Breast Cancer is the malignant neoplasm with the highest incidence and mortality among women worldwide. It is a heterogeneous and complex disease, its classification in different molecular subtypes is a clear manifestation of this. The recent abundance of genomic data on cancer, make possible to propose theoretical approaches to model the process of genetic regulation. One of these approaches is the use of Transcriptional Networks, which represent the regulation and co-expression of genes as well-defined mathematical objects. These complex networks have global topological and dynamic properties. One of these properties is modular structure, which may be related to known or annotated biological processes. Micro RNAs (miRNA) are a type of molecule transcribed from non-coding sequences in DNA and has been shown to be crucial in the regulation of gene expression. miRNAs are one of the most studied mechanisms of epigenetic regulation, in part because of their potential therapeutic role; however their role in the global regulatory programs is yet to be understood, especially in the context of breast cancer. The impact of miRNA regulation in the functional perturbations observed in the disease remains to be described. Studying miRNA regulation from a complex network perspective will provide novel insights to address these questions. In this work, we used information theory-based methods to study the role of miRNA-gene transcriptional interactions in breast cancer from a complex systems perspective. We analyzed the network structure associated with the four known subtypes of breast cancer, namely LumA, LumB, Basal, and Her2. These networks were inferred from high-throughput genomic data. We studied the hierarchical modular structure of these networks with the aim of finding functional modules associated with biological functions. Our results show a different network topology for each subtype. These differences are also observed in the modular structure, with modules reflecting particular functions of each breast cancer subtypes. miRNAs play a crucial role in both network structure and biological function in each phenotype. The results of our work may help us to identify small, accurate sets of miRNAs with therapeutic potential for individualized medicine.