Huge efforts are currently underway to address the organization of biological knowledge through linked open databases. These databases can be automatically queried to reconstruct regulatory and signaling networks. However, assembling networks implies manual operations due to sourcespecific identification of biological entities and relationships, multiple life-science databases with redundant information, and the difficulty of recovering logical flows in biological pathways. We propose a framework based on Semantic Web technologies to automate the reconstruction of largescale regulatory and signaling networks in the context of tumor cells modeling and drug screening. The proposed tool is pyBRAvo (python Biological netwoRk Assembly), and here we have applied it to a dataset of 910 gene expression measurements issued from liver cancer patients. The tool is publicly available at https://github.com/pyBRAvo/pyBRAvo