Genome dynamics of the human embryonic kidney 293 lineage in response to cell biology manipulations

Abstract

The HEK293 human cell lineage is widely used in cell biology and biotechnology. Here we use whole-genome resequencing of six 293 cell lines to study the dynamics of this aneuploid genome in response to the manipulations used to generate common 293 cell derivatives, such as transformation and stable clone generation (293T); suspension growth adaptation (293S); and cytotoxic lectin selection (293SG). Remarkably, we observe that copy number alteration detection could identify the genomic region that enabled cell survival under selective conditions (i.c. ricin selection). Furthermore, we present methods to detect human/vector genome breakpoints and a user-friendly visualization tool for the 293 genome data. We also establish that the genome structure composition is in steady state for most of these cell lines when standard cell culturing conditions are used. This resource enables novel and more informed studies with 293 cells, and we will distribute the sequenced cell lines to this effect.

Figure 1. HEK293 cell line expression profiling.

(a) Schematic overview of the studied 293 cell lines and their derivation history. FRT plasmid: pFRT/lacZeo; TetR plasmid: pcDNA6/TR; ecotropic receptor plasmid: pM5neo-mEcoR; MAPPIT reporter plasmid: pXP2d2-rPAP1-luci. (b) Heatmap of the 136 genes differentially expressed in every cell line when compared with the 293 line. Colour-coded values represent the log₂ expression values after summarization, normalization and averaging over three biological replicates per cell line. Genes (rows) and cell lines (columns) were clustered hierarchically according to similarity between expression levels. See also Supplementary Figs 6–8.

Figure 2. Plasmid insertion site detection.

(a) The Adenovirus 5 (Ad5) genome fragment is located in an 332.5-kb region on chr19 (48,221,000–48,553,500). This Ad5 sequence had been inserted and amplified in the 293 cell and the insertion and amplification have been maintained in the PSG4 gene of the whole 293 lineage. The Y-axis represents the genomic copy number. The dot plot in the right panel shows individual paired-reads aligning on the Ad5 genome (x axis) and chr19 (y axis). (b) Detection and confirmation of plasmid insertion sites in the 293FTM cell line. Four plasmids have been inserted into this cell line. Note the 11 additional bases inserted upstream of the pcDNA/TR plasmid (right panel), as well as the likely tandem insertion of pXP2d2-rPAP1-luci and pM5Neo-mEcoR plasmids on chr9 (bottom panel). Notably, we were unable to validate the plasmid–plasmid breakpoint of pXP2d2-rPAP1-luci and pM5Neo-mEcoR, probably due to the presence of stretches of homologous sequence in both plasmid sequences. Black sequence: consensus of several trace files, green or red sequences: derived from the representative trace file below the sequence. See also Supplementary File 4.

Figure 3. Notable amplifications and deletions in 293 cell lines.

(a) On the q-arm of chromosome 8, the 293S line shows an amplification of a 1.6-Mb region containing the MYC locus. The 293SG and 293SGGD lines seem to have partially lost this rearrangement. (b) Expression validation by quantitative real-time PCR for MYC and three microRNAs from the polycistronic MIR17HG locus (mir17, mir20a and mir92a, respectively). Expression levels of these microRNAs are markedly higher in 293T than in any of the other 293 lines (fold change between 2.5 and 8.8). Values are represented as normalized relative quantities (NRQ)±s.e.m. (n=3). Significantly different NRQs in comparison with the 293 line are indicated as *P value<0.05, **P value<0.01, ***P value<0.001 and were analysed using a one-way analysis of variance with a Tukey HSD post hoc test. (c) Similarly, the MIR17HG gene is located in an extended amplified region on chr13 in the 293T cell line, where copy numbers reach up to 8. (d) Part of the LRP1B gene—comprising exons 3–7 (300 kb) or 4–7 (400 kb)—has been deleted in the 293FTM and 293T line. Copy numbers downstream of this region are also reduced in 293FTM. See also Supplementary Fig. 5 for another notable deletion (including fumarate hydratase, found in all investigated 293 cell lines). In panels a, c and d, the Y-axis represents the genomic copy number.

Figure 4. Effect of freezing and passaging on 293T genome stability on SNP content, whole-genome CNV and gene copy number.

(a) PCA (principle component analysis)-correlated SNP clustering reveals a strong correlation between the different 293T sequencing samples. Notably, this analysis also substantiates the common origin of the S lineage cell lines. (b) Comparison of the genome-wide 2-kb CNV content of the 293T samples among each other and with the 293 line again confirms the high consistency between 293T samples. The darker the shade of blue in the chart, the higher the correlation. (c) Comparison of gene copy number between the various 293T samples and 293. While the copy number of genes in the 293 line considerably deviates from the 293T gene copy numbers, the pattern of gene copy number of the newly sequenced 293T samples is very similar to the sequenced line of lower passage number.

Figure 5. Deletion of MGAT1 in 293SG and 293SGGD.

(a) Selection for 293S cells without the GnTI activity of MGAT1 using EMS mutagenesis and the ricin toxin induced a 800-kb deletion at the end of chr5. This illustrates that the driving force for mutations in these cell lines are chromosomal rearrangements rather than point mutations. (b) Simplified scheme of early N-glycan processing of glycoproteins in the Golgi apparatus. Loss of MGAT1, responsible for GnTI activity, ensures that N-glycans in the Golgi are committed to the oligomannose type. In panel a, the Y-axis represents the genomic copy number.

Figure 6. Visualization of SNPs and indels in the 293 Variant Viewer.

(a) Snapshot of the 293 Variant Viewer for the PIGZ gene. The upper region gives an overview of the gene with its variations in each genome, colour-coded by variation type and cell line. Triangles indicate the presence of the variant in a particular genome. The lower part of the browser allows detailed inspection of the sequence and comparison with the human reference genome. A link to the same region in IGV is provided as well. (b) Overview of SNP calling and realignment data tracks in the IGV genome browser for the same gene as in a. The two SNP calling algorithm tracks (CG and RTG) are shown with homozygous SNPs (red bar) and heterozygous SNPs (red/blue). In the CG tracks, no-calls are also shown in light red. In regions where the realignment coverage is zero, the sequence is the same as the human reference sequence. The TRC shRNA track allows the detection of SNPs in target regions of the shRNAs from the TRC2 collection (Broad Institute and Sigma). Mousing-over the different tracks provides users with extra information about specific features, such as mapping quality, base type count and phred scores.