This article discusses the use of machine learning methods to predict allelic effects on cell-type-specific regulatory elements, which have been identified through large-scale consortiums and are associated with human complex traits. The article provides a history of machine learning approaches and explains key computational processes, such as convolution and self-attention, which have been used for DNA sequence analysis. This research has the potential to improve our understanding of the genetic basis of complex traits and inform future studies in this field.
