Construction of biologically-interpretable chemical–disease association focused on transcription factors organizing chemically-perturbed genes

• Published in: Proceedings for Annual Meeting of The Japanese Pharmacological Society Vol. 94; p. 1-Y-E3-4
• Main Authors: Zhaonan, Zou, Iwata, Michio, Yamanishi, Yoshihiro, Oki, Shinya
• Format: Journal Article
• Language: English; Japanese
• Published: Japanese Pharmacological Society 2021
• ISSN: 2435-4953; 2435-4953
• DOI: 10.1254/jpssuppl.94.0_1-Y-E3-4

Modification of disease-elicited gene expression is one of the core aspects in numerous drugs’ modes of action. To predict drug–disease associations, transcriptomics-based approaches with pathway analysis, graph theory and supervised machine learning-based calculation were developed. However, the pharmacological mechanism employed by drugs remain largely unknown. In this study, we focused on transcription factors (TFs) that integratively regulate differentially expressed genes (DEGs) in response to drug treatment. In particular, TF enrichment analysis (TFEA) was performed for each chemical to identify TFs with enriched binding for DEGs by combining the chemically perturbed transcriptome data (CTD) and TF-binding database ChIP-Atlas. Performance evaluation with area under the ROC curve (AUC) suggests the reliability of TFEA in drug target discovery (global AUC = 0.66). Furthermore, we successfully identified the key factors that link drugs to diseases or side effects by utilizing protein-disease database DisGeNET (global AUC = 0.68). This approach is with high confidence because it is fully based on actual experiments of given transcriptome data and public ChIP-seq data. In the pharmaceutical field, TFEA is useful to shed light on compounds failed to be approved by identifying TFs primarily involved in the modes of action, together with the factors associated with potential side effects. Approved drugs including agents composed of unidentified ingredients such as traditional herbal medicines can also be re-examined for novel targets and actions, thus beneficial to drug repositioning research.