Thao Pham, Mohamed Ghafoor, Sandra Grañana-Castillo, Catia Marzolini, Sara Gibbons, Saye Khoo, Justin Chiong, Dennis Wang, Marco Siccardi
{"title":"DeepARV:利用集合深度学习预测抗逆转录病毒疗法的临床相关药物相互作用。","authors":"Thao Pham, Mohamed Ghafoor, Sandra Grañana-Castillo, Catia Marzolini, Sara Gibbons, Saye Khoo, Justin Chiong, Dennis Wang, Marco Siccardi","doi":"10.1038/s41540-024-00374-0","DOIUrl":null,"url":null,"abstract":"<p><p>Drug-drug interaction (DDI) may result in clinical toxicity or treatment failure of antiretroviral therapy (ARV) or comedications. Despite the high number of possible drug combinations, only a limited number of clinical DDI studies are conducted. Computational prediction of DDIs could provide key evidence for the rational management of complex therapies. Our study aimed to assess the potential of deep learning approaches to predict DDIs of clinical relevance between ARVs and comedications. DDI severity grading between 30,142 drug pairs was extracted from the Liverpool HIV Drug Interaction database. Two feature construction techniques were employed: 1) drug similarity profiles by comparing Morgan fingerprints, and 2) embeddings from SMILES of each drug via ChemBERTa, a transformer-based model. We developed DeepARV-Sim and DeepARV-ChemBERTa to predict four categories of DDI: i) Red: drugs should not be co-administered, ii) Amber: interaction of potential clinical relevance manageable by monitoring/dose adjustment, iii) Yellow: interaction of weak relevance and iv) Green: no expected interaction. The imbalance in the distribution of DDI severity grades was addressed by undersampling and applying ensemble learning. DeepARV-Sim and DeepARV-ChemBERTa predicted clinically relevant DDI between ARVs and comedications with a weighted mean balanced accuracy of 0.729 ± 0.012 and 0.776 ± 0.011, respectively. DeepARV-Sim and DeepARV-ChemBERTa have the potential to leverage molecular structures associated with DDI risks and reduce DDI class imbalance, effectively increasing the predictive ability on clinically relevant DDIs. This approach could be developed for identifying high-risk pairing of drugs, enhancing the screening process, and targeting DDIs to study in clinical drug development.</p>","PeriodicalId":19345,"journal":{"name":"NPJ Systems Biology and Applications","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11074332/pdf/","citationCount":"0","resultStr":"{\"title\":\"DeepARV: ensemble deep learning to predict drug-drug interaction of clinical relevance with antiretroviral therapy.\",\"authors\":\"Thao Pham, Mohamed Ghafoor, Sandra Grañana-Castillo, Catia Marzolini, Sara Gibbons, Saye Khoo, Justin Chiong, Dennis Wang, Marco Siccardi\",\"doi\":\"10.1038/s41540-024-00374-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Drug-drug interaction (DDI) may result in clinical toxicity or treatment failure of antiretroviral therapy (ARV) or comedications. Despite the high number of possible drug combinations, only a limited number of clinical DDI studies are conducted. Computational prediction of DDIs could provide key evidence for the rational management of complex therapies. Our study aimed to assess the potential of deep learning approaches to predict DDIs of clinical relevance between ARVs and comedications. DDI severity grading between 30,142 drug pairs was extracted from the Liverpool HIV Drug Interaction database. Two feature construction techniques were employed: 1) drug similarity profiles by comparing Morgan fingerprints, and 2) embeddings from SMILES of each drug via ChemBERTa, a transformer-based model. We developed DeepARV-Sim and DeepARV-ChemBERTa to predict four categories of DDI: i) Red: drugs should not be co-administered, ii) Amber: interaction of potential clinical relevance manageable by monitoring/dose adjustment, iii) Yellow: interaction of weak relevance and iv) Green: no expected interaction. The imbalance in the distribution of DDI severity grades was addressed by undersampling and applying ensemble learning. DeepARV-Sim and DeepARV-ChemBERTa predicted clinically relevant DDI between ARVs and comedications with a weighted mean balanced accuracy of 0.729 ± 0.012 and 0.776 ± 0.011, respectively. DeepARV-Sim and DeepARV-ChemBERTa have the potential to leverage molecular structures associated with DDI risks and reduce DDI class imbalance, effectively increasing the predictive ability on clinically relevant DDIs. This approach could be developed for identifying high-risk pairing of drugs, enhancing the screening process, and targeting DDIs to study in clinical drug development.</p>\",\"PeriodicalId\":19345,\"journal\":{\"name\":\"NPJ Systems Biology and Applications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2024-05-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11074332/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"NPJ Systems Biology and Applications\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1038/s41540-024-00374-0\",\"RegionNum\":2,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATHEMATICAL & COMPUTATIONAL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"NPJ Systems Biology and Applications","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1038/s41540-024-00374-0","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
DeepARV: ensemble deep learning to predict drug-drug interaction of clinical relevance with antiretroviral therapy.
Drug-drug interaction (DDI) may result in clinical toxicity or treatment failure of antiretroviral therapy (ARV) or comedications. Despite the high number of possible drug combinations, only a limited number of clinical DDI studies are conducted. Computational prediction of DDIs could provide key evidence for the rational management of complex therapies. Our study aimed to assess the potential of deep learning approaches to predict DDIs of clinical relevance between ARVs and comedications. DDI severity grading between 30,142 drug pairs was extracted from the Liverpool HIV Drug Interaction database. Two feature construction techniques were employed: 1) drug similarity profiles by comparing Morgan fingerprints, and 2) embeddings from SMILES of each drug via ChemBERTa, a transformer-based model. We developed DeepARV-Sim and DeepARV-ChemBERTa to predict four categories of DDI: i) Red: drugs should not be co-administered, ii) Amber: interaction of potential clinical relevance manageable by monitoring/dose adjustment, iii) Yellow: interaction of weak relevance and iv) Green: no expected interaction. The imbalance in the distribution of DDI severity grades was addressed by undersampling and applying ensemble learning. DeepARV-Sim and DeepARV-ChemBERTa predicted clinically relevant DDI between ARVs and comedications with a weighted mean balanced accuracy of 0.729 ± 0.012 and 0.776 ± 0.011, respectively. DeepARV-Sim and DeepARV-ChemBERTa have the potential to leverage molecular structures associated with DDI risks and reduce DDI class imbalance, effectively increasing the predictive ability on clinically relevant DDIs. This approach could be developed for identifying high-risk pairing of drugs, enhancing the screening process, and targeting DDIs to study in clinical drug development.
期刊介绍:
npj Systems Biology and Applications is an online Open Access journal dedicated to publishing the premier research that takes a systems-oriented approach. The journal aims to provide a forum for the presentation of articles that help define this nascent field, as well as those that apply the advances to wider fields. We encourage studies that integrate, or aid the integration of, data, analyses and insight from molecules to organisms and broader systems. Important areas of interest include not only fundamental biological systems and drug discovery, but also applications to health, medical practice and implementation, big data, biotechnology, food science, human behaviour, broader biological systems and industrial applications of systems biology.
We encourage all approaches, including network biology, application of control theory to biological systems, computational modelling and analysis, comprehensive and/or high-content measurements, theoretical, analytical and computational studies of system-level properties of biological systems and computational/software/data platforms enabling such studies.