A comprehensive machine learning-based models for predicting mixture toxicity of azole fungicides toward algae (Auxenochlorella pyrenoidosa)

Quantitative structure–activity relationships (QSARs) have been used to predict mixture toxicity. However, current research faces gaps in achieving accurate predictions of the mixture toxicity of azole fungicides. To address this gap, the application of machine learning (ML) algorithms has emerged a...

Full description

Saved in:
Bibliographic Details
Main Authors: Li-Tang Qin, Xue-Fang Tian, Jun-Yao Zhang, Yan-Peng Liang, Hong-Hu Zeng, Ling-Yun Mo
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Environment International
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0160412024007487
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850123558417596416
author Li-Tang Qin
Xue-Fang Tian
Jun-Yao Zhang
Yan-Peng Liang
Hong-Hu Zeng
Ling-Yun Mo
author_facet Li-Tang Qin
Xue-Fang Tian
Jun-Yao Zhang
Yan-Peng Liang
Hong-Hu Zeng
Ling-Yun Mo
author_sort Li-Tang Qin
collection DOAJ
description Quantitative structure–activity relationships (QSARs) have been used to predict mixture toxicity. However, current research faces gaps in achieving accurate predictions of the mixture toxicity of azole fungicides. To address this gap, the application of machine learning (ML) algorithms has emerged as an effective strategy. In this study, we applied 12 algorithms, namely, k-nearest neighbor (KNN), kernel k-nearest neighbors (KKNN), support vector machine (SVM), random forest (RF), stochastic gradient boosting (GBM), cubist, bagged multivariate adaptive regression splines (Bagged MARS), eXtreme gradient boosting (XGBoost), boosted generalized linear model (GLMBoost), boosted generalized additive model (GAMBoost), bayesian regularized neural networks (BRNN), and recursive partitioning and regression trees (CART) to build ML models for 225 mixture toxicity of azole fungicides towards Auxenochlorella pyrenoidosa. A total of 36 single ML models and 12 consensus models were developed. The results indicated that models employing concentration addition (CA), independent action (IA), and molecular descriptors (MD) as variables demonstrated superior predictive abilities. The consensus model combining SVM and RF algorithms (labeled as CM0) demonstrated the highest level of accuracy in fitting the data, with a coefficient of determination of 0.980. Additionally, it showed strong predictive abilities when tested with external data, achieving an external R2 value of 0.945 and a Concordance Correlation Coefficient of 0.967. This study provides a positive contribution to the ecological risk assessment of a mixture of azole fungicides.
format Article
id doaj-art-5a40c061bd3e4f549977d3cd84e1407f
institution OA Journals
issn 0160-4120
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Environment International
spelling doaj-art-5a40c061bd3e4f549977d3cd84e1407f2025-08-20T02:34:34ZengElsevierEnvironment International0160-41202024-12-0119410916210.1016/j.envint.2024.109162A comprehensive machine learning-based models for predicting mixture toxicity of azole fungicides toward algae (Auxenochlorella pyrenoidosa)Li-Tang Qin0Xue-Fang Tian1Jun-Yao Zhang2Yan-Peng Liang3Hong-Hu Zeng4Ling-Yun Mo5College of Environmental Science and Engineering, Guilin University of Technology, Guilin 541004, China; Guangxi Key Laboratory of Theory and Technology for Environmental Pollution Control, Guilin University of Technology, Guilin 541006, China; Collaborative Innovation Center for Water Pollution Control and Water Safety in Karst Area, Guilin University of Technology, Guilin 541006, ChinaCollege of Environmental Science and Engineering, Guilin University of Technology, Guilin 541004, ChinaCollege of Environmental Science and Engineering, Guilin University of Technology, Guilin 541004, ChinaCollege of Environmental Science and Engineering, Guilin University of Technology, Guilin 541004, China; Guangxi Key Laboratory of Theory and Technology for Environmental Pollution Control, Guilin University of Technology, Guilin 541006, China; Collaborative Innovation Center for Water Pollution Control and Water Safety in Karst Area, Guilin University of Technology, Guilin 541006, ChinaCollege of Environmental Science and Engineering, Guilin University of Technology, Guilin 541004, China; Guangxi Key Laboratory of Theory and Technology for Environmental Pollution Control, Guilin University of Technology, Guilin 541006, China; Collaborative Innovation Center for Water Pollution Control and Water Safety in Karst Area, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Theory and Technology for Environmental Pollution Control, Guilin University of Technology, Guilin 541006, China; Collaborative Innovation Center for Water Pollution Control and Water Safety in Karst Area, Guilin University of Technology, Guilin 541006, China; Corresponding author.Quantitative structure–activity relationships (QSARs) have been used to predict mixture toxicity. However, current research faces gaps in achieving accurate predictions of the mixture toxicity of azole fungicides. To address this gap, the application of machine learning (ML) algorithms has emerged as an effective strategy. In this study, we applied 12 algorithms, namely, k-nearest neighbor (KNN), kernel k-nearest neighbors (KKNN), support vector machine (SVM), random forest (RF), stochastic gradient boosting (GBM), cubist, bagged multivariate adaptive regression splines (Bagged MARS), eXtreme gradient boosting (XGBoost), boosted generalized linear model (GLMBoost), boosted generalized additive model (GAMBoost), bayesian regularized neural networks (BRNN), and recursive partitioning and regression trees (CART) to build ML models for 225 mixture toxicity of azole fungicides towards Auxenochlorella pyrenoidosa. A total of 36 single ML models and 12 consensus models were developed. The results indicated that models employing concentration addition (CA), independent action (IA), and molecular descriptors (MD) as variables demonstrated superior predictive abilities. The consensus model combining SVM and RF algorithms (labeled as CM0) demonstrated the highest level of accuracy in fitting the data, with a coefficient of determination of 0.980. Additionally, it showed strong predictive abilities when tested with external data, achieving an external R2 value of 0.945 and a Concordance Correlation Coefficient of 0.967. This study provides a positive contribution to the ecological risk assessment of a mixture of azole fungicides.http://www.sciencedirect.com/science/article/pii/S0160412024007487Azole FungicidesQSARsMachine Learning AlgorithmsConsensus Model
spellingShingle Li-Tang Qin
Xue-Fang Tian
Jun-Yao Zhang
Yan-Peng Liang
Hong-Hu Zeng
Ling-Yun Mo
A comprehensive machine learning-based models for predicting mixture toxicity of azole fungicides toward algae (Auxenochlorella pyrenoidosa)
Environment International
Azole Fungicides
QSARs
Machine Learning Algorithms
Consensus Model
title A comprehensive machine learning-based models for predicting mixture toxicity of azole fungicides toward algae (Auxenochlorella pyrenoidosa)
title_full A comprehensive machine learning-based models for predicting mixture toxicity of azole fungicides toward algae (Auxenochlorella pyrenoidosa)
title_fullStr A comprehensive machine learning-based models for predicting mixture toxicity of azole fungicides toward algae (Auxenochlorella pyrenoidosa)
title_full_unstemmed A comprehensive machine learning-based models for predicting mixture toxicity of azole fungicides toward algae (Auxenochlorella pyrenoidosa)
title_short A comprehensive machine learning-based models for predicting mixture toxicity of azole fungicides toward algae (Auxenochlorella pyrenoidosa)
title_sort comprehensive machine learning based models for predicting mixture toxicity of azole fungicides toward algae auxenochlorella pyrenoidosa
topic Azole Fungicides
QSARs
Machine Learning Algorithms
Consensus Model
url http://www.sciencedirect.com/science/article/pii/S0160412024007487
work_keys_str_mv AT litangqin acomprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT xuefangtian acomprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT junyaozhang acomprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT yanpengliang acomprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT honghuzeng acomprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT lingyunmo acomprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT litangqin comprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT xuefangtian comprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT junyaozhang comprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT yanpengliang comprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT honghuzeng comprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa
AT lingyunmo comprehensivemachinelearningbasedmodelsforpredictingmixturetoxicityofazolefungicidestowardalgaeauxenochlorellapyrenoidosa