specimens for scientific research is finding high-throughput methods to extract phenotypic measurements on these datasets. In this paper, we test a pose estimation approach based on Deep Learning capable of accurately placing point labels to identify key locations on specimen images. We then apply the approach to two distinct challenges that each requires identification of key features in a 2D image: (i) identifying body region-specific plumage colouration on avian specimens and (ii) measuring morphometric shape variation in Littorina snail shells. For the avian dataset, 95% of images are correctly labelled and colour measurements derived from these predicted points are highly correlated with human-based measurements. For the Littorina dataset, more than 95% of landmarks were accurately placed relative to expert-labelled landmarks and predicted landmarks reliably captured shape variation between two distinct shell ecotypes ('crab' vs 'wave'). Overall, our study shows that pose estimation based on Deep Learning can generate high-quality and high-throughput point-based measurements for digitised image-based biodiversity datasets and could mark a step change in the mobilisation of such data. We also provide general guidelines for using pose estimation methods on large-scale biological datasets.

Plant Hormonomics: A Key Tool for Deep Physiological Phenotyping to Improve Crop Productivity

Agriculture is particularly vulnerable to climate change. To cope with the risks posed by climate-related stressors to agricultural production, global population growth, and changes in food preferences, it is imperative to develop new climate-smart crop varieties with increased yield and environmental resilience. Molecular genetics and genomic analyses have revealed that allelic variations in genes involved in phytohormone-mediated growth regulation have greatly improved productivity in major crops. Plant science has remarkably advanced our understanding of the molecular basis of various phytohormone-mediated events in plant life. These findings provide essential information for improving the productivity of crops growing in changing climates. In this review, we highlight the recent advances in plant hormonomics (multiple phytohormone profiling) and discuss its application to crop improvement. We present plant hormonomics as a key tool for deep physiological phenotyping, focusing on representative plant growth regulators associated with the improvement of crop productivity. Specifically, we review advanced methodologies in plant hormonomics, highlighting mass spectrometry- and nanosensor-based plant hormone profiling techniques. We also discuss the applications of plant hormonomics in crop improvement through breeding and agricultural management practices.

The impacts of fine-tuning, phylogenetic distance, and sample size on big-data bioacoustics

Vocalizations in animals, particularly birds, are critically important behaviors that influence their reproductive fitness. While recordings of bioacoustic data have been captured and stored in collections for decades, the automated extraction of data from these recordings has only recently been facilitated by artificial intelligence methods. These have yet to be evaluated with respect to accuracy of different automation strategies and features. Here, we use a recently published machine learning framework to extract syllables from ten bird species ranging in their phylogenetic relatedness from 1 to 85 million years, to compare how phylogenetic relatedness influences accuracy. We also evaluate the utility of applying trained models to novel species. Our results indicate that model performance is best on conspecifics, with accuracy progressively decreasing as phylogenetic distance increases between taxa. However, we also find that the application of models trained on multiple distantly related species can improve the overall accuracy to levels near that of training and analyzing a model on the same species. When planning big-data bioacoustics studies, care must be taken in sample design to maximize sample size and minimize human labor without sacrificing accuracy.

Towards the fully automated monitoring of ecological communities

High-resolution monitoring is fundamental to understand ecosystems dynamics in an era of global change and biodiversity declines. While real-time and automated monitoring of abiotic components has been possible for some time, monitoring biotic components-for example, individual behaviours and traits, and species abundance and distribution-is far more challenging. Recent technological advancements offer potential solutions to achieve this through: (i) increasingly affordable high-throughput recording hardware, which can collect rich multidimensional data, and (ii) increasingly accessible artificial intelligence approaches, which can extract ecological knowledge from large datasets. However, automating the monitoring of facets of ecological communities via such technologies has primarily been achieved at low spatiotemporal resolutions within limited steps of the monitoring workflow. Here, we review existing technologies for data recording and processing that enable automated monitoring of ecological communities. We then present novel frameworks that combine such technologies, forming fully automated pipelines to detect, track, classify and count multiple species, and record behavioural and morphological traits, at resolutions which have previously been impossible to achieve. Based on these rapidly developing technologies, we illustrate a solution to one of the greatest challenges in ecology: the ability to rapidly generate high-resolution, multidimensional and standardised data across complex ecologies.

Colour scales with climate in North American ratsnakes: a test of the thermal melanism hypothesis using community science images

Animal colour is a complex trait shaped by multiple selection pressures that can vary across geography. The thermal melanism hypothesis predicts that darker coloration is beneficial to animals in colder regions because it allows for more rapid solar absorption. Here, we use community science images of three closely related species of North American ratsnakes (genus Pantherophis) to examine if climate predicts colour variation across range-wide scales. We predicted that darker individuals are found in colder regions and higher elevations, in accordance with the thermal melanism hypothesis. Using an unprecedented dataset of over 8000 images, we found strong support for temperature as a key predictor of darker colour, supporting thermal melanism. We also found that elevation and precipitation are predictive of colour, but the direction and magnitude of these effects were more variable across species. Our study is the first to quantify colour variation in Pantherophis ratsnakes, highlighting the value of community science images for studying range-wide colour variation.

A high-throughput multispectral imaging system for museum specimens

We present an economical imaging system with integrated hardware and software to capture multispectral images of Lepidoptera with high efficiency. This method facilitates the comparison of colors and shapes among species at fine and broad taxonomic scales and may be adapted for other insect orders with greater three-dimensionality. Our system can image both the dorsal and ventral sides of pinned specimens. Together with our processing pipeline, the descriptive data can be used to systematically investigate multispectral colors and shapes based on full-wing reconstruction and a universally applicable ground plan that objectively quantifies wing patterns for species with different wing shapes (including tails) and venation systems. Basic morphological measurements, such as body length, thorax width, and antenna size are automatically generated. This system can increase exponentially the amount and quality of trait data extracted from museum specimens.

Phenomics in sport: Can emerging methodology drive advanced insights?

Methodologies in applied sport science have predominantly driven a reductionist grounding to component-specific mechanisms to drive athlete training and care. While linear mechanistic approaches provide useful insights, they have impeded progress in the development of more complex network physiology models that consider the temporal and spatial interactions of multiple factors within and across systems and subsystems. For this, a more sophisticated approach is needed and the development of such a methodological framework can be considered a Sport Grand Challenge. Specifically, a transdisciplinary phenomics-based scientific and modeling framework has merit. Phenomics is a relatively new area in human precision medicine, but it is also a developed area of research in the plant and evolutionary biology sciences. The convergence of innovative precision medicine, portable non-destructive measurement technologies, and advancements in modeling complex human behavior are central for the integration of phenomics into sport science. The approach enables application of concepts such as phenotypic fitness, plasticity, dose-response dynamics, critical windows, and multi-dimensional network models of behavior. In addition, profiles are grounded in indices of change, and models consider the athlete's performance or recovery trajectory as a function of their dynamic environment. This new framework is introduced across several example sport science domains for potential integration. Specific factors of emphasis are provided as potential candidate fitness variables and example profiles provide a generalizable modeling approach for precision training and care. Finally, considerations for the future are discussed, including scaling from individual athletes to teams and additional factors necessary for the successful implementation of phenomics.

An Outlook for Deep Learning in Ecosystem Science

Rapid advances in hardware and software, accompanied by public- and private-sector investment, have led to a new generation of data-driven computational tools. Recently, there has been a particular focus on deep learning—a class of machine learning algorithms that uses deep neural networks to identify patterns in large and heterogeneous datasets. These developments have been accompanied by both hype and scepticism by ecologists and others. This review describes the context in which deep learning methods have emerged, the deep learning methods most relevant to ecosystem ecologists, and some of the problem domains they have been applied to. Deep learning methods have high predictive performance in a range of ecological contexts, leveraging the large data resources now available. Furthermore, deep learning tools offer ecosystem ecologists new ways to learn about ecosystem dynamics. In particular, recent advances in interpretable machine learning and in developing hybrid approaches combining deep learning and mechanistic models provide a bridge between pure prediction and causal explanation. We conclude by looking at the opportunities that deep learning tools offer ecosystem ecologists and assess the challenges in interpretability that deep learning applications pose.

Changing allometric relationships among fossil and Recent populations in two colonial species

Allometry is vital for understanding the mechanisms underlying phenotypic evolution. Despite a large body of literature on allometry, studies based on fossil time series are limited for solitary organisms and nonexistent for colonial organisms. Allometric relationships have been found to be relatively constant across Recent populations of the same species, separated by space, but variable among fossil populations separated by thousands of years. How stable are allometric relationships at the module level for colonial organisms? We address this question using two extant species of the cheilostome bryozoan Microporella with fossil records spanning the Pleistocene of New Zealand. We investigate size covariation between feeding modules and three traits with separate functions (reproductive, resource uptake, and defense). We found that within-population (static) allometry can change on timescales of at least 0.1 million years. These within-population relationships do not consistently predict overintraspecific evolutionary allometry, which in turn does not predict those estimated at the genus level. Different functional traits are constrained to different extents by module size with defensive traits being the least constrained and most evolvable, compared with reproductive and resource uptake traits. Our study highlights the potential of colonial organisms in understanding the constraints and drivers of long-term phenotypic change.

Deep learning image segmentation reveals patterns of UV reflectance evolution in passerine birds

Ultraviolet colouration is thought to be an important form of signalling in many bird species, yet broad insights regarding the prevalence of ultraviolet plumage colouration and the factors promoting its evolution are currently lacking. In this paper, we develop a image segmentation pipeline based on deep learning that considerably outperforms classical (i.e. non deep learning) segmentation methods, and use this to extract accurate information on whole-body plumage colouration from photographs of >24,000 museum specimens covering >4500 species of passerine birds. Our results demonstrate that ultraviolet reflectance, particularly as a component of other colours, is widespread across the passerine radiation but is strongly phylogenetically conserved. We also find clear evidence in support of the role of light environment in promoting the evolution of ultraviolet plumage colouration, and a weak trend towards higher ultraviolet plumage reflectance among bird species with ultraviolet rather than violet-sensitive visual systems. Overall, our study provides important broad-scale insight into an enigmatic component of avian colouration, as well as demonstrating that deep learning has considerable promise for allowing new data to be brought to bear on long-standing questions in ecology and evolution.

Development of a portable toolkit to diagnose coral thermal stress

Coral bleaching, precipitated by the expulsion of the algal symbionts that provide colonies with fixed carbon is a global threat to reef survival. To protect corals from anthropogenic stress, portable tools are needed to detect and diagnose stress syndromes and assess population health prior to extensive bleaching. Here, medical grade Urinalysis strips, used to detect an array of disease markers in humans, were tested on the lab stressed Hawaiian coral species, Montipora capitata (stress resistant) and Pocillopora acuta (stress sensitive), as well as samples from nature that also included Porites compressa. Of the 10 diagnostic reagent tests on these strips, two appear most applicable to corals: ketone and leukocytes. The test strip results from M. capitata were explored using existing transcriptomic data from the same samples and provided evidence of the stress syndromes detected by the strips. We designed a 3D printed smartphone holder and image processing software for field analysis of test strips (TestStripDX) and devised a simple strategy to generate color scores for corals (reflecting extent of bleaching) using a smartphone camera (CoralDX). Our approaches provide field deployable methods, that can be improved in the future (e.g., coral-specific stress test strips) to assess reef health using inexpensive tools and freely available software.

Accurate image-based identification of macroinvertebrate specimens using deep learning-How much training data is needed?

Image-based methods for species identification offer cost-efficient solutions for biomonitoring. This is particularly relevant for invertebrate studies, where bulk samples often represent insurmountable workloads for sorting, identifying, and counting individual specimens. On the other hand, image-based classification using deep learning tools have strict requirements for the amount of training data, which is often a limiting factor. Here, we examine how classification accuracy increases with the amount of training data using the BIODISCOVER imaging system constructed for image-based classification and biomass estimation of invertebrate specimens. We use a balanced dataset of 60 specimens of each of 16 taxa of freshwater macroinvertebrates to systematically quantify how classification performance of a convolutional neural network (CNN) increases for individual taxa and the overall community as the number of specimens used for training is increased. We show a striking 99.2% classification accuracy when the CNN (EfficientNet-B6) is trained on 50 specimens of each taxon, and also how the lower classification accuracy of models trained on less data is particularly evident for morphologically similar species placed within the same taxonomic order. Even with as little as 15 specimens used for training, classification accuracy reached 97%. Our results add to a recent body of literature showing the huge potential of image-based methods and deep learning for specimen-based research, and furthermore offers a perspective to future automatized approaches for deriving ecological data from bulk arthropod samples.

Mathematical model and genomics construction of developmental biology patterns using digital image technology

Biological pattern formation ensures that tissues and organs develop in the correct place and orientation within the body. A great deal has been learned about cell and tissue staining techniques, and today’s microscopes can capture digital images. A light microscope is an essential tool in biology and medicine. Analyzing the generated images will involve the creation of unique analytical techniques. Digital images of the material before and after deformation can be compared to assess how much strain and displacement the material responds. Furthermore, this article proposes Development Biology Patterns using Digital Image Technology (DBP-DIT) to cell image data in 2D, 3D, and time sequences. Engineered materials with high stiffness may now be characterized via digital image correlation. The proposed method of analyzing the mechanical characteristics of skin under various situations, such as one direction of stress and temperatures in the hundreds of degrees Celsius, is achievable using digital image correlation. A DBP-DIT approach to biological tissue modeling is based on digital image correlation (DIC) measurements to forecast the displacement field under unknown loading scenarios without presupposing a particular constitutive model form or owning knowledge of the material microstructure. A data-driven approach to modeling biological materials can be more successful than classical constitutive modeling if adequate data coverage and advice from partial physics constraints are available. The proposed procedures include a wide range of biological objectives, experimental designs, and laboratory preferences. The experimental results show that the proposed DBP-DIT achieves a high accuracy ratio of 99,3%, a sensitivity ratio of 98.7%, a specificity ratio of 98.6%, a probability index of 97.8%, a balanced classification ratio of 97.5%, and a low error rate of 38.6%.

Street View Imagery (SVI) in the Built Environment: A Theoretical and Systematic Review

Street view imagery (SVI) provides efficient access to data that can be used to research spatial quality at the human scale. The previous reviews have mainly focused on specific health findings and neighbourhood environments. There has not been a comprehensive review of this topic. In this paper, we systematically review the literature on the application of SVI in the built environment, following a formal innovation–decision framework. The main findings are as follows: (I) SVI remains an effective tool for automated research assessments. This offers a new research avenue to expand the built environment-measurement methods to include perceptions in addition to physical features. (II) Currently, SVI is functional and valuable for quantifying the built environment, spatial sentiment perception, and spatial semantic speculation. (III) The significant dilemmas concerning the adoption of this technology are related to image acquisition, the image quality, spatial and temporal distribution, and accuracy. (IV) This research provides a rapid assessment and provides researchers with guidance for the adoption and implementation of SVI. Data integration and management, proper image service provider selection, and spatial metrics measurements are the critical success factors. A notable trend is the application of SVI towards a focus on the perceptions of the built environment, which provides a more refined and effective way to depict urban forms in terms of physical and social spaces.

Protecting endangered megafauna through AI analysis of drone images in a low-connectivity setting: a case study from Namibia

Assessing the numbers and distribution of at-risk megafauna such as the black rhino (Diceros bicornis) is key to effective conservation, yet such data are difficult to obtain. Many current monitoring technologies are invasive to the target animals and expensive. Satellite monitoring is emerging as a potential tool for very large animals (e.g., elephant) but detecting smaller species requires higher resolution imaging. Drones can deliver the required resolution and speed of monitoring, but challenges remain in delivering automated monitoring systems where internet connectivity is unreliable or absent. This study describes a model built to run on a drone to identify in situ images of megafauna. Compared with previously reported studies, this automated detection framework has a lower hardware cost and can function with a reduced internet bandwidth requirement for local network communication. It proposes the use of a Jetson Xavier NX, onboard a Parrot Anafi drone, connected to the internet throughout the flight to deliver a lightweight web-based notification system upon detection of the target species. The GPS location with the detected target species images is sent using MQ Telemetry Transport (MQTT), a lightweight messaging protocol using a publisher/subscriber architecture for IoT devices. It provides reliable message delivery when internet connection is sporadic. We used a YOLOv5l6 object detection architecture trained to identify a bounding box for one of five objects of interest in a frame of video. At an intersection over union (IoU) threshold of 0.5, our model achieved an average precision (AP) of 0.81 for black rhino (our primary target) and 0.83 for giraffe (Giraffa giraffa). The model was less successful at identifying the other smaller objects which were not our primary targets: 0.34, 0.25, and 0.42 for ostrich (Struthio camelus australis), springbok (Antidorcas marsupialis) and human respectively. We used several techniques to optimize performance and overcome the inherent challenge of small objects (animals) in the data. Although our primary focus for the development of the model was rhino, we included other species classes to emulate field conditions where many animal species are encountered, and thus reduce the false positive occurrence rate for rhino detections. To constrain model overfitting, we trained the model on a dataset with varied terrain, angle and lighting conditions and used data augmentation techniques (i.e., GANs). We used image tiling and a relatively larger (i.e., higher resolution) image input size to compensate for the difficulty faced in detecting small objects when using YOLO. In this study, we demonstrated the potential of a drone-based AI pipeline model to automate the detection of free-ranging megafauna detection in a remote setting and create alerts to a wildlife manager in a relatively poorly connected field environment.

Assessing Anatomical Changes in Male Reproductive Organs in Response to Larval Crowding Using Micro-computed Tomography Imaging

Ecological conditions shape (adaptive) responses at the molecular, anatomical, and behavioral levels. Understanding these responses is key to predict the outcomes of intra- and inter-specific competitions and the evolutionary trajectory of populations. Recent technological advances have enabled large-scale molecular (e.g., RNAseq) and behavioral (e.g., computer vision) studies, but the study of anatomical responses to ecological conditions has lagged behind. Here, we highlight the role of X-ray micro-computed tomography (micro-CT) in generating in vivo and ex vivo 3D imaging of anatomical structures, which can enable insights into adaptive anatomical responses to ecological environments. To demonstrate the application of this method, we manipulated the larval density of Drosophila melanogaster Meigen flies and applied micro-CT to investigate the anatomical responses of the male reproductive organs to varying intraspecific competition levels during development. Our data is suggestive of two classes of anatomical responses which broadly agree with sexual selection theory: increasing larval density led to testes and ejaculatory duct to be overall larger (in volume), while the volume of accessory glands and, to a lesser extent, ejaculatory duct decreased. These two distinct classes of anatomical responses might reflect shared developmental regulation of the structures of the male reproductive system. Overall, we show that micro-CT can be an important tool to advance the study of anatomical (adaptive) responses to ecological environments.

A pH Monitoring Algorithm for Orifice Plate Culture Medium

Recently, there has been renewed interest in cell therapy, which plays a key role in the clinical research of genetic diseases, advanced blood disease, and other diseases. It shows considerable clinical application value and is known as “the new pillar of future medicine”. Automatic cell culture and operation technology is the key to ensuring scale, standardization, and stability between batches of therapeutic cells. The pH of the cell culture medium is vital for cell growth. Most cells are suitable for growth at pH 7.2~7.4. A pH of cell culture medium lower than 6.8 or higher than 7.6 is harmful to cells, and cells will degenerate or even die. At present, the monitoring method of cell culture medium pH of automatic cell culture equipment is mainly a visual observation method, which can not accurately or quickly reflect changes in the cell culture medium. To address the issue of monitoring of cell culture fluid pH for automated cell culture equipment and the inability to employ invasive sensors to measure pH during well plate culture, a pH monitoring method for orifice plate culture medium algorithm based on HSV (hue, saturation, value) model is proposed by studying the changes of cell culture medium in the process of cell culture. The research presented here reveals the laws of cell culture fluid pH change and its color moment, and the intelligent monitoring of cell culture fluid pH was successfully achieved. The problem of non-destructive monitoring of the pH of cell culture fluids in well plates is also addressed.

Computer vision for assessing species color pattern variation from web-based community science images

Openly available community science digital vouchers provide a wealth of data to study phenotypic change across space and time. However, extracting phenotypic data from these resources requires significant human effort. Here, we demonstrate a workflow and computer vision model for automatically categorizing species color pattern from community science images. Our work is focused on documenting the striped/unstriped color polymorphism in the Eastern Red-backed Salamander (Plethodon cinereus). We used an ensemble convolutional neural network model to analyze this polymorphism in 20,318 iNaturalist images. Our model was highly accurate (∼98%) despite image heterogeneity. We used the resulting annotations to document extensive niche overlap between morphs, but wider niche breadth for striped morphs at the range-wide scale. Our work showcases key design principles for using machine learning with heterogeneous community science image data to address questions at an unprecedented scale.

•

We built a deep learning model to group color morphs from community science images

•

Our model achieved 98% accuracy for classifying striped and unstriped salamanders

•

We used our model to classify >20,000 images and built morph-specific niche models

•

We then determined if Red-backed salamanders niche partition at a range-wide scale

Genomic reaction norms inform predictions of plastic and adaptive responses to climate change

Genomic reaction norms represent the range of gene expression phenotypes (usually mRNA transcript levels) expressed by a genotype along an environmental gradient. Reaction norms derived from common‐garden experiments are powerful approaches for disentangling plastic and adaptive responses to environmental change in natural populations. By treating gene expression as a phenotype in itself, genomic reaction norms represent invaluable tools for exploring causal mechanisms underlying organismal responses to climate change across multiple levels of biodiversity.

Our goal is to provide the context, framework and motivation for applying genomic reaction norms to study the responses of natural populations to climate change.

Here, we describe the utility of integrating genomics with common‐garden‐gradient experiments under a reaction norm analytical framework to answer fundamental questions about phenotypic plasticity, local adaptation, their interaction (i.e. genetic variation in plasticity) and future adaptive potential.

An experimental and analytical framework for constructing and analysing genomic reaction norms is presented within the context of polygenic climate change responses of structured populations with gene flow. Intended for a broad eco‐evo readership, we first briefly review adaptation with gene flow and the importance of understanding the genomic basis and spatial scale of adaptation for conservation and management of structured populations under anthropogenic change. Then, within a high‐dimensional reaction norm framework, we illustrate how to distinguish plastic, differentially expressed (difference in reaction norm intercepts) and differentially plastic (difference in reaction norm slopes) genes, highlighting the areas of opportunity for applying these concepts.

We conclude by discussing how genomic reaction norms can be incorporated into a holistic framework to understand the eco‐evolutionary dynamics of climate change responses from molecules to ecosystems. We aim to inspire researchers to integrate gene expression measurements into common‐garden experimental designs to investigate the genomics of climate change responses as sequencing costs become increasingly accessible.

Insect egg morphology: evolution, development, and ecology

The insect egg can be viewed through many lenses: it is the single-celled developmental stage, a resource investment in the next generation, an unusually large and complex cell type, and the protective vessel for embryonic development. In this review, I describe the morphological diversity of insect eggs and then identify recent advances in understanding the patterns of egg evolution, the cellular mechanisms underlying egg development, and notable aspects of egg ecology. I also suggest areas for particularly promising future research on insect egg morphology; these topics touch upon diverse areas such as tissue morphogenesis, life history evolution, organismal scaling, cellular secretion, and oviposition ecology.

BOVIDS: A deep learning-based software package for pose estimation to evaluate nightly behavior and its application to common elands (Tragelaphus oryx) in zoos

Only a few studies on the nocturnal behavior of African ungulates exist so far, with mostly small sample sizes. For a comprehensive understanding of nocturnal behavior, the data basis needs to be expanded. Results obtained by observing zoo animals can provide clues for the study of wild animals and furthermore contribute to a better understanding of animal welfare and better husbandry conditions in zoos. The current contribution reduces the lack of data in two ways. First, we present a stand-alone open-source software package based on deep learning techniques, named Behavioral Observations by Videos and Images using Deep-Learning Software (BOVIDS). It can be used to identify ungulates in their enclosure and to determine the three behavioral poses "Standing," "Lying-head up," and "Lying-head down" on 11,411 h of video material with an accuracy of 99.4%. Second, BOVIDS is used to conduct a case study on 25 common elands (Tragelaphus oryx) out of 5 EAZA zoos with a total of 822 nights, yielding the first detailed description of the nightly behavior of common elands. Our results indicate that age and sex are influencing factors on the nocturnal activity budget, the length of behavioral phases as well as the number of phases per behavioral state during the night while the keeping zoo has no significant influence. It is found that males spend more time in REM sleep posture than females while young animals spend more time in this position than adult ones. Finally, the results suggest a rhythm between the Standing and Lying phases among common elands that opens future research directions.

Missing Links Between Gene Function and Physiology in Genomics

Knowledge of biological organisms at the molecular level that has been gathered is now organized into databases, often within ontological frameworks. To enable computational comparisons of annotations across different genomes and organisms, controlled vocabularies have been essential, as is the case in the functional annotation classifications used for bacteria, such as MultiFun and the more widely used Gene Ontology. The function of individual gene products as well as the processes in which collections of them participate constitute a wealth of classes that describe the biological role of gene products in a large number of organisms in the three kingdoms of life. In this contribution, we highlight from a qualitative perspective some limitations of these frameworks and discuss challenges that need to be addressed to bridge the gap between annotation as currently captured by ontologies and databases and our understanding of the basic principles in the organization and functioning of organisms; we illustrate these challenges with some examples in bacteria. We hope that raising awareness of these issues will encourage users of Gene Ontology and similar ontologies to be careful about data interpretation and lead to improved data representation.

Confronting Deep-Learning and Biodiversity Challenges for Automatic Video-Monitoring of Marine Ecosystems

With the availability of low-cost and efficient digital cameras, ecologists can now survey the world's biodiversity through image sensors, especially in the previously rather inaccessible marine realm. However, the data rapidly accumulates, and ecologists face a data processing bottleneck. While computer vision has long been used as a tool to speed up image processing, it is only since the breakthrough of deep learning (DL) algorithms that the revolution in the automatic assessment of biodiversity by video recording can be considered. However, current applications of DL models to biodiversity monitoring do not consider some universal rules of biodiversity, especially rules on the distribution of species abundance, species rarity and ecosystem openness. Yet, these rules imply three issues for deep learning applications: the imbalance of long-tail datasets biases the training of DL models; scarce data greatly lessens the performances of DL models for classes with few data. Finally, the open-world issue implies that objects that are absent from the training dataset are incorrectly classified in the application dataset. Promising solutions to these issues are discussed, including data augmentation, data generation, cross-entropy modification, few-shot learning and open set recognition. At a time when biodiversity faces the immense challenges of climate change and the Anthropocene defaunation, stronger collaboration between computer scientists and ecologists is urgently needed to unlock the automatic monitoring of biodiversity.

Using comprehensive machine-learning models to classify complex morphological characters

Recognizing and classifying multiple morphological features, such as patterns, sizes, and textures, can provide a comprehensive understanding of their variability and phenotypic evolution. Yet, quantitatively measuring complex morphological characters remains challenging.We provide a machine learning-based pipeline (SVMorph) to consider and classify complex morphological characters in multiple organisms that have either small or large datasets.Our pipeline integrates two descriptors, histogram of oriented gradient and local binary pattern, to meet various classification needs. We also optimized feature extraction by adding image data augmentation to improve model generalizability.We tested SVMorph on two real-world examples to demonstrate that it can be used with small training datasets and limited computational resources. Comparing with multiple CNN-based methods and traditional techniques, we show that SVMorph is reliable and fast in texture-based individual classification. Thus, SVMorph can be used to efficiently classify multiple morphological characters in distinct nonmodel organisms.

Field Phenomics: Will It Enable Crop Improvement?

Field phenomics has been identified as a promising enabling technology to assist plant breeders with the development of improved cultivars for farmers. Yet, despite much investment, there are few examples demonstrating the application of phenomics within a plant breeding program. We review recent progress in field phenomics and highlight the importance of targeting breeders' needs, rather than perceived technology needs, through developing and enhancing partnerships between phenomics researchers and plant breeders.