The gene expression patterns as surrogate indices of pH in the brain

Abstract

Hydrogen ion (H⁺) is one of the most potent intrinsic neuromodulators in the brain in terms of concentration. Changes in H⁺ concentration, expressed as pH, are thought to be associated with various biological processes, such as gene expression, in the brain. Accumulating evidence suggests that decreased brain pH is a common feature of several neuropsychiatric disorders, including schizophrenia, bipolar disorder, autism spectrum disorder, and Alzheimer's disease. However, it remains unclear whether gene expression patterns can be used as surrogates for pH changes in the brain. In this study, we performed meta-analyses using publicly available gene expression datasets to profile the expression patterns of pH-associated genes, whose expression levels were correlated with brain pH, in human patients and mouse models of major central nervous system (CNS) diseases, as well as in mouse cell-type datasets. Comprehensive analysis of 281 human datasets from 11 CNS disorders revealed that gene expression associated with decreased pH was over-represented in disorders including schizophrenia, bipolar disorder, autism spectrum disorders, Alzheimer's disease, Huntington's disease, Parkinson's disease, and brain tumors. Expression patterns of pH-associated genes in mouse models of neurodegenerative disease showed a common time course trend toward lower pH over time. Furthermore, cell type analysis identified astrocytes as the cell type with the most acidity-related gene expression, consistent with previous experimental measurements showing a lower intracellular pH in astrocytes than in neurons. These results suggest that the expression pattern of pH-associated genes may be a surrogate for the state- and trait-related changes in pH in brain cells. Altered expression of pH-associated genes may serve as a novel molecular mechanism for a more complete understanding of the transdiagnostic pathophysiology of neuropsychiatric and neurodegenerative disorders.

Keywords: gene expression patterns; meta-analysis; neurodegenerative diseases; neuropsychiatric disorders; pH; postmortem brain.

Figure 1

Overview of the analysis. (A) Calculation of acid-gene and alkaline-gene indices of the queried datasets. pH-up/downregulated genes obtained from a previous study (60) were compared with each of the DEGs in the queried datasets. The overlap P-values were calculated for each comparison using the Running Fisher algorithm. The overlap P-values were transformed to alkaline-gene and acid-gene indices, respectively. (B) Individual subject datasets were used for correlation analysis with tissue pH. (C) The alkaline-gene and acid-gene indices were plotted in the two-dimensional (2-D) plane for each dataset in the analysis of grouped datasets.

Figure 2

Acid-gene index and alkaline-gene index correlate with actual tissue pH on an individual basis. Scatter plots showing correlations between acid-gene index and tissue pH (A) and between alkaline-gene index and tissue pH (B). Each plot represents a single subject. Regression line (solid line) and 95% confidence intervals (dashed line) are shown.

Figure 3

Expression patterns of pH-associated genes in the brain of neuropsychiatric and neurodegenerative disorders. (A) The two-dimensional plot results of individual datasets within each disease. Black plots indicate individual datasets and red plots indicate the mean of the datasets in the disease. Error bars are standard errors of the mean. (B) The two-dimensional plots of 11 diseases based on the means of the acid-gene and alkaline-gene indices within each disease. Error bars are standard errors of the mean. (C) Hierarchical clustering of 11 diseases based on acid-gene and alkaline-gene indices.

Figure 4

Time-dependent changes in acid-gene and alkaline-gene indices in mouse models of neurodegenerative disorders. (A–F) Pattern of changes in acid-gene and alkaline-gene indices in the cortex [CTX; (A–C)] and hippocampus [HIP; (D–F)] of AD mouse models with heterozygous mutation in APP and PSEN1 (A, D), homozygous mutation in APP and PSEN1 (B, E), and heterozygous mutation in MAPT (C, F) (GSE64389). (G–I) Patterns of changes in acid-gene and alkaline-gene indices in the spinal cord (SC) of an ALS mouse model with the SOD1 (G93A) mutation (GSE18597, GSE46298). (J) Patterns of changes in acid-gene and alkaline-gene indices in the striatum (STR) of an HD mouse model with the huntingtin (HTT) mutation (GSE64386). d, days old; wk, weeks old. (K, L) Scatter plots showing the correlation between time point and acid-gene index and alkaline-gene index of ten datasets. Time points were normalized within each dataset and expressed on a scale of 0–1. Regression line (solid line) and 95% confidence intervals (dashed line) are shown.

Figure 5

Cell type differences in acid-gene and alkaline-gene indices. Patterns of acid-gene and alkaline-gene indices for each cell type using datasets from GSE13379 (A), GSE21997 (B), and GSE30626 (C).