Fig. 4From: Prediction of sensitivity to gefitinib/erlotinib for EGFR mutations in NSCLC based on structural interaction fingerprints and multilinear principal component analysisClassification accuracies of the five most commonly used classifiers against different values of H. H means the number of most discriminative components of the output feature vector retained for classification. a The classification accuracies for EGFR mutant-gefitinib complexes. b The classification accuracies for EGFR mutant-erlotinib complexesBack to article page