Cross-species prediction of transcription factor binding by adversarial training of a novel nucleotide-level deep neural network

Cross-species prediction of TF binding remains a major challenge due to the rapid evolutionary turnover of individual TF binding sites, resulting in cross-species predictive performance being consistently worse than within-species performance. In this study, we first propose a novel Nucleotide-Level Deep Neural Network (NLDNN) to predict TF binding within or across species. NLDNN regards the task of TF binding prediction as a nucleotide-level regression task. Beyond predictive performance, we also assess model performance by locating potential TF binding regions, discriminating TF-specific single-nucleotide polymorphisms (SNPs), and identifying causal disease-associated SNPs. Then, we design a dual-path framework for adversarial training of NLDNN to further improve the cross-species prediction performance by pulling the domain space of human and mouse species closer.