以階層式綜合預測蛋白質磷酸化位置

ASIA unversity > 資訊學院 > 生物資訊與醫學工程學系 > 博碩士論文 > Item 310904400/111032

Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/111032

Title:	以階層式綜合預測蛋白質磷酸化位置
Authors:	周力行
Contributors:	生物資訊與醫學工程學系
Keywords:	磷酸化位置預測、綜合預測、即時決策問題、階層式綜合預測、乘性權重更新演算法、機器學習、Phosphorylation sites prediction、Meta-prediction、On-line decision problem、Hierarchical meta-prediction、Multiplicative weighted update algorithms、Machine learning
Date:	2018
Issue Date:	2018-06-22 01:20:37 (UTC+0)
Publisher:	亞洲大學
Abstract:	目前已經開發了許多的磷酸化預測網站來預測磷酸化位置，但卻沒有任何一個預測網站能在任何情況下，性能皆能夠勝於其他預測網站。綜合預測策略，是由Wan 等人的團隊所提出一個預測方法，此策略為整合許多預測磷酸化位置網站的預測結果。他們的綜合預測策略效能取得相當不錯的結果，且在大多情況下效能皆優於各基礎預測網站。他們執行一個廣義的權重投票策略藉由限制格點搜尋來產生綜合預測程式。但是，限制格點分析因為使用組合分析法，導致其有著大量的參數組合，若隨著樣本或是參數的增加，運算量會呈指數成長，非常耗時。在本論文中，我們使用了乘性權重更新演算法及階層式綜合預測來學習綜合預測較好的參數，並且以此為基礎，嘗試刪除性能較差的預測網站，以取得更好的效能參數。實驗結果顯示我們的綜合預測性能超過了KinasePhos, KinasePhos 2.0, PPSP, GPS3.0,在 S/T 位置在四個激酶,PKA,PKC,CDK,CK2 上的預測正確率。 There are numerous predictors have been developed to the phosphorylation sites prediction. However, there are no developed prediction programs that could make more accurate prediction than other prediction programs in every situation.Meta-prediction strategies. It is a phosphorylation sites prediction method proposed by Wan et al's team. The method integrate results of several prediction tools for phosphorylation sites prediction. Their meta-predictor gained an outstanding prediction performance that surpasses that of all combined prediction programs. They performed a generalized weighted voting strategy with parameters determined by restricted grid search to produce meta-prediction programs. Unfortunately, restricted grid search is time-consuming and the values of restricted grids should be computed using combinatorial analysis. In this paper, we make use of multiplicative update algorithms and hierarchical meta-prediction to learn better parameters for meta-predictions. Remove several prediction tools of bad performance. To get better performance parameters. The experimental results show that the hierarchical meta-prediction performs better KinasePhos, KinasePhos 2.0, PPSP, GPS3.0 for S/T kinase families, PKA, PKC, CDK, CK2.
Appears in Collections:	[生物資訊與醫學工程學系 ] 博碩士論文

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	273	View/Open

View Licence

Loading...