Table 1 Current drug response prediction approaches
Date | Author | Best model | Compared models | Cancer cell line features | Drug response | Validation | Performance | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
EXP | MUT | CNV | Others | GDSC | CCLE | ||||||
2013/04/30 | Menden et al. [10] | ANN | RF | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | 8-fold CV | \(\hbox {R}^{2} = 0.72\) | |||
2014/01/01 | Jang et al. [11] | GLM | RF, SVM, PCA, PLS | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | CLS | \(\checkmark\) | \(\checkmark\) | 5-fold CV | r = \(\sim\) 0.5 |
2014/03/03 | Geeleher et al. [12] | GLM | \(\checkmark\) | \(\checkmark\) | LOOCV | AUC = 0.81 | |||||
2015/06/30 | Dong et al. [13] | SVM | \(\checkmark\) | \(\checkmark\) | 10-fold CV | Accuracy = \(\sim\) 0.8 | |||||
2015/09/29 | Zhang et al. [14] | Network | EN | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | LOOCV | r = 0.6 | |||
2016/03/31 | Gupta et al. [15] | SVM | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | LOOCV | r = 0.78 | |||
2016/09/01 | Ammad-Ud-Din et al. [16] | Kernel | GLM | PWY | \(\checkmark\) | 5-fold CV | \(\rho\) = \(\sim\) 0.22 | ||||
2016/12/28 | Nguyen et al. [17] | MANOVA | RF | \(\checkmark\) | \(\checkmark\) | 10-fold CV | MCC = 0.18 | ||||
2017/01/09 | Stanfield et al. [18] | Network | Kernel | \(\checkmark\) | PPI | \(\checkmark\) | \(\checkmark\) | LOOCV | AUC = 0.881 | ||
2017/07/15 | Ammad-Ud-Din et al. [19] | GLM | RF, SVM, PLS, SGL | \(\checkmark\) | PWY | \(\checkmark\) | LOOCV | \(\rho\) = 0.375 | |||
2017/08/28 | Geeleher et al. [20] | Ridge | \(\checkmark\) | \(\checkmark\) | 10-fold CV | \(\rho\) = 0.48 | |||||
2017/09/12 | Rahman et al. [21] | RF | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | 3-fold CV | AUC = \(\sim\) 0.3 | ||||
2018/02/01 | Ding et al. [22] | DNN | EN, SVM | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | 25-fold CV | AUC = 0.87 | |
2018/06/11 | Chang et al. [23] | CNN | RF, SVM | SNP | \(\checkmark\) | 5% leave-out | \(\hbox {R}^{2}\) = 0.843 | ||||
2018/07/01 | Cichonska et al. [24] | Kernel | \(\checkmark\) | \(\checkmark\) | SNP, MET | \(\checkmark\) | 10-fold CV | r = 0.858 | |||
2018/08/15 | He et al. [25] | Kernel | RF, EN, Ridge | \(\checkmark\) | \(\checkmark\) | 3-fold CV | Precision = \(\sim\) 0.35 | ||||
2018/09/14 | Juan-Blanco et al. [26] | Network | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | LOOCV | AUC = \(\sim\) 0.72 | ||||
2018/09/14 | Le and Pham [27] | Network | Kernel | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | 5-fold CV | r = 0.804 | ||
2018/12/07 | Liu et al. [28] | Network | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | 10-fold CV | r = 0.73 | ||||
2019/01/22 | Wei et al. [29] | Network | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | LOOCV | r = 0.63 | ||||
2019/01/31 | Wang et al. [30] | EN | \(\checkmark\) | PWY | \(\checkmark\) | 10-fold CV | MSE = \(\sim\) 2.8 | ||||
2019/01/31 | Chiu et al. [31] | DNN | SVM, PCA, LR | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | 10% leave-out | r = \(\sim\) 0.86 | |||
2019/02/27 | Li et al. [32] | Mixture | RF, GLM | \(\checkmark\) | \(\checkmark\) | 20% leave-out | r = 0.882 | ||||
2019/05/01 | Yang et al. [33] | Network + SVM | Kernel | \(\checkmark\) | \(\checkmark\) | PPI, MET | \(\checkmark\) | 5-fold CV | AUC = 0.788 | ||
2019/07/11 | Lind and Anderson [34] | RF | ANN, SVM | \(\checkmark\) | \(\checkmark\) | 5-fold CV | r = 0.86 | ||||
2019/07/29 | Liu et al. [35] | CNN | ANN | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | 10% leave-out | \(\hbox {R}^{2}\) = 0.826 | |||
2019/10/31 | Manica et al. [36] | MCA + CNN | RF, SVM | \(\checkmark\) | \(\checkmark\) | PPI | \(\checkmark\) | 5-fold CV | \(\underline{\textit{R}^{\textit{2}}\,=\,0.86}\) | ||
2019/11/04 | Oskooei et al. [37] | Network | RF, LR | \(\checkmark\) | PPI | \(\checkmark\) | 30-fold CV | r = \(\sim\) 0.9 | |||