<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">toxreview</journal-id><journal-title-group><journal-title xml:lang="ru">Токсикологический вестник</journal-title><trans-title-group xml:lang="en"><trans-title>Toxicological Review</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">0869-7922</issn><issn pub-type="epub">3034-4611</issn><publisher><publisher-name>Federal Scientific Center of Hygiene named after F.F. Erisman</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.47470/0869-7922-2023-31-6-413-417</article-id><article-id custom-type="edn" pub-id-type="custom">kijkhn</article-id><article-id custom-type="elpub" pub-id-type="custom">toxreview-789</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ОРИГИНАЛЬНЫЕ СТАТЬИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>ORIGINAL ARTICLES</subject></subj-group></article-categories><title-group><article-title>Проблема отбора релевантных дескрипторов при прогнозировании токсичности химических веществ</article-title><trans-title-group xml:lang="en"><trans-title>The problem of selecting relevant descriptors in predicting the toxicity of chemicals</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-8389-7981</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гусева</surname><given-names>Екатерина Андреевна</given-names></name><name name-style="western" xml:lang="en"><surname>Guseva</surname><given-names>Ekaterina A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ассистент кафедры экологии человека и гигиены окружающей среды Института общественного здоровья им. Ф.Ф. Эрисмана ФГАОУ ВО Первый МГМУ им. И.М. Сеченова Минздрава России (Сеченовский Университет), 199911, Москва, Россия</p><p>e-mail: guseva_e_a@staff.sechenov.ru</p></bio><bio xml:lang="en"><p>Assistant of the Department of Human Ecology and Environmental Hygiene of the Institute of Public Health named after F.F. Erisman, Sechenov First Moscow State Medical University of the Ministry of Health of Russia (Sechenov University), Moscow, 199911, Russian Federation</p><p>e-mail: guseva_e_a@staff.sechenov.ru</p></bio><email xlink:type="simple">guseva_e_a@staff.sechenov.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Федеральное государственное автономное образовательное учреждение высшего образования Первый Московский государственный медицинский университет имени И.М. Сеченова Министерства здравоохранения Российской Федерации (Сеченовский Университет)</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Federal State Autonomous Educational Institution of Higher Education I.M. Sechenov First Moscow State Medical University of the Ministry of Health of the Russian Federation (Sechenov University)</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2023</year></pub-date><pub-date pub-type="epub"><day>15</day><month>01</month><year>2024</year></pub-date><volume>31</volume><issue>6</issue><fpage>413</fpage><lpage>417</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Гусева Е.А., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Гусева Е.А.</copyright-holder><copyright-holder xml:lang="en">Guseva E.A.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://www.toxreview.ru/jour/article/view/789">https://www.toxreview.ru/jour/article/view/789</self-uri><abstract><sec><title>Введение</title><p>Введение. Математические модели широко применимы при проведении токсикологических исследований и могут использоваться для заполнения пробелов, возникающих при оценке химической безопасности. Большая часть внимания уделяется вопросам изучения алгоритмов построения моделей, а не подходам к выбору наиболее информативных признаков.</p><p>Поэтому, цель настоящей работы — осветить аспекты проблемы выбора полезных переменных при проведении математического моделирования.</p></sec><sec><title>Материал и методы</title><p>Материал и методы. В интерактивной среде Google Colaboratory на основании программного кода при помощи обеспечения RDKit, Mordred были сгенерированы SMILES и молекулярные дескрипторы для фосфорорганических инсектицидов. С помощью инструментов библиотеки scikit-learn Ver. 1.2.2 происходил отбор признаков методом фильтрации и методом рекурсивного исключения признаков. Из официальных информационных источников о химических веществах были взяты значения параметров острой пероральной токсичности. Полученные модели прошли процедуру внутренней валидации, проведена сравнительная оценка производительности моделей.</p></sec><sec><title>Результаты</title><p>Результаты. Необходимо отметить, что модели, где использовалось рекурсивное исключение признаков, обладают лучшими характеристиками, чем модели на основе дескрипторов, отобранных методом фильтрации. В частности, модель прогнозирования острой токсичности для органотиофосфатов на основе метода дерева принятия решения с рекурсивным исключением признаков обладает высоким коэффициентом детерминации (R2=0,91713), сравнительно небольшой среднеквадратичной ошибкой (RMSE=0,35099), а также высоким значением коэффициента детерминации кросс-валидации (Q2LOO= 0,79756).</p></sec><sec><title>Ограничения исследования</title><p>Ограничения исследования. Полученные результаты могут быть использованы только при прогнозировании токсичности указанной группы химических веществ со сходным механизмом действия.</p></sec><sec><title>Заключение</title><p>Заключение. Использование математического моделирования — перспективный инструмент оценки токсичности химических веществ, имеющий ряд особенностей: с одной стороны, это быстрый и удобный ресурс для проведения скрининга токсичности веществ, с другой — модель необходимо обучить на основе не только надежных данных исследований, но и провести процедуру качественного отбора признаков, вносящих значительный вклад в функционирование прогностической модели.</p><p>Соблюдение этических стандартов. Исследование не требует представления заключения комитета по биомедицинской этике или иных документов.</p></sec><sec><title>Конфликт интересов</title><p>Конфликт интересов. Авторы заявляют об отсутствии конфликтов интересов.</p></sec><sec><title>Финансирование</title><p>Финансирование. Исследование не имело спонсорской поддержки.</p></sec><sec><title>Дата поступления</title><p>Дата поступления: 21 сентября 2023 / Дата принятия к печати: 03 декабря 2023 / Дата публикации: 29 декабря 2023</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>Introduction</title><p>Introduction. Mathematical models are widely applicable in conducting toxicological studies and can be used to fill gaps that arise in the assessment of chemical safety. Most of the attention is paid to the study of algorithms for constructing models, rather than approaches to choosing the most informative features.</p><p>The purpose of this study is to highlight aspects of the problem of choosing useful variables during mathematical modeling.</p></sec><sec><title>Material and methods</title><p>Material and methods. SMILES and molecular descriptors for organothiophosphates were generated in the interactive Google Colaboratory environment based on the program code using the RDKit, Mordred software. Using the tools of the scikit-learn Ver. 1.2.2 library, features were selected by filtering and by recursive feature exclusion. The values of acute oral toxicity parameters were taken from official information sources about chemicals. The obtained models are subjected to an internal validation procedure to evaluate the performance of the models.</p></sec><sec><title>Results</title><p>Results. It should be noted that models where recursive exclusion of features was used have better characteristics than models based on descriptors selected by the filtering method. In particular, the acute toxicity prediction model for organothiophosphates based on the decision tree method with recursive exclusion of features has a high coefficient of determination (R2=0,91713), a relatively small root-mean-square error (RMSE= 0,35099), as well as high values of the cross-validation coefficient of determination (Q2LOO= 0,79756).</p></sec><sec><title>Limitations</title><p>Limitations. The results obtained can be used only in predicting the toxicity of the specified group of chemicals with a similar mechanism of action.</p></sec><sec><title>Conclusion</title><p>Conclusion. The use of mathematical modeling is a promising tool for assessing the toxicity of chemicals, which has a number of features: on the one hand, it is a quick and convenient resource for screening the toxicity of substances, on the other hand, the model needs to be trained based not only on reliable research data, but also to carry out a qualitative selection procedure for signs that make a significant contribution to the functioning of the prognostic model.</p><p>Compliance with ethical standards. The study does not require the submission of the conclusion of the Biomedical ethics committee or other documents.</p></sec><sec><title>Conflict of interest</title><p>Conflict of interest. Author declare no conflict of interest.</p></sec><sec><title>Funding</title><p>Funding. The study had no sponsorship.</p></sec><sec><title>Date of receipt</title><p>Date of receipt: September 21, 2023 / Date of acceptance for printing: December 3, 2023 / Date of publication: December 29, 202</p></sec><sec><title> </title><p> </p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>токсичность</kwd><kwd>прогнозирование</kwd><kwd>дескрипторы</kwd></kwd-group><kwd-group xml:lang="en"><kwd>toxicity</kwd><kwd>prediction</kwd><kwd>descriptors</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Сухачев В.С., Иванов С.М., Филимонов Д.А., Поройков В.В. Альтернативные методы исследования. Компьютерная оценка острой токсичности для грызунов. Лабораторные животные для научных исследований. 2019; 4. https://doi.org/10.29296/2618723X-2019-04-04</mixed-citation><mixed-citation xml:lang="en">Suhachev V.S., Ivanov S.M., Filimonov D.A., Porojkov V.V. Al’ternativnye metody issledovaniya. Komp’yuternaya ocenka ostroj toksichnosti dlya gryzunov. Laboratornye zhivotnye dlya nauchnyh issledovanij. 2019; 4. https://doi.org/10.29296/2618723X-2019-04-04 (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Gramatica P., Papa E., Sangion A. QSAR modeling of cumulative environmental end-points for the prioritization of hazardous chemicals. Environmental Science: Processes &amp; Impacts. 2018; 20(1): 38–47. https://doi.org/10.1039/C7EM00519A</mixed-citation><mixed-citation xml:lang="en">Gramatica P., Papa E., Sangion A. QSAR modeling of cumulative environmental end-points for the prioritization of hazardous chemicals. Environmental Science: Processes &amp; Impacts. 2018; 20(1): 38–47. https://doi.org/10.1039/C7EM00519A</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Carrio P., Sanz F., Pastor M. Towards a unifying strategy for predicting toxicological endpoints based on structure. Archive of Toxicology. 2016; 90: 2445–460. https://doi.org/10.1007/s00204-015-1618-2</mixed-citation><mixed-citation xml:lang="en">Carrio P., Sanz F., Pastor M. Towards a unifying strategy for predicting toxicological endpoints based on structure. Archive of Toxicology. 2016; 90: 2445–460. https://doi.org/10.1007/s00204-015-1618-2</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Reyes A.B., Bayich V.B. In silico toxicology: computational methods for predicting chemical toxicity. Interdisciplinary reviews of Wiley: Computational Molecular Science. 2016; 6(2): 147–72. https://doi.org/10.1002/wcms.1240</mixed-citation><mixed-citation xml:lang="en">Reyes A.B., Bayich V.B. In silico toxicology: computational methods for predicting chemical toxicity. Interdisciplinary reviews of Wiley: Computational Molecular Science. 2016; 6(2): 147–72. https://doi.org/10.1002/wcms.1240</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Villaverde J.J., Sevilla-Moran B., Lopez-Goti S., Alonso-Prados J.L., Sandin-España P. QSAR/QSPR models based on quantum chemistry for assessing the risk of pesticides in accordance with current European legislation. SAR and QSAR in environmental studies. 2020; 31(1): 49–72. https://doi.org/10.1080/1062936X.2019.1692368</mixed-citation><mixed-citation xml:lang="en">Villaverde J.J., Sevilla-Moran B., Lopez-Goti S., Alonso-Prados J.L., Sandin-España P. QSAR/QSPR models based on quantum chemistry for assessing the risk of pesticides in accordance with current European legislation. SAR and QSAR in environmental studies. 2020; 31(1): 49–72. https://doi.org/10.1080/1062936X.2019.1692368</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Жолдакова З.И., Харчевникова Н.В. Система ускоренной оценки токсичности и опасности химических веществ в воде. Здоровье населения и среда обитания. 2014; 8(257): 21–3.</mixed-citation><mixed-citation xml:lang="en">Zholdakova Z.I., Harchevnikova N.V. Sistema uskorennoj ocenki toksichnosti i opasnosti himicheskih veshchestv v vode.Zdorov’e naseleniya i sreda obitaniya. 2014, 8(257): 21–3. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Idakwo G., Luttrell J., Chen M., et al. A review on machine learning methods for in silico toxicity prediction. Journal of environmental science and health. Part C. Environmental carcinogenesis &amp; ecotoxicology reviews. 2018; 36(4): 169–91. https://doi.org/10.1080/10590501.2018.153711</mixed-citation><mixed-citation xml:lang="en">Idakwo G., Luttrell J., Chen M., et al. A review on machine learning methods for in silico toxicity prediction. Journal of environmental science and health. Part C. Environmental carcinogenesis &amp; ecotoxicology reviews. 2018; 36(4): 169–91. https://doi.org/10.1080/10590501.2018.153711</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Moriwaki H., Tian Y.S., Kawashita N. et al. Mordred: a molecular descriptor calculator. J Cheminform 2018; 10, 4. https://doi.org/10.1186/s13321-018-0258-y</mixed-citation><mixed-citation xml:lang="en">Moriwaki H., Tian Y.S., Kawashita N. et al. Mordred: a molecular descriptor calculator. J Cheminform 2018; 10, 4. https://doi.org/10.1186/s13321-018-0258-y</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Gallagher M.E. Toxicity testing requirements, methods and proposed alternatives. Environmental Law and Policy Journal. 2003; 26(2): 257–73.</mixed-citation><mixed-citation xml:lang="en">Gallagher M.E. Toxicity testing requirements, methods and proposed alternatives. Environmental Law and Policy Journal. 2003; 26(2): 257–73.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Dearden J.C., Cronin M. T.D., Kaiser K.L.E. How not to develop a quantitative structure–activity or structure–property relationship (QSAR/QSPR). SAR and QSAR in Environmental Research. 2009; 20(3–4): 241–66. https://doi.org/10.1080/10629360902949567</mixed-citation><mixed-citation xml:lang="en">Dearden J.C., Cronin M. T.D., Kaiser K.L.E. How not to develop a quantitative structure–activity or structure–property relationship (QSAR/QSPR). SAR and QSAR in Environmental Research. 2009; 20(3–4): 241–66. https://doi.org/10.1080/10629360902949567</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Golbraikh A., Tropsha A. Predictive QSAR modeling based on diversity sampling of experimental datasets for the training and test set selection. Journal of Computer-Aided Molecular Design. 2002; 16(5/6): 357–69. https://doi.org/10.1023/A:1020869118689</mixed-citation><mixed-citation xml:lang="en">Golbraikh A., Tropsha A. Predictive QSAR modeling based on diversity sampling of experimental datasets for the training and test set selection. Journal of Computer-Aided Molecular Design. 2002; 16(5/6): 357–69. https://doi.org/10.1023/A:1020869118689</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Frimayanti N., Yam M.L., Lee H.B., Othman R., Zain S.M., Rahman N.A. Validation of Quantitative Structure-Activity Relationship (QSAR) Model for Photosensitizer Activity Prediction. International Journal of Molecular Sciences. 2011; 12(12): 8626–44. https://doi.org/10.3390/ijms12128626</mixed-citation><mixed-citation xml:lang="en">Frimayanti N., Yam M.L., Lee H.B., Othman R., Zain S.M., Rahman N.A. Validation of Quantitative Structure-Activity Relationship (QSAR) Model for Photosensitizer Activity Prediction. International Journal of Molecular Sciences. 2011; 12(12): 8626–44. https://doi.org/10.3390/ijms12128626</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
