Alla P. Toropova , Andrey A. Toropov , Natalja Fjodorova
{"title":"Quasi-SMILES for predicting toxicity of Nano-mixtures to Daphnia Magna","authors":"Alla P. Toropova , Andrey A. Toropov , Natalja Fjodorova","doi":"10.1016/j.impact.2022.100427","DOIUrl":null,"url":null,"abstract":"<div><p>Quasi-SMILES is an extension of the traditional SMILES. The classic SMILES is a way to represent the molecular structure. The quasi-SMILES is a way to describe all eclectic conditions that are able to affect the activity of a substance or a mixture. Nano-QSAR for prediction of toxicity of Nano-mixtures built up using the database on the corresponding experimental data. Models built up for five random splits of available data in training and validation sets are suggested. The Monte Carlo method of optimization is applied to calculate so-called optimal descriptors. The optimization was carried out with two criteria of predictive potential. These are the so-called index of ideality of correlation (<em>IIC</em>) and correlation intensity index (<em>CII</em>). Applying <em>CII</em> gives the better statistical quality of models for toxicity Nano-mixtures towards <span><em>Daphnia Magna</em><em>.</em></span> The statistical quality of the best model follows the determination coefficients 0.987 (training set) and 0.980 (validation set).</p></div>","PeriodicalId":18786,"journal":{"name":"NanoImpact","volume":null,"pages":null},"PeriodicalIF":4.7000,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"NanoImpact","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2452074822000490","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 5
Abstract
Quasi-SMILES is an extension of the traditional SMILES. The classic SMILES is a way to represent the molecular structure. The quasi-SMILES is a way to describe all eclectic conditions that are able to affect the activity of a substance or a mixture. Nano-QSAR for prediction of toxicity of Nano-mixtures built up using the database on the corresponding experimental data. Models built up for five random splits of available data in training and validation sets are suggested. The Monte Carlo method of optimization is applied to calculate so-called optimal descriptors. The optimization was carried out with two criteria of predictive potential. These are the so-called index of ideality of correlation (IIC) and correlation intensity index (CII). Applying CII gives the better statistical quality of models for toxicity Nano-mixtures towards Daphnia Magna. The statistical quality of the best model follows the determination coefficients 0.987 (training set) and 0.980 (validation set).
期刊介绍:
NanoImpact is a multidisciplinary journal that focuses on nanosafety research and areas related to the impacts of manufactured nanomaterials on human and environmental systems and the behavior of nanomaterials in these systems.