Jump to main content
Jump to site search


FPSC-DTI: drug–target interaction prediction based on feature projection fuzzy classification and super cluster fusion

Author affiliations

Abstract

Identifying drug–target interactions (DTIs) is an important part of drug discovery and development. However, identifying DTIs is a complex process that is time consuming, costly, long, and often inefficient, with a low success rate, especially with wet-experimental methods. Computational methods based on drug repositioning and network pharmacology can effectively overcome these defects. In this paper, we develop a new fusion method, called FPSC-DTI, that fuses feature projection fuzzy classification (FP) and super cluster classification (SC) to predict DTI. As the experimental result, the mean percentile ranking (MPR) that was yielded by FPSC-DTI achieved 0.043, 0.084, 0.072, and 0.146 on enzyme, ion channel (IC), G-protein-coupled receptor (GPCR), and nuclear receptor (NR) datasets, respectively. And the AUC values exceeded 0.969 over all four datasets. Compared with other methods, FPSC-DTI obtained better predictive performance and became more robust.

Graphical abstract: FPSC-DTI: drug–target interaction prediction based on feature projection fuzzy classification and super cluster fusion

Back to tab navigation

Supplementary files

Article information


Submitted
20 May 2020
Accepted
05 Oct 2020
First published
08 Oct 2020

Mol. Omics, 2020, Advance Article
Article type
Research Article

FPSC-DTI: drug–target interaction prediction based on feature projection fuzzy classification and super cluster fusion

D. Yu, G. Liu, N. Zhao, X. Liu and M. Guo, Mol. Omics, 2020, Advance Article , DOI: 10.1039/D0MO00062K

Social activity

Search articles by author

Spotlight

Advertisements