Fig. 3From: Mining influential genes based on deep learningThe density plot (a, c) and scatter plot (b, d) are used for comparison of the landmark genes inferred from our method (labelled as “D1000”) and that of L1000 (labelled as “L1000”) in terms of MAE (a, b) and PCC (c, d). In B and D, each dot represents a predicted target gene, and the red dot indicates that D1000 is better than L1000Back to article page