Progress in Machine Learning-based Predicting Subcellular Localizations of Proteins with Multiple Sites
- 10.2991/csss-14.2014.85How to use a DOI?
- protein subcellular localization; dataset; feature extraction; predicting algorithm; validation test
Prediction of protein subcellular localizations is a key step to determinate the functions of proteins. The experimental methods are both expensive and time-consuming. Therefore, many machine learning based computational approaches were proposed in the last two decades. Recently, it is proved that the number of proteins with multiple sites is rising. To determinate the subcellular localizations of this kind of proteins is a more difficult problem. Generally, dataset construction, feature representation, algorithm design and validation test are the four main aspects need to be considered in developing the predicting algorithms. This paper reviewed these four topics in detail. Although a great success has been got by many researchers, there are still a lot of problems need to study deeply.
- © 2014, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Qiao Shanping PY - 2014/06 DA - 2014/06 TI - Progress in Machine Learning-based Predicting Subcellular Localizations of Proteins with Multiple Sites BT - Proceedings of the 3rd International Conference on Computer Science and Service System PB - Atlantis Press SP - 362 EP - 365 SN - 1951-6851 UR - https://doi.org/10.2991/csss-14.2014.85 DO - 10.2991/csss-14.2014.85 ID - Shanping2014/06 ER -