DMCA
Protein Function Prediction using Weak-label Learning
| Citations: | 3 - 2 self |
BibTeX
@MISC{Yu_proteinfunction,
author = {Guoxian Yu and Guoji Zhang and Carlotta Domeniconi and Zhiwen Yu and Huzefa Rangwala},
title = {Protein Function Prediction using Weak-label Learning},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Protein function prediction is one of the fundamental issues in the post-genomic era. Multi-label learning is widely used for predicting functions of proteins. Most multi-label learning methods assume that the proteins with annotation do not have any missing functions. However, in practice, we may have a subset of the ground-truth functions for a protein, and whether the protein has other functions is unknown. To complete the partial annotation of proteins, we propose a Protein Function Prediction method with W eaklabel Learning (ProWL), and a variant of ProWL (ProWL-IF). Both ProWL and ProWL-IF replenish the functions of proteins under the assumption that proteins are partially annotated. In addition, ProWL-IF takes advantage of the knowledge that a protein cannot have certain functions (called irrelevant functions), which can further boost the performance of protein function prediction. Our experimental results on protein-protein interaction and gene microarray expression benchmarks validate the effectiveness of ProWL and ProWL-IF.
Keyphrases
protein function prediction weak-label learning ground-truth function certain function multi-label learning post-genomic era protein-protein interaction protein cannot fundamental issue multi-label learning method eaklabel learning gene microarray expression benchmark missing function experimental result protein function prediction method partial annotation irrelevant function
