Fig. 6From: Inverse similarity and reliable negative samples for drug side-effect predictionComparison results using the proposed negative sample selection method and random sample selection method. The x-axis denotes F1-scores of results based on negative samples selected randomly, and the y-axis denotes F1-scores of results based on negative samples selected by the proposed method. The line “ y=x” on which F1-scores are equal, is used as the reference line. Panel (a), (b), (c) and (d) show the scatter plots of F1-scores using the proposed negative sample selection method and random sample selection method achieved by KNN, ELM, SVM and RBF respectivelyBack to article page