1
|
Huang K, Zhang H. Classification and Regression Machine Learning Models for Predicting Aerobic Ready and Inherent Biodegradation of Organic Chemicals in Water. ENVIRONMENTAL SCIENCE & TECHNOLOGY 2022; 56:12755-12764. [PMID: 35973069 DOI: 10.1021/acs.est.2c01764] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Machine learning (ML) is viewed as a promising tool for the prediction of aerobic biodegradation, one of the most important elimination pathways of organic chemicals from the environment. However, available models only have small datasets (<3200 records), make binary classification predictions, evaluate ready biodegradability, and do not incorporate experimental conditions (e.g., system setup and reaction time). This study addressed all these limitations by first compiling a large database of 12,750 records, considering both ready and inherent biodegradation under different conditions, and then developing regression and classification models using different chemical representations and ML algorithms. The best regression model (R2 = 0.54 and root mean square error of 0.25) and classification model (the prediction accuracy from 85.1%) achieved very good performance. The model interpretation indicated that the models correctly captured the effects of chemical substructures, following the order of C═O > O═C-O > OH > CH3 > halogen > branching > N > 6-member ring. The consideration of chemical speciation based on pKa and α notations did not affect the regression model performance but significantly improved the classification model performance (the accuracy increased to 87.6%). The models also showed large applicability domains and provided reasonable predictions for more than 98% of over 850,000 environmentally relevant chemicals in the Distributed Structure-Searchable Toxicity database. These robust, trustable models were finally made widely accessible through two free online predictors with graphical user interface.
Collapse
Affiliation(s)
- Kuan Huang
- Department of Civil and Environmental Engineering, Case Western Reserve University, Cleveland, Ohio 44106, United States
| | - Huichun Zhang
- Department of Civil and Environmental Engineering, Case Western Reserve University, Cleveland, Ohio 44106, United States
| |
Collapse
|
2
|
Tang W, Li Y, Yu Y, Wang Z, Xu T, Chen J, Lin J, Li X. Development of models predicting biodegradation rate rating with multiple linear regression and support vector machine algorithms. CHEMOSPHERE 2020; 253:126666. [PMID: 32289603 DOI: 10.1016/j.chemosphere.2020.126666] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/16/2020] [Revised: 03/27/2020] [Accepted: 03/30/2020] [Indexed: 06/11/2023]
Abstract
Biodegradation is a significant process for removing organic chemicals from water, soil and sediment environments, and therefore biodegradability is critical to evaluate the environmental persistence of organic chemicals. In this study, based on a dataset with 171 compounds, four quantitative structure-activity relationship (QSAR) models were developed for predicting primary and ultimate biodegradation rate rating with multiple linear regression (MLR) and support vector machine (SVM) algorithms. Two MLR models were built with a dataset with carbon atom number ≤9, and two SVM models were built with a dataset with carbon atom number >9. In the MLR models, nArX (number of X on aromatic ring) is the most important descriptor governing primary and ultimate biodegradation of organic chemicals. For the SVM models, determination coefficient (R2) values, cross-validated coefficients (Q2LOO) and external validation coefficient (Q2ext) values are over 0.9, indicating the SVM models have satisfactory goodness-of-fit, robustness and external predictive abilities. The applicability domains of these models were visualized by the Williams plot. The developed models can be used as effective tools to predict biodegradability of organic chemicals.
Collapse
Affiliation(s)
- Weihao Tang
- Key Laboratory of Industrial Ecology and Environmental Engineering (MOE), School of Environmental Science and Technology, Dalian University of Technology, Dalian, 116024, China
| | - Yanying Li
- Key Laboratory of Industrial Ecology and Environmental Engineering (MOE), School of Environmental Science and Technology, Dalian University of Technology, Dalian, 116024, China
| | - Yang Yu
- Solid Waste and Chemicals Management Center, Ministry of Ecology and Environment (MEE), Beijing, 100029, China
| | - Zhongyu Wang
- Key Laboratory of Industrial Ecology and Environmental Engineering (MOE), School of Environmental Science and Technology, Dalian University of Technology, Dalian, 116024, China
| | - Tong Xu
- Key Laboratory of Industrial Ecology and Environmental Engineering (MOE), School of Environmental Science and Technology, Dalian University of Technology, Dalian, 116024, China
| | - Jingwen Chen
- Key Laboratory of Industrial Ecology and Environmental Engineering (MOE), School of Environmental Science and Technology, Dalian University of Technology, Dalian, 116024, China
| | - Jun Lin
- Solid Waste and Chemicals Management Center, Ministry of Ecology and Environment (MEE), Beijing, 100029, China
| | - Xuehua Li
- Key Laboratory of Industrial Ecology and Environmental Engineering (MOE), School of Environmental Science and Technology, Dalian University of Technology, Dalian, 116024, China.
| |
Collapse
|
3
|
Zhan Z, Li L, Tian S, Zhen X, Li Y. Prediction of chemical biodegradability using computational methods. MOLECULAR SIMULATION 2017. [DOI: 10.1080/08927022.2017.1328556] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/26/2023]
Affiliation(s)
- Zhixiong Zhan
- Institute of Functional Nano and Soft Materials (FUNSOM), Soochow University, Suzhou, P.R. China
| | - Linlang Li
- Jiangsu Key Laboratory of Translational Research and Therapy for Neuro-Psycho-Diseases and College of Pharmaceutical Sciences, Soochow University, Suzhou, P.R. China
| | - Sheng Tian
- Jiangsu Key Laboratory of Translational Research and Therapy for Neuro-Psycho-Diseases and College of Pharmaceutical Sciences, Soochow University, Suzhou, P.R. China
| | - Xuechu Zhen
- Jiangsu Key Laboratory of Translational Research and Therapy for Neuro-Psycho-Diseases and College of Pharmaceutical Sciences, Soochow University, Suzhou, P.R. China
| | - Youyong Li
- Institute of Functional Nano and Soft Materials (FUNSOM), Soochow University, Suzhou, P.R. China
| |
Collapse
|
4
|
Cao Q, Leung KM. Prediction of Chemical Biodegradability Using Support Vector Classifier Optimized with Differential Evolution. J Chem Inf Model 2014; 54:2515-23. [DOI: 10.1021/ci500323t] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Qi Cao
- Department
of Training, Logistical Engineering University, Chongqing 401311, China
- Department
of Computer Science and Engineering, Polytechnic School of Engineering, New York University, Brooklyn, New York 11201, United States
| | - K. M. Leung
- Department
of Computer Science and Engineering, Polytechnic School of Engineering, New York University, Brooklyn, New York 11201, United States
| |
Collapse
|
5
|
Lozano N, Andrade NA, Deng D, Torrents A, Rice CP, McConnell LL, Ramirez M, Millner PD. Fate of microconstituents in biosolids composted in an aerated silage bag. JOURNAL OF ENVIRONMENTAL SCIENCE AND HEALTH. PART A, TOXIC/HAZARDOUS SUBSTANCES & ENVIRONMENTAL ENGINEERING 2014; 49:720-730. [PMID: 24521417 DOI: 10.1080/10934529.2014.865461] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/03/2023]
Abstract
Although most composting studies report pathogen concentrations, little is known about the fate of Endocrine Disruptor Chemicals (EDCs) during composting. In this study, a positively aerated polyethylene bag composting system was filled with a mixture of woodchips and limed biosolids from a large Waste Water Treatment Plant (WWTP) to study the removal efficiency of two different groups of EDCs. Two antibacterial compounds, Triclocarban (TCC) and Triclosan (TCS), and a TCS byproduct, Methyltriclosan (MeTCS), as well as seven congeners of flame retardants known as PBDEs (Polybrominated Diphenyl Ethers) were studied during two phases of composting: 1) a thermophilic phase, in which positive mechanical aeration, pushing air into and through the materials matrix, was conducted for 2 months; and 2) a curing and stabilization phase in which no mechanical aeration was provided and the bag was opened to ambient passive aeration to simulate storage conditions for seven months. Our results showed that while TCC concentrations remained constant, TCS degradation took place during both phases. The degradation of TCS was corroborated by the formation of MeTCS in both phases. The TCS concentrations decreased from 18409 ± 1,877 to 11955 ± 288 ng g(-1) dry wt. during the thermophilic phase and declined from 11,955 ± 288 to 7,244 ± 909. ng g(-1) dry wt. by the end of the curing phase. Thus, slightly greater TCS transformation occurred during the second than during the first (35.1 vs. 39.4%). MeTCS concentrations increased from 189.3 ± 8.6 to 364.6 ± 72.5 ng g(-1) dry wt. during the first phase and reached 589.0 ± 94.9 ng g(-1) dry wt. at the end of the second phase. PBDEs concentrations were below quantification limits for all but two of the congeners analyzed (BDE-47 and BDE-99). PBDE concentrations were measured at the end of the first phase only and were comparable to initial concentrations.
Collapse
Affiliation(s)
- Nuria Lozano
- a Department of Water and Environmental Science and Technology , University of Cantabria , Santander , Cantabria , Spain
| | | | | | | | | | | | | | | |
Collapse
|
6
|
Cheng F, Ikenaga Y, Zhou Y, Yu Y, Li W, Shen J, Du Z, Chen L, Xu C, Liu G, Lee PW, Tang Y. In silico assessment of chemical biodegradability. J Chem Inf Model 2012; 52:655-69. [PMID: 22332973 DOI: 10.1021/ci200622d] [Citation(s) in RCA: 68] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/18/2023]
Abstract
Biodegradation is the principal environmental dissipation process. Due to a lack of comprehensive experimental data, high study cost and time-consuming, in silico approaches for assessing the biodegradable profiles of chemicals are encouraged and is an active current research topic. Here we developed in silico methods to estimate chemical biodegradability in the environment. At first 1440 diverse compounds tested under the Japanese Ministry of International Trade and Industry (MITI) protocol were used. Four different methods, namely support vector machine, k-nearest neighbor, naïve Bayes, and C4.5 decision tree, were used to build the combinatorial classification probability models of ready versus not ready biodegradability using physicochemical descriptors and fingerprints separately. The overall predictive accuracies of the best models were more than 80% for the external test set of 164 diverse compounds. Some privileged substructures were further identified for ready or not ready biodegradable chemicals by combining information gain and substructure fragment analysis. Moreover, 27 new predicted chemicals were selected for experimental assay through the Japanese MITI test protocols, which validated that all 27 compounds were predicted correctly. The predictive accuracies of our models outperform the commonly used software of the EPI Suite. Our study provided critical tools for early assessment of biodegradability of new organic chemicals in environmental hazard assessment.
Collapse
Affiliation(s)
- Feixiong Cheng
- Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
| | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
7
|
Pal R, Megharaj M, Kirkbride KP, Heinrich T, Naidu R. Biotic and abiotic degradation of illicit drugs, their precursor, and by-products in soil. CHEMOSPHERE 2011; 85:1002-1009. [PMID: 21777940 DOI: 10.1016/j.chemosphere.2011.06.102] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/26/2011] [Revised: 06/23/2011] [Accepted: 06/26/2011] [Indexed: 05/31/2023]
Abstract
This study presents the first systematic information on the degradation patterns of clandestine drug laboratory chemicals in soil. The persistence of five compounds - parent drugs (methamphetamine, 3,4-methylenedioxymethamphetamine (MDMA)), precursor (pseudoephedrine), and synthetic by-products N-formylmethylamphetamine and 1-benzyl-3-methylnaphthalene) - were investigated in laboratory scale for 1 year in three different South Australian soils both under non-sterile and sterile conditions. The results of the degradation study indicated that 1-benzyl-3-methylnaphthalene and methamphetamine persist for a long time in soil compared to MDMA and pseudoephedrine; N-formylmethylamphetamine exhibits intermediate persistence. The role of biotic versus abiotic soil processes on the degradation of target compounds was also varied significantly for different soils as well as with the progress in incubation period. The degradation of methamphetamine and 1-benzyl-3-methylnaphthalene can be considered as predominantly biotic as no measureable changes in concentrations were recorded in the sterile soils within a 1 year period. The results of the present work will help forensic and environmental scientists to precisely determine the environmental impact of chemicals associated with clandestine drug manufacturing laboratories.
Collapse
Affiliation(s)
- Raktim Pal
- Centre for Environmental Risk Assessment and Remediation, University of South Australia, Mawson Lakes, Adelaide, South Australia 5095, Australia
| | | | | | | | | |
Collapse
|
8
|
Zhao G, Pang Y, Liu L, Gao J, Lv B. Highly efficient and energy-saving sectional treatment of landfill leachate with a synergistic system of biochemical treatment and electrochemical oxidation on a boron-doped diamond electrode. JOURNAL OF HAZARDOUS MATERIALS 2010; 179:1078-1083. [PMID: 20413218 DOI: 10.1016/j.jhazmat.2010.03.115] [Citation(s) in RCA: 11] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/16/2009] [Revised: 03/12/2010] [Accepted: 03/28/2010] [Indexed: 05/29/2023]
Abstract
In this paper, a synergistic combination of the biochemical treatment and electrochemical oxidation (SBEO) of landfill leachate with sectional treatment on a boron-doped diamond (BDD) electrode is proposed. The first stage involves the synergistic system of biochemical treatment and electrochemical oxidation. Then, the second stage is followed by individual biochemical treatment. Comparisons among the SBEO, electrochemical oxidation, biochemical treatment and biochemical treatment with the pretreatment of electrochemical oxidation are made systematically, which show that this method is both highly efficient and energy-saving. The higher TOC removal and low energy cost on the BDD electrode can be explained by the conversion of the bio-refractory pollutants to biodegradable organics in the electrochemical oxidation process, improving the current efficiency and reducing the energy cost. The treated wastewater is degraded only with biochemical treatment in the second stage, which further improves efficiency and reduced the energy cost.
Collapse
Affiliation(s)
- Guohua Zhao
- Department of Chemistry, Tongji University, 1239 Siping Road, 200092 Shanghai, China.
| | | | | | | | | |
Collapse
|
9
|
Prediction for Biodegradability of Chemicals by Kernel Partial Least Squares. JOURNAL OF COMPUTER AIDED CHEMISTRY 2009. [DOI: 10.2751/jcac.10.1] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
|
10
|
Ying GG, Yu XY, Kookana RS. Biological degradation of triclocarban and triclosan in a soil under aerobic and anaerobic conditions and comparison with environmental fate modelling. ENVIRONMENTAL POLLUTION (BARKING, ESSEX : 1987) 2007; 150:300-5. [PMID: 17459543 DOI: 10.1016/j.envpol.2007.02.013] [Citation(s) in RCA: 231] [Impact Index Per Article: 13.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/06/2006] [Revised: 02/05/2007] [Accepted: 02/08/2007] [Indexed: 05/12/2023]
Abstract
Triclocarban and triclosan are two antimicrobial agents widely used in many personal care products. Their biodegradation behaviour in soil was investigated by laboratory degradation experiments and environmental fate modelling. Quantitative structure-activity relationship (QSAR) analyses showed that triclocarban and triclosan had a tendency to partition into soil or sediment in the environment. Fate modelling suggests that either triclocarban or triclosan "does not degrade fast" with its primary biodegradation half-life of "weeks" and ultimate biodegradation half-life of "months". Laboratory experiments showed that triclocarban and triclosan were degraded in the aerobic soil with half-life of 108 days and 18 days, respectively. No negative effect of these two antimicrobial agents on soil microbial activity was observed in the aerobic soil samples during the experiments. But these two compounds persisted in the anaerobic soil within 70 days of the experimental period.
Collapse
Affiliation(s)
- Guang-Guo Ying
- State Key Laboratory of Organic Geochemistry, Guangzhou Institute of Geochemistry, Chinese Academy of Sciences, Guangzhou 510640, China.
| | | | | |
Collapse
|
11
|
Sakuratani Y, Yamada J, Kasai K, Noguchi Y, Nishihara T. External validation of the biodegradability prediction model CATABOL using data sets of existing and new chemicals under the Japanese Chemical Substances Control Law. SAR AND QSAR IN ENVIRONMENTAL RESEARCH 2005; 16:403-31. [PMID: 16272041 DOI: 10.1080/10659360500320289] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/05/2023]
Abstract
External validation of the biodegradability prediction model CATABOL was conducted using test data of 338 existing chemicals and 1123 new chemicals under the Japanese Chemical Substances Control Law. CATABOL predicts that 1089 chemicals will have a BOD < 60% while 925 (85%) actually have an observed BOD<60%. The percentage of chemicals with an observed BOD value <60% tends to increase as the predicted BOD values decrease. In contrast, 340 chemicals were predicted to have a BOD > or = 60% and 234 (69%) actually had an observed BOD > or = 60%. The prediction of poor biodegradability was more accurate than the predictions of high biodegradability. The features of chemical structures affecting CATABOL predictability were also investigated.
Collapse
Affiliation(s)
- Y Sakuratani
- Chemical Management Center, National Institute of Technology and Evaluation, 2-49-10 Nishihara, Shibuya-ku, Tokyo 151-0066, Japan.
| | | | | | | | | |
Collapse
|
12
|
ALIKHANIDI S, TAKAHASHI Y. Pesticide Persistence in the Environment - Collected Data and Structure-Based Analysis. JOURNAL OF COMPUTER CHEMISTRY-JAPAN 2004. [DOI: 10.2477/jccj.3.59] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Affiliation(s)
- Sokratis ALIKHANIDI
- Department of Knowledge-based Information Engineering, Toyohashi University of Technology,
| | - Yoshimasa TAKAHASHI
- Department of Knowledge-based Information Engineering, Toyohashi University of Technology,
| |
Collapse
|