Predicting how and where proteins, especially transcription factors (TFs), interact with DNA is an important problem in biology. We present here a systematic study of predictive modeling approaches to the TF-DNA binding problem, which have been frequently shown to be more efficient than those methods only based on position-speciﬁc weight matrices (PWMs). In these approaches, a statistical relationship between genomic sequences and gene expression or ChIP-binding intensities is inferred through a regression framework; and inﬂuential sequence features are identiﬁed by variable selection. We examine a few state-of-the-art learning methods including stepwise linear regression, multivariate adaptive regression splines (MARS), neural networks, support vector machines, boosting, and Bayesian additive regression trees (BART). These methods are applied to both simulated datasets and two whole-genome ChIP-chip datasets on the TFs Oct4 and Sox2, respectively, in human embryonic stem cells. We ﬁnd that, with proper learning methods, predictive modeling approaches can signiﬁcantly improve the predictive power and identify more biologically interesting features, such as TF-TF interactions, than the PWM approach. In particular, BART and boosting show the best and the most robust overall performance among all the methods.