Table 14 Comparison of the prediction accuracy of TL and SuperPred for the fourth level ATC codes
From: Predicting anatomic therapeutic chemical classification codes using tiered learning
4th level ATC Code Prediction using different initializations and comparison to STP | ||||||
|---|---|---|---|---|---|---|
Initialization method | Supervised learning | ChEMBL (Perfect 1st level) | SuperPred Prediction Results | |||
Prediction method | A(4) | CA(4) (N(4)) | A(4) | CA(4) (N(4)) | A(4) | CA(4) (N(4)) |
MLP | 39.71% | 47.55% (22.55%) | 47.55% | 69.36% (33.82%) | 56.86% | 48.04% (38.24%) |
Naive Bayes | 35.78% | 42.89% (15.20%) | 45.59% | 65.93% (27.94%) | ||
Random Forest | 35.29% | 44.61% (21.57%) | 49.51% | 68.87% (33.82%) | ||
SVM | 38.24% | 47.79% (27.94%) | 49.02% | 70.59% (38.73%) | ||