Deep Multimodal Classification Model for Predicting Successes and Failures of Clinical Trials
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
From the discovery of new drug candidates through clinical trials to their approval, it takes approximately 15 years to launch a new drug into the market, and costs approximately one trillion to two trillion won. Despite several improvements in the drug development pipeline over the past 30 years, failures have skyrocketed at all stages of clinical trials owing to safety reasons. To improve the success rate of clinical trials, it is necessary to identify drug candidates that may fail in the clinical trials. Therefore, we need to develop reliable models to predict the outcomes of clinical trials of drug candidates. In this paper, we propose a deep multimodal classification model based on informative chemical features of the drugs and targetbased features. Experimental results reported on the PrOCTOR dataset indicate that the proposed model performs better in a multimodal setting. Comparing ensemble models based on random forests and extra trees, the proposed deep multimodal classifier obtains the highest value for the area under the receiver operator curve and area under the precision-recall curve. The results of this study demonstrate that the proposed multimodal classifier can be used to predict the outcomes of clinical trials effectively.
Abstract
From the discovery of new drug candidates through clinical trials to their approval, it takes approximately 15 years to launch a new drug into the market, and costs approximately one trillion to two trillion won. Despite several improvements in the drug development pipeline over the past 30 years, failures have skyrocketed at all stages of clinical trials owing to safety reasons. To improve the success rate of clinical trials, it is necessary to identify drug candidates that may fail in the clinical trials. Therefore, we need to develop reliable models to predict the outcomes of clinical trials of drug candidates. In this paper, we propose a deep multimodal classification model based on informative chemical features of the drugs and targetbased features. Experimental results reported on the PrOCTOR dataset indicate that the proposed model performs better in a multimodal setting. Comparing ensemble models based on random forests and extra trees, the proposed deep multimodal classifier obtains the highest value for the area under the receiver operator curve and area under the precision-recall curve. The results of this study demonstrate that the proposed multimodal classifier can be used to predict the outcomes of clinical trials effectively.
참고문헌 (20)
- Hay M, "Clinical development success rates for investigational drugs", Nat Biotechnol, 32, pp.40~51 (2014)
- Ledford H, "Translational research : 4 ways to fix the clinical trial", Nature, 477, pp.526~528 (2011)
- Scannell JW, "Diagnosing the decline in pharmaceutical R&D efficiency", Nat Rev Drug Discov, 11, pp.191~200 (2012)
- Lipinski CA, "Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings", Adv Drug Deliv Rev, 46, pp.3~26 (1997)
- Lipinski CA, "Lead-and drug-like compounds : the rule-of-five revolution", Drug Discov Today Technol, 1, pp.337~341 (2004)
- Veber DF, "Molecular properties that influence the oral bioavailability of drug candidates", J Med Chem, 45, pp.2615~2623 (2002)
- Ghose AK, "A knowledgebased approach in designing combinatorial or medicinal chemistry libraries for drug discovery. 1. A qualitative and quantitative characterization of known drug databases", J Comb Chem, 1, pp.55~68 (1999)
- Bickerton GR, "Quantifying the chemical beauty of drugs", Nat Chem, 4, pp.90~98 (2012)
- Hay M, "Clinical development success rates for investigational drugs", Nat Biotechnol, 32, pp.40~51 (2014)
- Gayvert KM, "A data-driven approach to predicting successes and failures of clinical trials", Cell Chem Bio, 23, pp.1294~1301 (2016)
- 임자연, "Deeper Integrative Neural Network Analysis for Multi-level Omics Data", Quantitative Bio-Science, 38(2), pp.73~79 (2019), 자연과학연구소[DOI]
- 서윤범, "Predicting Bitcoin Market Trend with Deep Learning Models", Quantitative Bio-Science, 37(1), pp.65~71 (2018), 자연과학연구소[DOI]
- Baltrušaitis T, "Multimodal machine learning : A survey and taxonomy", IEEE Trans Pattern Anal Machine Intel, 15, pp.850~863 (2019)
- Gallo I, "Multimodal classification fusion in real-world scenarios", Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition (2017)
- Kim DH, "Multi-modal emotion recognition using semi-supervised learning and multiple neural networks in the wild", Proceedings of the 19th ACM International Conference on Multimodal Interaction, pp.529~535 (2017)
- Vielzeuf V, "Temporal multimodal fusion for video emotion classification in the wild", Proceedings of the 19th ACM International Conference on Multimodal Interaction, pp.569~576 (2017)
- Wang Y, "Dynamic curriculum learning for imbalanced data classification", CoRR abs, 2019 (1901)
- Chawla NV, "SMOTE:Synthetic minority over-sampling technique", J Artifi Intelli Res, 16, pp.321~357 (2002)
- Boughorbel S, "Optimal classifier for imbalanced data using Matthews correlation coefficient metric", PLoS ONE, 12, pp.e0177678~ (2017)
- Fernández A, "Learning from imbalanced data sets" (2018), Springer