Arlm1 is a male-specific modifier of astrocytoma resistance on mouse Chr 12

Abstract

While many cancers show a sex bias, the genetic basis and molecular mechanisms underlying sex bias are not always clear. Astrocytoma and glioblastoma show male predominance in humans. We have shown previously that glial tumors forming in the Nf1-/+; Trp53-/+cis (NPcis) mouse model also show a sex bias in some genetic contexts. Using cross-species comparisons we have identified candidate male-specific modifiers of astrocytoma/glioblastoma. Linkage analysis of B6X(B6X129)-NPcis mice identifies a modifier of astrocytoma resistance specific to males, named Arlm1, on distal mouse Chr 12. Arlm1 is syntenic to human Chr 7p15, 7p21, 7q36, and 14q32 regions that are altered in human glioblastoma. A subset of these genes shows male-specific correlations to glioblastoma patient survival time and represents strong candidates for the Arlm1 modifier gene. Identification of male-specific modifier genes will lead to a better understanding of the molecular basis of male predominance in astrocytoma and glioblastoma.

Fig. 1.

Comparison of astrocytoma-free survival and incidence for male and female NPcis mice on the B6, 129, B6X129, and B6X(B6X129) strain backgrounds. (A) Astrocytoma-free survival for NPcis males. (B) Astrocytoma-free survival for females. (C) Astrocytoma incidence by grade for NPcis males and females.

Fig. 2.

Linkage analysis for astrocytoma resistance in B6X(B6X129)-NPcis males and females. A graph of the genome-wide linkage analysis LOD scores for males is shown in (A) and for females in (B). The dotted line indicates the 0.05 alpha thresholds for statistical significance using permutation testing. (C) Linkage analysis of Chr 12 for both males (blue) and females (red). (D) The effect size of Arlm1^B6/129 (SB) and Arlm1^B6/B6 (BB) at 63.5 cM for males and females.

Fig. 3.

Diagram of candidate gene analysis. The region of the Arlm1 locus was defined and compared to human syntenic genome regions. The genes in the region were examined in both mouse and human data. Cross-species comparisons were used to prioritize candidate Arlm1 genes.

Fig. 4.

Graph of the expression level of Arlm1 candidate genes in B6 and 129 male mouse brains, taken from publicly available microarray data. Genes are organized along the Y-axis by their synteny with human Chr 7p (cyan), 7q (magenta), or 14q (green), corresponding to the cartoon in Fig. 3. Genes with no clear human homolog are shown in gray. The X-axis shows the ratio of 129/B6 on the log₂ scale. Red dotted lines indicate the 1.5-fold up or down threshold used to prioritize candidates. The Igh locus showed a lot of variability between different probes in the dataset and was not included in the graph. Abbreviation: N.H., no homolog.

Fig. 5.

Males with 2-fold higher levels of CRIP2 in their tumors survive less time than males with intermediate or low levels of CRIP2. Graphs show survival curves for male GBM patients (A and C) and female GBM patients (B and D) stratified by expression level of CRIP2 for the REMBRANDT dataset (A and B) and the TCGA dataset (C and D). The survival curve for all pooled samples is shown in black. Survival curves for samples with 2-fold overexpression are shown in red and samples with 2-fold underexpression are shown in green. The gold line in the REMBRANDT data represents the survival of patients with intermediate levels of CRIP2 in their tumors. Data for which the survival curve for CRIP2-overexpressing GBMs is shifted to the right suggest an oncogenic effect of CRIP2 in human GBM.

Fig. 6.

Males with 2-fold higher levels of CDCA7L in their tumors survive less time than males with intermediate or low levels of CDCA7L. Graphs show survival curves for male GBM patients (A and C) and female GBM patients (B and D) stratified by expression level of CDCA7L for the REMBRANDT dataset (A and B) and the TCGA dataset (C and D). The survival curve for all pooled samples is shown in black. Survival curves for samples with 2-fold overexpression are shown in red and samples with 2-fold underexpression are shown in green. The gold line in the REMBRANDT data represents the survival of patients with intermediate levels of CDCA7L in their tumors. Data for which the survival curve for CDCA7L-overexpressing GBMs is shifted to the right suggest an oncogenic effect of CDCA7L in human GBM.

Fig. 7.

Strain differences in expression of Cdca7l and Crip2 in mouse brains. Wt B6 female brains (n = 5) and wt B6 male brains (n = 7) express lower levels of Cdca7l than wt 129 female brains (n = 5) and wt 129 male brains (n = 8) (A). The difference between B6 and 129 females is suggestive (t-test P = .056) and the difference between B6 and 129 males is significant (t-test P = .0030). Wt B6 female brains express higher levels of Crip2 than wt 129 female brains (t-test P = .049), but males show no difference in Crip2 expression between B6 and 129 (B). Brackets indicate which data comparison is statistically significant (*P < .05; **P < .005). Female B6-NPcis astrocytoma lines (n = 2) express lower levels of Cdca7l than female 129-NPcis astrocytoma lines (n = 4) (C), consistent with results in normal brains (A); however, the number of available tumor lines is too low to draw statistically significant conclusions. The level of Crip2 in female B6-NPcis astrocytoma lines (n = 2) and 129-NPcis astrocytoma lines (n = 4) (D) is variable and does not reflect the expression differences seen in normal brain (B). Red bars indicate B6 samples and blue bars indicate 129 samples. Solid bars represent male samples and checked bars represent female samples.