Transformative Opportunities for Single-Cell Proteomics

Abstract

Many pressing medical challenges, such as diagnosing disease, enhancing directed stem-cell differentiation, and classifying cancers, have long been hindered by limitations in our ability to quantify proteins in single cells. Mass spectrometry (MS) is poised to transcend these limitations by developing powerful methods to routinely quantify thousands of proteins and proteoforms across many thousands of single cells. We outline specific technological developments and ideas that can increase the sensitivity and throughput of single-cell MS by orders of magnitude and usher in this new age. These advances will transform medicine and ultimately contribute to understanding biological systems on an entirely new level.

Keywords: Simpson’s paradox; causal inference; counting noise; disease diagnosis; network inference; sample preparation; single-cell analysis; single-cell mass-spectrometry; systems biology; ultrasensitive proteomics.

Figure 1.

Differential cell-type sampling confounds the interpretation of population-average data. (a) Population-average levels of a protein may differ significantly across patients because the sampled tissues contain different fractions of the constituent cell types even when the cell-type-specific levels of the protein are identically distributed. Such differences may arise from biased sampling or from altered proportions of cell types between the two patients. (b) Similarly, increased levels of the protein in α cells may be obscured because of different representation of α and β cells in the analyzed samples.

Figure 2.

Simpson’s paradox confounds the interpretation of population-average protein and mRNA measurements. (a) For a particular gene, its protein levels across tissues can be poorly predicted by its mRNA levels, whereas the average protein levels can be well predicted by scaled mRNA levels. Thus mRNAs levels are unreliable surrogates for relative protein levels, and we need direct measurements of proteins. (b) Related manifestation of Simpson’s paradox indicates that the average levels of the ith and the jth proteins may appear positively correlated, even though they are inversely correlated within a cell type. Averaging across cells, even cell types sorted based on markers, will obscure the relationship between the ith and the jth proteins.

Figure 3.

Transformative opportunities for improving the quantification of single-cell proteomes. (a) Most bulk samples prepared for MS have volume of 10−100 μL.^,, Reducing the volume for sample preparation to 1 to 2 nL can significantly reduce protein losses from surface adsorption. (b) The sharper the separation peaks, the larger the fraction of the ions can be analyzed for a fixed sampling (injection) time. Sharper peaks can be achieved by reducing the bore of LC columns, using monolithic columns, PLOT columns, or capillary electrophoresis. (c) Typically elution peaks have a full width at the base of ∼60 s and about 10−15 s at midheight, whereas ions for MS2 are sampled for mere milliseconds. These settings are typical for bulk proteomics and result in sampling <1% of the ions delivered to the instruments. Thus increasing the sampling time 100× can substantially increase the ions analyzed by MS, the sensitivity, and the accuracy of quantification. While, the panel displays sampling during the apex of the peak, this cannot always be achieved for all ions. (d) Automated liquid handling and 96/384-well plates can increase the consistency of sample preparation, decrease volumes to the nanoliter range, and increase throughput. (e) Parallel accumulation and serial injection of ions can afford increased ion sampling without reducing throughput. (f) A larger number of barcodes will increase the number cellular proteomes quantified per run without reducing proteome coverage or ion sampling.