css-palm,CSS-Palm - Palmitoylation Site Prediction

During the past decade, we have developed a series

of high-performance protein palmitoylation sites predictors. In 2006,

CSS-Palm 1.0 was designed by Zhou et al. as the first program for palmitoylation

site prediction (CSS-Palm 4.0

was released, which include a fourth-generation of GPS algorithm and

the latest training data set containing 583 palmitoylation sites from

277 distinct proteins. Notably, in the fourth-generation GPS algorithm, we integrated Particle Swarm Optimize (PSO) to improve the convergence speed and training accuracy.

To evaluate the prediction performance and system

robustness of CSS-Palm 4.0, the leave- one-out

validation and 4-, 6-, 8-, 10-fold cross-validations were performed.

By comparison with our previous versions, the performance of CSS-Palm

4.0 was greatly improved. Finally, the standalone version of

CSS-Palm 4.0 was implemented in Java SE

6 with high speed. The

CSS-Palm 4.0 could predict out potential palmitoylation sites for ~1,000

proteins (with an average length of ~1000aa) within two minutes. Also, with PHP and JavaScript, the online version was developed.Taken

together, we proposed that the CSS-Palm 4.0 will be a great help for

experimentalists. The CSS-Palm 4.0 is freely available at: