-
Notifications
You must be signed in to change notification settings - Fork 29
Implementing OWL NETS
OWL-NETS (NEtwork Transformation for Statistical learning) is a computational method that reversibly abstracts Web Ontology Language (OWL)-encoded biomedical knowledge into a more biologically meaningful network representation. OWL-NETS generates semantically rich knowledge graphs that contain heterogeneous nodes and edges and can be used for tasks that do not require OWL semantics. The algorithm consists of the following three steps:
- Decode all OWL-encoded classes
- Remove all triples that contain subjects, predicates, and/or objects that are needed to ensure OWL semantics, but are not biologically meaningful
- Purify the decoded knowledge graph to match an input knowledge graph construction approach (i.e. subclass or instance) Resources:
Callahan TJ, Baumgartner Jr WA, Bada M, Stefanski AL, Tripodi I, White EK, Hunter LE. OWL-NETS: Transforming OWL representations for improved network inference. Pacific Symposium for Biocomputing 2018 Nov (pp. 133-144). Article Access
The tutorial is presented as Jupyter Notebook (OWLNETS_Example_Application.ipynb ) and provides an example of how to run the OWL-NETS independent of the pkt_kg knowledge graph construction work flow. In this notebook, we demonstrate how to apply OWL-NETS to the Human Phenotype Ontology.