Premium
Assessment of an In Silico Mechanistic Model for Proarrhythmia Risk Prediction Under the Ci PA Initiative
Author(s) -
Li Zhihua,
Ridder Bradley J.,
Han Xiaomei,
Wu Wendy W.,
Sheng Jiansong,
Tran Phu N.,
Wu Min,
Randolph Aaron,
Johnstone Ross H.,
Mirams Gary R.,
Kuryshev Yuri,
Kramer James,
Wu Caiyun,
Crumb William J.,
Strauss David G.
Publication year - 2019
Publication title -
clinical pharmacology and therapeutics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.941
H-Index - 188
eISSN - 1532-6535
pISSN - 0009-9236
DOI - 10.1002/cpt.1184
Subject(s) - proarrhythmia , metric (unit) , in silico , ranking (information retrieval) , computer science , standardization , harmonization , quality (philosophy) , pharmacology , data mining , computational biology , machine learning , medicine , biology , engineering , drug , biochemistry , operations management , gene , operating system , physics , philosophy , epistemology , acoustics
The International Council on Harmonization (ICH) S7B and E14 regulatory guidelines are sensitive but not specific for predicting which drugs are pro‐arrhythmic. In response, the Comprehensive In Vitro Proarrhythmia Assay (Ci PA ) was proposed that integrates multi‐ion channel pharmacology data in vitro into a human cardiomyocyte model in silico for proarrhythmia risk assessment. Previously, we reported the model optimization and proarrhythmia metric selection based on Ci PA training drugs. In this study, we report the application of the prespecified model and metric to independent Ci PA validation drugs. Over two validation datasets, the Ci PA model performance meets all pre‐specified measures for ranking and classifying validation drugs, and outperforms alternatives, despite some in vitro data differences between the two datasets due to different experimental conditions and quality control procedures. This suggests that the current Ci PA model/metric may be fit for regulatory use, and standardization of experimental protocols and quality control criteria could increase the model prediction accuracy even further.