From: Predicting anatomic therapeutic chemical classification codes using tiered learning
2 nd level ATC Code Prediction using different initializations and comparison to STP | ||||||||
---|---|---|---|---|---|---|---|---|
Initialization method | Supervised learning | SuperPred | ChEMBL (Perfect 1st level) | STP | ||||
Prediction method | A(2) | CA(2) (N(2)) | A(2) | CA(2) (N(2)) | A(2) | CA(2) (N(2)) | A(2) | CA(2) (N(2)) |
MLP | 69.18% | 71.42% (64.34%) | 70.79% | 74.37% (68.47%) | 79.03% | 89.52% (79.03%) | 69.89% | 71.77% (67.56%) |
Naive Bayes | 48.21% | 47.94% (36.74%) | 60.22% | 69.09% (57.35%) | 65.41% | 82.71% (65.05%) | 46.95% | 47.31% (36.38%) |
Random Forest | 63.98% | 65.23% (57.71%) | 68.28% | 73.12% (66.49%) | 77.60% | 88.80% (77.60%) | 62.19% | 64.34% (58.96%) |
SVM | 67.92% | 69.89% (63.26) | 72.40% | 75.18% (70.79%) | 81.90% | 90.95% (81.90%) | 68.46% | 70.16% (64.52%) |