Analysis of Effect of the Position on Weighted Degree Kernel for Splice Site Prediction
Tian-Qi Wang, Yong Xu
Available Online January 2016.
- https://doi.org/10.2991/bst-16.2016.27How to use a DOI?
- Splice site prediction, Weighted degree kernel, Position factor, Support vector machine.
- Prediction of splice sites plays a key role in the annotation of genes. SVM with the weighted degree kernel has been proved to achieve a satisfactory performance. However, this kernel did not consider the effect of the position. In this article, we explored the relationship between the weighted degree kernel and the position of single base match. We defined a position factor to measure the effect of the position on weighted degree kernel, and selected several positions with high position factors to be key positions. Then we constructed a classification model and applied it to the Homo sapiens splice site dataset. To analyze the effect of the position of single base match, we removed the base in the key position and compared the classification accuracy with the accuracy without removing. The result shows that the position of single base match has significant influence on weighted degree kernel.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Tian-Qi Wang AU - Yong Xu PY - 2016/01 DA - 2016/01 TI - Analysis of Effect of the Position on Weighted Degree Kernel for Splice Site Prediction BT - The International Conference on Biological Sciences and Technology PB - Atlantis Press SP - 175 EP - 182 SN - 2468-5747 UR - https://doi.org/10.2991/bst-16.2016.27 DO - https://doi.org/10.2991/bst-16.2016.27 ID - Wang2016/01 ER -