Transcriptomic changes in oligodendrocytes and precursor cells associate with clinical outcomes of Parkinson's disease

Abstract

Several prior studies have proposed the involvement of various brain regions and cell types in Parkinson's disease (PD) pathology. Here, we performed snRNA-seq on the prefrontal cortex and anterior cingulate regions from a small cohort of post-mortem control and PD brain tissue. We found a significant association of oligodendrocytes (ODCs) and oligodendrocyte precursor cells (OPCs) with PD-linked risk loci and report several dysregulated genes and pathways, including regulation of tau-protein kinase activity, regulation of inclusion body assembly and protein processing involved in protein targeting to mitochondria. In an independent PD cohort with clinical measures (681 cases and 549 controls), polygenic risk scores derived from the dysregulated genes significantly predicted Montreal Cognitive Assessment (MoCA)-, and Beck Depression Inventory-II (BDI-II)-scores but not motor impairment (UPDRS-III). We extended our analysis of clinical outcome prediction by incorporating differentially expressed genes from three separate datasets that were previously published by different laboratories. In the first dataset from the anterior cingulate cortex, we identified an association between ODCs and BDI-II. In the second dataset obtained from the substantia nigra (SN), OPCs displayed an association with UPDRS-III. In the third dataset from the SN region, a distinct subtype of OPCs, labeled OPC_ADM, exhibited an association with UPDRS-III. Intriguingly, the OPC_ADM cluster also demonstrated a significant increase in PD samples. These results suggest that by expanding our focus to glial cells, we can uncover region-specific molecular pathways associated with PD symptoms.

Keywords: Oligodendrocyte precursor cells; Oligodendrocytes; PD symptoms; Parkinson’s disease; Polygenic risk scores; snRNA-seq.

Fig. 1

Overview of snRNA-seq profiling in the human post-mortem brain tissues. A Schematic overview of the experimental plan (see Table S1). B Uniform manifold approximation and projection (UMAP) visualization of the snRNA-seq clusters from 88,876 high quality nuclei. C Percentage of nuclei for each cell type across samples, mutation group and brain regions (see Table S2). D UMAP embeddings of nuclei colored by mutation group and brain regions. E Barplot displaying the distribution of cell-type percentage sample-wise. F Violin plot illustrating the expression distribution of known gene markers (see Table S3). G Genes most up-regulated in identified cell types: excitatory neurons (ExN), inhibitory neurons (InN), oligodendrocytes (ODCs), oligodendrocyte precursor cells (OPCs), microglia (MG), astrocytes (Astro) and vascular cells (Vas)

Fig. 2

Association of PD susceptibility with ODCs and OPCs. A Multi-marker analysis of genomic annotation (MAGMA) gene set enrichment based on all the 88,876 high quality nuclei showed significant associations with oligodendrocytes (ODCs) and oligodendrocyte precursor cells (OPCs) (see Table S4). B Number of differentially expressed genes (DEGs) in each comparison and cell-type (see Table S5). C MAGMA gene set enrichment based on DEGs in LRRK2 vs HC (upper) and in GBA1 vs HC (lower) (see Table S6). D Gene ontology enrichment analysis of up-regulated (left) or down-regulated (right) genes. Top five biological process terms for each gene list are indicated. Enrichr combined score is calculated by the logarithmic transformation of the p-value obtained from Fisher’s exact test, multiplied by the z-score representing the deviation from the expected rank (see Table S7)

Fig. 3

Polygenic prediction of PD measures using the ODCs and OPCs DEGs in publicly available datasets. A–C Prediction of clinical outcomes using Feleke et al. [9] from anterior cingulate cortex region (A), Lee et al. [10] from substantia nigra region (B) and Kamath et al. [11] from substantia nigra region (C) (see Table S10). D Gene ontology enrichment analysis of DEGs in predictive subpopulation of cell-types in Kamath et al. [11] from substantia nigra region. Top five biological process terms for each gene list are indicated (see Table S11)