Divergent gene expression patterns in alcohol and opioid use disorders lead to consistent alterations in functional networks within the Dorsolateral Prefrontal Cortex

Abstract

Substance Use Disorders (SUDs) manifest as persistent drug-seeking behavior despite adverse consequences, with Alcohol Use Disorder (AUD) and Opioid Use Disorder (OUD) representing prevalent forms associated with significant mortality rates and economic burdens. The co-occurrence of AUD and OUD is common, necessitating a deeper comprehension of their intricate interactions. While the causal link between these disorders remains elusive, shared genetic factors are hypothesized. Leveraging public datasets, we employed genomic and transcriptomic analyses to explore conserved and distinct molecular pathways within the dorsolateral prefrontal cortex associated with AUD and OUD. Our findings unveil modest transcriptomic overlap at the gene level between the two disorders but substantial convergence on shared biological pathways. Notably, these pathways predominantly involve inflammatory processes, synaptic plasticity, and key intracellular signaling regulators. Integration of transcriptomic data with the latest genome-wide association studies (GWAS) for problematic alcohol use (PAU) and OUD not only corroborated our transcriptomic findings but also confirmed the limited shared heritability between the disorders. Overall, our study indicates that while alcohol and opioids induce diverse transcriptional alterations at the gene level, they converge on select biological pathways, offering promising avenues for novel therapeutic targets aimed at addressing both disorders simultaneously.

Figure 1:. Transcriptomic changes in the DLPFC from donors with OUD.

(A-B) Volcano plot of RNA-seq data shows DEGs (red) from OUD1 versus unaffected control donors (A) and OUD2 versus control donors (B). The horizontal dashed line represents the FDR significance cut-off (< 0.05), and the dashed vertical lines represent a Log2FC cut-off ± 0.26 (FC=1.2). (C) Venn diagram representing the overlap of DEGs in OUD1, OUD2, and OUD groups shows 56 shared DEGs across all group comparisons. (D) Correlation analysis of the fold change of combined DEGs from OUD1, (orange) OUD2 (blue). DEGs shared between OUD1 and OUD2 are shown in yellow. (E) RRHO analysis shows concordance of gene expression between OUD1 and OUD2 versus control in the DLPFC. Pixels represent overlap between the genome-wide transcriptome of each comparison, with the significance of overlap color-coded. The bottom left quadrant includes co-up-regulated genes, and the top right quadrant includes co-down-regulated genes compared to the control. Bottom right and top left quadrants include oppositely regulated genes. (F) Top: Hypergeometric analysis quantifying the enrichment of immediate early genes (IEGs) within the list of DEGs in OUD (red), OUD1 (orange) OUD2 (blue) groups. The X-axis represents –log10(P-value); the size of the circle represents the number of overlapping genes. Bottom: heatmap represents the Log2FC of the 25 IEGs expressed in the DLPFC samples across OUD1, OUD2, and OUD groups. (G) Top Gene Ontology (GO) terms shared between OUD1 (orange) and OUD2 (blue) groups. The x-axis represents the odds ratio and measures effect size, and the size of the circle represents the –log10(P-value). (H) Top 20 canonical pathways commonly enriched in the OUD1 and OUD2 groups. Pathways were clustered into four distinct groups based on the similarity of overlapping genes.

Figure 2:. Transcriptomic changes in the DLPFC from donors with AUD.

(A) Volcano plot shows DEGs (red) from AUD versus control donors in the DLPFC. The horizontal dashed line represents the FDR significance cut-off (< 0.25), and the dashed vertical lines represent a Log2FC cut-off ± 0.20 (FC=1.15). (B) Heatmap representing gene expression of all 364 DEGs. Samples were clustered using hierarchical cluster analysis by expression similarity. Each column represents a different subject. Top bar plots represent phenotypic data from each subject. Samples from donors with AUD are shown in green, and the control is in grey. AUD samples are clustered into a single distinct group. (C) PCA shows a large overlap between the AUD and control samples. Ellipses represent a 90% confidence range. (D) Top GO terms enriched in the AUD group. The size of the circle represents the –log10(P-value), and the odds ratio measures the effect size. (E) Pathway analysis shows the top 20 canonical pathways enriched in the AUD group. Pathways were clustered based on the extent of overlap among genes.

Figure 3:. Comparing changes in the DLPFC in donors with AUD and OUD 1.

(A) RRHO plot shows a large overlap between AUD and OUD1 groups at the genome-wide level. See Fig. 1A for the definition of each quadrant. (B) Biotype analysis of all DEGs in the AUD and OUD1 groups reveals the distribution of gene products within each group. The inset provides a closer look at the less common biotypes. (C) Scatterplot illustrating the correlation between the fold change of the AUD group (green) and OUD1 group (orange) for all expressed genes in the DLPC. Common DEGs are highlighted in blue, while unchanged changes are represented in gray. (D) Venn diagram shows DEGs shared between AUD and OUD1 (blue) along with exclusive DEGs for AUD (green) and OUD1 (orange). The heatmap shows the Log2FC of the 72 shared DEGs between OUD1 and AUD groups. The gene symbols for the top 4 upregulated and downregulated genes in the OUD1 group are highlighted. (E) The top GO terms enriched for the common DEGs in both AUD and OUD1 groups are depicted. The circle size reflects the –log10(P-value), and the x-axis illustrates the odds ratio, indicating the effect size. (F) Pathway analysis shows the top 15 canonical pathways enriched for common DEGs in both AUD and OUD1 groups. Pathways were clustered based on the extent of overlap among genes.

Figure 4:. Comparing Transcriptomic changes in the DLPFC of donors with AUD and OUD at the pathway level.

(A) Left: Bar plot illustrating the percentage of enriched pathways shared between OUD1 (orange) and AUD groups (blue), as well as pathways uniquely enriched in each group. Right: Scatterplot depicting the Z-score correlation of canonical pathways commonly enriched between OUD1 and AUD groups. Pathways were distributed in three quadrants representing their activation status in each group. Pathways with a Z-score > 0 are considered activated, and those with a Z-score < 0 are considered deactivated. (B) Gene-level analysis shows down-regulated (blue) and upregulated (red), genes within selected pathways from each quadrant. (C) Upstream modulators exhibiting enrichment in both AUD (green) and OUD1 (orange) groups. The x-axis displays the activation Z-score, with the circle size representing the –log10(P-value). Only upstream regulators with an absolute Z-score greater than 2 are included in the plot. The red-shaded area denotes regions with non-significant Z-scores. (D) Upstream modulators enriched exclusively in OUD1 (on the left), or AUD (on the right) groups are depicted. The x-axis indicates the activation Z-score, and the circle size corresponds to the –log10(P-value). The red-shaded area shows zones with non-significant Z-scores. Notably, none of the upstream modulators exclusive to AUD reached Z-score significance. (E) Heatmap representing the Log2FC of protein-coding upstream modulators within the AUD and OUD1 groups. Cells marked with an asterisk indicate differentially expressed genes.

Figure 5:. Genomic and transcriptomic integration.

(A) Extent of heritability elucidated by AUD and OUD1-DEGs across various traits and neuropsychiatric conditions. (B) Transcriptome-wide association analysis showing predicted gene expression levels within the DLPFC based on genetic variants associated with PAU and OUD and their overlapping with the set of OUD1-DEGs. Displayed are the genes shared across multiple conditions, accompanied by their predicted and observed gene expression levels. Genes showing upregulation are highlighted in red, while those exhibiting downregulation are depicted in blue.

Figure 6:. Heterogeneity in the gene expression pattern within OUD samples.

(A) Volcano plot shows DEGs (red) from OUD versus healthy control donors in the DLPFC. The horizontal dashed line represents the FDR significance cut-off (< 0.05), and the dashed vertical lines represent a Log2FC cut-off ± 0.26 (FC=1.2). (B) Heatmap representing gene expression of all DEGs. Samples were clustered using hierarchical cluster analysis by expression similarity. Each column represents a different subject. The top bar plots represent phenotypic data from each subject. OUD donors are shown in red, and control in grey. OUD samples clustered into two distinct groups, OUD1 (orange) and OUD2 (blue). (C) Top: Cluster analysis using categorical phenotypic data shows the existence of two distinct clusters, control (gray) and OUD (red). Bottom: Principal component analysis showing the separation of the OUD samples in reduced space. Ellipses represent a 90% confidence range for OUD1 (orange), OUD2 (blue), and Control (grey) groups.

Figure 7:. Transcription-wide and pathway-level comparisons between AUD and OUD groups.

(A) RRHO analysis shows limited concordance of gene expression between OUD2 and AUD versus control in the DLPFC. Pixels represent overlap between the genome-wide transcriptome of each comparison, with the significance of overlap colorcoded. The bottom left quadrant includes co-up-regulated genes, and the top right quadrant includes co-down-regulated genes compared to the control. The bottom right and top left quadrants include oppositely regulated genes. (B, left) Scatterplot illustrating pathways exclusively enriched in OUD1 (orange) and AUD (green) groups. The x-axis displays the activation Z-score, while the y-axis shows -log10(P-value). Only pathways with a non-zero Z-score are included in the plot. Right, Gene-level analysis displays down-regulated genes (blue), upregulated genes(red), non-changed genes (gray), and undetected genes (white) within selected pathways.