Biology subjects

Pylatiuk, C.

Publications and source records attributed to Pylatiuk, C..

7 recordsLinked to original sources

bioRxiv2026

Entomoscope 2.0 and ENIMAS 2.0: An Open-Source, AI-Integrated Platform for Rapid and Affordable Insect Digitization

The rapid decline of global biodiversity necessitates scalable and accessible tools for monitoring insect populations, yet the high cost and slow pace of specimen digitization remain significant bottlenecks. To address this challenge, we present the Entomoscope 2.0, an open-source platform that integrates a low-cost photomicroscope with an AI-integrated software suite, ENIMAS 2.0. The system combines optimized hardware with an end-to-end software module for digital specimen curation. This module comprises automated specimen cropping, background standardization, morphometric analysis using an Oriented Bounding Box (OBB) with a human-in-the-loop (HITL) supervision, and a flexible interface for rapid taxonomic screening using custom AI identification models. With a material cost of only 400 {euro}, the system offers a cost-effective alternative to expensive commercial solutions. We compare results from the Entomoscope 2.0 with a high-end commercial system (Keyence) using 54 insect specimens and demonstrate the efficiency of the proposed AI workflow. Entomoscope 2.0 completed the whole digitization process in an average of 54.6 seconds per specimen, representing a 2.28-fold increase in speed over the Keyence systems multi-step workflow (124.3 seconds). Crucially, all hardware specifications and construction manuals are freely available to support widespread adoption. By lowering financial barriers and accelerating research workflows, the Entomoscope 2.0 platform offers a practical solution to enable high-throughput digitization for researchers, educators, and citizen scientists.

bioengineering↗

bioRxiv2025

Automated Specimen Triage for Dark Taxa: Deep Learning Enables Orientation, Sex Identification, and Anatomical Segmentation from Robotic Imaging

Robotic specimen processing is transforming biodiversity discovery by replacing labor-intensive handling with scalable systems that can simultaneously generate high-quality specimen images. We demonstrate that these images can be leveraged by deep learning to efficiently extract key biological information and guide targeted specimen processing. Using a model dark taxon, the Phoridae (Diptera), the workflow performs three core tasks: sex identification, specimen orientation classification, and anatomical segmentation. Sex identification allows selective retention of diagnostically informative specimens, avoiding wasted effort on non-diagnostic individuals. Orientation classification enables specimens in the desired orientation to proceed immediately, while suboptimally oriented specimens can be repositioned for informative processing. Anatomical segmentation allows targeted processing of specimens displaying diagnostic characters or targeted analysis of specific anatomical regions in subsequent workflow steps. Comparative analysis of model architectures shows task-specific selection is crucial: a Convolutional Neural Network achieved an accuracy of 0.94 for orientation, a Vision Transformer achieved 0.88 for sex, and a U-Net precisely segmented nine anatomical regions with a mean IoU of 0.78. These results demonstrate that robotic imaging combined with deep learning provides a validated foundation for high-throughput, targeted specimen processing, maximising efficiency and utility for taxonomic and trait-based analyses, and supporting scalable, sustainable biodiversity workflows.

bioinformatics↗

bioRxiv2025

Deep Learning-Based Methods for Automated Estimation of Insect Length, Volume, and Biomass

We present InsectMorphoAI, an open-source, user-friendly software package that automates the measurement of insects from 2D images. The software addresses the need for high-throughput, non-invasive alternatives to laborious and often destructive manual measurement methods. InsectMorphoAI provides two analysis modes: a rapid, general-purpose method using oriented bounding boxes for linear length estimation across diverse taxa, and a high-precision, taxon-specific instance segmentation method for detailed curvilinear length, volume, and biomass estimation. We demonstrate the softwares accuracy, showing that the volume estimates from the segmentation module are strongly correlated with dry weight (R = 0.907), and the general length module achieves a mean absolute error corresponding to ~2.3% of the average specimen length. InsectMorphoAI is distributed with a graphical user interface and is freely available, with straightforward installation via a Docker container or a native Python environment. By streamlining data acquisition, InsectMorphoAI facilitates the integration of detailed trait data into large-scale ecological research, from biodiversity monitoring to functional trait analysis.

bioinformatics↗

bioRxiv2024

Measurement and classification of bold-shy behaviours in medaka fish

MotivationBoldness-shyness is considered a fundamental axis of behavioural variation in humans and other species, with obvious adaptive causes and evolutionary implications. Besides an individuals own genetics, this phenotype is also affected by the genetic makeup of peers in the individuals social environment. To identify genetic determinants of variation along the bold-shy behavioural axis, a reliable experimental and analytical setup able to highlight direct and indirect genetic effects is needed. ResultsWe describe a custom assay designed to detect bold-shy behaviours in medaka fish, combining an open-field and novel-object component. We use this assay to explore direct and social genetic effects on the behaviours of 307 pairs of fish from five inbred medaka strains. Applying a Hidden Markov Model (HMM) to classify behavioural modes, we find that direct genetic effects influence the proportions of time the five strains spent in slow-moving states, explaining up to 29.7% of the variance in time spent in those states. We also found that an individuals behaviour is influenced by the genetics of its tank partner, explaining up to 8.64% of the variance in the time spent in slow-moving states. Our behavioural assay in combination with the HMM analysis is applicable to follow-up genetic linkage studies of genetic variants involved in direct behavioural effects and indirect social genetic effects. A suitable genetic resource for such studies, the Medaka Inbred Kiyosu-Karlsruhe panel (MIKK) has recently been established.

bioinformatics↗

bioRxiv2024

Image-Based Recognition of Parasitoid Wasps Using Advanced Neural Networks

Hymenoptera have some of the highest diversity and number of individuals among insects. Many of these species potentially play key roles as food sources, pest controllers, and pollinators. However, little is known about their diversity and biology, and about 80% of the species have not been described yet. Classical taxonomy based on morphology is a rather slow process, but DNA barcoding has already brought considerable progress in identification. Innovative methods such as image-based identification and automation can even further speed up the process. We present a proof of concept for image data recognition of a parasitic wasp family, the Diapriidae (Hymenoptera), obtained as part of the GBOL III project. These tiny (1.2 - 4.5 mm) wasps were photographed and identified using DNA barcoding to provide a solid ground truth for training a neural network. Subsequently, three different neural network architectures were trained, evaluated, and optimized. As a result, 11 different classes of diaprids and one class of "other Hymenoptera can be classified with an average accuracy of 96%. Additionally, the sex of the specimen can be classified automatically with an accuracy of > 96%.

zoology↗

bioRxiv2021

DiversityScanner: Robotic discovery of small invertebrates with machine learning methods

Invertebrate biodiversity remains poorly explored although it comprises much of the terrestrial animal biomass, more than 90% of the species-level diversity and supplies many ecosystem services. The main obstacle is specimen- and species-rich samples. Traditional sorting techniques require manual handling and are slow while molecular techniques based on metabarcoding struggle with obtaining reliable abundance information. Here we present a fully automated sorting robot, which detects each specimen, images and measures it before moving it from a mixed invertebrate sample to the well of a 96-well microplate in preparation for DNA barcoding. The images are then used by a newly trained convolutional neural network (CNN) to assign the specimens to 14 particularly common, usually family-level "classes" of insects in Malaise trap samples and an "other-class" (N=15). The average assignment precision for the classes is 91.4% (75-100%). In order to obtain biomass information, the specimen images are also used to measure specimen length and estimate body volume. We outline how the DiversityScanner robot can be a key component for tackling and monitoring invertebrate diversity. The robot generates large numbers of images that become training sets for CNNs once the images are labelled with identifications based on DNA barcodes. In addition, the robot allows for taxon-specific subsampling of large invertebrate samples by only removing the specimens that belong to one of the 14 classes. We conclude that a combination of automation, machine learning, and DNA barcoding has the potential to tackle invertebrate diversity at an unprecedented scale.

zoology↗

bioRxiv2019

Automated high-throughput heart rate measurement in medaka and zebrafish embryos under physiological conditions

RationaleAccurate and efficient quantification of heartbeats in small fish models is an important readout to study cardiovascular biology, disease states and pharmacology at large scale. However, dependence on anesthesia, laborious sample orientation or requirement for fluorescent reporters have hampered the establishment of high-throughput heartbeat analysis. ObjectiveTo overcome these limitations, we aimed to develop a high-throughput assay with automated heart rate scoring in medaka (Oryzias latipes) and zebrafish (Danio rerio) embryos under physiological conditions designed for genetic screens and drug discovery and validation. Methods and ResultsWe established an efficient screening assay employing automated label-free heart rate determination of randomly oriented, non-anesthetized specimen in microtiter plates. Automatically acquired bright-field data feeds into an easy-to-use HeartBeat software, a MATLAB algorithm with graphical user interface developed for automated quantification of heart rate and rhythm. Sensitivity of the assay and algorithm was demonstrated by profiling heart rates during entire embryonic development. Our analysis pipeline revealed acute temperature changes triggering rapid adaption of heart rates, which has implications for standardization of experimental layout. The approach is scalable and allows scoring of multiple embryos per well resulting in a throughput of >500 embryos per 96-well plate. In a proof of principle screen for compound testing, our assay captured concentration-dependent effects of nifedipine and terfenadine over time. ConclusionA novel workflow and HeartBeat software provide efficient means for reliable and direct quantification of heart rate and rhythm of small fish in a physiological environment. Importantly, confounding factors such as anesthetics or laborious mounting are eliminated. We provide detailed profiles of embryonic heart rate dynamics in medaka and zebrafish as reference for future assay development. Ease of sample handling, automated imaging, physiological conditions and software-assisted analysis now facilitate various large-scale applications ranging from phenotypic screening, interrogation of gene functions to cardiovascular drug development pipelines.

developmental biology↗