Predicting the Outcomes of Clinical Trials with an Ensemble LS-SVR
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
For various reasons, most drug candidates cannot successfully pass the drug approval process. Therefore, the deve- lopment of reliable methods for predicting clinical trial outcomes of drug candidates is crucial in improving drug development. In this study, we propose an ensemble classifier based on a weighted least squares support vector regression (LS-SVR) for predicting successes and failures of clinical trials. The efficacy of the proposed ensemble classifier is demonstrated through an experimental study on the PrOCTOR dataset, which consists of informative chemical and target-based features of drugs. Upon comparison with other models, the proposed ensemble classifier obtained the highest area under the receiver operator curve (AUC). These results demonstrate that our classifier can be used to effectively predict the outcomes of clinical trials.
Abstract
For various reasons, most drug candidates cannot successfully pass the drug approval process. Therefore, the deve- lopment of reliable methods for predicting clinical trial outcomes of drug candidates is crucial in improving drug development. In this study, we propose an ensemble classifier based on a weighted least squares support vector regression (LS-SVR) for predicting successes and failures of clinical trials. The efficacy of the proposed ensemble classifier is demonstrated through an experimental study on the PrOCTOR dataset, which consists of informative chemical and target-based features of drugs. Upon comparison with other models, the proposed ensemble classifier obtained the highest area under the receiver operator curve (AUC). These results demonstrate that our classifier can be used to effectively predict the outcomes of clinical trials.
참고문헌 (15)
- Helen D, "Trends in clinical success rates and therapeutic focus", Nat Rev Drug Discov, 18, pp.495~496 (2019)
- Richard KH, "Phase II and phase III failures : 2013-2015", Nat Rev Drug Discov, 15, pp.817~818 (2019)
- Graul AI, "The year’s new drugs biologics 2016 : Part II-Trends and highlights of an unforgettable year", Drugs Today(Barc), 53, pp.117~158 (2017)
- Graul AI, "The year’s new drugs & biologics, 2017, part II-News that shaped the industry in 2017", Drugs Today(Barc), 54, pp.137~167 (2018)
- Graul AI, "The year’s new drugs and biologics 2018 : Part II-News that shaped the industry in 2018", Drugs Today(Barc), 55, pp.131~160 (2019)
- Artem VA, "Integrated deep learned transcriptomic and structure-based predictor of clinical trials outcomes" (2016)[DOI]
- Gayvert KM, "A data-driven approach to predicting successes and failures of clinical trials", Cell Chem Biol, 23, pp.1294~1301 (2016)
- 황창하, "Deep Multimodal Classification Model for Predicting Successes and Failures of Clinical Trials", Quantitative Bio-Science, 39(1), pp.75~79 (2020), 자연과학연구소[DOI]
- Vapnik VN, "The nature of statistical learning theory" (1995), Springer
- Suykens JAK, "Least square support vector machine classifier", Neural Process Lett, 9, pp.293~300 (1999)
- 심주용, "Multiclass Classiffication via Least Squares Support Vector Machine Regression", Communications for Statistical Applications and Methods, 15(3), pp.441~450 (2008), 한국통계학회
- Kimeldorf GS, "Some results on Tchebycheffian spline functions", J Math Anal Appl, 33, pp.82~95 (1971)
- Robust cross-validation score functions with application to weighted least squares support vector machine function estimation, "De Brabanter J", ESAT-SISTA, ~ (2003)
- Imam T, "z-SVM: An SVM for improved classification of imbalanced data", 19th Australian Joint Conference on Artificial Intelligence, pp.264~273 (2006), Advances in Artificial Intelligence
- Chawla NV, "SMOTE : synthetic minority over-sampling technique", Artif Intell Res, 16, pp.321~357 (2002)