Automated staging of zebrafish embryos using machine learning

Jones, Rebecca A.; Renshaw, Matthew J.; Barry, David J.; Smith, James C.

doi:10.12688/wellcomeopenres.18313.1

Cited by 8 publications

(11 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We went on to ask whether premature hatching might be secondary to a general acceleration of development. We were unable manually to detect any differences in developmental rate in MZ- fam83fa −/− embryos compared to WT, but to test this in an unbiased fashion, we used a machine-learning based object classification algorithm that enables the temporal trajectory of mutant embryos to be directly compared with their WT counterparts (Jones et al, 2022). Images were obtained of 96 embryos from WT and the most severely affected line, MZ -fam83fa −/− KO1, every 15 minutes from 4-18 hpf, then assessed by the classifier.…”

Section: Resultsmentioning

confidence: 99%

Zebrafish reveal new roles for Fam83f in hatching and the DNA damage-mediated autophagic response

Jones,

Cooper,

Kelly

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

The FAM83 (Family with sequence similarity 83) family is highly conserved in vertebrates, but little is known of the functions of these proteins beyond their association with oncogenesis. Of the family, FAM83F is of particular interest because it is the only membrane-targeted FAM83 protein. When over-expressed, FAM83F activates the canonical Wnt signalling pathway and binds to and stabilizes p53; it therefore interacts with two pathways often dysregulated in disease. Insights into gene function can often be gained by studying the roles they play during development, and here we report the generation offam83fknock-out (KO) zebrafish, which we have used to study the role of Fam83f in vivo. We show that endogenousfam83fis most strongly expressed in the hatching gland of developing zebrafish embryos, and thatfam83fKO embryos hatch earlier than their wild-type (WT) counterparts, despite developing at a comparable rate. We also demonstrate thatfam83fKO embryos are more sensitive to ionizing radiation than WT embryos, an unexpected finding, bearing in mind the previously-reported ability of FAM83F to stabilize p53. Transcriptomic analysis shows that loss offam83fleads to downregulation of phosphatidylinositol-3-phosphate (PI(3)P) binding proteins and impairment of cellular degradation pathways, particularly autophagy, a crucial component of the DNA damage response. Finally, we show that Fam83f protein is itself targeted to the lysosome when over-expressed in HEK293T cells, and that this localization is dependent upon a C terminal signal sequence. The zebrafish lines we have generated suggest that Fam83f plays an important role in autophagic/lysosomal processes, resulting in dysregulated hatching and increased sensitivity to genotoxic stress in vivo.

show abstract

Section: Resultsmentioning

confidence: 99%

Zebrafish reveal new roles for Fam83f in hatching and the DNA damage-mediated autophagic response

Jones,

Cooper,

Kelly

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…All images are the same as those used in a previously published study (Jones et al, 2022). Certain wells were manually excluded if it was apparent that the embryos died or were significantly out of view - the complete list of excluded wells is explicitly listed in the code (see github.com/djpbarry/KimmelNET/blob/main/trainmodel.py).…”

Section: Methodsmentioning

confidence: 99%

“…Image Data from Jones et al (2022) corresponding to embryos grown at 28.5°C was split randomly 50:50 into training and test data on a well-by-well basis. Image data corresponding to embryos grown at 25.0°C was used exclusively for testing.…”

Section: Methodsmentioning

confidence: 99%

“…All training and test image data used in this study is the same as that described in Jones et al (2022) and is available to download from the BioImage Archive (accession number S-BIAD531).…”

Section: Data Availabilitymentioning

confidence: 99%

“…We recently published a machine-learning based method for the staging of zebrafish embryos (Jones et al, 2022). While this method successfully discriminated between different populations of zebrafish developing at different rates, the developmental profiles it produced were distinctly non-linear.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated staging of zebrafish embryos with deep learning

Barry

Jones

Renshaw

2023

Preprint

Self Cite

View full text Add to dashboard Cite

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 with reference to staging guides, which is both time-consuming and subjective. We recently reported a machine learning-based classifier, capable of quantifying the developmental delay between two populations of zebrafish embryos. Here, we build on that work by introducing a deep learning-based model (KimmelNet) that has been trained to predict the age (hours post fertilisation) of individual zebrafish embryos. We show that when KimmelNet is tested on 2D brightfield images of zebrafish embryos, the predictions generated agree closely with those expected from the Kimmel equation. Random sampling of the test data demonstrate that KimmelNet can be used to detect developmental delay between two populations with high confidence based on as few as 20 images of each population. Finally, we show that KimmelNet's predictions are resilient against low levels of additive noise. 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.

show abstract

Robotic sorting of zebrafish embryos

Diouf,

Sadak,

Gerena

et al. 2024

J Micro-Bio Robot

View full text Add to dashboard Cite

Transcriptomics and metabolomics, two biological research fields that need large numbers of zebrafish embryos, require the removal of unfertilized or nonviable zebrafish embryos. Biologists routinely conduct the tedious, error-prone, and time-consuming manual sorting of embryos. We suggest a novel approach that combines deep learning and microfluidics for automated sorting to overcome this difficulty. To determine the developmental stage and viability of zebrafish eggs, we trained an optimized YOLOv5 model with 95.8% accuracy and a processing speed of 10.6 ms per frame, classifying them as dead, unfertilized, or alive. The eggs are contained in traps on a microfluidic chip using micro-pumps. After that, the deep learning system can identify and automatically sort the eggs according to their viability by positioning this chip on an XYZ motorized stage. The sorting experiment was conducted in two modes: without feedback and with feedback while using the dead egg position. The first one had a sorting success rate of 90% as opposed to 97.9% for the feedback mode with 3 seconds required for each dead egg. This automated approach provides a precise and efficient way to handle a large number of zebrafish embryos while also greatly reducing the workload associated with manual sorting. The success rates attained demonstrate the usefulness and effectiveness of our suggested methodology, opening new avenues for biological research involving accurate embryo selection.

show abstract

Automated staging of zebrafish embryos using machine learning

Cited by 8 publications

References 51 publications

Zebrafish reveal new roles for Fam83f in hatching and the DNA damage-mediated autophagic response

Zebrafish reveal new roles for Fam83f in hatching and the DNA damage-mediated autophagic response

Automated staging of zebrafish embryos with deep learning

Robotic sorting of zebrafish embryos

Contact Info

Product

Resources

About