Tracking Major Sources of Water Contamination Using Machine Learning

Development of a logic regression-based approach for the discovery of host- and niche-informative biomarkers in Escherichia coli and their application for microbial source tracking

Microbial source tracking leverages a wide range of approaches designed to trace the origins of fecal contamination in aquatic environments. Although source tracking methods are typically employed within the laboratory setting, computational techniques can be leveraged to advance microbial source tracking methodology. Herein, we present a logic regression-based supervised learning approach for the discovery of source-informative genetic markers within intergenic regions across the Escherichia coli genome that can be used for source tracking. With just single intergenic loci, logic regression was able to identify highly source-specific (i.e., exceeding 97.00%) biomarkers for a wide range of host and niche sources, with sensitivities reaching as high as 30.00%-50.00% for certain source categories, including pig, sheep, mouse, and wastewater, depending on the specific intergenic locus analyzed. Restricting the source range to reflect the most prominent zoonotic sources of E. coli transmission (i.e., bovine, chicken, human, and pig) allowed for the generation of informative biomarkers for all host categories, with specificities of at least 90.00% and sensitivities between 12.50% and 70.00%, using the sequence data from key intergenic regions, including emrKY-evgAS, ibsB-(mdtABCD-baeSR), ompC-rcsDB, and yedS-yedR, that appear to be involved in antibiotic resistance. Remarkably, we were able to use this approach to classify 48 out of 113 river water E. coli isolates collected in Northwestern Sweden as either beaver, human, or reindeer in origin with a high degree of consensus-thus highlighting the potential of logic regression modeling as a novel approach for augmenting current source tracking efforts.IMPORTANCEThe presence of microbial contaminants, particularly from fecal sources, within water poses a serious risk to public health. The health and economic burden of waterborne pathogens can be substantial-as such, the ability to detect and identify the sources of fecal contamination in environmental waters is crucial for the control of waterborne diseases. This can be accomplished through microbial source tracking, which involves the use of various laboratory techniques to trace the origins of microbial pollution in the environment. Building on current source tracking methodology, we describe a novel workflow that uses logic regression, a supervised machine learning method, to discover genetic markers in Escherichia coli, a common fecal indicator bacterium, that can be used for source tracking efforts. Importantly, our research provides an example of how the rise in prominence of machine learning algorithms can be applied to improve upon current microbial source tracking methodology.

Machine learning modeling for the prediction of phosphorus and nitrogen removal efficiency and screening of crucial microorganisms in wastewater treatment plants

The effectiveness of wastewater treatment plants (WWTPs) is largely determined by the microbial community structure in their activated sludge (AS). Interactions among microbial communities in AS systems and their indirect effects on water quality changes are crucial for WWTP performance. However, there is currently no quantitative method to evaluate the contribution of microorganisms to the operating efficiency of WWTPs. Traditional assessments of WWTP performance are limited by experimental conditions, methods, and other factors, resulting in increased costs and experimental pollutants. Therefore, an effective method is needed to predict WWTP efficiency based on AS community structure and quantitatively evaluate the contribution of microorganisms in the AS system. This study evaluated and compared microbial communities and water quality changes from WWTPs worldwide by meta-analysis of published high-throughput sequencing data. Six machine learning (ML) models were utilized to predict the efficiency of phosphorus and nitrogen removal in WWTPs; among them, XGBoost showed the highest prediction accuracy. Cross-entropy was used to screen the crucial microorganisms related to phosphorus and nitrogen removal efficiency, and the modeling confirmed the reasonableness of the results. Thirteen genera with nitrogen and phosphorus cycling pathways obtained from the screening were considered highly appropriate for the simultaneous removal of phosphorus and nitrogen. The results showed that the microbes Haliangium, Vicinamibacteraceae, Tolumonas, and SWB02 are potentially crucial for phosphorus and nitrogen removal, as they may be involved in the process of phosphorus and nitrogen removal in sewage treatment plants. Overall, these findings have deepened our understanding of the relationship between microbial community structure and performance of WWTPs, indicating that microbial data should play a critical role in the future design of sewage treatment plants. The ML model of this study can efficiently screen crucial microbes associated with WWTP system performance, and it is promising for the discovery of potential microbial metabolic pathways.

Seasonal prevalence of bacteria in the outflow of two full-scale municipal wastewater treatment plants

Despite many modern wastewater treatment solutions, the most common is still the use of activated sludge (AS). Studies indicate that the microbial composition of AS is most often influenced by the raw sewage composition (especially influent ammonia), biological oxygen demand, the level of dissolved oxygen, technological solutions, as well as the temperature of wastewater related to seasonality. The available literature mainly refers to the relationship between AS parameters or the technology used and the composition of microorganisms in AS. However, there is a lack of data on the groups of microorganisms leaching into water bodies whose presence is a signal for possible changes in treatment technology. Moreover, sludge flocs in the outflow contain less extracellular substance (EPS) which interferes microbial identification. The novelty of this article concerns the identification and quantification of microorganisms in the AS and in the outflow by fluorescence in situ hybridization (FISH) method from two full-scale wastewater treatment plants (WWTPs) in terms of 4 key groups of microorganisms involved in the wastewater treatment process in the context of their potential technological usefulness. The results of the study showed that Nitrospirae, Chloroflexi and Ca. Accumulibacter phosphatis in treated wastewater reflect the trend in abundance of these bacteria in activated sludge. Increased abundance of betaproteobacterial ammonia-oxidizing bacteria and Nitrospirae in the outflow were observed in winter. Principal component analysis (PCA) showed that loadings obtained from abundance of bacteria in the outflow made larger contributions to the variance in the PC1 factorial axis, than loadings obtained from abundance of bacteria from activated sludge. PCA confirmed the reasonableness of conducting studies not only in the activated sludge, but also in the outflow to find correlations between technological problems and qualitative and quantitative changes in the outflow microorganisms.

Fast detection of minerals in rice leaves under chromium stress based on laser-induced breakdown spectroscopy

Minerals in rice leaves is a crucial indicator of plant health, and their concentrations can be used to guide plant management. It is important to predict mineral content in contaminated rice rapidly. In this study, laser-induced breakdown spectroscopy (LIBS) was applied to quantify minerals (Ca, Cu, Fe, K, Mg, Mn, and Na) in rice leaves under chromium (Cr) stress. Two feature extraction methods, including principal component analysis (PCA) and extreme gradient boosting (XGBoost), were compared to identify important variables that related to mineral concentrations. Results showed that partial least square regression (PLSR) achieved good performance in Ca, Fe Mg, K, Mn, and Na, with correlation coefficient of 0.9782, 0.8712, 0.8933, 0.9206, 0.9856, and 0.9865, root mean square error of 219.25, 14.78, 1192.47, 385.12, 9.56, and 124.32 mg/kg, respectively. In addition, the correlation between different spectral lines were further analyzed. Cr exhibited a positive correlation with Ca, Mg, and Na, and a negative correlation with Mn, Cu, and K. The proposed method provides a high-accuracy and fast approach for minerals prediction in rice leaves under Cr stress, which is important for environmental protection and food safety.

DeepToA: An Ensemble Deep-Learning Approach to Predicting the Theater of Activity of a Microbiome

MOTIVATION

Metagenomics is the study of microbiomes using DNA sequencing. A microbiome consists of an assemblage of microbes that is associated with a "theater of activity" (ToA). An important question is, to what degree does the taxonomic and functional content of the former depend on the (details of the) latter? Here we investigate a related technical question: Given a taxonomic and/or functional profile estimated from metagenomic sequencing data, how to predict the associated ToA? We present a deep-learning approach to this question. We use both taxonomic and functional profiles as input. We apply node2vec to embed hierarchical taxonomic profiles into numerical vectors. We then perform dimension reduction using clustering, to address the sparseness of the taxonomic data and thus make the problem more amenable to deep-learning algorithms. Functional features are combined with textual descriptions of protein families or domains. We present an ensemble deep-learning framework DeepToA for predicting the "theater of activity" of amicrobial community, based on taxonomic and functional profiles. We use SHAP (SHapley Additive exPlanations) values to determine which taxonomic and functional features are important for the prediction.

RESULTS

Based on 7,560 metagenomic profiles downloaded from MGnify, classified into ten different theaters of activity, we demonstrate that DeepToA has an accuracy of 98.30%. We show that adding textual information to functional features increases the accuracy.

AVAILABILITY

Our approach is available at http://ab.inf.uni-tuebingen.de/software/deeptoa.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Nitrogen-enriched discharges from a highly managed watershed intensify red tide (Karenia brevis) blooms in southwest Florida

Karenia brevis blooms on Florida's Gulf Coast severely affect regional ecosystems, coastal economies, and public health, and formulating effective management and policy strategies to address these blooms requires an advanced understanding of the processes driving them. Recent research suggests that natural processes explain offshore bloom initiation and shoreward transport, while anthropogenic nutrient inputs may intensify blooms upon arrival along the coast. However, past correlation studies have failed to detect compelling evidence linking coastal blooms to watershed covariates indicative of anthropogenic inputs. We explain why correlation is neither necessary nor sufficient to demonstrate a causal relationship-i.e., a persistent pattern of interaction governed by deterministic rules-and pursue an empirical investigation leveraging the fact that systematic temporal patterns may reveal systematic cause-and-effect relationships. Using time series derived from in-situ sample data, we applied singular spectrum analysis-a non-parametric spectral decomposition method-to recover deterministic signals in the dynamics of K. brevis blooms and upstream water quality and discharge covariates in the Charlotte Harbor region between 2012 and 2021. Next, we applied causal analysis methods based on chaos theory-i.e., convergent cross-mapping and S-mapping-to detect and quantify persistent, state-dependent interaction regimes between coastal blooms and watershed covariates. We discovered that nitrogen-enriched Caloosahatchee River discharges have consistently intensified K. brevis blooms to varying degrees over time. River discharge was typically most influential at the earliest stages of blooms, while total nitrogen concentrations exerted the strongest influence during blooms' growth/maintenance stages. These results indicate that discharges and nitrogen inputs influence blooms through distinct yet synergistic causal mechanisms. Additionally, we traced this anthropogenic influence upstream to Lake Okeechobee (which discharges to the Caloosahatchee River) and the Kissimmee River basin (which drains into Lake Okeechobee), suggesting that watershed-scale nutrient management and modifications to Lake Okeechobee discharge protocols will likely be necessary to mitigate coastal blooms.

Ontology-aware deep learning enables ultrafast and interpretable source tracking among sub-million microbial community samples from hundreds of niches

The taxonomic structure of microbial community sample is highly habitat-specific, making source tracking possible, allowing identification of the niches where samples originate. However, current methods face challenges when source tracking is scaled up. Here, we introduce a deep learning method based on the Ontology-aware Neural Network approach, ONN4MST, for large-scale source tracking. ONN4MST outperformed other methods with near-optimal accuracy when source tracking among 125,823 samples from 114 niches. ONN4MST also has a broad spectrum of applications. Overall, this study represents the first model-based method for source tracking among sub-million microbial community samples from hundreds of niches, with superior speed, accuracy, and interpretability. ONN4MST is available at https://github.com/HUST-NingKang-Lab/ONN4MST.

Integrated analyses of fecal indicator bacteria, microbial source tracking markers, and pathogens for Southeast Asian beach water quality assessment

The degradation of coastal water quality from fecal pollution poses a health risk to visitors at recreational beaches. Fecal indicator bacteria (FIB) are a proxy for fecal pollution; however the accuracy of their representation of fecal pollution health risks at recreational beaches impacted by non-point sources is disputed due to non-human derivation. This study aimed to investigate the relationship between FIB and a range of culturable and molecular-based microbial source tracking (MST) markers and pathogenic bacteria, and physicochemical parameters and rainfall. Forty-two marine water samples were collected from seven sampling stations during six events at two tourist beaches in Thailand. Both beaches were contaminated with fecal pollution as evident from the GenBac3 marker at 88%-100% detection and up to 8.71 log₁₀ copies/100 mL. The human-specific MST marker human polyomaviruses JC and BK (HPyVs) at up to 4.33 log₁₀ copies/100 mL with 92%-94% positive detection indicated that human sewage was likely the main contamination source. CrAssphage showed lower frequencies and concentrations; its correlations with the FIB group (i.e., total coliforms, fecal coliforms, and enterococci) and GenBac3 diminished its use as a human-specific MST marker for coastal water. Human-specific culturable AIM06 and SR14 bacteriophages and general fecal indicator coliphages also showed less sensitivity than the human-specific molecular assays. The applicability of the GenBac3 endpoint PCR assay as a lower-cost prescreening step prior to the GenBac3 qPCR assay was supported by its 100% positive predictive value, but its limited negative predictive values required subsequent qPCR confirmation. Human enteric adenovirus and Vibrio cholerae were not found in any of the samples. The HPyVs related to Vibrio parahaemolyticus, Vibrio vulnificus, and 5-d rainfall records, all of which were more prevalent and concentrated during the wet season. More monitoring is therefore recommended during wet periods. Temporal differences but no spatial differences were observed, suggesting the need for a sentinel site at each beach for routine monitoring. The exceedance of FIB water quality standards did not indicate increased prevalence or concentrations of the HPyVs or Vibrio spp. pathogen group, so the utility of FIB as an indicator of health risks at tropical beaches maybe challenged. Accurate assessment of fecal pollution by incorporating MST markers could lead to developing a more effective water quality monitoring plan to better protect human health risks in tropical recreational beaches.