Deep neural network and molecular docking supported toxicity profile of prometryn

Basit Öğe Kaydı
dc.contributor.authorÇakir, Feride
dc.contributor.authorKutluer, Fatih
dc.contributor.authorYalçin, Emine
dc.contributor.authorÇavuşoğlu, Kültiğin
dc.contributor.authorAcar, Ali
dc.date.accessioned2025-01-21T16:27:12Z
dc.date.available2025-01-21T16:27:12Z
dc.date.issued2023
dc.departmentKırıkkale Üniversitesi
dc.description.abstractIn this study, the versatile toxicity profile of prometryn herbicide on Allium cepa was investigated. In this context, 4 different groups were formed. While the control group was treated with distilled water, Groups II, III and IV were treated with 200 mg/L, 400 mg/L and 800 mg/L prometryn, respectively. After 72 h of germination, cytogenetic, biochemical, physiological and anatomical changes were investigated. As a result increase in malondialdehyde levels, decrease in glutathione level, changes in superoxide dismutase and catalase activities in root tip cells show that prometryn causes oxidative stress. The decrease in mitotic index values and the increase in the frequency of micronucleus and chromosomal abnormalities observed after prometryn treatment indicate genotoxic effects. The genotoxic effects may be due to the induced oxidative stress as well as the promethryn-DNA interaction. Molecular docking analyses revealed that prometryn interacts with various bases in DNA. As a result of the Comet assay, exposure to prometryn was found to cause DNA fragmentation. In physiological parameters final weight, germination percentage and root length decreased by 23.8%, 59.1% and 87.3%, respectively, in the 800 mg/L prometryn applied group. Deep neural network (DNN) model was optimized to predict the effects of different doses of prometryn on 4 different endpoints: micronucleus, mitotic index, chromosomal abnormalities and DNA Damage. The predicted data was found to be very similar to the actual data. The performance of the model was evaluated using MAE, MAPE, RMSE and R2, and these metrics indicate that the model performed well. Overall, the findings of this study suggest that the DNN model developed here is a valuable tool for predicting genotoxicity biomarkers in response to the application doses of prometryn, and has the potential to contribute to the development of safer and more sustainable agricultural practices. © 2023 Elsevier Ltd
dc.identifier.doi10.1016/j.chemosphere.2023.139962
dc.identifier.issn0045-6535
dc.identifier.pmid37633608
dc.identifier.scopus2-s2.0-85169006978
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.chemosphere.2023.139962
dc.identifier.urihttps://hdl.handle.net/20.500.12587/23295
dc.identifier.volume340
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherElsevier Ltd
dc.relation.ispartofChemosphere
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241229
dc.subjectAllium cepa; Deep neural network; Genotoxicity; Molecular docking; Oxidative damage; Prometryn
dc.titleDeep neural network and molecular docking supported toxicity profile of prometryn
dc.typeArticle

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu