Krautenbacher N, Kabesch M, Horak E, et al. - This study was undertaken to determine if the prediction of childhood asthma by genetic determinants differs from the environmental setting, especially farm exposure. In the GABRIELA study with 850 cases (9% farm children) and 857 controls (14% farm children), statistical learning approaches based on penalized regression and decision trees were used to predict asthma. According to findings, asthma in farm children appears to be distinct from asthma in non‐farm children, at least with regard to genetic and environmental predictors. Family history, which can integrate genotype and degree of penetrance conditional on the environmental setting, is the common denominator. Retrospectively, the potential of genome‐wide data for the prediction of polygenic diseases may have been overrated, while the power of the environment merits a second look.