Rho-GTPase pathways may differentiate treatment response to TNF-alpha and IL-17A inhibitors in psoriatic arthritis

Abstract

Biological therapies have dramatically improved the therapeutic landscape of psoriatic arthritis (PsA); however, 40-50% of patients are primary non-responders with response rates declining significantly with each successive biological therapy. Therefore, there is a pressing need to develop a coherent strategy for effective initial and subsequent selection of biologic agents. We interrogated 40 PsA patients initiating either tumour necrosis factor inhibitors (TNFi) or interleukin-17A inhibitors (17Ai) for active PsA. Patients achieving low disease activity according to the Disease Activity Index for PsA (DAPSA) at 3 months were classified as responders. Baseline and 3-month CD4⁺ transcript profiling were performed, and novel signaling pathways were identified using a multi-omics profiling and integrative computational analysis approach. Using transcriptomic data at initiation of therapy, we identified over 100 differentially expressed genes (DEGs) that differentiated IL-17Ai response from non-response and TNFi response from non-response. Integration of cell-type-specific DEGs with protein-protein interactions and further comprehensive pathway enrichment analysis revealed several pathways. Rho GTPase signaling pathway exhibited a strong signal specific to IL-17Ai response and the genes, RAC1 and ROCKs, are supported by results from prior research. Our detailed network and pathway analyses have identified the rewiring of Rho GTPase pathways as potential markers of response to IL17Ai but not TNFi. These results need further verification.

Figure 1

Schematic overview of study. (A) CD4⁺ T-cell transcriptomes of 40 patients with active PsA, at baseline and 3 months after treatment with TNFi or IL-17Ai. (B) Hierarchical clustering and PCA analysis clearly distinguished response groups. (C) Since the protein products of deregulated genes perform in groups, their physical connectivity can bring an additional layer of confidence to selection of genes whose statistical significance may not reflect their importance due to small sample size. We developed a multilayer analysis approach that annotates protein interactions with DEGs, protein families, and pathways. Our analysis identified signaling pathways likely involved in response to each biologic.

Figure 2

Sample Clustering and PCA analysis based on CD4⁺ cell transcriptomic data. The hierarchical clustering in heatmaps and 2D PCA plots with ellipses concentration clearly show separation of the responder and non-responders. In the heatmaps, columns are samples and rows are differentially expressed genes, the expression levels are presented as median-centered. Samples in the red-dashed lines were non-responders and samples in the blue-dashed lines were responders. (a) and (b) are heatmap and PCA plot for IL17i responder and non-responders; (c) and (d) are heatmap and PCA plot for TNFi responder and non-responders.

Figure 3

Pathway enrichment analysis of selected DEGs using PPI network. (A) Overlap of DEGs between response groups to each biologic at baseline and their enriched pathways. (B,C) Key-terms of pathways enriched in DEGs between response groups to (B) TNFi and (C) IL-17Ai. Size of the terms is proportional with statistical significance of each term in titles of enriched pathways. Colors are different only for clarity. While most of the large terms in each panel are present in the other panel in a different size, MET, JAK, STAT in panel B, and, Rho-GTPase and EPH in panel C are absent from the other panel. Thus, high deregulation of these pathways between responders and non-responders is specific to one of the two biologics.

Figure 4

DEGs in Rho-GTPase pathways and their overlap. (A) Membership of DEGs in Rho-GTPase pathways. Black labels show DEGs in more than one comparison or members of more than 4 Rho-GTPase pathways. Red labels show DEGs whose protein product is characterized as Rho family GTPase or Rho-GTPase activating protein (based on HGNC annotation). (B) Overlap size of Rho-GTPase DEGs in pairs of comparisons.

Figure 5

Fold change (represented with color) and p value (shown in numbers in the cells) of DEGs in RAC1/PAK1/p38/MMP2 pathway across different comparisons. Pathway genes were downloaded from PathDIP. Each column represents DEGs between two groups of “group1” and “group 2” and “group1 versus group2” comparison, fold change shows expression in group 1 minus expression in group 2. The range of fold change changes between negative 1.5 (downregulated in group 1) and positive 1.7 (upregulated in group 1). Color-code shows log2 of fold change values. The two columns that compare IL17Ai responder group to IL17Ai non-responders and TNFi responders pre-treatment show the highest number of significant pathway DEGs (6 out of 14). In addition, fold change of RAC1 is statistically significant only in IL17A-i responders versus IL17Ai non-responders pre-treatment, and its p value (0.06) is only slightly above the threshold of 0.05 in IL17Ai responders versus TNFi responders pre-treatment.