Single-Cell Multiomics: Multiple Measurements from Single Cells

Abstract

Single-cell sequencing provides information that is not confounded by genotypic or phenotypic heterogeneity of bulk samples. Sequencing of one molecular type (RNA, methylated DNA or open chromatin) in a single cell, furthermore, provides insights into the cell's phenotype and links to its genotype. Nevertheless, only by taking measurements of these phenotypes and genotypes from the same single cells can such inferences be made unambiguously. In this review, we survey the first experimental approaches that assay, in parallel, multiple molecular types from the same single cell, before considering the challenges and opportunities afforded by these and future technologies.

Keywords: epigenomics; genomics; multiomics; proteomics; single cell; transcriptomics.

Figure 1

Experimental Approaches for DNA- and RNA-Sequencing of the Same Single Cell. (A) Following complete cell lysis, one has the option to follow principles of genomic DNA (gDNA)–mRNA sequencing (DR-seq) or genome and transcriptome sequencing (G&T-seq). (i) In DR-seq, lysis of the cell is directly followed by reverse transcription of RNA to synthesise single-stranded cDNA incorporating the 5′ T7 promoter. The gDNA and single-stranded cDNA are then amplified together in the same reaction by a quasi-linear approach, using principles of the multiple annealing and looping-based amplification cycles (MALBAC) protocol for single-cell WGA, after which the reaction is split. gDNA in one half of the reaction is further amplified by PCR, leading to co-amplification of contaminating cDNA, while in the other reaction cDNA-specific second-strand synthesis is followed by in vitro transcription (IVT) for further amplification of the mRNA. (ii) In G&T-seq, lysis of the cell is followed by physical separation of polyadenylated mRNA from DNA using oligo-dT-coated magnetic beads either manually or on a robotic liquid handling platform. Following separation, the mRNA is converted on the bead to cDNA and further amplified using a modified Smart-seq2 approach. The DNA of the same cell is precipitated and prepared for genome sequencing following a WGA method of choice or for methylome sequencing following bisulphite conversion and amplification. Alternatively, (B) following lysis of the cell membrane but not the nuclear membrane, the nucleus can be physically isolated from the cytoplasmic lysate of the cell. The latter contains the cytoplasmic mRNA molecules and can be used for the preparation of a RNA-seq library. In parallel, the nucleus containing the genomic DNA can be lysed and used for the preparation of genome sequencing or (reduced representation) DNA methylation sequencing libraries, as in single-cell methylome and transcriptome sequencing (scMT-seq) and single-cell genome, DNA methylome and transcriptome sequencing (scTrio-seq). (C) Comparison of pros and cons of current single-cell multiomics methods. scBS, single-cell bisulphite sequencing; WGA, whole-genome amplification.

Figure 2

Integrative Genome and Transcriptome Sequence Analyses of Single Cells. Single-cell genotype–phenotype correlations are enabled by sequencing its DNA and RNA, including (A) investigating gene expression dosage effects resulting from DNA copy number alterations; (B) detecting the expression of fusion transcripts from DNA structural variation, permitting base-level reconstruction of both fusion transcript and the causative genomic lesion; (C) studying the expression of coding genomic variants – including allele-specific expression or the expression of an acquired single nucleotide variant – or observing RNA editing; and (D) examining the expression level of transcripts from genes mutated in their coding or noncoding genomic parts (e.g., a gene regulatory region), and thus determining the functional consequences of acquired genetic variation on the cell. We note that limitations of transcriptional profiling for inferring genomic variation include that (i) only genomic variants within or encompassing expressed genes in the cell can be represented in the single cell's RNA-seq data – that is, nontranscribed genomic variation may not be inferred from the cell's RNA-seq data alone; (ii) artefacts resulting from whole-transcriptome amplification (and whole-genome amplification) should be taken into account when inferring genomic variation; and (iii) transcriptional profiles can be less predictive of genomic variation when read coverage is limited.

Figure 3

Cell Lineage Trees Depict the Genealogical Record of Acquired DNA Mutations Overlaid with the Transcriptomic Phenotypes of the Same Cells. Cancers arise due to the acquisition of driver mutations (red stars) in a single cell, resulting in a clonal expansion of that cell (blue droplet). During this expansion, more driver mutations can accumulate giving rise to tumour subclones (green, light blue and purple droplets) with common and unique DNA mutations. Single-cell multiomics on a heterogeneous population exposes both the acquired DNA mutations per cell by DNA-seq analyses and the transcriptomic cell type and state of each cell by dimensionality reduction techniques on RNA-sequences of the same cells. The single-cell DNA mutation matrix can reconstruct the cell lineage tree, which can then be overlaid with transcriptomic states of the same cells, disclosing the gene expression of profiles of, for example, tumour subclones.

Figure 4

Integrative Epigenome and Transcriptome Sequence Analyses of Single Cells. (A) Gene regulatory elements, in particular, can show homogeneous (Regulatory Feature 1) or heterogeneous (Regulatory Feature 2) methylation states in populations of cells. (B and C) The variance in DNA methylation across cells at a particular genomic locus may be coupled or uncoupled to variance in expression of nearby gene(s) across the cells. Parallel single-cell analysis of DNA methylation and gene expression allows the correlation of expression measurements with methylation at various potential regulatory sites. (D) From single-cell DNA-bisulphite sequences, it is also possible to compute DNA copy number profiles (e.g., scTrio-seq), allowing investigation of correlations between DNA numerical alterations, DNA methylation states and transcriptomic phenotypes across single cells in a population. scTrio-seq, single-cell genome, DNA methylome and transcriptome sequencing.

Figure 5

Experimental Approaches for Integrative Transcript and Protein Analyses of Single Cells. (A) The lysate of a whole cell can be split into two separate reactions: one for measuring abundance of specific proteins by quantitative PCR (qPCR)-based proximity extension assay (PEA) and one for quantifying transcripts of specific genes by qPCR on cDNA. (B) Cells are fixed and permeabilised, and specific transcripts and proteins are marked for mass cytometry quantification. To this end, transcripts are first hybridised with proximity ligation assay for RNA (PLAYR) probes, and following ligation of the insert (blue) and backbone (orange) probes, this circle is amplified by rolling circle amplification and the multiple insert sequences per transcript are hybridised with mass cytometry-compatible probes. Specific proteins are quantified using antibodies conjugated to distinct heavy metals enabling mass cytometry measurement. Both methods then enable the correlation of protein and transcript abundance from the same single cells. Here, a positive correlation is shown, although it is expected that this correlation would vary depending on the dynamics of transcript and protein expression.

Figure 6

Key Figure: Spatial Omni-Seq of Single Cells Using novel high-accuracy genome sequencing approaches for single cells, highly reliable cell lineage trees can be inferred that capture the history of acquired genetic variants in the cells. These could also serve as cell clonal marks to study cell dynamics within the population. Together with epigenomic, transcriptomic and proteomic measurements of the same cells, the phenotype of each cell in the tree can be assessed to exquisite detail. While beyond the scope of current technologies, the development of tools that allow retention of the spatial ‘addresses’ of the analysed single cells in the original tissues, questions about cell–cell interactions and influences of microenvironment on the cellular state can be determined, and cell atlases can be annotated with spatial and phylogenetic information of the populating cells. In addition, technologies that acquire metabolomics and lipidomics information of the cell are maturing .