BIOINFORMATICS SEMINAR SERIES
https://bioinformatics.udel.edu/seminar
Prediction of kinase-substrate phosphorylation interaction using knowledge graph embedding and machine learning technique
Manju Anandakrishnan
PhD Student in Bioinformatics Data Science
Protein kinases are enzymes that phosphorylate substrate proteins, causing a functional modification of the target, and play a crucial role in different cellular processes. Aberrant kinase regulation triggers abnormal phosphorylation or dysfunction of the substrate, resulting in numerous human disease conditions. Kinases have thus turned out to be potential therapeutic targets. Despite their role as probable therapeutic targets, human kinases remain understudied. It is crucial to understand the function and interaction of the understudied kinases, the knowledge of which can aid in drug discovery targeting specific kinases. However, experimentally investigating the kinase phosphorylation of the different substrates in a wet lab is expensive and a time-consuming process. As an alternative, machine learning techniques can be employed to predict the interaction of kinases in a time and cost-efficient manner. We study the phosphorylation activity by embedding the association of the protein kinases and substrates with other functional relationships of the biomolecules using a knowledge graph.
BIOGRAPHY
Manju is a Ph.D. student in the Bioinformatics Data Science program at UD. She is doing her research in predicting kinase-substrate phosphorylation using graph embedding and machine learning techniques under the supervision of Dr. Cathy Wu. Manju received her bachelor’s degree in Genetic Engineering from SRM University, India. Before joining UD, she worked in the field of software development for 12 years. Her research interests include applying machine learning and embedding techniques to study large biological datasets for link prediction and novel pattern identification.
Download Flyer