Deconvolution of Human Urine across the Transcriptome and Metabolome

Abstract

Background: Early detection of the cell type changes underlying several genitourinary tract diseases largely remains an unmet clinical need, where existing assays, if available, lack the cellular resolution afforded by an invasive biopsy. While messenger RNA in urine could reflect the dynamic signal that facilitates early detection, current measurements primarily detect single genes and thus do not reflect the entire transcriptome and the underlying contributions of cell type-specific RNA.

Methods: We isolated and sequenced the cell-free RNA (cfRNA) and sediment RNA from human urine samples (n = 6 healthy controls and n = 12 kidney stone patients) and measured the urine metabolome. We analyzed the resulting urine transcriptomes by deconvolving the noninvasively measurable cell type contributions and comparing to plasma cfRNA and the measured urine metabolome.

Results: Urine transcriptome cell type deconvolution primarily yielded relative fractional contributions from genitourinary tract cell types in addition to cell types from high-turnover solid tissues beyond the genitourinary tract. Comparison to plasma cfRNA yielded enrichment of metabolic pathways and a distinct cell type spectrum. Integration of urine transcriptomic and metabolomic measurements yielded enrichment for metabolic pathways involved in amino acid metabolism and overlapped with metabolic subsystems associated with proximal tubule function.

Conclusions: Noninvasive whole transcriptome measurements of human urine cfRNA and sediment RNA reflects signal from hard-to-biopsy tissues exhibiting low representation in blood plasma cfRNA liquid biopsy at cell type resolution and are enriched in signal from metabolic pathways measurable in the urine metabolome.

Fig. 1.

Cell types of origin across the urine sediment and cell-free transcriptomes. All P values were determined by a two-sided Mann–Whitney U-test unless otherwise specified. *P < 0.05, **P < 0.01, ***P < 0.001. (A), Schematic overview of study design; (B), Mean fractional contributions of cell-type-specific RNA of the urinary sediment transcriptome in healthy controls (n = 4); (C), Box plot of intestinal cell type marker gene expression across healthy control and stone patients in urine sediment RNA (n = 17) and cfRNA (n = 13) (MUC2, P = 6.89 * 10⁻⁴; ANPEP, P = 2.25 * 10⁻³); (D), Signature scores of cell types across healthy control and stone patients in urine sediment RNA (n = 17) and cfRNA (n = 13) (P = 0.867, bladder urothelial cell; P = 0.770, proximal tubule) and male patients only (n = 13 sediment RNA and n = 11 cfRNA) (P = 3.77 * 10⁻³, luminal prostate epithelial cell); (E), Bladder urothelial cell signature score in urine sediment RNA of bladder cancer patients and control patients using data from Sin et al. (P = 0.0219, one-sided Mann–Whitney U-test; n = 10 controls and n = 13 bladder cancer patients). Components of Fig. 1A were created with BioRender.com. R. LaMantia provided permission for use of the rainbow cell spectrum in Fig 1A.

Fig. 2.

Volcano plot of the deconvolved fractions of cell type specific RNA between the urine transcriptomes and plasma cfRNA. Positive log-fold change indicates cell type enrichment in urine cfRNA or urine sediment RNA; negative log-fold change, plasma cfRNA.

Fig. 3.

Cell type repertoires across the urine cell-free and sediment transcriptomes are distinct from the plasma cf-transcriptome. (A), Complete linkage cluster map of relative deconvolved fractions of cell-type specific RNA across all samples (n = 13, 17, 18 urine cfRNA, urine sediment RNA, plasma cfRNA respectively); (B), Complete linkage cluster map of pairwise Pearson correlation of deconvolved cell type fractions across all samples (n = 13, 17, 18 urine cfRNA, urine sediment RNA, plasma cfRNA respectively); (C), Kyoto Encyclopedia of Genes and Genomes pathway enrichment on genes upregulated in the urine sediment and cf-transcriptomes relative to the plasma cf-transcriptome, all from healthy controls.

Fig. 4.

Pathway and cell type level integration of the urine transcriptome and metabolome. (A), Tree map of the chemical classes of molecules measured by hydrophilic interaction liquid chromatography-MS/MS with threshold greater than or equal to 3 metabolites. 1-hydroxy-2-unsubstituted benzenoids (HUB); 5′-deoxy-5′-thionucleosides (5D5T); alpha hydroxy acids and derivatives (AHAD); benzene and substituted derivatives (BSD); benzene-sulfonic acid and derivatives (BSAD); indolyl carboxylic acids and derivatives (ICAD); (B), Kyoto Encyclopedia of Genes and Genomes pathways jointly enriched in urine sediment RNA or urine cfRNA relative to plasma cfRNA and untargeted metabolomics data; (C), Sankey plot linking overlapping metabolic pathways from untargeted metabolomics and measured proximal tubule cell type specific genes. A given metabolic subsystem (middle column) was considered if there were at least measured two cell type specific genes by transcriptomics or three metabolites by untargeted metabolomics.