In Biomedical research, the ability to retrieve the adequate information from the ever growing literature is an extremely important asset. This work provides an enhanced and general purpose approach to the process of document retrieval that enables the filtering of PubMed query results. The system is based on semantic indexing providing, for each set of retrieved documents, a network that links documents and relevant terms obtained by the annotation of biological entities (e.g. genes or proteins). This network provides distinct user perspectives and allows navigation over documents with similar terms and is also used to assess document relevance. A network learning procedure, based on previous work from e-mail spam filtering, is proposed, receiving as input a training set of manually classified documents.