Single-cell somatic copy number variants in brain using different amplification methods and reference genomes

Abstract

The presence of somatic mutations, including copy number variants (CNVs), in the brain is well recognized. Comprehensive study requires single-cell whole genome amplification, with several methods available, prior to sequencing. We compared PicoPLEX with two recent adaptations of multiple displacement amplification (MDA): primary template-directed amplification (PTA) and droplet MDA, across 93 human brain cortical nuclei. We demonstrated different properties for each, with PTA providing the broadest amplification, PicoPLEX the most even, and distinct chimeric profiles. Furthermore, we performed CNV calling on two brains with multiple system atrophy and one control brain using different reference genomes. We found that 38% of brain cells have at least one Mb-scale CNV, with some supported by bulk sequencing or single-cells from other brain regions. Our study highlights the importance of selecting whole genome amplification method and reference genome for CNV calling, while supporting the existence of somatic CNVs in healthy and diseased human brain.

Fig. 1. Experimental overview and scWGS preliminary analysis from human post-mortem brain samples.

a Methodology overview created with BioRender.com (agreement KB25LPBTEK). b Mean depth of coverage for each WGA method. PicoPLEX vs PTA ns (adj. p>0.99), PicoPLEX vs dMDA ** (adj. p=0.008) and PTA vs dMDA * (adj. p=0.04). Kruskal-Wallis test with Dunn’s multiple comparisons correction. c Bases potentially covered if sequenced deeper. P value for all pairwise comparisons <0.001. Brown-Forsythe and Welch ANOVA tests with Dunnett’s T3 multiple comparisons correction. d Median Absolute Deviation (MAD) scores. P value for all pairwise comparisons <0.001 (adj. p<0.001). Kruskal-Wallis test with Dunn’s multiple comparisons correction. For b-d PicoPLEX (n=33), PTA (n=21), dMDA (n=39); Mean ± SD shown.

Fig. 2. scWGA method comparison from brain analyzed by Ginkgo at 500 kb bin size.

a Visual view of copy number profiles of single-nuclei amplified by PicoPLEX, PTA and dMDA from the control (top) and MSA1 (bottom) brains. b Lorenz curves. The black lines with slope 1 represent perfect coverage uniformity. Increasing divergence of the curve of each cell from this indicates lower overage uniformity. c Effect of GC content in scWGA. For b-c PicoPLEX n=33, PTA n=21, dMDA n=40.

Figure 3.. Comparison of discordant read pairs of brain nuclei amplified with each method.

a Outward pairs. Differences analyzed using Brown-Forsythe and Welch ANOVA test with Dunnett’s T2 multiple comparisons test. PicoPLEX vs PTA *** (adj. p<0.001), PicoPLEX vs dMDA *** (adj. p<0.001), PTA vs dMDA * (adj. p=0.02). b Pairs on different chromosomes indicating translocations. Differences analyzed by Kruskal-Wallis test with Dunn’s multiple comparisons test. PicoPLEX vs PTA ns (adj. p>0.99), PicoPLEX vs dMDA ** (adj. p=0.002), PTA vs dMDA *** (adj. p=0.02). c Pairs in other orientations. Differences analyzed by Kruskal-Wallis test with Dunn’s multiple comparisons test. PicoPLEX vs PTA *** (adj. p<0.001), PicoPLEX vs dMDA *** (adj. p<0.001), PTA vs dMDA ns (adj. p=0.18. a-c PicoPLEX (n=33), PTA (n=10). dMDA (n=38).

Fig. 4:. Samplot views demonstrating tentative support for single cell CNV calls in bulk short read WGS.

These show all read pairs in the designated regions in cingulate cortex, with pairs supporting a particular type of CNV / SV indicated according to the scheme at the top, and those supporting each single-cell CNV arrowed. The left and right panel of each plot show the regions around the reported proximal and distal breakpoint respectively, which is at the middle of each panel, with the chromosomal numbers and positions on the x axis below. The y axis indicates the calculated insert size for the read pairs of interest on the left, and the local coverage on the right. a-c MSA1 and d MSA2. a duplication 2.47 Mb (cell A24), b deletion 1.58 Mb (cell A24), c deletion 9.54 Mb (cell L21), d duplication 3.45 Mb (cell A82). A read pair identical to c was found in the cingulate white matter, suggesting mosaicism across both brain regions.

Fig. 5.. Evaluation of T2T-CHM13 specific CNV calls using different WGA methods (PTA and PicoPLEX) and mapping quality filtering.

a no mapping quality filter, b mapping quality 1, c mapping quality 10.