Improving coeliac disease risk prediction by testing non-HLA variants additional to HLA variants

Abstract

BackgroundThe majority of coeliac disease (CD) patients are not being properly diagnosed and therefore remain untreated, leading to a greater risk of developing CD-associated complications. The major genetic risk heterodimer, HLA-DQ2 and DQ8, is already used clinically to help exclude disease. However, approximately 40% of the population carry these alleles and the majority never develop CD.ObjectiveWe explored whether CD risk prediction can be improved by adding non-HLA-susceptible variants to common HLA testing.DesignWe developed an average weighted genetic risk score with 10, 26 and 57 single nucleotide polymorphisms (SNP) in 2675 cases and 2815 controls and assessed the improvement in risk prediction provided by the non-HLA SNP. Moreover, we assessed the transferability of the genetic risk model with 26 non-HLA variants to a nested case–control population (n=1709) and a prospective cohort (n=1245) and then tested how well this model predicted CD outcome for 985 independent individuals.ResultsAdding 57 non-HLA variants to HLA testing showed a statistically significant improvement compared to scores from models based on HLA only, HLA plus 10 SNP and HLA plus 26 SNP. With 57 non-HLA variants, the area under the receiver operator characteristic curve reached 0.854 compared to 0.823 for HLA only, and 11.1% of individuals were reclassified to a more accurate risk group. We show that the risk model with HLA plus 26 SNP is useful in independent populations.ConclusionsPredicting risk with 57 additional non-HLA variants improved the identification of potential CD patients. This demonstrates a possible role for combined HLA and non-HLA genetic testing in diagnostic work for CD.

MultiBLUP: improved SNP-based prediction for complex traits

“…We again find Adaptive MultiBLUP to be the best performing method (Table 2; Supplemental Table 5). For celiac disease, we additionally consider a linear prediction model constructed from 77 susceptibility SNPs: 6 SNPs tagging four human leukocyte antigen (HLA) haplotypes (Monsuur et al 2008) and 71 SNPs based on Romanos et al (2014). For this model, the average correlation is 0.40 and the average AUC is 0.78 (see Supplemental Table 6), demonstrating here that it is better to incorporate genome-wide SNP data than use only top associated SNPs.…”

Genetic and epigenetic aspects of celiac disease

“…Két, a teljes génállományra kiterjedő vizsgálat (genome-wide association studies: GWAS) és egy génfeltérképező program (fi ne mapping project) összesen 57 olyan non-HLA single nukleotid poliformizmust (SNP) fedezett fel, amelyek összefüggést mutatnak a coeliakia kialakulásával [7]. Romanos és mtsai 2675 coeliakiás beteg és 2815 egész-séges kontrollegyén bevonásával készült vizsgálatukban kimutatták, hogy a HLA-tipizálás és az 57, coeliakiára jellemző SNP-meghatározás együttes alkalmazása a vizsgált egyének 11,1%-ánál segítette a potenciális coeliakiakockázat előrejelzését, pontosította a diagnózist [8].…”

Demographics, clinical features and treatment of pediatric celiac disease

“…non-HLA genes in comparison to HLA alone, resulted in decreased positive predictive value, from 94% to 57%, although sensitivity increased (Romanos 2014). …”