Novel tools for comparing the architecture of psychopathology between neurogenetic disorders: An application to X- versus Y-chromosome aneuploidy effects in males

Abstract

Background: Psychiatric symptoms are typically highly inter-correlated at the group level. Collectively, these correlations define the architecture of psychopathology - informing taxonomic and mechanistic models in psychiatry. However, to date, it remains unclear if this architecture differs between etiologically distinct subgroups, despite the core relevance of this understanding for personalized medicine. Here, we introduce a new analytic pipeline to probe group differences in the psychopathology architecture - demonstrated through the comparison of two distinct neurogenetic disorders.

Methods: We use a large questionnaire battery in 300 individuals aged 5-25 years (n = 102 XXY/KS, n = 64 XYY, n = 134 age-matched XY) to characterize the structure of correlations among 53 diverse measures of psychopathology in XXY/KS and XYY syndrome - enabling us to compare the effects of X- versus Y-chromosome dosage on the architecture of psychopathology at multiple, distinctly informative levels.

Results: Behavior correlation matrices describe the architecture of psychopathology in each syndrome. A comparison of matrix rows reveals that social problems and externalizing symptoms are most differentially coupled to other aspects of psychopathology in XXY/KS versus XYY. Clustering the difference between matrices captures coordinated group differences in pairwise coupling between measures of psychopathology: XXY/KS shows greater coherence among externalizing, internalizing, and autism-related features, while XYY syndrome shows greater coherence in dissociality and early neurodevelopmental impairment.

Conclusions: These methods offer new insights into X- and Y-chromosome dosage effects on behavior, and our shared code can now be applied to other clinical groups of interest - helping to hone mechanistic models and inform the tailoring of care.

Keywords: Jacobs syndrome; Klinefelter syndrome; XXY/KS; XYY; behavioral phenotyping; gene dosage disorders; sex chromosome aneuploidy; symptom network analysis.

Figure 1.

Schematic overviewing analytic workflow. (a) Raw scores for each of the 53 scales are scaled in each SCA group using the mean and standard deviation in their corresponding XY control group. (b) Cross-individual correlations between each unique pair of scales yield a 53×53 square, symmetric correlation matrix for both the XXY/KS and XYY groups. This matrix can be conceptualized as a signed, weighted, and unthresholded network, where each node is a scale and each edge captures the strength and direction of correlation between scales. A single row of these matrices captures the ‘fingerprint’ of a single scale’s correlation with all other scales. Row averages capture each scale’s ‘nodal degree,’ indexing the overall strength of its correlation with all other scales. (c) Correlating nodal degree values between groups (across scales) quantifies the overall similarity of each scale’s connectivity with all others in XXY/KS and XYY and highlights scales that differ most in the overall strength of their coupling with other scales between groups. (d) Correlating fingerprints between groups identifies scales that are most divergent in the specific profile of their coupling with all others between XXY/KS and XYY. (e) Subtracting the two matrices in panel (b) yields a single 53×53 square symmetric matrix of the differences in correlation between each unique pair of scales in XXY/KS vs. XYY. Clustering this difference matrix identifies sets of edges that show coordinated differences in strength between groups (i.e. sets of scales that are more or less coherent in one group vs. the other).

Figure 2.

Comparing XXY/KS and XYY for the magnitude and profile of psychopathology connectivity at the level of individual behavioral scales. (a) Scatterplot showing the relationship between nodal degree (magnitude of a scale’s overall connectivity) for 53 different behavioral scales in XXY/KS versus XYY. The identity y = x line is dashed gray. The fit line from Deming regression is solid blue. Scales are colored by the domain of psychopathology they measure. (b) Dot plot showing the divergence between nodal edge profiles (the profile of a scale’s connectivity with all others) in XXY/KS versus XYY for 53 different behavioral scales. Dot color and bold text indicate scales with statistically significant divergence scores. (c) Scatterplots showing the correlation between each scale and two of the nominally significant scales from panel (b) in each group, physical aggression (ag.p_SHRP) and social problems (soc_CBCL). Bolded scale labels indicate scales with nominally significant (p < .05) differences in correlation between groups. The Deming regression fit line is solid blue and the identity y = x line is dashed gray. Scales are colored by the domain of psychopathology they measure. (d) Scatterplot showing the relationship between the absolute difference in effect size of XXY/KS versus XYY on the mean score of each behavioral scale (x-axis) and the difference in connectivity profile of each scale with all others in XXY/KS versus XYY (y-axis).

Figure 3.

The distribution of all inter-scale correlations in XXY/KS versus XYY. Density plots show the distribution of Fisher’s Z-transformed correlations for all unique pairs of scales in XXY/KS (red) and XYY (blue) groups. The mean edge strength for each group is indicated with dashed vertical lines and specified in inset text, together with the observed difference in mean edge strength ( z) and the permutation-basedp-value for this group difference statistic.

Figure 4.

Fine-grained differences between XXY/KS and XYY syndrome in the coupling between different domains of psychopathology. (a) Heatmap depicting the weighted stochastic block modeling (WSBM) solution of six clusters (outlined in black) for the delta matrix (Fisher’s Z-transformed correlations of XXY/KS – XYY). Scale names are color-coded to the instrument (see Supplementary Table S1). Heatmap cells encode the direction (red: XXY/KS > XYY/blue: XYY > XXY/KS) and magnitude (hue intensity) of group differences in correlation between each unique pair of scales. Blocks with significantly non-zero mean edge strength (nominal p < .05) are outlined in bolded black, while blocks within non-significant average group differences in coupling (i.e., mean edge strength statistically indistinguishable from zero) are grayed out. (b) Network representation of the WSBM solution. Nodes (circles) represent blocks, and the lines represent edges color-coded by statistical significance. The thickness of the line depicts the edge strength between any two blocks and the node size represents the weighted nodal degree.