Genome-wide association study shows BCL11A associated with persistent fetal hemoglobin and amelioration of the phenotype of beta-thalassemia

Abstract

beta-Thalassemia and sickle cell disease both display a great deal of phenotypic heterogeneity, despite being generally thought of as simple Mendelian diseases. The reasons for this are not well understood, although the level of fetal hemoglobin (HbF) is one well characterized ameliorating factor in both of these conditions. To better understand the genetic basis of this heterogeneity, we carried out genome-wide scans with 362,129 common SNPs on 4,305 Sardinians to look for genetic linkage and association with HbF levels, as well as other red blood cell-related traits. Among major variants affecting HbF levels, SNP rs11886868 in the BCL11A gene was strongly associated with this trait (P < 10(-35)). The C allele frequency was significantly higher in Sardinian individuals with elevated HbF levels, detected by screening for beta-thalassemia, and patients with attenuated forms of beta-thalassemia vs. those with thalassemia major. We also show that the same BCL11A variant is strongly associated with HbF levels in a large cohort of sickle cell patients. These results indicate that BCL11A variants, by modulating HbF levels, act as an important ameliorating factor of the beta-thalassemia phenotype, and it is likely they could help ameliorate other hemoglobin disorders. We expect our findings will help to characterize the molecular mechanisms of fetal globin regulation and could eventually contribute to the development of new therapeutic approaches for beta-thalassemia and sickle cell anemia.

Fig. 1.

Genome-wide linkage and association scan results for HbF. (A) Result of genome-wide linkage scan. Variance component linkage analysis lod scores were calculated at positions 0.5 cM apart along each chromosome. Dotted line indicates the conventional lod >3 significance threshold. (B) Genome-wide association scan results using only 1,412 individuals genotyped with the 500K chip. For each marker that passed quality-control filters, -log₁₀ of the P value resulting from an association test that evaluates its additive effect on the phenotype is plotted. The position of selected genes (discussed in the text) is annotated. (C) Genome-wide association scan results after imputation of missing genotypes.

Fig. 2.

Association with HbF levels and linkage disequilibrium patterns in the region surrounding BCL11A. (A Upper) Summary of association between the SNPs and the proportion of HbF in each individual (-log₁₀ of the P value). The SNP showing strongest association (rs11886868) is highlighted. Other SNPs are colored according to their degree of disequilibrium with rs11886868, ranging from high (red) to intermediate (green) to low (blue). (A Lower) Alternative transcripts for BCL11A are indicated, with an arrow indicating transcript direction. (B) Summary of the patterns of disequilibrium in the region in Sardinia and in two of the HapMap populations (CEU and YRI). r² values are colored as in A and ref. . The gray bar marks the region of association and facilitates comparisons between images.

Fig. 3.

Association between rs11886868 genotypes and proportion of HbF. The box plot shows the distribution of the HbF levels within each genotype class on the followup sample.