Biology subjects

Coulombe, V.

Publications and source records attributed to Coulombe, V..

4 recordsLinked to original sources

bioRxiv2026

Evidence-based re-identification: Leveraging appearance cues to correct tracking mistakes rather than trying to prevent them

Naturalistic behavioral neuroscience experiments, in which groups of animals interact in enriched environments over prolonged periods, require each animal's identity to remain correct throughout the recording. Current multi-animal tracking tools assign identities frame by frame without revisiting past assignment decisions. A single, even sporadic, identity swap is therefore likely to persist until the end of the recording. Consequently, error-free tracking results become progressively less likely as recordings lengthen and cohorts grow. Even state-of-the-art multi-object tracking (MOT) methods that leverage appearance cues do so only to make each assignment more robust. This robustness, however, only delays the inevitable as even the most robust assignment process will eventually make a mistake over prolonged recordings. A mistake that will then persist just as it otherwise would have. Here, we introduce evidence-based re-identification, which uses appearance cues to correct tracking mistakes rather than prevent them. This fundamental shift allows the algorithm to build and progressively enrich appearance representations for each tracked subject. Tracking mistakes are then detected by continuously monitoring the evolution of these representations, triggering a correction whenever two representations drift toward one another in a sustained way. On two distinct, minutes-long benchmarks of mice interacting in enriched environments, motion-only trackers (DeepLabCut, SLEAP, ByteTrack) and the appearance-based BoT-SORT-ReID began accumulating identity errors within seconds, whereas ByteTrack paired with evidence-based re-identification remained reliable, outperforming even ByteTrack paired with the marker-based Tailtag system. This reliability was also positively correlated with the accuracy of the appearance extractor, but only when it was used through evidence-based re-identification. Foundation image encoders (CLIP, MegaDescriptor, DINOv3) showed promising out-of-the-box performance yet still required fine-tuning to be effective. Together, these results show that multi-animal tracking algorithms can remain reliable over prolonged periods only if they can reliably recover from tracking mistakes, and that fine-tuning appearance extractors remains essential to doing so.

neuroscience↗

bioRxiv2025

Modulation of SLP-2 expression protects against alpha-synuclein neuropathology by mitigating mitochondrial dysfunction

Parkinsons Disease (PD) is a progressive neurodegenerative disorder characterized by dopaminergic neuron loss and the accumulation of alpha-synuclein (Syn)-rich aggregates known as Lewy bodies. Mitochondrial dysfunction is a key contributor to PD pathology, and mitochondrial defects are part of the pathogenic mechanisms induced by Syn. Stomatin-Like protein 2 (SLP-2) is a mitochondrial scaffold protein that regulates mitochondrial integrity and function. Here, we investigated whether SLP-2 induction can counteract Syn-induced mitochondrial dysfunction and neurodegeneration. We found that SLP-2 levels were reduced in human PD brains and an A53T Syn mouse model. Mild overexpression of SLP-2 improved mitochondrial function, reduced oxidative stress, and prevented Syn-mitochondria interactions in human iPSC-derived neurons. In vivo, SLP-2 overexpression protected dopaminergic neurons and motor function, while its depletion exacerbated degeneration and motor deficits in both mouse and Drosophila models. These findings suggest SLP-2 as a key regulator of mitochondrial resilience and a potential therapeutic target for PD and alpha-synucleinopathies.

neuroscience↗

bioRxiv2024

PrecisionTrack: Reliable Tracking of Large Groups of Animals Interacting in Complex Environments Over Extended Periods

Large-scale ethological behavioral studies can provide insights into the neuronal processes underlying complex and social behaviors, potentially opening new avenues for mental health research. However, studying socially interacting animals in naturalistic environments remains technically challenging, as current approaches struggle to simultaneously maintain subject identity, extract behavior, and characterize social interactions over prolonged periods. Here, we present PrecisionTrack, an open-source and fully integrated framework designed for real-time multi-animal tracking, behavioral analysis, and social interaction inference in large groups of interacting animals. PrecisionTrack achieves high spatiotemporal accuracy in crowded and highly occlusive environments while maintaining robust long-term identity tracking and low-latency processing. To extend behavioral inference beyond pose estimation, we developed the Multi-animal Action Recognition Transformer (MART), a transformer-based architecture enabling real-time subject-level action recognition, and Graph-MART (G-MART), a graph neural network module that infers directed social interactions and interaction partners within groups. In addition, PrecisionTrack supports quantitative analysis of evolving social networks across time, enabling investigation of the temporal organization and stability of social dynamics in naturalistic settings. The entire framework is open source and accompanied by standardized workflows and documentation, enabling users to train, evaluate, and deploy custom behavioral analysis pipelines across species and experimental contexts. PrecisionTrack provides a scalable platform for quantitative investigation of complex social behaviors at a resolution and duration not accessible with existing methods.

neuroscience↗

bioRxiv2024

The Tailtag System: Tracking Multiple Mice in a Complex Environment Over a Prolonged Period Using ArUco Markers.

Despite recent advancements, safely and reliably tracking individual movements over extended periods, particularly within complex social groups, remains challenging. Traditional methods like colour coding, tagging, and RFID tracking, while effective, have notable practical limitations. State-of-the-art neural network-based trackers often struggle to maintain individual identities in large groups for more than a few seconds. Fiducial tags like ArUco codes present a potential solution by enabling accurate tracking and identity management, yet their topical application on mammals has proven difficult without frequent human intervention. In this study, we introduce the Tailtag system: a non-invasive, ergonomic tail ring embedded with an ArUco marker. This system includes a comprehensive parameter optimization guide along with practical guidelines on marker selection. Our Tailtag system demonstrated the ability to automatically and reliably track individual mice in social colonies of up to 20 individuals over a period of seven days without performance degradation, facilitating a detailed analysis of social dynamics in naturalized environments.

animal behavior and cognition↗