In disease research, understanding the key genes involved and how they interact to drive disease occurrence or severity is extremely valuable. Discovering previously unknown gene-disease relationships helps us gain insights to develop new potential therapies. To this end, we applied machine learning (ML) to our QIAGEN Knowledge Graph (QKG) to predict novel gene-disease associations. A research team at MicroMatrices, who study familial paraganglioma, investigated potential new targets by identifying differentially expressed genes using laser dissection targeted transcriptomics analysis in tumor vs. normal tissue. They compared the changes found in their case study with predicted gene alterations made by our ML process and found potential new drug targets and candidate drugs. Their treatment hypotheses can be tested in a 3D model of paraganglioma using SpheroMatrices microtissue array (microTMA) technology.

If you'd like to explore a new way to identify potential new drug targets, you won't want to miss this unique opportunity to learn from industry experts about:

• How machine learning used known relationships in the QKG to infer hidden relationships between potential targets and diseases
• A library of 1500 disease networks available in QIAGEN Ingenuity Pathway Analysis (IPA)
• MicroMatrices' research into paraganglioma and evaluation of novel gene associations predicted by our disease network
• Opportunities to verify new drug targets for paraganglioma as well as potential targets in other diseases