Gomes, B. D. | Search bioRxiv

bioRxiv2026

Motor sequence analysis as a sensitive biomarker of dopaminergic degeneration in a non-human primate model of parkinsonism

Parkinsons disease is characterized by progressive dopaminergic degeneration, yet motor symptoms emerge only after substantial neuronal loss - a dissociation that challenges the sensitivity of conventional behavioral endpoints in preclinical models. Here, we present a proof-of-principle study establishing a graded hemiparkinsonism model in adult male capuchin monkeys (Sapajus apella) through unilateral, MRI-guided stereotaxic injection of 6-hydroxydopamine into the substantia nigra pars compacta. Three toxin concentrations (4, 10, and 40 mg/mL; n = 3) were tested alongside a vehicle-injected sham control (n = 1). Motor function was assessed longitudinally before and after surgery using a three-task battery comprising the Staircase test, Tube test, and Brinkman board, capturing complementary dimensions of motor functions, including gross lateralization, forelimb use asymmetry, and fine digit coordination. Critically, we introduce a novel sequence-deviation metric applied to Brinkman board performance data to quantify disruption in the spatial organization of pellet retrieval independently of task success. Post-surgical tyrosine hydroxylase immunohistochemistry combined with optical fractionator stereology revealed ipsilateral dopaminergic cell losses of 47%, 59%, and 44% relative to the contralateral hemisphere across the three treated animals, with the sham showing no meaningful hemispheric difference. Behavioral impairments were heterogeneous and strategy-dependent: task completion rates were largely preserved, whereas fine motor strategy analysis revealed post-lesion increases in retrieval sequence disorganization in two of three animals. Exploratory regression analyses suggested that strategy-level metrics were more sensitive to nigrostriatal degeneration than global performance measures. These findings demonstrate that capuchin monkeys subjected to unilateral 6-hydroxydopamine lesions reproduce clinically relevant features of hemiparkinsonism and that motor sequence analysis constitutes a sensitive readout of subclinical dopaminergic dysfunction, and can outperform conventional performance-based metrics detecting early motor alterations, therefore a potential biomarker of subclinical dopaminergic dysfunction, with implications for early detection paradigms in Parkinsons disease research.

neuroscience↗

bioRxiv2024

LizardNet: A mobile hybrid deep learning tool for classification of 3D representations of Amazonian lizards

Image classification is a highly significant field in machine learning (ML), especially when applied to address longstanding and challenging issues in the biological sciences. In this study, we present the development of a hybrid deep learning-based tool suitable for deployment on mobile devices. This tool is aimed at processing and classifying three-dimensional samples of endemic lizard species from the Amazon rainforest. The dataset used in our experiment was collected at the Museu Paraense Emilio Goeldi (MPEG), Belem-PA, Brazil, and comprises three species: a) Anolis fuscoauratus; b) Hoplocercus spinosus; and c) Polychrus marmoratus. We compared the effectiveness of four artificial neural networks (ANN) for feature extraction: a) MobileNet; b) MobileNetV2; c) MobileNetV3Small; and d) MobileNetV3Large. Additionally, we evaluated five classical ML models for classifying the extracted patterns: a) Support Vector Machine (SVM); b) GaussianNB (GNB); c) AdaBoost (ADB); d) K-Nearest Neighbors (KNN); and e) Random Forest (RF). Our most effective model, MobileNetV3-Small + Linear SVM, achieved an accuracy of 0.948 and a f1-score of 0.955. Notably, it not only proved to be the least complex model among all combinations but also demonstrated the best performance after a statistical comparison. These results indicate that the combination of deep learning (DL) models with less complex classical ML algorithms, which have a lower error propensity, emerges as a viable and efficient technique for classifying three-dimensional lizard species samples. Such an approach facilitates taxonomic identification work for professionals in the field and provides a tool adaptable for integration into mobile data recording equipment, such as smartphones. Author summaryThe taxonomic classification of lizards requires an exceptional level of knowledge and attention to minute details beyond the ordinary to accurately categorize specimens. Such tasks impose significant mental and visual costs on humans, unlike computer vision algorithms capable of extracting visual patterns from images imperceptible to the human eye. In this research, we utilized a dataset from the herpetarium of the Emilio Goeldi Museum in Belem-PA, Brazil. The data were self-captured, with each sample comprised of three photos: dorsal, lateral, and ventral views of each specimen. The sample size was constrained by the quality and abundance of preserved specimens, necessitating the application of a data augmentation method on the pre-separated training and validation sets. This augmentation led to a considerable increase in the number of samples per species, from a few dozen to several hundred. Our experimental approach involved utilizing pre-trained neural networks to extract 3D sample characteristics, subsequently classified using classical machine learning algorithms. This hybrid strategy was adopted due to the nature of data collection and synthetic data augmentation. Our method enables specimen identification through three-dimensional representations, allowing for a more comprehensive utilization of morphological information by the model.

systems biology↗