Fig. 7

KDM5B interacts directly with MALAT1 to modulate its expression in triple negative breast carcinoma cells. a Sequence-based prediction of MALAT1-KDM5B interaction, with random forest, RF classifier score of 0.85 and support vehicle machine, SVM classifier score of 0.99. * Interaction probabilities generated by RPISeq range from 0 to 1. In performance evaluation experiments, predictions with probabilities > 0.5 were considered “positive,” i.e., indicating that the corresponding RNA and protein are likely to interact. b PyMOL view of long non-coding RNA, MALAT1 in complex with KDM5B. c Post-SCULPTing rendering of the KDM5B-MALAT1 complex. d Mol script/R3D Input representation of the complex, show KDM5B wrapped around MALAT1. e Heat map of KDM5B-MALAT1 interaction using the catRAPID graphic. Interaction propensity is measured in procedure defined unit, p.d.u. f, g Interaction strength based on interaction propensity rank of binding regions in the positive set (10201 interacting pairs) using catRAPID strength; Error bars, S.E