Automated staging of zebrafish embryos with deep learning.

The zebrafish (Danio rerio) is an important biomedical model organism used in many disciplines. The phenomenon of developmental delay in zebrafish embryos has been widely reported as part of a mutant or treatment-induced phenotype. However, the detection and quantification of these delays is often achieved through manual observation, which is both time-consuming and subjective. We present KimmelNet, a deep learning model trained to predict embryo age (hours post fertilisation) from 2D brightfield images. KimmelNet's predictions agree closely with established staging methods and can detect developmental delays between populations with high confidence using as few as 100 images. Moreover, KimmelNet generalises to previously unseen data, with transfer learning enhancing its performance. With the ability to analyse tens of thousands of standard brightfield microscopy images on a timescale of minutes, we envisage that KimmelNet will be a valuable resource for the developmental biology community. Furthermore, the approach we have used could easily be adapted to generate models for other organisms.

Investigating the effects of synbiotic supplementation on functional movement, strength and muscle health in older Australians: a study protocol for a double-blind, randomized, placebo-controlled trial.

BACKGROUND: Aging has been associated with a progressive loss of skeletal muscle quality, quantity and strength, which may result in a condition known as sarcopenia, leading to a decline in physical performance, loss of independence and reduced quality of life. While the cause of impaired physical functioning observed in elderly populations appears to be multifactorial, recent evidence suggests that age-associated alterations in gut microbiota could be a contributing factor. The primary objective will be to assess the effects of a dietary synbiotic formulation on sarcopenia-related functional outcomes such as handgrip strength, gait speed and physical performance within older individuals living independently. The secondary objective will be to examine associations between changes in gut microbiota composition, functional performance and lean muscle mass. METHODS: Seventy-four elderly (60-85 years) participants will be randomized in a double-blind, placebo-controlled fashion to either an intervention or control group. The intervention group (n = 37) will receive oral synbiotic formulation daily for 16 weeks. The control group (n = 37) will receive placebo. Assessments of physical performance (including Short Physical Performance Battery, handgrip strength and timed up-and-go tests) and muscle ultrasonography will be performed at 4 time points (baseline and weeks 8, 16 and 20). Likewise, body composition via bioelectric impedance analysis and blood and stool samples will be collected at each time point. Dual-energy X-ray absorptiometry will be performed at baseline and week 16. The primary outcomes will be between-group changes in physical performance from baseline to 16 weeks. Secondary outcomes include changes in body composition, muscle mass and architecture, fecal microbiota composition and diversity, and fecal and plasma metabolomics. DISCUSSION: Gut-modulating supplements appear to be effective in modifying gut microbiota composition in healthy older adults. However, it is unclear whether these changes translate into functional and/or health improvements. In the present study, we will investigate the effects of a synbiotic formulation on measures of physical performance, strength and muscle health in healthy older populations. TRIAL REGISTRATION: This study was prospectively registered with the Australian New Zealand Clinical Trials Registry (ACTRN12622000652774) in May 2022.