Predicting Protein Crystallization Using a Simple Scoring Card Method

檔案

本條目沒有附加檔案。

日期

2013

期刊名稱

PROCEEDINGS OF THE 2013 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN BIOINFORMATICS AND COMPUTATIONAL BIOLOGY (CIBCB)

卷期與頁次

頁 23–30

ISBN

978-1-4673-5875-0

語言

英文

摘要

Many computational methods have been developed to predict protein crystallization. Most methods use amino acid and dipeptide compositions as part of the informative features. To advance the prediction accuracy, the support vector machine (SVM) based classifiers and ensemble approaches were effective and commonly-used techniques. However, these techniques suffer from the low interpretation ability of insight into crystallization. In this study, we utilize a newly-developed scoring card method (SCM) with a dipeptide composition feature to predict protein crystallization. This SCM classifier obtains prediction results 74%, 0.55 and 0.83 for accuracy, sensitivity and specificity, respectively, which is comparable to the SVM classifier using the same benchmarks. The experimental results show that the SCM classifier has advantages of simplicity, high interpretability, and high accuracy in predicting protein crystallization, compared with existing SVM-based ensemble classifiers.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

引用此條目

Shoombuatong, W., Charoenkwan, P., Huang, H.-L., Lee, H.-C., Chaijaruwanich, J., & Ho, S.-Y. (2013). Predicting Protein Crystallization Using a Simple Scoring Card Method. PROCEEDINGS OF THE 2013 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN BIOINFORMATICS AND COMPUTATIONAL BIOLOGY (CIBCB), 23–30. https://ir.lib.nycu.edu.tw/handle/11536/134730

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/134730