Skip to main content
Browse by:
GROUP

Effective March 10, 2020, all Duke-sponsored events over 50 people have been cancelled, rescheduled, postponed or virtualized.
Please check with the event contact regarding event status. For more information, please see https://coronavirus.duke.edu/events

CNR Data Science Webinar Series: Deep Mining Heterogeneous Networks of Biomedical Linked Data to Predict Novel Drug-Target Associations

Event Image
Icon calendar
Wednesday, January 29, 2020
Icon time
2:00 pm - 3:00 pm
Icon speaker
Dr. Nansu Zong, Mayo Clinic
Icon series
D2S2 Duson Data Seminar Series

Talk Description:
Exploration and discovery of novel drug-target interactions (DTI) is a critical component of drug development. Despite the availability of a variety of biological assays, experimental prediction remains laborious and expensive. Consequently, computational (in silico) methods have become popular and are commonly applied for poly-pharmacology and for drug repurposing in drug development. Machine learning algorithms are widely applied to predict drug-target associations, and heterogeneous datasets, such as multipartite networks, have been utilized. Despite these methods have achieved promising results in many studies, they are currently not suitable for use in practical drug development due to the remarkable limitations, where (a) results are often biased due to a large number of highly imbalanced negative samples, and (b) novel drug-target associations with new (or isolated) drugs/targets canno

Contact: Karen Judge