Mishra, D. R. | bioRxiv Science

bioRxiv2025

Optimizing Oyster Breeding with Machine Learning and BigData for Superior Quality

1.Oyster aquaculture is a vital component of global marine ecosystems and food production, yet winter mortality events threaten both ecological stability and economic viability. Traditional selective breeding methods, reliant on phenotypic traits and slow generational cycles, struggle to address these challenges efficiently. This study introduces an innovative approach integrating machine learning with multi-omics data genomics, transcriptomics, and proteomics to optimize oyster breeding for resilience and quality. By analyzing high-resolution datasets encompassing genetic markers, environmental stressors, and survival metrics, our ML models identified key SNPs linked to cold tolerance and disease resistance. Marker-assisted selection (MAS) accelerated breeding cycles, while predictive algorithms achieved 92.4% accuracy in forecasting survival and growth traits. Controlled trials demonstrated a 30% reduction in winter mortality and a 25% improvement in growth rates among ML-selected oyster lineages compared to traditional methods. Additionally, a smartphone-based diagnostic tool was developed to enable real-time monitoring of oyster health, empowering farmers to adapt feeding and environmental strategies dynamically. This research bridges the gap between conventional aquaculture and computational innovation, offering a scalable framework to enhance genetic diversity, sustainability, and yield. By replacing trial-and-error practices with data-driven precision, our approach not only mitigates immediate industry challenges but also establishes a pathway for climate-resilient aquaculture. The fusion of ML with multi-omics technologies marks a transformative shift, enabling breeders to make rapid, evidence-based decisions that harmonize ecological stewardship with commercial demands.

bioinformatics↗

bioRxiv2024

Capturing spatiotemporal variation in salt marsh belowground biomass, a key resilience metric, through geoinformatics

The Belowground Ecosystem Resiliency Model (BERM) is a geoinformatics tool that was developed to predict belowground biomass (BGB) of Spartina alterniflora in salt marshes based on remote sensing of aboveground characteristics and other readily available hydrologic, climatic, and physical data. We sought to characterize variation in S. alterniflora BGB over both temporal and spatial gradients through extensive marsh field observations in coastal Georgia, USA, to quantify their relationship with a suite of predictor variables, and to use these results to improve performance and expand the parameter space of BERM. We conducted pairwise comparisons of S. alterniflora growth metrics measured at nine sites over three to eight years and found that BGB grouped by site differed in 69% of comparisons, while only in 21% when grouped by year. This suggests that BGB varies more spatially than temporally. We used the BERM machine learning algorithms to evaluate how variables relating to biological, climatic, hydrologic, and physical attributes covaried with these BGB observations. Flooding frequency and intensity were most influential in predicting BGB, with predictor variables related to hydrology composing 61% of the total feature importance in the BERM framework. When we used this expanded calibration dataset and associated predictors to advance BERM, model error was reduced from a normalized root mean square error of 13.0% to 9.4% in comparison to the original BERM formulation. This reflects both an improvement in predictive performance and an expansion in conditions for potential model application. Finally, we used regression commonality analysis to show that model estimates reflected the spatiotemporal structure of BGB variation observed in field measurements. These results can help guide future data collection efforts to describe landscape-scale BGB trends. The advanced BERM is a robust tool that can characterize S. alterniflora productivity and resilience over broad spatial and temporal scales.

ecology↗