AI-guided identification of risk variants for adrenocortical tumours in p.R337H carrier children: a genetic association study.

BACKGROUND

Adrenocortical tumours (ACT) in children are part of the Li-Fraumeni cancer spectrum and are frequently associated with a germline pathogenic variant. p.R337H is highly prevalent in the south and southeast of Brazil and predisposes to ACT with low penetrance. Thus, we aimed to investigate whether genetic variants exist which are associated with an increased risk of developing ACT in p.R337H carrier children.

METHODS

A genetic association study was conducted in trios of children (14 girls, 7 boys) from southern Brazil carriers of p.R337H with ( = 18) or without ( = 3) ACT and their parents, one of whom also carries this pathogenic variant (discovery cohort). Results were confirmed in a validation cohort of p.R337H carriers with ( = 90; 68 girls, 22 boys) or without ACT ( = 302; 165 women, 137 men).

FINDINGS

We analysed genomic data from whole exome sequencing of blood DNA from the trios. Using deep learning algorithms, according to a model where the affected child inherits from the non-carrier parent variant(s) increasing the risk of developing ACT, we found a significantly enriched representation of non-coding variants in genes involved in the cyclic AMP (cAMP) pathway known to be involved in adrenocortical tumorigenesis. One among those variants (rs2278986 in the gene) was confirmed to be significantly enriched in the validation cohort of p.R337H carriers with ACT compared to carriers without ACT (OR 1.858; 95% CI 1.146, 3.042, p = 0.01).

INTERPRETATION

Profiling of the variant rs2278986 is a candidate for future confirmation and possible use as a tool for ACT risk stratification in p.R337H carriers.

FUNDING

Centre National de la Recherche Scientifique (CNRS), Behring Foundation, Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq).