Predicting protein crystallization using a simple scoring card method
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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 格式: | Conference Proceeding |
| 出版: |
2018
|
| 在線閱讀: | https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84885053814&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/47580 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | 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-basedensemble classifiers. © 2013 IEEE. |
|---|