In silico diagnosis through microRNA expression profiling experiments is a promising direction in the clinical practices of bioinformatics science. The task is computationally defined as a classification problem where a query experiment is required to be assigned into one of the predefined diseases using a learned model from previously labeled samples. While several powerful machine learning models exist to perform this task, the challenging issue is how to feed these models by effectively encoded samples. This encoding requires a sensible representation of experiment content. In contrast to previous data-driven representations based on observed differential expressions of individual miRNAs, we offer here a network-driven representation scheme that considers the active interactions of miRNAs with other entities in either direction of gene regulation, i.e. regulating or being regulated. We use the enrichment scores of the miRNA sets annotated by corresponding interaction elements to encode the input experiments. We have empirically shown that the new encoding can lead to a higher disease classification accuracy compared with the traditional data-driven approach.