We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Accurate Identification of Human Phosphorylated Proteins by Ensembling Supervised Kernel Self‐organizing Maps.
- Authors
Cui, Bei‐Liang; Ding, Yong
- Abstract
Protein phosphorylation is a vital physiological process, which plays a critical role in controlling survival differentiation, cell growth, metabolism and apoptosis. The accurate identification of whether a protein will be phosphorylated solely from protein sequence is especially useful for both basic research and drug development. In this study, a new predictor specifically designed for the prediction of human phosphorylated proteins is proposed. The proposed method first train two supervised kernel self‐organizing maps (SKSOMs): one is trained with feature from protein physiochemical composition view, while the other is trained with feature from protein evolutionary information view. Then, the two trained SKSOMs are ensembled to perform the final prediction. Rigorous computational experiments show that the proposed method achieves 78.75 % and 0.561 on ACC and MCC, which are 6.96 % and 12.5 % higher than that of the state‐of‐the‐art predictor. Overall, the study demonstrated a new sensitive avenue to identify human phosphorylated proteins and could be readily extended to recognize phosphorylated proteins for other species.
- Subjects
SELF-organizing maps; AMINO acid sequence; PROTEINS; CELL growth; DRUG development
- Publication
Molecular Informatics, 2020, Vol 39, Issue 7, p1
- ISSN
1868-1743
- Publication type
Article
- DOI
10.1002/minf.201900141