40. Data Model
Concept
E1 Drug
E2 Protein
E3 Pathway
E4 Adverse Drug
Reac*on
RelaSon
R1 Drug hasTarget Protein
R2 Drug hasEnzyme Protein
R3 Drug hasTransporter Protein
R4 Protein isPresentIn Pathway
R5 Pathway isImplicatedIn ADR
48. Future Work …
• How to test the significance of the associa*ons discovered?
• Implement other models (e.g. simple path enrichment)
– Deal with repor*ng bias.
• Use exis*ng “Silver standards” such as OMOP, EU-ADR,
Drugbank DDIs, MedSpan, etc.
• Relevance of the associa*ons, as well as the correctness of
the underlying mechanisms.
• Importance of the sources to create such networks.
52. Acknowledgments
Musen Lab
- Mark Musen
- Tania Tudorache
- Csongor Nyulas
- MaMhew Horridge
- Rafael Gonçalves
- Josef Hardi
- Marcos Mar*nez
- Mar*n O’Connor
- John Graybeal
- Alex Screnchuk
And others …
52
Michel Dumon*er
Russ Altman
Rainer Winnenberg
Juan Banda
Amrapali Zaveri
BMI Students
Saleem M.
Ali Hasnain
Axel Ngonga
Helena Deus
Jonas Almeida
Stefan Decker
“Discovery informa[cs is in its infancy. Search engines are grappling with the need
for deep search, but it is doub^ul they will fulfill the needs of the biomedical research
community when it comes to finding and analyzing the appropriate datasets …”
- Philip Bourne, Associate Director for Data Science, NIH, 2014