ProteinSeq: high-performance proteomic analyses by proximity ligation and next generation sequencing

Abstract

Despite intense interest, methods that provide enhanced sensitivity and specificity in parallel measurements of candidate protein biomarkers in numerous samples have been lacking. We present herein a multiplex proximity ligation assay with readout via realtime PCR or DNA sequencing (ProteinSeq). We demonstrate improved sensitivity over conventional sandwich assays for simultaneous analysis of sets of 35 proteins in 5 µl of blood plasma. Importantly, we observe a minimal tendency to increased background with multiplexing, compared to a sandwich assay, suggesting that higher levels of multiplexing are possible. We used ProteinSeq to analyze proteins in plasma samples from cardiovascular disease (CVD) patient cohorts and matched controls. Three proteins, namely P-selectin, Cystatin-B and Kallikrein-6, were identified as putative diagnostic biomarkers for CVD. The latter two have not been previously reported in the literature and their potential roles must be validated in larger patient cohorts. We conclude that ProteinSeq is promising for screening large numbers of proteins and samples while the technology can provide a much-needed platform for validation of diagnostic markers in biobank samples and in clinical use.

Figure 1. Principle of multiplex SP-PLA.

Pools of microparticles, each coated with one of the antibodies, are mixed with the sample (I). After washes, pairs of PLA probes directed against each of the proteins are incubated with the microparticles (II), followed by washes and ligation of the attached DNA strands (III). Ligated molecules are first amplified with primers directed against sequences present on all ligated DNA molecules (IV). This universal pre-amplification is then followed by preparation of the reporter strands for next generation sequencing, or for qPCR (V). Subsequently the abundance of each protein is calculated and multivariable classification of cases and controls is performed (VI).

Figure 2. a) Cross-reactivity table.

The figure reflects the signals obtained when each protein in the panel was incubated individually with all PLA probes of the panel. Correct signals are indicated along the diagonal. The colors indicate the protein concentration required to elicit detection signals significantly exceeding the background. Recombinant proteins at known concentrations were used for the purpose of this experiment. b) Change in background signals as a result of multiplexing. The background signals were measured for every antibody when incubated individually or in combination with all other antibodies of the panel for multiplex SP-PLA and sandwich immunoassays. The y-axis shows the increase of background when moving from individual to multiplex reactions. c) Limit of detection comparison between multiplex SP-PLA and sandwich immunoassay. The log₁₀ fold change in LOD between multiplex SP-PLA and sandwich immunoassay. d) Correlation between results of sequencing and qPCR. Correlation between two replicated measurements of the same blood sample by qPCR (upper left), by sequencing (lower right), and between measurement by realtime PCR and sequencing (upper right). The axes represent numbers of starting DNA amplicons for PCR measurements and normalized numbers of reads for sequencing.

Figure 3. a) Supervised multivariate classification.

Typical results of a multivariate classifier design using 80% of the CVD samples. The cyan (control) and magenta (patient) open circles indicate the positions of the training examples in the compressed three-dimensional meta-protein space, created by the supervised procedure to classify the samples (see methods). The blue (controls) and red (patients) filled circles indicate the positions of the external test examples used to evaluate the particular classifier designed. These examples were assigned to the most common class among the three closest training examples (3-nearest neighbour classification). b) Supervised univariate analysis of individual proteins. Results obtained from the CVD samples by a supervised univariate analysis of the individual proteins with respect to their discriminatory power when they were used individually for 3-nearest neighbour classification. Each protein is displayed in terms of estimates of the probabilities of false alarm and miss that one would obtain if an optimal cut-off level for that particular protein was used alone to distinguish patients and controls.