Deciphering cis-regulatory networks has become an attractive yet challenging task. This paper presents a simple model for cis-regulatory network discovery which aims to avoid most of the common problems of previous approaches. Using promoter sequences and gene co-expression profiles as input, rather than clustering the genes by the co-expression data, it includes neighborhood co-expression information for each individual gene from the co-expression data, thereby overcoming the disadvantages of current clustering based models which miss specific information for individual genes. Applications on Saccharomyces cerevisiae have shown a good prediction accuracy, which outperforms a phylogenetic footprinting approach. In addition, the top dozens of discovered gene-motif regulatory clusters are evidently functionally coregulated.