U.S. flag

An official website of the United States government

Figure 1.

Figure 1. From: Predicting subcellular localization of proteins for Gram-negative bacteria by support vector machines based on n-peptide compositions.

The query sequence is encoded by different coding schemes to obtain (a1a2•), (b1b2•), and (c1c2•), which are used to train the SVM classifiers. We combine votes from these classifiers and use the jury votes to determine the final assignment. We use four coding schemes in this work, which are A1, A2, X4, and F3X5. Because we use the one-against-one methods, we construct 40 SVM classifiers for the prediction of five subcellular localization sites.

Chin-Sheng Yu, et al. Protein Sci. 2004 May;13(5):1402-1406.

Supplemental Content

Filter your results:

Search details

See more...

Recent activity

Your browsing activity is empty.

Activity recording is turned off.

Turn recording back on

See more...
Support Center