A generative model for constructing nucleic acid sequences binding to a protein

摘要

Due to recent advances in high-throughput experimental technologies, a large amount of data on interactions between proteins and nucleic acids have been generated. Motivated by the increased amount of data on protein-nucleic acid interactions, several machine learning methods have been used either to predict binding sites in a sequence [ – ] or to determine if an interaction exists between a pair of sequences [ – ].