Flowchart and comparisons of prediction accuracy.

(A) The CMap analysis flowchart. All eight sets from EHCO2 (Group 1), 100-member random sets, Frequent sets, and Clique sets (Group 2) were individually queried with CMap. Only drugs with a p-value of less than 0.05 and a negative enrichment score were retained. (B) Comparison of the accuracy of predicted drugs from each set. The top 10 drugs from each set were labeled according to their anti-cancer effects. (C) The comparison of the Frequency sets and the Clique sets. The average effectiveness of drugs was compared side by side.