SAMBA: A Segment Anything Model-based tool for semi-automated Behavioural Analysis of Drosophila and other model organisms
Preprint
Abstract
Quantitative behavioural analysis is a powerful approach for linking genotype to phenotype, but many existing tools require specialised hardware, extensive preprocessing, or coding expertise. We present SAMBA (Segment Anything Model for Behavioural Analysis), an open-access, Google Colab-based pipeline that harnesses the Segment Anything Model 2 (SAM2) for accurate, semi-automated tracking without thresholding or background subtraction. With minimal user input, SAMBA extracts movement parameters, detects behavioural states, and supports batch processing. Validating SAMBA in a Drosophila melanogaster model of 3-hydroxyisobutyryl-CoA hydrolase (HIBCH) deficiency revealed impaired locomotion, reduced speed, and altered decision-making, highlighting its ability to capture nuanced phenotypes in neurometabolic disease. We further demonstrate adaptability to adult Drosophila and larval zebrafish, underscoring its cross-species utility. By combining foundation-model segmentation with an accessible interface, SAMBA lowers technical barriers to high-throughput behavioural phenotyping and is readily extendable to diverse model organisms, life stages, and experimental paradigms. This flexibility positions SAMBA as a valuable platform for accelerating disease mechanism studies, genetic screens, and preclinical testing. SUMMARY STATEMENT: We present an easy-to-use, open-access tool designed for Drosophila larval movement analysis, and readily customised for other applications, enabling rapid, scalable assessment of organism behaviour without specialised equipment or coding expertise.Keywords
All Related Versions
- Published version: Disease Models & Mechanisms, 19 (2).
This publication has 19 references indexed in Scilit:
- Ectopic protein lysine methacrylation contributes to defects caused by loss of HIBCH or ECHS1Cell Reports, 2025
- Zebrafish models of candidate human epilepsy-associated genes provide evidence of hyperexcitabilityiScience, 2024
- Drug repurposing for neurodegenerative diseases using Zebrafish behavioral profilesBiomedicine & Pharmacotherapy, 2024
- Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issuesArray, 2021
- A biallelic pathogenic variant in the OGDH gene results in a neurological disorder with features of a mitochondrial diseaseJournal of Inherited Metabolic Disease, 2020
- Deep Learning in Medical Image Analysis2020
- Neuron-specific knockdown of Drosophila HADHB induces a shortened lifespan, deficient locomotive ability, abnormal motor neuron terminal morphology and learning disabilityExperimental Cell Research, 2019
- Identification of HIBCH Gene Mutations Causing Autosomal Recessive Leigh Syndrome: A Gene Involved in Valine MetabolismPediatric Neurology, 2015
- Drosophila – a versatile model in biology & medicineMaterials Today, 2011
- How maggots move: Allometry and kinematics of crawling in larval DipteraJournal of Insect Physiology, 1995