Improving residue-residue contact prediction via low-rank and sparse decomposition of residue correlation matrix
详细信息 查看全文
- 作者：Haicang Zhanga ; b ; 1 ; Yujuan Gaoc ; 1 ; Minghua Dengc ; d ; e ; Chao Wanga ; b ; Jianwei Zhua ; b ; Shuai Cheng Lif ; Wei-Mou Zhengg ; zheng@itp.ac.cn" class="auth_mail" title="E-mail the corresponding author ; Dongbo Bua ; dbu@ict.ac.cn" class="auth_mail" title="E-mail the corresponding author
- 关键词：Protein contacts prediction ; Correlation analysis ; Background correlation removal ; Low-rank and sparse matrix decomposition
- 刊名：Biochemical and Biophysical Research Communications
- 出版年：2016
- 出版时间：25 March 2016
- 年：2016
- 卷：472
- 期：1
- 页码：217-222
- 全文大小：1325 K
文摘
- •
In contact prediction, correlation analysis is hampered by background correlations.
- •
We used LRS (low rank and sparse decomposition) to remove background correlations.
- •
True contacts were inferred based on the sparse component of correlation matrix.
- •
Our results suggested that LRS significantly improved prediction precision.
- •
LRS outperformed the popular denoising technique APC.