Gene-Specific Machine Learning Models to Classify Driver Mutations in Clonal Hematopoiesis

There is no general consensus on the set of mutations capable of driving the age-related clonal expansions in hematopoietic stem cells known as clonal hematopoiesis, and current variant classifications typically rely on rules derived from expert knowledge. In this issue of Cancer Discovery, Damajo and colleagues trained and validated machine learning models without prior knowledge of clonal hematopoiesis driver mutations to classify somatic mutations in blood for 12 genes in a purely data-driven way.

See related article by Demajo et al., p. 1717 (9).