심근 세포의 전기생리학적 특징을 이용한 인공 신경망 기반 약물의 심장독성 평가
An Artificial Neural Network-Based Drug Proarrhythmia Assessment Using Electrophysiological Characteristics of Cardiomyocytes
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Cardiotoxicity assessment of all drugs has been performed according to the ICH guidelines since 2005. Non-clinical evaluation S7B has focused on the hERG assay, which has a low specificity problem. The comprehensive in vitro proarrhythmia assay (CiPA) project was initiated to correct this problem, which presented a model for clas- sifying the Torsade de pointes (TdP)-induced risk of drugs as biomarkers calculated through an in silico ventricular model. In this study, we propose a TdP-induced risk group classifier of artificial neural network (ANN)-based. The model was trained with 12 drugs and tested with 16 drugs. The ANN model was performed according to nine fea- tures, seven features, five features as an individual ANN model input, and the model with the highest performance was selected and compared with the classification performance of the qNet input logistic regression model. When the five features model was used, the results were AUC 0.93 in the high-risk group, AUC 0.73 in the intermediate- risk group, and 0.92 in the low-risk group. The model's performance using qNet was lower than the ANN model in the high-risk group by 17.6% and in the low-risk group by 29.5%. This study was able to express performance in the three risk groups, and it is a model that solved the problem of low specificity, which is the problem of hERG assay.
Abstract
Cardiotoxicity assessment of all drugs has been performed according to the ICH guidelines since 2005. Non-clinical evaluation S7B has focused on the hERG assay, which has a low specificity problem. The comprehensive in vitro proarrhythmia assay (CiPA) project was initiated to correct this problem, which presented a model for clas- sifying the Torsade de pointes (TdP)-induced risk of drugs as biomarkers calculated through an in silico ventricular model. In this study, we propose a TdP-induced risk group classifier of artificial neural network (ANN)-based. The model was trained with 12 drugs and tested with 16 drugs. The ANN model was performed according to nine fea- tures, seven features, five features as an individual ANN model input, and the model with the highest performance was selected and compared with the classification performance of the qNet input logistic regression model. When the five features model was used, the results were AUC 0.93 in the high-risk group, AUC 0.73 in the intermediate- risk group, and 0.92 in the low-risk group. The model's performance using qNet was lower than the ANN model in the high-risk group by 17.6% and in the low-risk group by 29.5%. This study was able to express performance in the three risk groups, and it is a model that solved the problem of low specificity, which is the problem of hERG assay.
참고문헌 (15)
- D M Roden, "Cellular basis of drug-induced torsades de pointes", British Journal of Pharmacology, 154(7), pp.1502~1507 (2008), Wiley[DOI]
- Rashmi R Shah, "Drugs, QTc Interval Prolongation and Final ICH E14 Guideline", Drug Safety, 28(11), pp.1009~1028 (2005), Springer Science and Business Media LLC[DOI]
- Icilio Cavero, "ICH S7B draft guideline on the non-clinical strategy for testing delayed cardiac repolarisation risk of drugs: a critical analysis", Expert Opinion on Drug Safety, 4(3), pp.509~530 (2005), Informa UK Limited[DOI]
- David G. Strauss, "Comprehensive In Vitro Proarrhythmia Assay (CiPA) Update from a Cardiac Safety Research Consortium", Health and Environmental Sciences Institute, Therapeutic Innovation & Regulatory Science, pp.2019, 53(4)[DOI]
- Thomas Colatsky, "The Comprehensive in Vitro Proarrhythmia Assay (CiPA) initiative — Update on progress", Journal of Pharmacological and Toxicological Methods, 81, pp.15~20 (2016), Elsevier BV[DOI]
- Dutta S, "Optimization of an in silico cardiac cell model for proarrhythmia risk assessment", Front. Physiol, 8, pp.1~15 (2017)[DOI]
- Thomas O'Hara, "Simulation of the Undiseased Human Cardiac Ventricular Action Potential: Model Formulation and Experimental Validation", PLoS Computational Biology, 7(5), pp.e1002061~ (2011), Public Library of Science (PLoS)[DOI]
- Zhihua Li, "Assessment of an In Silico Mechanistic Model for Proarrhythmia Risk Prediction Under the Ci PA Initiative", Clinical Pharmacology & Therapeutics, 105(2), pp.466~475 (2019), Wiley[DOI]
- Jordi Llopis-Lorente, "InSilico Classifiers for the Assessment of Drug Proarrhythmicity", Journal of Chemical Information and Modeling, 60(10), pp.5172~5187 (2020), American Chemical Society (ACS)[DOI]
- M Cummins Lancaster, "Improved Prediction of Drug-Induced Torsades de Pointes Through Simulations of Dynamics and Machine Learning Algorithms", Clinical Pharmacology & Therapeutics, 100(4), pp.371~379 (2016), Wiley[DOI]
- Walaa N. Ismail, "CNN-Based Health Model for Regular Health Factors Analysis in Internet-of-Medical Things Environment", IEEE Access, 8, pp.52541~52549 (2020), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Kelly C. Chang, "Uncertainty Quantification Reveals the Importance of Data Variability and Experimental Design Considerations for in Silico Proarrhythmia Risk Assessment", Frontiers in Physiology, 8, pp.1~7 (2017), Frontiers Media SA[DOI]
- Minki Hwang, "In silico models for evaluating proarrhythmic risk of drugs", APL Bioengineering, 4(2), pp.021502~ (2020), AIP Publishing[DOI]
- Simundic AM, "Measures of Diagnostic Accuracy: Basic Definitions", Ejifcc, 19(4), pp.203~211 (2009)
- Zhihua Li, "General Principles for the Validation of Proarrhythmia Risk Prediction Models: An Extension of the CiPA In Silico Strategy", Clinical Pharmacology & Therapeutics, 107(1), pp.102~111 (2019), Wiley[DOI]