Exploration of machine learning algorithms for predicting the changes in abundance of antibiotic resistance genes in anaerobic digestion

Antibiotic resistance genes in anaerobic digestion: Unresolved challenges and potential solutions

Antimicrobial resistance (AMR) threatens public health, necessitating urgent efforts to mitigate the global impact of antibiotic resistance genes (ARGs). Anaerobic digestion (AD), known for volatile solid reduction and energy generation, also presents a feasible approach for the removal of ARGs. This review encapsulates the existing understanding of ARGs and antibiotic-resistant bacteria (ARB) during the AD process, highlighting unresolved challenges pertaining to their detection and quantification. The questions raised and discussed include: Do current ARGs detection methods meet qualitative and quantitative requirements? How can we conduct risk assessments of ARGs? What happens to ARGs when they come into co-exposure with other emerging pollutants? How can the application of internal standards bolster the reliability of the AD resistome study? What are the potential future research directions that could enhance ARG elimination? Investigating these subjects will assist in shaping more efficient management strategies that employ AD for effective ARG control.

Application of Machine Learning for FOS/TAC Soft Sensing in Bio-Electrochemical Anaerobic Digestion

This study explores the application of various machine learning (ML) models for the real-time prediction of the FOS/TAC ratio in microbial electrolysis cell anaerobic digestion (MEC-AD) systems using data collected during a 160-day trial treating brewery wastewater. This study investigated models including decision trees, XGBoost, support vector regression, a variant of support vector machine (SVM), and artificial neural networks (ANNs) for their effectiveness in the soft sensing of system stability. The ANNs demonstrated superior performance, achieving an explained variance of 0.77, and were further evaluated through an out-of-fold ensemble approach to assess the selected model's performance across the complete dataset. This work underscores the critical role of ML in enhancing the operational efficiency and stability of bio-electrochemical systems (BES), contributing significantly to cost-effective environmental management. The findings suggest that ML not only aids in maintaining the health of microbial communities, which is essential for biogas production, but also helps to reduce the risks associated with system instability.

The simultaneous addition of chitosan and peat enhanced the removals of antibiotics resistance genes during biogas residues composting

Direct reuse of biogas residue (BR) has the potential to contribute to the dissemination of antibiotic resistance genes (ARGs). Although high-temperature composting has been demonstrated as an effective method for the harmless treatment of organic waste, there is few researches on the fate of ARGs in high-temperature composting of BR. This research examined the impact of adding 5% chitosan and 15% peat on physicochemical characteristics, microbial communities, and removal of ARGs during BR-straw composting in 12 Biolan 220L composters for 48 days. Our results showed that the simultaneous addition of chitosan and peat extended the high-temperature period, and increased the highest temperature to 74 °C and germination index. These effects could be attributed to the presence of thermophilic cellulose-decomposing genera (Thermomyces and Thermobifida). Although the microbial communities differed compositionally among temperature stages, their dissimilarity drastically reduced at final stage, indicating that the impact of different treatments on microbial community composition decreases at the end of composting. Peat had a greater impact on aerobic genera capable of cellulose degradation at thermophilic stage than chitosan. Surprisingly, despite the total copy number of ARGs significantly decreased during composting, especially in the treatment with both chitosan and peat, intl1 gene abundance significantly increased 2 logs at thermophilic stage and maintained high level in the final compost, suggesting there is still a potential risk of transmission and proliferation of ARGs. Our work shed some lights on the development of waste resource utilization and emerging contaminants removal technology.

Microbial electrosynthesis technology for CO2 mitigation, biomethane production, and ex-situ biogas upgrading

Currently, global annual CO2 emissions from fossil fuel consumption are extremely high, surpassing tens of billions of tons, yet our capacity to capture and utilize CO2 remains below a small fraction of the amount generated. Microbial electrosynthesis (MES) systems, an integration of microbial metabolism with electrochemistry, have emerged as a highly efficient and promising bio-based carbon-capture-and-utilization technology over other conventional techniques. MES is a unique technology for lowering the atmospheric CO2 as well as CO2 in the biogas, and also simultaneously convert them to renewable bioenergy, such as biomethane. As such, MES techniques could be applied for biogas upgrading to generate high purity biomethane, which has the potential to meet natural gas standards. This article offers a detailed overview and assessment of the latest advancements in MES for biomethane production and biogas upgrading, in terms of selecting optimal methane production pathways and associated electron transfer processes, different electrode materials and types, inoculum sources and microbial communities, ion-exchange membrane, externally applied energy level, operating temperature and pH, mode of operation, CO2 delivery method, selection of inorganic carbon source and its concentration, start-up time, and system pressure. It also highlights the current MES challenges associated with upscaling, design and configuration, long-term stability, energy demand, techno-economics, achieving net negative carbon emission, and other operational issues. Moreover, we provide a summary of current and future opportunities to integrate MES with other unique biosystems, such as methanotrophic bioreactors, and incorporate quorum sensing, 3D printing, and machine learning to further develop MES as a better biomethane-producer and biogas upgrading technique.

Understanding the mechanism of microplastic-associated antibiotic resistance genes in aquatic ecosystems: Insights from metagenomic analyses and machine learning

The pervasive presence of microplastics (MPs) in aquatic systems facilitates the transmission of antibiotic resistance genes (ARGs), thereby posing risks to ecosystems and human well-being. However, owing to variations in environmental backgrounds and the limited scope of research subjects, studies on ARGs in MPs lack unified conclusions, particularly regarding whether different types of MPs selectively promote ARG enrichment. Analysing large-scale datasets can better encompass broad spatiotemporal scales and diverse samples, facilitating a more extensive exploration of the complex ecological relationships between MPs and ARGs. The present study integrated existing metagenomic datasets to conduct a comprehensive risk assessment and comparative analysis of resistance groups across various MPs. In addition, we endeavoured to elucidate potential associations between ARGs and bacterial taxa, as well as MP structural features, using machine learning (ML) methods. The findings of our research highlight the pivotal role of MP type in shaping plastispheres, accounting for 9.56 % of the biotic variation (Adonis index) and explaining 18.59 % of the ARG variance. Compared to conventional MPs, biodegradable MPs, such as polyhydroxyalkanoates (PHA) and polylactic acid (PLA), exhibit lower species uniformity and diversity but pose a higher risk of ARG occurrence. These ML approaches effectively forecasted ARG abundance by using the bacterial taxa and molecular structure descriptors (MDs) of MPs (average R2tra = 0.882, R2test = 0.759). Feature analysis showed that MDs associated with lipophilicity, solubility, toxicity, and surface potential significantly influenced the relative abundance of ARGs in the plastispheres. The interpretable multiple linear regression (MLR) model, particularly notable, elucidated a linear relationship between bacterial genera and ARGs, offering promise for identifying potential ARG hosts. This study offers novel insights into ARG dynamics and ecological risks within aquatic plastispheres, highlighting the importance of comprehensive MP monitoring initiatives.

Explainable machine learning-driven predictive performance and process parameter optimization for caproic acid production

In this study, four machine learning (ML) prediction models were developed to predict and optimize the production performance of caproic acid based on substrates, products, and process parameters. The XGBoost outperformed others, with a high R2 of 0.998 on the training set and 0.885 on the test set. Feature importance analysis revealed hydraulic retention time (HRT) and butyric acid concentration are decisive. The SHAP method offered profound insights into the interplay and cumulative effects of substrate composition, identified the synergistic effects between butyric acid and lactic acid, and emphasized adding glucose can benefit caproic with lactic acid co-fermentation. By integrating the Adaptive Variation Particle Swarm Optimization (AVPSO) algorithm, the optimal process conditions to achieve a maximum caproic acid production of 8.64 g/L was obtained. This study not only advances caproic acid production but contributes a versatile ML-driven strategy applicable to bioprocess optimizations, potentially transformative for sustainable and economically viable bioproduction.

Deciphering and predicting changes in antibiotic resistance genes during pig manure aerobic composting via machine learning model

Livestock manure is one of the most important pools of antibiotic resistance genes (ARGs) in the environment. Aerobic composting can effectively reduce the spread of antibiotic resistance risk in livestock manure. Understanding the effect of aerobic composting process parameters on manure-sourced ARGs is important to control their spreading risk. In this study, the effects of process parameters on ARGs during aerobic composting of pig manure were explored through data mining based on 191 valid data collected from literature. Machine learning (ML) models (XGBoost and Random Forest) were utilized to predict the rate of ARGs changes during pig manure composting. The model evaluation index of the XGBoost model (R2 = 0.651) was higher than that of the Random Forest (R2 = 0.490), indicating that XGBoost had better prediction performance. Feature importance was further calculated for the XGBoost model, and the XGBoost black box model was interpreted by Shapley additive explanations analysis. Results indicated that the influencing factors on the ARGs variation in pig manure were sequentially divided into thermophilic period, total composting period, composting real time, and thermophilic stage average temperature. The findings gave an insight into the application of ML models to predict and decipher the ARG changes during manure composting and provided suggestions for better composting manipulation and optimization of process parameters.

Correlations and impact of anaerobic digestion operating parameters on the start-up duration: Database construction for robust start-up guidelines

Anaerobic digestion (AD) has become a popular technique for organic waste management while offering economic and environmental advantages. As AD becomes increasingly prevalent worldwide, research efforts are primarily focused on optimizing its processes. During the operation of AD systems, the occurrence of unstable events is inevitable. So far, numerous conclusions have been drawn from full and lab-scale studies regarding the driving factors of start-up perturbations. However, the lack of standardized practices reported in start-up studies raises concerns about the comparability and reliability of obtained data. This study aims to develop a knowledge database and investigate the possibility of applying machine learning techniques on experimentation-extracted data to assist start-up planning and monitoring. Thus, a standardized database referencing 75 cases of start-up of one-stage wet continuously-stirred tank reactors (CSTR) processing agricultural, industrial, or municipal organic effluent in mono-digestion from 31 studies was constructed. 10 % of the total observations included in this database concern failed start-up experiments. Then, correlations between the parameters and their impacts on the start-up duration were studied using multivariate analysis and a model-based ranking methodology. Insights into trends of choices were highlighted through the correlation analysis of the database. As such, scenarios favoring short start-up duration were found to involve relatively low retention times (average initial and final hydraulic retention times, (HRTi) and (HRTf) of 26.25 and 20.6 days, respectively), high mean organic loading rates (average OLRmean of 5.24 g VS·d-1·L -1) and the processing of highly fermentable substrates (average feed volatile solids (VSfeed) of 81.35 g L-1). The model-based ranking of AD parameters demonstrated that the HRTf, the VSfeed, and the target temperature (Tf) have the strongest impact on the start-up duration, receiving the highest relative scores among the evaluated AD parameters. The database could serve as a reference for comparison purposes of future start-up studies allowing the identification of factors that should be closely controlled.

Exploring an accurate machine learning model to quickly estimate stability of diverse energetic materials

High energy and low sensitivity have been the focus of developing new energetic materials (EMs). However, there has been a lack of a quick and accurate method for evaluating the stability of diverse EMs. Here, we develop a machine learning prediction model with high accuracy for bond dissociation energy (BDE) of EMs. A reliable and representative BDE dataset of EMs is constructed by collecting 778 experimental energetic compounds and quantum mechanics calculation. To sufficiently characterize the BDE of EMs, a hybrid feature representation is proposed by coupling the local target bond into the global structure characteristics. To alleviate the limitation of the low dataset, pairwise difference regression is utilized as a data augmentation with the advantage of reducing systematic errors and improving diversity. Benefiting from these improvements, the XGBoost model achieves the best prediction accuracy with R2 of 0.98 and MAE of 8.8 kJ mol-1, significantly outperforming competitive models.

Machine learning reveals the selection pressure exerted by nonantibiotic pharmaceuticals at environmentally relevant concentrations on antibiotic resistance genotypes

The emergence and increasing prevalence of antibiotic resistance pose a global public risk for human health, and nonantimicrobial pharmaceuticals play an important role in this process. Herein, five nonantimicrobial pharmaceuticals, including acetaminophen (ACT), clofibric acid (CA), carbamazepine (CBZ), caffeine (CF) and nicotine (NCT), tetracycline-resistant strains, five ARGs (sul1, sul2, tetG, tetM and tetW) and one integrase gene (intI1), were detected in 101 wastewater samples during two typical sewage treatment processes including anaerobic-oxic (A/O) and biological aerated filter (BAF) in Harbin, China. The impact of nonantibiotic pharmaceuticals at environmentally relevant concentrations on both the resistance genotypes and resistance phenotypes were explored. The results showed that a significant impact of nonantibiotic pharmaceuticals at environmentally relevant concentrations on tetracycline resistance genes encoding ribosomal protection proteins (RPPs) was found, while no changes in antibiotic phenotypes, such as minimal inhibitory concentrations (MICs), were observed. Machine learning was applied to further sort out the contribution of nonantibiotic pharmaceuticals at environmentally relevant concentrations to different ARG subtypes. The highest contribution and correlation were found at concentrations of 1400-1800 ng/L for NCT, 900-1500 ng/L for ACT and 7000-10,000 ng/L for CF for tetracycline resistance genes encoding RPPs, while no significant correlation was found between the target compounds and ARGs when their concentrations were lower than 500 ng/L for NCT, 100 ng/L for ACT and 1000 ng/L for CF, which were higher than the concentrations detected in effluent samples. Therefore, the removal of nonantibiotic pharmaceuticals in WWTPs can reduce their selection pressure for resistance genes in wastewater.

Interpretable ensemble prediction for anaerobic digestion performance of hydrothermal carbonization wastewater

Hydrothermal carbonization (HTC) is a method to improve fuel quality that can directly treat wet solid waste, but the treatment produces large amounts of wastewater. Hydrothermal carbonation wastewater treatment for methane production by anaerobic digestion can lead to waste utilization and energy saving. However, anaerobic digestion performance prediction of HTC wastewater is challenging due to the complexity of influencing factors. This study applies interpretable machine learning combined with ensemble learning to construct ensemble prediction models for the biogas yield and CH4 concentration. The machine learning ensemble model can integrate the advantages of single models and effectively improve the prediction accuracy of the anaerobic digestion performance of HTC wastewater, with the best R2 reaching 0.836 and 0.820, respectively, which is better than 0.780 and 0.802 of the best single models. The SHapley Additive exPlanations theory is combined with the ensemble models to show that anaerobic digestion reacted time with HTC temperature, pH, and COD has a coupling effect on daily biogas yield and CH4 concentration.

Insights into the recent advances of agro-industrial waste valorization for sustainable biogas production

Recent years have seen a transition to a sustainable circular economy model that uses agro-industrial waste biomass waste to produce energy while reducing trash and greenhouse gas emissions. Biogas production from lignocellulosic biomass (LCB) is an alternative option in the hunt for clean and renewable fuels. Different approaches are employed to transform the LCB to biogas, including pretreatment, anaerobic digestion (AD), and biogas upgradation to biomethane. To maintain process stability and improve AD performance, machine learning (ML) tools are being applied in real-time monitoring, predicting, and optimizing the biogas production process. An environmental life cycle assessment approach for biogas production systems is essential to calculate greenhouse gas emissions. The current review presents a detailed overview of the utilization of agro-waste for sustainable biogas production. Different methods of waste biomass processing and valorization are discussed that contribute towards developing an efficient agro-waste to biogas-based circular economy.

Predicting variable gene content in Escherichia coli using conserved genes

Having the ability to predict the protein-encoding gene content of an incomplete genome or metagenome-assembled genome is important for a variety of bioinformatic tasks. In this study, as a proof of concept, we built machine learning classifiers for predicting variable gene content in Escherichia coli genomes using only the nucleotide k-mers from a set of 100 conserved genes as features. Protein families were used to define orthologs, and a single classifier was built for predicting the presence or absence of each protein family occurring in 10%-90% of all E. coli genomes. The resulting set of 3,259 extreme gradient boosting classifiers had a per-genome average macro F1 score of 0.944 [0.943-0.945, 95% CI]. We show that the F1 scores are stable across multi-locus sequence types and that the trend can be recapitulated by sampling a smaller number of core genes or diverse input genomes. Surprisingly, the presence or absence of poorly annotated proteins, including "hypothetical proteins" was accurately predicted (F1 = 0.902 [0.898-0.906, 95% CI]). Models for proteins with horizontal gene transfer-related functions had slightly lower F1 scores but were still accurate (F1s = 0.895, 0.872, 0.824, and 0.841 for transposon, phage, plasmid, and antimicrobial resistance-related functions, respectively). Finally, using a holdout set of 419 diverse E. coli genomes that were isolated from freshwater environmental sources, we observed an average per-genome F1 score of 0.880 [0.876-0.883, 95% CI], demonstrating the extensibility of the models. Overall, this study provides a framework for predicting variable gene content using a limited amount of input sequence data. IMPORTANCE Having the ability to predict the protein-encoding gene content of a genome is important for assessing genome quality, binning genomes from shotgun metagenomic assemblies, and assessing risk due to the presence of antimicrobial resistance and other virulence genes. In this study, we built a set of binary classifiers for predicting the presence or absence of variable genes occurring in 10%-90% of all publicly available E. coli genomes. Overall, the results show that a large portion of the E. coli variable gene content can be predicted with high accuracy, including genes with functions relating to horizontal gene transfer. This study offers a strategy for predicting gene content using limited input sequence data.

Metagenomic next generation sequencing for studying antibiotic resistance genes in the environment

Bacterial antimicrobial resistance (AMR) is a persisting and growing threat to human health. Characterization of antibiotic resistance genes (ARGs) in the environment is important to understand and control ARG-associated microbial risks. Numerous challenges exist in monitoring ARGs in the environment, due to the extraordinary diversity of ARGs, low abundance of ARGs with respect to the complex environmental microbiomes, difficulties in linking ARGs with bacterial hosts by molecular methods, difficulties in achieving quantification and high throughput simultaneously, difficulties in assessing mobility potential of ARGs, and difficulties in determining the specific AMR determinant genes. Advances in the next generation sequencing (NGS) technologies and related computational and bioinformatic tools are facilitating rapid identification and characterization ARGs in genomes and metagenomes from environmental samples. This chapter discusses NGS-based strategies, including amplicon-based sequencing, whole genome sequencing, bacterial population-targeted metagenome sequencing, metagenomic NGS, quantitative metagenomic sequencing, and functional/phenotypic metagenomic sequencing. Current bioinformatic tools for analyzing sequencing data for studying environmental ARGs are also discussed.

Elucidating nitrogen removal performance and response mechanisms of anammox under heavy metal stress using big data analysis and machine learning

In this study, machine learning algorithms and big data analysis were used to decipher the nitrogen removal rate (NRR) and response mechanisms of anammox process under heavy metal stresses. Spearman algorithm and Statistical analysis revealed that Cr⁶⁺ had the strongest inhibitory effect on NRR compared to other heavy metals. The established machine learning model (extreme gradient boost) accurately predicted NRR with an accuracy greater than 99%, and the prediction error for new data points was mostly less than 20%. Additionally, the findings of feature analysis demonstrated that Cu²⁺ and Fe³⁺ had the strongest effect on the anammox process, respectively. According to the new insights from this study, Cr⁶⁺ and Cu²⁺ should be removed preferentially in anammox processes under heavy metal stress. This study revealed the feasible application of machine learning and big data analysis for NRR prediction of anammox process under heavy metal stress.

Ensemble machine learning approach for examining critical process parameters and scale-up opportunities of microbial electrochemical systems for hydrogen peroxide production

Hydrogen peroxide (H₂O₂) production in microbial electrochemical systems (MESs) is an attractive option for enabling a circular economy in the water/wastewater sector. Here, a machine learning algorithm was developed, using a meta-learning approach, to predict the H₂O₂ production rates in MES based on the seven input variables, including various design and operating parameters. The developed models were trained and cross-validated using the experimental data collected from 25 published reports. The final ensemble meta-learner model (combining 60 models) demonstrated a high prediction accuracy with very high R² (0.983) and low root-mean-square error (RMSE) (0.647 kg H₂O₂ m^-3 d^-1) values. The model identified the carbon felt anode, GDE cathode, and cathode-to-anode volume ratio as the top three most important input features. Further scale-up analysis for small-scale wastewater treatment plants indicated that proper design and operating conditions could increase the H₂O₂ production rate to as high as 9 kg m^-3 d^-1.

Applications of artificial intelligence in anaerobic co-digestion: Recent advances and prospects

Anaerobic co-digestion (AcoD) offers several merits such as better digestibility and process stability while enhancing methane yield due to synergistic effects. Operation of an efficient AcoD system, however, requires full comprehension of important operational parameters, such as co-substrates ratio, their composition, volatile fatty acids/alkalinity ratio, organic loading rate, and solids/hydraulic retention time. AcoD process optimization, prediction and control, and early detection of system instability are often difficult to achieve through tedious manual monitoring processes. Recently, artificial intelligence (AI) has emerged as an innovative approach to computational modeling and optimization of the AcoD process. This review discusses AI applications in AcoD process optimization, control, prediction of unknown input/output parameters, and real-time monitoring. Furthermore, the review also compares standalone and hybrid AI algorithms as applied to AcoD. The review highlights future research directions for data preprocessing, model interpretation and validation, and grey-box modeling in AcoD process.

Accuracy of tropical peat and non-peat fire forecasts enhanced by simulating hydrology

Soil moisture deficits and water table dynamics are major biophysical controls on peat and non-peat fires in Indonesia. Development of modern fire forecasting models in Indonesia is hampered by the lack of scalable hydrologic datasets or scalable hydrology models that can inform the fire forecasting models on soil hydrologic behaviour. Existing fire forecasting models in Indonesia use weather data-derived fire probability indices, which often do not adequately proxy the sub-surface hydrologic dynamics. Here we demonstrate that soil moisture and water table dynamics can be simulated successfully across tropical peatlands and non-peatland areas by using a process-based eco-hydrology model (ecosys) and publicly available data for weather, soil, and management. Inclusion of these modelled water table depth and soil moisture contents significantly improves the accuracy of a neural network model in predicting active fires at two-weekly time scale. This constitutes an important step towards devising an operational fire early warning system for Indonesia.

Fate of intracellular, extracellular polymeric substances-associated, and cell-free antibiotic resistance genes in anaerobic digestion of thermally hydrolyzed sludge

Thermal hydrolysis of sludge is a promising approach to mitigate antibiotic resistance genes (ARGs) propagation in anaerobic digestion (AD). Although ARGs in sludge may be fractioned into intracellular, extracellular polymeric substance (EPS)-associated, and cell-free ARGs, the fate of these different fractions in AD has never been investigated. This study presents a detailed characterization of intracellular and extracellular ARGs in AD of sludge thermally hydrolyzed at 90 °C and 140 °C. EPS-associated ARGs represented the major fraction of the total extracellular ARGs in all samples, while its lowest abundance was observed for thermal hydrolysis at 140 °C along with the lowest EPS levels. The results suggested a positive correlation between EPS-associated ARGs with intracellular and cell-free ARGs. Furthermore, various EPS components, such as proteins and e-DNA, were positively correlated with β-lactam resistance genes. sul1 dominated all samples as an EPS-associated resistance gene. These results provide new insights into the significance of different ARGs fractions in their overall dissemination in AD integrated with thermal hydrolysis.