Title:Predicting Drug-Target Interactions with Neighbor Interaction Information and Discriminative Low-rank Representation
VOLUME: 19 ISSUE: 5
Author(s):Lihong Peng, Bo Liao*, Wen Zhu and Zejun Li
Affiliation:Key Laboratory for Embedded and Network Computing of Hunan Province, the College of Information Science and Engineering, Hunan University, Changsha Hunan, 410082, Key Laboratory for Embedded and Network Computing of Hunan Province, the College of Information Science and Engineering, Hunan University, Changsha Hunan, 410082, Key Laboratory for Embedded and Network Computing of Hunan Province, the College of Information Science and Engineering, Hunan University, Changsha Hunan, 410082, Key Laboratory for Embedded and Network Computing of Hunan Province, the College of Information Science and Engineering, Hunan University, Changsha Hunan, 410082
Keywords:Drug-target interaction, new drugs or targets, neighbor interaction profile, nonnegative matrix factorization, discriminative
low-rank representation, sparse representation classification.
Abstract:Background: Inferring drug-target interaction (DTI) candidates for new drugs or targets without
any interaction information is a critical challenge for modern drug design and discovery. Results from
existing DTI inference methods indicate that these approaches necessitate further improvement.
Methods: In this paper, we developed a novel DTI identification model (PreNNDS) by integrating
Neighbor interaction profiles, Nonnegative matrix factorization, Discriminative low-rank representation,
and Sparse representation classification into a unified framework.
Results: AUPR values on four types of datasets show that PreNNDS can efficiently identify potential
DTIs for new drugs or targets. We listed predicted top 20 drugs interacting with hsa1132 and hsa1124 and
top 20 targets interacting with D00255 and D00195.
Conclusions: PreNNDS can be applied to identify multi-target drugs and multi-drug resistance proteins,
as well as to provide clues for microRNA-disease and gene-disease association prediction.
