Machine Learning for Predicting Risk of Drug-Induced Autoimmune Diseases by Structural Alerts and Daily Dose
An effective approach for assessing a drug’s potential to induce autoimmune diseases (ADs) is needed in drug development. Here, we aim to develop a workflow to examine the association between structural alerts and drugs-induced ADs to improve toxicological prescreening tools. Considering reactive me...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | International Journal of Environmental Research and Public Health |
Subjects: | |
Online Access: | https://www.mdpi.com/1660-4601/18/13/7139 |
id |
doaj-dc57550d722746cf8799db9fde1dd841 |
---|---|
record_format |
Article |
spelling |
doaj-dc57550d722746cf8799db9fde1dd8412021-07-15T15:35:54ZengMDPI AGInternational Journal of Environmental Research and Public Health1661-78271660-46012021-07-01187139713910.3390/ijerph18137139Machine Learning for Predicting Risk of Drug-Induced Autoimmune Diseases by Structural Alerts and Daily DoseYue Wu0Jieqiang Zhu1Peter Fu2Weida Tong3Huixiao Hong4Minjun Chen5National Center for Toxicological Research, Division of Bioinformatics and Biostatistics, U.S. Food and Drug Administration, Jefferson, AR 72079, USANational Center for Toxicological Research, Division of Bioinformatics and Biostatistics, U.S. Food and Drug Administration, Jefferson, AR 72079, USANational Center for Toxicological Research, Division of Biochemical Toxicology, U.S. Food and Drug Administration, Jefferson, AR 72079, USANational Center for Toxicological Research, Division of Bioinformatics and Biostatistics, U.S. Food and Drug Administration, Jefferson, AR 72079, USANational Center for Toxicological Research, Division of Bioinformatics and Biostatistics, U.S. Food and Drug Administration, Jefferson, AR 72079, USANational Center for Toxicological Research, Division of Bioinformatics and Biostatistics, U.S. Food and Drug Administration, Jefferson, AR 72079, USAAn effective approach for assessing a drug’s potential to induce autoimmune diseases (ADs) is needed in drug development. Here, we aim to develop a workflow to examine the association between structural alerts and drugs-induced ADs to improve toxicological prescreening tools. Considering reactive metabolite (RM) formation as a well-documented mechanism for drug-induced ADs, we investigated whether the presence of certain RM-related structural alerts was predictive for the risk of drug-induced AD. We constructed a database containing 171 RM-related structural alerts, generated a dataset of 407 AD- and non-AD-associated drugs, and performed statistical analysis. The nitrogen-containing benzene substituent alerts were found to be significantly associated with the risk of drug-induced ADs (odds ratio = 2.95, <i>p</i> = 0.0036). Furthermore, we developed a machine-learning-based predictive model by using daily dose and nitrogen-containing benzene substituent alerts as the top inputs and achieved the predictive performance of area under curve (AUC) of 70%. Additionally, we confirmed the reactivity of the nitrogen-containing benzene substituent aniline and related metabolites using quantum chemistry analysis and explored the underlying mechanisms. These identified structural alerts could be helpful in identifying drug candidates that carry a potential risk of drug-induced ADs to improve their safety profiles.https://www.mdpi.com/1660-4601/18/13/7139drug-induced autoimmune diseasesstructural alertsmachine learningquantum chemistry |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yue Wu Jieqiang Zhu Peter Fu Weida Tong Huixiao Hong Minjun Chen |
spellingShingle |
Yue Wu Jieqiang Zhu Peter Fu Weida Tong Huixiao Hong Minjun Chen Machine Learning for Predicting Risk of Drug-Induced Autoimmune Diseases by Structural Alerts and Daily Dose International Journal of Environmental Research and Public Health drug-induced autoimmune diseases structural alerts machine learning quantum chemistry |
author_facet |
Yue Wu Jieqiang Zhu Peter Fu Weida Tong Huixiao Hong Minjun Chen |
author_sort |
Yue Wu |
title |
Machine Learning for Predicting Risk of Drug-Induced Autoimmune Diseases by Structural Alerts and Daily Dose |
title_short |
Machine Learning for Predicting Risk of Drug-Induced Autoimmune Diseases by Structural Alerts and Daily Dose |
title_full |
Machine Learning for Predicting Risk of Drug-Induced Autoimmune Diseases by Structural Alerts and Daily Dose |
title_fullStr |
Machine Learning for Predicting Risk of Drug-Induced Autoimmune Diseases by Structural Alerts and Daily Dose |
title_full_unstemmed |
Machine Learning for Predicting Risk of Drug-Induced Autoimmune Diseases by Structural Alerts and Daily Dose |
title_sort |
machine learning for predicting risk of drug-induced autoimmune diseases by structural alerts and daily dose |
publisher |
MDPI AG |
series |
International Journal of Environmental Research and Public Health |
issn |
1661-7827 1660-4601 |
publishDate |
2021-07-01 |
description |
An effective approach for assessing a drug’s potential to induce autoimmune diseases (ADs) is needed in drug development. Here, we aim to develop a workflow to examine the association between structural alerts and drugs-induced ADs to improve toxicological prescreening tools. Considering reactive metabolite (RM) formation as a well-documented mechanism for drug-induced ADs, we investigated whether the presence of certain RM-related structural alerts was predictive for the risk of drug-induced AD. We constructed a database containing 171 RM-related structural alerts, generated a dataset of 407 AD- and non-AD-associated drugs, and performed statistical analysis. The nitrogen-containing benzene substituent alerts were found to be significantly associated with the risk of drug-induced ADs (odds ratio = 2.95, <i>p</i> = 0.0036). Furthermore, we developed a machine-learning-based predictive model by using daily dose and nitrogen-containing benzene substituent alerts as the top inputs and achieved the predictive performance of area under curve (AUC) of 70%. Additionally, we confirmed the reactivity of the nitrogen-containing benzene substituent aniline and related metabolites using quantum chemistry analysis and explored the underlying mechanisms. These identified structural alerts could be helpful in identifying drug candidates that carry a potential risk of drug-induced ADs to improve their safety profiles. |
topic |
drug-induced autoimmune diseases structural alerts machine learning quantum chemistry |
url |
https://www.mdpi.com/1660-4601/18/13/7139 |
work_keys_str_mv |
AT yuewu machinelearningforpredictingriskofdruginducedautoimmunediseasesbystructuralalertsanddailydose AT jieqiangzhu machinelearningforpredictingriskofdruginducedautoimmunediseasesbystructuralalertsanddailydose AT peterfu machinelearningforpredictingriskofdruginducedautoimmunediseasesbystructuralalertsanddailydose AT weidatong machinelearningforpredictingriskofdruginducedautoimmunediseasesbystructuralalertsanddailydose AT huixiaohong machinelearningforpredictingriskofdruginducedautoimmunediseasesbystructuralalertsanddailydose AT minjunchen machinelearningforpredictingriskofdruginducedautoimmunediseasesbystructuralalertsanddailydose |
_version_ |
1721299496443314176 |