Predicting acute aquatic toxicity of structurally diverse chemicals in fish using artificial intelligence approaches

Singh, Kunwar P.; Gupta, Shikha; Rai, Premanjali

doi:10.1016/j.ecoenv.2013.05.017

Cited by 74 publications

(43 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For binary classification, statistical parameters (sensitivity, specificity, accuracy and Matthews's correlation coefficient (MCC)) are considered (Singh et al, 2014). The performance of the regression models constructed here was evaluated using the root mean squared error (RMSE) and squared correlation coefficient (R 2 ) between the measured and predicted values of the response (Singh et al, 2013a). The RMSE represents the error associated with the model.…”

Section: Model Validation and Prediction Verificationmentioning

confidence: 99%

“…For a molecule, TSI is calculated as; TSI AB ¼ 2Z AB ½Z AA þ Z BB À Z AB À1 , where Z is the similarity matrix, A and B are the two molecules being compared. A good cutoff for biologically similar molecules is 0.7 or 0.8 (Singh et al, 2013a). The distribution of the TSI values of PACs considered in three test species is given in Fig.…”

Section: Data Setsmentioning

confidence: 99%

“…The lowest ranked features were then removed (Singh et al, 2013a). The QSTRs were retained by using the remaining set of features, and the corresponding prediction accuracies (misclassification rate, and mean squared error of prediction) were computed by means of 10-fold cross validation.…”

Section: Molecular Descriptors Feature Selection and Data Processingmentioning

confidence: 99%

“…MLR using a few molecular descriptors successfully predicted toxicities of PACs in the acceptable range, however, the set of compounds considered were small, limiting its applicability over larger data set. Moreover, all these methods are based on linear relationships and cannot capture the nonlinearities in data, which is a common feature of the experimental toxicity data (Singh et al, 2013a). Moreover, these studies, in general consider single test species and no attempts have yet been made to develop a multispecies QSTRs (model developed using toxicity data in one species and capable of predicting toxicity in other test species).…”

Section: Introductionmentioning

confidence: 96%

See 3 more Smart Citations

QSTR modeling for predicting aquatic toxicity of pharmacological active compounds in multiple test species for regulatory purpose

Singh

Basant²

2015

Chemosphere

Self Cite

View full text Add to dashboard Cite

Section: Model Validation and Prediction Verificationmentioning

confidence: 99%

Section: Data Setsmentioning

confidence: 99%

Section: Molecular Descriptors Feature Selection and Data Processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

See 2 more Smart Citations

QSTR modeling for predicting aquatic toxicity of pharmacological active compounds in multiple test species for regulatory purpose

Singh

Basant²

2015

Chemosphere

Self Cite

View full text Add to dashboard Cite

“…Despite the development of tools to predict the toxicity of structurally diverse chemicals [16,17], the limited understanding of interactions between contaminant toxicity and temperature hampers the interpretation of laboratory toxicity data to guide climate change adaptation for the protection of aquatic ecosystems [18].…”

Section: Introductionmentioning

confidence: 99%

Interactions between water temperature and contaminant toxicity to freshwater fish

Patra

Chapman

Lim

et al. 2015

Enviro Toxic and Chemistry

View full text Add to dashboard Cite

Warming of freshwaters as a result of climate change is expected to have complex interactions with the toxicity of contaminants to aquatic organisms. The present study evaluated the effects of temperature on the acute toxicity of endosulfan, chlorpyrifos, and phenol to 3 warm water species of fish-silver perch, rainbowfish, and western carp gudgeon-and 1 cold water species, rainbow trout. Endosulfan was more toxic to silver perch at 30 °C and 35 °C than at 15 °C, 20 °C and 25 °C during short exposures of 24 h, but at 96 h, temperature had no effect on toxicity. Toxicity to rainbow trout increased with increasing temperature, whereas warm water species exhibited maximum toxicity at around 30 °C, decreasing again toward 35 °C. Chlorpyrifos became more toxic to all species with increasing temperature. Phenol toxicity to all species decreased at low to intermediate temperatures; but as temperatures increased further toward the upper thermal limit, phenol became more toxic. Increasing toxicity in the upper thermal range of cold water species may contribute to upstream range contraction in rivers with high toxicant loads. In contrast, warm water species may not exhibit a range shift within rivers as a result of interactions between temperature and toxicity. Catchment management to offset global warming at local scales may present opportunities to mitigate increased toxicity of contaminants to fish.

show abstract

Machine Learning Approaches in Computational Toxicology Studies

Ambure¹,

Barigye²,

Gozalbes³

2021

Chemometrics and Cheminformatics in Aquatic Toxicology

View full text Add to dashboard Cite

Predicting acute aquatic toxicity of structurally diverse chemicals in fish using artificial intelligence approaches

Cited by 74 publications

References 44 publications

QSTR modeling for predicting aquatic toxicity of pharmacological active compounds in multiple test species for regulatory purpose

QSTR modeling for predicting aquatic toxicity of pharmacological active compounds in multiple test species for regulatory purpose

Interactions between water temperature and contaminant toxicity to freshwater fish

Machine Learning Approaches in Computational Toxicology Studies

Contact Info

Product

Resources

About