An Intelligent Early Warning System for Harmful Algal Blooms: Harnessing the Power of Big Data and Deep Learning.

Harmful algal blooms (HABs) pose a significant ecological threat and economic detriment to freshwater environments. In order to develop an intelligent early warning system for HABs, big data and deep learning models were harnessed in this study. Data collection was achieved utilizing the vertical aquatic monitoring system (VAMS). Subsequently, the analysis and stratification of the vertical aquatic layer were conducted employing the "DeepDPM-Spectral Clustering" method. This approach drastically reduced the number of predictive models and enhanced the adaptability of the system. The Bloomformer-2 model was developed to conduct both single-step and multistep predictions of Chl-a, integrating the " Alert Level Framework" issued by the World Health Organization to accomplish early warning for HABs. The case study conducted in Taihu Lake revealed that during the winter of 2018, the water column could be partitioned into four clusters (Groups W1-W4), while in the summer of 2019, the water column could be partitioned into five clusters (Groups S1-S5). Moreover, in a subsequent predictive task, Bloomformer-2 exhibited superiority in performance across all clusters for both the winter of 2018 and the summer of 2019 (MAE: 0.175-0.394, MSE: 0.042-0.305, and MAPE: 0.228-2.279 for single-step prediction; MAE: 0.184-0.505, MSE: 0.101-0.378, and MAPE: 0.243-4.011 for multistep prediction). The prediction for the 3 days indicated that Group W1 was in a Level I alert state at all times. Conversely, Group S1 was mainly under an Level I alert, with seven specific time points escalating to a Level II alert. Furthermore, the end-to-end architecture of this system, coupled with the automation of its various processes, minimized human intervention, endowing it with intelligent characteristics. This research highlights the transformative potential of integrating big data and artificial intelligence in environmental management and emphasizes the importance of model interpretability in machine learning applications.

Effects of high-flux hemodialysis and hemodiafiltration on the mortality of patients with end-stage kidney disease: a meta-analysis.

BACKGROUND: High-flux hemodialysis (HFHD) is widely used in hemodialysis centers and is the mode of hemodialysis actively recommended by the guidelines. Additionally, hemodiafiltration (HDF) is widely used in clinical practice. However, there are some inconsistencies in the results of studies on the effects of HDF and HFHD, which has caused controversy regarding which of these two dialysis modalities to select. OBJECTIVE: To explore the effect of HFHD and HDF on the survival of patients with end-stage kidney disease (ESKD). METHODS: A systematic search of the PubMed, EMBASE, Cochrane Library, CNKI, Wanfang, and VIP databases was conducted, focusing on cohort studies and randomized controlled trials on hemodialysis in patients with ESKD using HFHD or HDF. A meta-analysis of all-cause mortality and cardiovascular mortality was conducted using Review Manager 5.3 software, and fixed and random effect models were applied according to the heterogeneity results. RESULTS: A total of 13 studies, including six cohort studies and seven randomized controlled trials, were included in the final analysis. The results revealed that HFHD had no statistically significant effect on the all-cause mortality (odds ratio (OR): 1.16, 95% confidence interval (CI): 0.86, 1.57) or cardiovascular mortality (OR: 0.86, 95% CI: 0.64, 1.15) of patients with ESKD. However, compared with HDF, HFHD reduced the infection mortality rate (OR: 0.50, 95% CI: 0.33, 0.77). CONCLUSIONS: Compared with HDF, HFHD has no obvious benefits for all-cause mortality or cardiovascular mortality in patients with ESKD, but reduced risk of infection-related death.

A Memorizing and Generalizing Framework for Lifelong Person Re-Identification.

In this paper, we introduce a challenging yet practical setting for person re-identification (ReID) task, named lifelong person re-identification (LReID), which aims to continuously train a ReID model across multiple domains and the trained model is required to generalize well on both seen and unseen domains. It is therefore critical to learn a ReID model that can learn a generalized representation without forgetting knowledge of seen domains. In this paper, we propose a new MEmorizing and GEneralizing framework (MEGE) for LReID, which can jointly prevent the model from forgetting and improve its generalization ability. Specifically, our MEGE is composed of two novel modules, i.e., Adaptive Knowledge Accumulation (AKA) and differentiable Ranking Consistency Distillation (RCD). Taking inspiration from the cognitive processes in the human brain, we endow AKA with two special capacities, knowledge representation and knowledge operation by graph convolution networks. AKA can effectively mitigate catastrophic forgetting on seen domains while improving the generalization ability to unseen domains. By considering the ranking factor that is specifically important in ReID, RCD is designed to distill the ranking knowledge in a differentiable manner, which can further prevent the catastrophic forgetting. To supporting the study of LReID, we build a new and large-scale benchmark with two practical evaluation protocols that consider the metrics of non-forgetting and generalization. Experiments demonstrate that 1) our MEGE framework can effectively improve the performance on seen and unseen domains under the domain-incremental learning constraint, and that 2) the proposed MEGE outperforms state-of-the-art competitors by large margins.

Efficient production of poly-3-hydroxybutyrate from acetate and butyrate by halophilic bacteria Salinivibrio spp. TGB4 and TGB19.

Volatile fatty acids (VFAs) derived from biomass are considered to be economical and environmentally friendly feedstocks for microbial fermentation. Converting VFAs to polyhydroxyalkanoate (PHA) could reduce the substrate cost and provide an economically viable route for the commercialization of PHA. The halophilic bacteria Salinivibrio spp. TGB4 and TGB19, newly isolated from salt fields, were found to accumulate poly-3-hydroxybutyrate (PHB) using acetate or butyrate as the substrate. Both strains exhibited considerable cell growth (OD600 of ~8) even at acetate concentration of 100 g/L. In shake flask cultures, TGB4 produced PHB titers of 0.90 and 1.34 g/L, while TGB19 produced PHB titers of 0.25 and 2.53 g/L with acetate and butyrate, respectively. When acetate and butyrate were both applied, PHB production was significantly increased, and the PHB titer of TGB4 and TGB19 reached 6.14 and 6.84 g/L, respectively. After optimizing the culture medium, TGB19 produced 8.42 g/L PHB, corresponding to 88.55 wt% of cell dry weight. During fed-batch cultivation, TGB19 produced a PHB titer of 53.23 g/L. This is the highest reported PHB titer using acetate and butyrate by pure microbial cultures and would provide promising hosts for the industrial production of PHA from VFAs.

Complete genome sequence of Neptunomonas concharum JCM17730T: An acetate assimilating bacterium isolated from a dead ark clam.

The marine bacterium Neptunomonas concharum was firstly characterized in 2012. It preferred to utilize acetate as the carbon source to accumulate poly-3-hydroxybutyrate (PHB) as intracellular carbon and energy storage. Here we report the genomic characteristics of N. concharum JCM17730T. The complete genome sequence of N. concharum JCM17730T consists of 3,561,992 bp in one contig, without plasmid. Analysis of coding sequences revealed the presence of genomic features involved in acetate assimilation and PHB metabolism. The genome of N. concharum JCM17730T contains three genes encoding acetyl-CoA synthetase and two genes encoding isocitrate lyase. Three polyhydroxyalkanoate synthases and one polyhydroxyalkanoate depolymerase are scattered throughout the genomic DNA. The genome features provide interesting insights into the acetate and PHB metabolism of N. concharum JCM17730T and would facilitate further research on the genetic engineering of marine bacteria for efficient PHB production.

Characterization of polyhydroxyalkanoate synthases from the marine bacterium Neptunomonas concharum JCM17730.

Neptunomonas concharum JCM17730 was isolated from an ark clam sample and characterized as a mesophilic bacterium. The genome of N. concharum JCM17730 contains thirteen genes related to polyhydroxyalkanoates (PHA) metabolism. Three PHA synthase encoding genes were identified, and phylogenetic analysis of enzyme sequences suggested the presence of two class I PHA synthases and one class III PHA synthase. The PHA synthases of N. concharum were heterologously expressed with acetyl-CoA acetyltransferase and acetoacetyl-CoA reductase in Escherichia coli to confirm the catalytic activity of each PHA synthase. Recombinants harboring different PHA synthase exhibit important distinctions in poly-3-hydroxybutyrate synthesis ability under various temperatures. Decreased cultivation temperature (≤30 °C) significantly improved PHB titer and content. This is the first report on characterization of PHA synthases from the marine genus Neptunomonas and would provide molecular basis for PHA production using Neptunomonas species.