Predicting drug-target interaction using positive-unlabeled learning
Wei Lan 1, Jianxin Wang 1, Min Li1, Jin Liu1, Fang-Xiang Wu2, Yi Pan1, 3
1School of Information Science and Engineering, Central South University, Changsha, 410083, China.
2 Division of Biomedical Engineering and Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SKS7N5A9, Canada.
3Department of Computer Science, Georgia State University, Atlanta, GA30303, USA.
Software download: PUDT.zip
PUDT is a tool for identifying drug-target interaction based on PU learning. It divided unlabeled data U into reliable negative set RN and likely negative set LN, based on different target information.
Author: Wei Lan
The MATLAB Compiler Runtime (MCR) is required and ensure you have installed version 7.17 (R2012a). If the MCR is not installed, please downloading Windows 32bit version of MCR from the MathWorks website: http://www.mathworks.com/products/compiler/
The result contains top 50 predicted drug-target interacton
The first column is the target ID and the second column is drug ID