Multilineage hematopoietic reconstitution without clonal selection in ADA-SCID patients treated with stem cell gene therapy

Abstract

Gene transfer into HSCs is an effective treatment for SCID, although potentially limited by the risk of insertional mutagenesis. We performed a genome-wide analysis of retroviral vector integrations in genetically corrected HSCs and their multilineage progeny before and up to 47 months after transplantation into 5 patients with adenosine deaminase-deficient SCID. Gene-dense regions, promoters, and transcriptionally active genes were preferred retroviral integrations sites (RISs) both in preinfusion transduced CD34(+) cells and in vivo after gene therapy. The occurrence of insertion sites proximal to protooncogenes or genes controlling cell growth and self renewal, including LMO2, was not associated with clonal selection or expansion in vivo. Clonal analysis of long-term repopulating cell progeny in vivo revealed highly polyclonal T cell populations and shared RISs among multiple lineages, demonstrating the engraftment of multipotent HSCs. These data have important implications for the biology of retroviral vectors, the dynamics of genetically modified HSCs, and the safety of gene therapy.

Figure 1. RISs favor TSSs and gene-dense regions.

(A) Distribution of RISs within a 30-kb window around TSSs. Each bar corresponds to the frequency of integration sites retrieved by LM-PCR technique in pretransplant CD34⁺ cells (in vitro, n = 212) or posttransplant hematopoietic cells (in vivo, n = 251) at 5-kb intervals from the TSS of the nearest gene. (B) Correlation between RISs and gene density in the human genome within a 1-Mb window. The number of RefSeq genes was determined in a region of 500 kb on either side of the RIS for both in vitro and in vivo samples. The data are compared with the average gene density of the human genome.

Figure 2. RIS hot spots in patients with ADA-SCID without clonal expansion or overexpression.

(A) Schematic representation of RISs in the most frequently hit genes. Additional RISs outside these intervals in the proximity of CCND2 and BCL2 are also indicated. In vitro RISs are shown as green arrows and in vivo RISs as blue arrows; the direction of the arrow denotes orientation of the retroviral vector. The upper or lower position of the arrow refers to an LTR-genomic junction sequence mapping to the positive (above line) or negative (below line) chromosomal strand, respectively. Genes are depicted in red, with filled boxes and red arrows indicating exons and TSSs, respectively. RISs in the LMO2 locus were detected in T cells (Pt1, S1_049, 27 months after GT; Pt3, S3_042, 18 months after GT; Pt4, S4_048, 26 months after GT), granulocytes (Pt5, S5_144 and S5_163, 6 and 12 months after GT, respectively), and in Pt5 preinfusion CD34⁺ cells (S5_P048). (B) Quantification of the LMO2-containing clones within the total T cell population. The frequency of insertions was measured by sequence-specific real-time PCR in purified CD3⁺ T cells isolated at different time points after GT. Dotted lines show the frequencies of nonrecurrent (neutral) RISs retrieved from Pt3 as a control of physiologic clonal fluctuations. (C) Expression of LMO2 in peripheral blood T cells and granulocytes. Total RNA was isolated from the indicated cell subsets of GT-treated patients, patients with ADA-SCID undergoing polyethylene glycol-modified bovine ADA treatment (UT, not treated with GT), or age-matched healthy controls (ND). LMO2 gene expression was measured by quantitative RT-PCR using the standard curve of a reference sample and normalized for the expression of the housekeeping gene HPRT.

Figure 3. Gene expression profiling of genes hit by retroviral vectors.

(A) Correlation between insertion sites and gene expression profile of CD34⁺ cells at the time of transduction. The expression level profile of all probesets present on an Affymetrix HG-U133A microarray was determined in CD34⁺ cells and compared with the expression profile of probesets corresponding to targeted genes (inside or <10 kb upstream) by retroviral vector insertion in preinfusion CD34⁺ cells (in vitro) and cells after GT (in vivo), respectively, or in both samples. Bars show the percentage distribution of expression levels classified as present and absent by Affymetrix MAS 5.0 software. The present probesets were categorized in 3 subgroups according to 2 cutoffs identified by first (0–25) and third (75–100) quartiles of expression levels. (B) Correlation between insertion sites and genes expressed in T cells. Comparison of expression level of all probesets versus probesets of genes hit (inside or <10 kb upstream) by retroviral vector insertion and found in T cells of patients with ADA-SCID after GT. Analysis was performed as in A.

Figure 4. Functional clustering of targeted genes by GO.

The probesets of genes targeted (inside and within 30 kb) by retroviral insertion were classified in accordance with GO criteria. Each bar refers to the percentage of all targeted probesets falling within a specific gene category. The difference between groups was tested by both Fisher exact test and EASE score, corrected for multiple comparisons with the Bonferroni-Holm correction. The only difference was revealed for in vivo sample versus expected in “protein binding” category (*P = 0.022, Fisher exact test; P = 0.034, EASE score). No major differences were observed in RIS distribution and hierarchical clustering between lymphoid and myeloid cells.

Figure 5. Vector clonal composition in distinct hematopoietic lineages after GT.

(A) Clonal analysis by LM-PCR and I-PCR in purified CD3⁺ T cells and CD15⁺ granulocytes from 5 patients with ADA-SCID treated with GT. Nested PCR products were analyzed by electrophoresis on acrilamide gels with a 100-bp ladder as a marker (M). In Pt2, who received a low CD34⁺ cell dose and displayed poor myeloid engraftment (<0.1%), no RISs could be isolated from multiple samples of granulocytes, thus confirming the lack of potential contamination from T cells. The following representative time points are shown for LM-PCR in T cells: Pt1, 20 months; Pt2, 39 months; Pt3, 26 months; Pt4, 22 months; Pt5, 9 months. The following representative time points are shown for LM-PCR in granulocytes: Pt1, 47 months; Pt3, 33 months; Pt4, 22 months; Pt5, 12 months. The following representative time points are shown for I-PCR in granulocytes: Pt1, 5 months, Pt3, 26 months; Pt4, 4 months; Pt5, 3 months. (B) Evidence for common integrants identified in different cell subpopulations during long-term follow-up. Each RIS from Pt1, Pt2, Pt3, or Pt4 is identified by a unique number. The circles indicate the presence of a specific RIS detected after 6 months of follow-up at 2 or more different time points by random cloning in the indicated population. Numbers in red text refer to the number of independent RISs retrieved by random cloning for the time points in which ≥30 colonies were analyzed. The random cloning analysis in Pt1 (47 months) and Pt3 (33 months) T cells was not carried out because the material was not available. In Pt5, 1 common integration site was detected in T cells at 6 and 8 months after GT. The presence of common integrants was confirmed in selected cases by sequence-specific PCR, which allowed us to unequivocally track integrants in different lineages.