Johns Hopkins University professor Elana Fertig details her research to enhance precision medicine in cancer, using the techniques developed for finding patterns in Netflix movie ratings.
The methods involve a matrix factorization algorithm that can identify movies with similar ratings among a small group of users.
The program connects each user with a group of films to a different extent, based upon their individual preferences. Relationships among users are called "patterns" that are learned from the data, and may reveal common rankings unpredicted by movie genre alone.
Fertig proposes gene dysregulation measurements are analogous to movie ratings, movie genres to biological function, and users to patients' tumors.
The program can search across tumors to find patterns in gene dysregulation that induce the malignant biological function in each tumor. "This allows us to compute the probability of each gene being used in each biological function in a tumor," Fertig says.
From The Conversation
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found