Clonal hematopoiesis in sickle cell disease

Abstract

BACKGROUNDCurative gene therapies for sickle cell disease (SCD) are currently undergoing clinical evaluation. The occurrence of myeloid malignancies in these trials has prompted safety concerns. Individuals with SCD are predisposed to myeloid malignancies, but the underlying causes remain undefined. Clonal hematopoiesis (CH) is a premalignant condition that also confers significant predisposition to myeloid cancers. While it has been speculated that CH may play a role in SCD-associated cancer predisposition, limited data addressing this issue have been reported.METHODSHere, we leveraged 74,190 whole-genome sequences to robustly study CH in SCD. Somatic mutation calling methods were used to assess CH in all samples and comparisons between individuals with and without SCD were performed.RESULTSWhile we had sufficient power to detect a greater than 2-fold increased rate of CH, we found no detectable variation in rate or clone properties between individuals affected by SCD and controls. The rate of CH in individuals with SCD was unaltered by hydroxyurea use.CONCLUSIONSWe did not observe an increased risk for acquiring detectable CH in SCD, at least as measured by whole-genome sequencing. These results should help guide ongoing efforts and further studies that seek to better define the risk factors underlying myeloid malignancy predisposition in SCD and help ensure that curative therapies can be more safely applied.FUNDINGNew York Stem Cell Foundation and the NIH.

Trial registration: ClinicalTrials.gov NCT00492531.

Keywords: Hematology; Leukemias.

Figure 1. Prevalence of CH is similar in unaffected and SCD populations.

(A) A generalized additive model was used here to fit rates of CH within WGS data from a total of 71,100 individuals unaffected by SCD and 3,090 individuals affected by SCD, which indicates no significantly increased prevalence of CH within individuals affected by SCD (OR = 1.30, P = 0.20). (B) Generalized additive model as in A was used to fit rates of CH using a genetically matched cohort without SCD. The matched cohort was created by selecting the 10 most similar individuals by the first 10 PCs for each individual in the SCD cohort. Resampling of individuals without SCD was permitted. SCD samples without sufficient matches were excluded. (C) Genes ranked by variant load across all individuals separated by SCD status into unaffected (blue) and affected (red). (D) Type of genetic change ranked by prevalence in all individuals separated by SCD status into unaffected (blue) and affected (red).

Figure 2. Mutation signatures do not vary in SCD and hydroxyurea (HU) treatment does not impact the rate of CH development.

Percentages of total single-base substitutions made up by each possible 96 substitution and trinucleotide context pairs per individual (error is SD across individuals). Signatures are separated into (A) individuals without SCD and (B) individuals with SCD (data represent mean ± SD). (C) A generalized additive model is used here to fit rates of CH within WGS from individuals with SCD separated into never-HU-treated or HU-treated groups. There is no significant difference in the rate of CH in either the HU-treated or untreated groups adjusted for age, age², sex, study, and the first 10 principal components (OR = 0.58, P = 0.23). (D) Genes ranked by variant load across all individuals with SCD separated by HU treatment status into untreated (green) and (E) treated (purple).