CYCLON and NPM1 Cooperate within an Oncogenic Network Predictive of R-CHOP Response in DLBCL

Abstract

R-CHOP immuno-chemotherapy significantly improved clinical management of diffuse large B-cell lymphoma (DLBCL). However, 30-40% of DLBCL patients still present a refractory disease or relapse. Most of the prognostic markers identified to date fail to accurately stratify high-risk DLBCL patients. We have previously shown that the nuclear protein CYCLON is associated with DLBCL disease progression and resistance to anti-CD20 immunotherapy in preclinical models. We also recently reported that it also represents a potent predictor of refractory disease and relapse in a retrospective DLBCL cohort. However, only sparse data are available to predict the potential biological role of CYCLON and how it might exert its adverse effects on lymphoma cells. Here, we characterized the protein interaction network of CYCLON, connecting this protein to the nucleolus, RNA processing, MYC signaling and cell cycle progression. Among this network, NPM1, a nucleolar multi-functional protein frequently deregulated in cancer, emerged as another potential target related to treatment resistance in DLBCL. Immunohistochemistry evaluation of CYCLON and NPM1 revealed that their co-expression is strongly related to inferior prognosis in DLBCL. More specifically, alternative sub-cellular localizations of the proteins (extra-nucleolar CYCLON and pan-cellular NPM1) represent independent predictive factors specifically associated to R-CHOP refractory DLBCL patients, which could allow them to be orientated towards risk-adapted or novel targeted therapies.

Keywords: CYCLON; NPM1; R-CHOP; R-IPI; nucleolus; prognosis.

Figure 1

CYCLON protein network exerts oncogenic effects through nucleolar gene expression regulation and cell-cycle dependent functions. (A) CYCLON protein-protein interaction network and associated functions in B593 DLBCL cell line. (B) Gene ontology (GO) enrichment analysis of CYCLON interacting proteins for biological pathway (upper panel) and cellular component (lower panel) classifiers. (C) CYCLON and NPM1 sub-cellular interphase localization in B593 GFP-CYCLON cell line. Images were captured with a confocal microscope. Bar, 2 µm. (D) CYCLON and NPM1 gene expression levels in DLBCL TCGA samples (T) vs. normal B cells (N, from TCGA and GTEx databases), * p < 0.0001. (E) CYCLON and NPM1 gene expression correlation plot in DLBCL TCGA samples, R: Pearson coefficient. TCGA and GTEx data were retrieved through GEPIA interface.

Figure 2

NPM1 and CYCLON co-expression is associated with progression-free survival in DLBCL patients. (A) Mosaic plot showing the distribution of NPM1^(−/+) cases according to CYCLON ^(−/+) status. (B) Kaplan–Meier analysis of progression-free survival (PFS) associated with CYCLON single expressors (CYCLON⁽⁺⁾ NPM1⁽⁻⁾) or CYCLON/NPM1 double expressors (CYCLON ⁽⁺⁾ NPM1⁽⁺⁾). (C) Mosaic plot showing the distribution of NPM1^(−/+) cases according to CYCLON IHC staining patterns (pan: pan-nuclear, nuc: nucleolar, ext: extra-nucleolar). (D) Kaplan–Meier analysis of PFS associated with CYCLON non-extra-nucleolar (CYCLON ^(ext−)), CYCLON extra-nucleolar/NPM1 negative (CYCLON ^(ext+) NPM1⁽⁻⁾) or CYCLON extra-nucleolar/NPM1 double expressors (CYCLON ^(ext+) NPM1⁽⁺⁾). p values are derived from a log rank test. (E) Survival Cox model regression analyses of CYCLON ^(ext+) NPM1⁽⁺⁾ cases (n = 13) and CYCLON ^(ext+) NPM1⁽⁻⁾ cases (n = 5) for PFS and specific overall survival (SOS). CYCLON non-extra-nucleolar staining (CYCLON ^(ext−)) (n = 79) is the reference category in both models. HR: hazard ratio, CI: confidence interval, * 95% CI based on bootstrap resampling (1000 replicates). Schoenfeld residual test: PFS model: global p = 0.91; SOS model: global p = 0.98.

Figure 3

NPM1 subcellular localization is a predictive factor in DLBCL patients. (A) IHC analysis of NPM1 revealing distinct expression patterns in DLBCL patients as indicated. (B). Kaplan–Meier survival analysis of PFS (left) and SOS (right) associated with NPM1 IHC patterns. p values are derived from an overall log rank test.