The regulatory target genes and functional roles of nucleic acid-binding proteins (NABPs), including DNA- and RNA-binding proteins, can vary in a cell- or tissue-specific manner. However, experimentally identifying NABP-binding sites and functionally characterizing these proteins remain technically challenging. Deep learning methods have been developed to predict gene expression levels across diverse cell and tissue types using DNA-binding profiles derived from ChIP-seq experiments. In this study, I predicted the regulatory targets and inferred the functional roles of NABPs using gene co-expression data. Gene co-expression correlations, derived from transcriptomic profiles across multiple cell and tissue types, were used to represent potential interactions between NABPs and their associated genes. These interactions were integrated into a deep learning framework by partially replacing the model's original input features, enabling expression-level prediction based on co-expression networks. The functional predictions of NABP target genes were consistent with their known biological roles. Moreover, several additional functional annotations not currently present in gene function databases were supported by evidence from previously published experimental studies. These results highlight the potential of combining gene co-expression data with deep learning to uncover both known and previously uncharacterized functional roles of NABPs in a cell type-specific context.