Co-regulation networks are frameworks that describe coordinated activity patterns between biological molecules. These networks play a crucial role in regulating specific genetic behaviors and are key for discovering the relationships between joint expression dynamics and diverse biological phenomena. Among such tools, RNACOREX is a Python library designed to infer multi-layered post-transcriptional regulatory networks using Bayesian networks. By integrating interactions between microRNA-mRNA and mRNA-mRNA, RNACOREX uses conditional linear Gaussian distributions within probabilistic graphical models to learn regulatory interactions, combining expression data with curated knowledge. The inherent explanatory characteristics of Bayesian networks provide researchers with insights into the molecular players and activity flows linked to diseases, while also enabling predictions in unseen datasets. We evaluated the performance of these models using the SARC dataset from TCGA, constructing co-regulation networks, identifying key interactions, and extracting essential classification metrics. Additionally, we identified specific interactions associated with distinct pathways involved in sarcoma pathology, pointing to key regulatory mechanisms in this cancer.