Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: Epigenetic landscape of drug responses revealed through large-scale ChIP-seq data analyses

Fig. 3

Prediction of chemical–TF–disease associations. a, b Distributions of AUROC (a) and AUPR scores (b) for each chemical–disease association predicted using the proposed ChIPEA-based approach and approaches that ignore TFs. Red and black horizontal lines inside the box represent mean and median scores, respectively, and global scores are noted beside the violin plots. Differences between the methods are presented with p-values by Wilcoxon rank-sum test above the violin plots. c Distribution of AUROC scores by chemical class according to the first level of the Anatomical Therapeutic Chemical classification system (ATC code). Chemicals are assigned the following ATC codes. A: alimentary tract and metabolism; B: blood and blood-forming organs; C: cardiovascular system; D: dermatologicals; G: genitourinary system and sex hormones; H: systemic hormonal preparations, excluding sex hormones and insulins; J: anti-infectives for systemic use; L: antineoplastic and immunomodulating agents; M: musculoskeletal system; N: nervous system; P: anti-parasitic products, insecticides and repellents; R: respiratory system; S: sensory organs; V: various; NaN: not assigned. The numbers of chemicals assigned each ATC code are noted above the violin plots. Mean, median, and global AUROC scores are shown with red, black, and blue horizontal lines, respectively

Back to article page