Oncotarget

Research Papers:

2L-PCA: a two-level principal component analyzer for quantitative drug design and its applications

Qi-Shi Du _, Shu-Qing Wang, Neng-Zhong Xie, Qing-Yan Wang, Ri-Bo Huang and Kuo-Chen Chou

PDF  |  HTML  |  Supplementary Files  |  How to cite

Oncotarget. 2017; 8:70564-70578. https://doi.org/10.18632/oncotarget.19757

Metrics: PDF 1906 views  |   HTML 2510 views  |   ?  


Abstract

Qi-Shi Du1,4,*, Shu-Qing Wang2,*, Neng-Zhong Xie1,*, Qing-Yan Wang1, Ri-Bo Huang1 and Kuo-Chen Chou3,4

1State Key Laboratory of China for Biomass Energy Enzyme Technology, National Engineering Research Center of China for Non-Food Biorefinery, Guangxi Academy of Sciences, Nanning 530007, China

2School of Pharmacy, Tianjin Medical University, Tianjin 300070, China

3Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu 610054, China

4Gordon Life Science Institute, Boston, MA 02478, USA

*These authors have contributed equally to this work

Correspondence to:

Qi-Shi Du, email: [email protected]

Kuo-Chen Chou, email: [email protected]

Keywords: drug design, PCA, molecular fragments, physicochemical properties, peptides

Received: April 26, 2017     Accepted: June 30, 2017     Published: August 01, 2017

ABSTRACT

A two-level principal component predictor (2L-PCA) was proposed based on the principal component analysis (PCA) approach. It can be used to quantitatively analyze various compounds and peptides about their functions or potentials to become useful drugs. One level is for dealing with the physicochemical properties of drug molecules, while the other level is for dealing with their structural fragments. The predictor has the self-learning and feedback features to automatically improve its accuracy. It is anticipated that 2L-PCA will become a very useful tool for timely providing various useful clues during the process of drug development.


Creative Commons License All site content, except where otherwise noted, is licensed under a Creative Commons Attribution 4.0 License.
PII: 19757