Risk prediction of microcystins based on water quality surrogates: A case study in a eutrophicated urban river network

He, Xinchen; Wang, Hua; Zhuang, Wei; Liang, Dongfang; Ao, Yanhui

doi:10.1016/j.envpol.2021.116651

Cited by 14 publications

(4 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The WHO recommends a limit of 1 g/L for the most harmful cyanotoxins, microcystin-LR, and saxitoxins, which are present in drinking and recreational waters and block protein phosphatase, causing liver failure and hepatic hemorrhage [54]. Additionally, dissolved microcystin may stay in water for a long time without any adverse effects [55].…”

Section: Monitoring Of Phycotoxin Pollutants In Environmental and Dri...mentioning

confidence: 99%

Recent Advances in Aptasensing Strategies for Monitoring Phycotoxins: Promising for Food Safety

Zahraee

Mehrzad²,

Abnous

et al. 2022

Biosensors

View full text Add to dashboard Cite

Phycotoxins or marine toxins cause massive harm to humans, livestock, and pets. Current strategies based on ordinary methods are long time-wise and require expert operators, and are not reliable for on-site and real-time use. Therefore, it is urgent to exploit new detection methods for marine toxins with high sensitivity and specificity, low detection limits, convenience, and high efficiency. Conversely, biosensors can distinguish poisons with less response time and higher selectivity than the common strategies. Aptamer-based biosensors (aptasensors) are potent for environmental monitoring, especially for on-site and real-time determination of marine toxins and freshwater microorganisms, and with a degree of superiority over other biosensors, making them worth considering. This article reviews the designed aptasensors based on the different strategies for detecting the various phycotoxins.

show abstract

Section: Monitoring Of Phycotoxin Pollutants In Environmental and Dri...mentioning

confidence: 99%

Recent Advances in Aptasensing Strategies for Monitoring Phycotoxins: Promising for Food Safety

Zahraee

Mehrzad²,

Abnous

et al. 2022

Biosensors

View full text Add to dashboard Cite

show abstract

“…There is a clear need for this since machine learning models are becoming increasingly popular in predicting pollutants because of their advantages over traditional statistical models, such as their ability to simulate the complex nonlinear response between drivers and response − and often more accurate prediction performance. , Moreover, some studies applied machine learning models to simulate trace pollutants without accounting for the issues with left-censoring. In those studies, data preprocessing by substitution or discretization is required, − which can introduce bias and other limitations as discussed in statistical models. A few machine learning techniques do take into account the issues with censored data; for instance, survival analysis deals with the issue of censoring and also widely adopts machine learning models. − However, survival analysis is specifically designed for right censoring to estimate the time until the occurrence of an event of interest, , which is very different from predicting pollutant concentrations and thus not applicable to our analysis.…”

Section: Introductionmentioning

confidence: 99%

A Two-Stage Interpretable Machine Learning Framework for Accurate Prediction of Trace Pollutants: With an Application to Microcystin

Wu,

Liang,

Qiu

2023

ACS EST Water

View full text Add to dashboard Cite

Trace pollutants are widely observed in aquatic ecosystems and can significantly impact human health and the environment. Accurate prediction of trace pollutants and understanding their response to environmental drivers are key to environmental management, yet these tasks remain challenging. An important reason for this challenge is that monitoring data for trace pollutants are often left-censored, leading to biased estimation and inaccurate response-driver relationships. Here we propose a novel two-stage interpretable machine learning framework applicable to left-censored trace pollutant data. The two stages include (1) a classifier to predict the presence of the pollutant and (2) a regressor to predict the pollutant concentration if present. The two stages were followed by a model interpretation to understand the contribution of drivers to the presence and concentration of the pollutant accordingly. We take the prediction of microcystin (MICX) in lakes across the United States as a case study. Applying this framework to MICX consistently improved prediction accuracy, including prediction of its occurrence and concentration regardless of the algorithms and performance metrics used. The best-performing algorithm using the two-stage framework, compared with the baseline model, improves classification performance by 48% to 290% and the regression performance by 11% to 33%, depending on the metric used to evaluate the performance. The interpretable machine learning model also successfully revealed the impacts of the most important drivers on the presence of MICX and its concentration. Our results showed the advantages of this framework, including its interpretability to understand the driver-response relationship, ability to handle nonlinearity, better prediction performance, differentiation between the underlying processes, and potential to be generalized to other pollutants. As such, we anticipate that the framework we propose will be a starting point for using state-of-the-art interpretable machine learning models for predicting trace pollutants.

show abstract

“…Among them, the most threatening one is microcystin‐leucine arginine (MC‐LR). It is known that MC‐LR concentrations in Taihu Lake and Chaohu Lake in China can reach 14.36 and 26.7 μg/L, respectively 22,23 . In some heavily contaminated aquatic systems, the concentration of MC‐LR could even reach several 1000 μg/L 9 .…”

Section: Introductionmentioning

confidence: 99%

“…It is known that MC-LR concentrations in Taihu Lake and Chaohu Lake in China can reach 14.36 and 26.7 μg/L, respectively. 22,23 In some heavily contaminated aquatic systems, the concentration of MC-LR could even reach several 1000 μg/L. 9 In addition, the chemical properties of MC-LR are stable, and it is difficult to be completely removed by conventional drinking water treatment methods.…”

Section: Introductionmentioning

confidence: 99%

PI3K/AKT/mTOR pathway mediated‐cell cycle dysregulation contribute to malignant proliferation of mouse spermatogonia induced by microcystin‐leucine arginine

Liu

Tian

et al. 2022

Environmental Toxicology

View full text Add to dashboard Cite

Environmental cyanotoxin exposure may be a trigger of testicular cancer. Activation of PI3K/AKT/mTOR signaling pathway is the critical molecular event in testicular carcinogenesis. As a widespread cyanotoxin, microcystin-leucine arginine (MC-LR) is known to induce cell malignant transformation and tumorigenesis. However, the effects of MC-LR on the regulatory mechanism of PI3K/AKT/mTOR pathway in seminoma, the most common testicular tumor, are unknown. In this study, mouse spermatogonia cell line (GC-1) and nude mice were used to investigate the effects and mechanisms of MC-LR on the malignant transformation of spermatogonia by nude mouse tumorigenesis assay, cell migration invasion assay, western blot, and cell cycle assay, and so forth. The results showed that, after continuous exposure to environmentally relevant concentrations of MC-LR (20 nM) for 35 generations, the proliferation, migration, and invasion abilities of GC-1 cells were increased by 120%, 340%, and 370%, respectively. In nude mice, MC-LR-treated GC-1 cells formed tumors with significantly greater volume (0.998 ± 0.768 cm 3 ) and weight (0.637 ± 0.406 g) than the control group (0.067 ± 0.039 cm 3 ; 0.094 ± 0.087 g) (P < .05). Furthermore, PI3K inhibitor Wortmannin inhibited the PI3K/AKT/mTOR pathway and its downstream proteins (c-MYC, CDK4, CCND1, and MMP14) activated by MC-LR.Blocking PI3K alleviated MC-LR-induced cell cycle disorder and malignant proliferation, migration and invasive of GC-1 cells. Altogether, our findings suggest that MC-LR can induce malignant transformation of mouse spermatogonia, and the PI3K/ AKT/mTOR pathway-mediated cell cycle dysregulation may be an important target for malignant proliferation. This study provides clues to further reveal the etiology and pathogenesis of seminoma.

show abstract

Risk prediction of microcystins based on water quality surrogates: A case study in a eutrophicated urban river network

Cited by 14 publications

References 51 publications

Recent Advances in Aptasensing Strategies for Monitoring Phycotoxins: Promising for Food Safety

Recent Advances in Aptasensing Strategies for Monitoring Phycotoxins: Promising for Food Safety

A Two-Stage Interpretable Machine Learning Framework for Accurate Prediction of Trace Pollutants: With an Application to Microcystin

PI3K/AKT/mTOR pathway mediated‐cell cycle dysregulation contribute to malignant proliferation of mouse spermatogonia induced by microcystin‐leucine arginine

Contact Info

Product

Resources

About