Integrated transcriptomics reveals master regulators of lung adenocarcinoma and novel repositioning of drug candidates

Abstract

Background: Lung adenocarcinoma is the major cause of cancer-related deaths in the world. Given this, the importance of research on its pathophysiology and therapy remains a key health issue. To assist in this endeavor, recent oncology studies are adopting Systems Biology approaches and bioinformatics to analyze and understand omics data, bringing new insights about this disease and its treatment.

Methods: We used reverse engineering of transcriptomic data to reconstruct nontumorous lung reference networks, focusing on transcription factors (TFs) and their inferred target genes, referred as regulatory units or regulons. Afterwards, we used 13 case-control studies to identify TFs acting as master regulators of the disease and their regulatory units. Furthermore, the inferred activation patterns of regulons were used to evaluate patient survival and search drug candidates for repositioning.

Results: The regulatory units under the influence of ATOH8, DACH1, EPAS1, ETV5, FOXA2, FOXM1, HOXA4, SMAD6, and UHRF1 transcription factors were consistently associated with the pathological phenotype, suggesting that they may be master regulators of lung adenocarcinoma. We also observed that the inferred activity of FOXA2, FOXM1, and UHRF1 was significantly associated with risk of death in patients. Finally, we obtained deptropine, promazine, valproic acid, azacyclonol, methotrexate, and ChemBridge ID compound 5109870 as potential candidates to revert the molecular profile leading to decreased survival.

Conclusion: Using an integrated transcriptomics approach, we identified master regulator candidates involved with the development and prognostic of lung adenocarcinoma, as well as potential drugs for repurposing.

Keywords: computational drug repositioning; connectivity map; lung cancer; master regulator; transcriptomic.

Figure 1

Common and Consensus Master Regulator of Lung Adenocarcinoma. A, Subnetwork of inferred common master regulators and their association for each reference transcription network. Node sizes map the number of genes inferred for a given transcription factor, the number of connections (degree) was mapped to the color of the nodes and edge widths represent the number of overlapped genes shared by pairs of TF Insert shows a Venn diagram of the regulons in TN1 and TN2 networks (intersection regulons were termed consensus master regulators). B, Master regulator analysis showing the statistical overrepresentation (enrichment) of differentially expressed genes in each consensus master regulator, for all case‐control datasets and for both reference TN. Our criteria of differential expression were false discovery rate (FDR)‐adjusted P‐value <.05 and absolute log fold change (logFC) > 1

Figure 2

Activation State and Survival Network of Consensus Master Regulators. A, Two‐tailed gene set enrichment analysis was used to query the activation state of consensus master regulators in both reference TNs. B, Regulon enrichment was used to investigate the altered regulatory units’ association with survival risk using Cox proportional hazards regression in 10 transcriptomic studies. The results were mapped over the common MR networks in each transcription network. Node size represents the number of studies in which a significant association of regulons’ activity with survival was observed. Node color shows the hazard ratio of these associations

Figure 3

Kaplan‐Meier Survival Curves of Master Regulators. Enrichment scores of consensus master regulators consistently associated with patient survival were standardized (z‐score), merged and their distributions were discretized. The discretized quartile segments (low = first quartile; mid = second quartile; high = third quartile) were then evaluated using Kaplan‐Meier curves and log‐rank test (lower segments) in both (A) TN1 and (B) TN2 reference networks

Figure 4

Master Regulator Connectivity Maps. A, Venn diagrams of drug candidates obtained from the connectivity maps method. Genes from the common master regulator regulons, the eight consensus master regulator regulons, and the three master regulators of survival regulons were each combined to form the different sets of gene lists. We only counted molecules in which connectivity score reverted the expression profiles of each gene list; and had FDR‐adjusted P‐value <.05 in all 13 adenocarcinoma case‐control studies. Left diagram shows the count of drug candidates found for TN1 and right diagram shows counts of candidates found for TN2 reference network. B, Table showing the six drugs observed in the intersections of the connectivity maps of both reference TNs, their anatomical therapeutic chemical (ATC) classification, and chemical abstracts service (CAS) registry number