Positive-Unlabeled Learning for inferring drug interactions based on heterogeneous attributes.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: Investigating and understanding drug-drug interactions (DDIs) is important in improving the effectiveness of clinical care. DDIs can occur when two or more drugs are administered together. Experimentally based DDI detection methods require a large cost and time. Hence, there is a great interest in developing efficient and useful computational methods for inferring potential DDIs. Standard binary classifiers require both positives and negatives for training. In a DDI context, drug pairs that are known to interact can serve as positives for predictive methods. But, the negatives or drug pairs that have been confirmed to have no interaction are scarce. To address this lack of negatives, we introduce a Positive-Unlabeled Learning method for inferring potential DDIs.

Authors

  • Pathima Nusrath Hameed
    Department of Mechanical Engineering, University of Melbourne, Parkville, Melbourne, 3010, Australia. nusrath@dcs.ruh.ac.lk.
  • Karin Verspoor
    Dept of Computing and Information Systems, School of Engineering, University of Melbourne, Melbourne, Australia.
  • Snezana Kusljic
    Department of Nursing, University of Melbourne, Parkville, Melbourne, 3010, Australia.
  • Saman Halgamuge