Supervised machine learning improves general applicability of eDNA metabarcoding for reservoir health monitoring

Integrating external stressors in supervised machine learning algorithm achieves high accuracy to predict multi-species biological integrity index of aquaculture wastewater

Monitoring and predicting the environmental impact of wastewater is essential for sustainable aquaculture. The environmental DNA metabarcoding-integrated supervised machine learning (SML) algorithm is an alternative method for ecological quality assessment and prediction. However, the ecological integrity of aquaculture wastewater and available effective input features for prediction remain unclear. Here, we used the multispecies biological integrity index (Ms-IBI) to provide a detailed categorization, identifying over half of the samples (53.85 %) as highly impacted, emphasizing the urgency to address ecological degradation; Ms-IBI emerged as a reliable label for SML models. By condensing 410 effective indicators and integrating 25 core operational taxonomic unit features with external stressors, an accuracy of 0.78 and R2 of 0.96 was achieved. Utilizing only external stressors yielded a comparably good performance with fewer input features, obtaining an accuracy of 0.74 and an R2 of 0.91. The integration of external stressors in this study highlights a practical predictive method that meets the ecological quality requirements of aquaculture wastewater, aiding the reversal of global ecological decline.

Biogeographic patterns of meio- and micro-eukaryotic communities in dam-induced river-reservoir systems

Although the Three Gorges Dam (TGD) is the world's largest hydroelectric dam, little is known about the spatial-temporal patterns and community assembly mechanisms of meio- and micro-eukaryotes and its two subtaxa (zooplankton and zoobenthos). This knowledge gap is particularly evident across various habitats and during different water-level periods, primarily arising from the annual regular dam regulation. To address this inquiry, we employed mitochondrial cytochrome c oxidase I (COI) gene-based environmental DNA (eDNA) metabarcoding technology to systematically analyze the biogeographic pattern of the three communities within the Three Gorges Reservoir (TGR). Our findings reveal distinct spatiotemporal characteristics and complementary patterns in the distribution of meio- and micro-eukaryotes. The three communities showed similar biogeographic patterns and assembly processes. Notably, the diversity of these three taxa gradually decreased along the river. Their communities were less shaped by stochastic processes, which gradually decreased along the longitudinal riverine-transition-lacustrine gradient. Hence, deterministic factors, such as seasonality, environmental, and spatial variables, along with species interactions, likely play a pivotal role in shaping these communities. Environmental factors primarily drive seasonal variations in these communities, while hydrological conditions, represented as spatial distance, predominantly influence spatial variations. These three communities followed the distance-decay pattern. In winter, compared to summer, both the decay and species interrelationships are more pronounced. Taken together, this study offers fresh insights into the composition and diversity patterns of meio- and micro-eukaryotes at the spatial-temporal level. It also uncovers the mechanisms behind community assembly in various environmental niches within the dam-induced river-reservoir systems. KEY POINTS: • Distribution and diversity of meio- and micro-eukaryotes exhibit distinct spatiotemporal patterns in the TGR. • Contribution of stochastic processes in community assembly gradually decreases along the river. • Deterministic factors and species interactions shape meio- and micro-eukaryotic community.

Supervised machine learning for understanding and predicting the status of bistable eukaryotic plankton community in urbanized rivers

Understanding and predicting the ecological status of urbanized rivers is crucial for their restoration and management. However, the complex and nonlinear nature of ecological responses poses a challenge to the development of predictive models. Here, the study investigated and predicted the status of eukaryotic plankton communities in urbanized rivers by coupling environmental DNA metabarcoding, the alternative stable states theory, and supervised machine learning (SML) models. The results revealed two distinct states of eukaryotic plankton communities under similar environmental conditions: one state was characterized by the enrichment of a diverse phytoplankton population and the high relative abundance of protozoa, whereas the alternative state was characterized by abundant phytoplankton and fungi with an associated risk of algal blooms. Turbidity was identified as a key driver based on the SML model and Mantel test. Potential analysis demonstrated that the response pattern of eukaryotic plankton communities to turbidity was thresholds with hysteresis (Threshold1 = 17 NTU, Threshold2 = 24 NTU). A reduction in turbidity induced a regime shift in the eukaryotic plankton community toward an alternative state associated with a risk of algal blooms. In the prediction of ecological status, both SML models showed excellent performance (R2 > 0.80, RMSE < 0.1, Kappa > 0.70). Additionally, SHapley Additive exPlanations analysis identified turbidity, chlorophyll-a, chemical oxygen demand (COD), ammonia nitrogen and green algae's amplicon sequence variants as crucial features for prediction, with turbidity and COD showing a synergistic effect on ecological status. A framework was further proposed to enhance the understanding and prediction of ecological status in urbanized rivers. The obtained results of this study demonstrated the feasibility of using SML models to predict and explain the ecological status of urbanized rivers with alternative stable states. This provides valuable insights for the application of SML models in the restoration and management of urbanized rivers.

Revolutionizing aquatic eco-environmental monitoring: Utilizing the RPA-Cas-FQ detection platform for zooplankton

The integration of recombinase polymerase amplification (RPA) with CRISPR/Cas technology has revolutionized molecular diagnostics and pathogen detection due to its unparalleled sensitivity and trans-cleavage ability. However, its potential in the ecological and environmental monitoring scenarios for aquatic ecosystems remains largely unexplored, particularly in accurate qualitative/quantitative detection, and its actual performance in handling complex real environmental samples. Using zooplankton as a model, we have successfully optimized the RPA-CRISPR/Cas12a fluorescence detection platform (RPA-Cas-FQ), providing several crucial "technical tips". Our findings indicate the sensitivity of CRISPR/Cas12a alone is 5 × 109 copies/reaction, which can be dramatically increased to 5 copies/reaction when combined with RPA. The optimized RPA-Cas-FQ enables reliable qualitative and semi-quantitative detection within 50 min, and exhibits a good linear relationship between fluorescence intensity and DNA concentration (R2 = 0.956-0.974***). Additionally, we developed a rapid and straightforward identification procedure for single zooplankton by incorporating heat-lysis and DNA-barcode techniques. We evaluated the platform's effectiveness using real environmental DNA (eDNA) samples from the Three Gorges Reservoir, confirming its practicality. The eDNA-RPA-Cas-FQ demonstrated strong consistency (Kappa = 0.43***) with eDNA-Metabarcoding in detecting species presence/absence in the reservoir. Furthermore, the two semi-quantitative eDNA technologies showed a strong positive correlation (R2 = 0.58-0.87***). This platform also has the potential to monitor environmental pollutants by selecting appropriate indicator species. The novel insights and methodologies presented in this study represent a significant advancement in meeting the complex needs of aquatic ecosystem protection and monitoring.