Related Experiment Video
Updated: Aug 14, 2026
10:12
High-throughput DNA Extraction and Genotyping of 3dpf Zebrafish Larvae by Fin Clipping
Published on: June 29, 2018
Gene Expression-Based Classification of European Seabass Larval Batches According to Saddleback Syndrome Incidence
Andreas Tsipourlianos1, Alice Printzi2, Alexia Fytsili1
1Department of Biochemistry and Biotechnology, University of Thessaly, Biopolis, 41500 Larissa, Greece.
Animals : an Open Access Journal From MDPI
|August 13, 2026
Summary
Gene expression profiling and machine learning can identify poor quality European seabass larvae with saddleback syndrome (SBS). This molecular approach aids in early detection and improving hatchery batch quality.
Area of Science:
- Aquaculture
- Molecular Biology
- Bioinformatics
Background:
- Skeletal deformities like saddleback syndrome (SBS) in European seabass (Dicentrarchus labrax) larvae pose significant challenges in marine fish hatcheries.
- These deformities impact larval quality, welfare, production efficiency, and market value.
Purpose of the Study:
- To investigate the potential of gene expression markers combined with machine learning for a stage-specific molecular assessment of SBS-associated larval batch quality.
- To identify informative genes and develop predictive models for discriminating between high and low SBS incidence larval populations.
Main Methods:
- Larval populations were classified as GOOD or POOR based on SBS incidence at mid-metamorphosis.
- Gene expression analysis was performed at multiple larval stages (first feeding, flexion, post-flexion, mid-metamorphosis).
- Stage-specific random forest models were employed to analyze gene expression profiles and identify candidate genes.
Main Results:
- Machine learning models achieved high predictive performance (ROC AUC 0.83–0.962), particularly at the flexion stage.
- Reduced models using the top three informative genes maintained comparable performance.
- Key candidate genes were identified in pathways including mitochondrial energy production, iron metabolism, stress response, and muscle development.
Conclusions:
- Gene expression profiling coupled with machine learning offers a promising stage-aware approach for discriminating larval batches with varying SBS incidence.
- This molecular strategy could support improved quality control in marine fish hatcheries, pending further validation.
- Candidate genes related to energy metabolism and stress are potential biomarkers for assessing larval quality.
