※ Documentation:

Frequently Asked Questions:

1. Q: How to use CSS-Palm web service?

A: Please visit the latest version of CSS-Palm 4.0 at http://csspalm.biocuckoo.org/online.php. Unlike previous version, the web service does not require a JRE runtime environment. For Windows and Unix/Linux users, please use the keyboard shortcuts "Ctrl+C & Ctrl+V" to copy and paste your FASTA format sequences into TEXT form for prediction. And for Mac users, please use the keyboard shortcuts "Command+C & Command+V". Then please click on the "Submit" button to run the program. The prediction results will be shown in the Prediction form. Again, please click on the ‘Download’ button on the top of the Prediction form to save the results in text or html format.


2. Q: I can't launch the program properly, what should I do?

A: We have tested CSS-Palm 4.0 on several operating system, including Windows, Linux and MacOS. For Windows and Linux systems, a latest version of Java Runtime Environment (JRE) package (JAVA 1.6 or later versions) of Sun Microsystems should be pre-installed for using the CSS-Palm 4.0 program. Please download and install the proper JRE package on your computer from http://java.com page or our website. However, for Mac OS, the CSS-Palm4.0 could be used directly without any additional packages. Finally, if you still can’t launch the program properly, please send us an email and tell me the OS information on your computer. We will resolve the problem ASAP.


3. Q: Is CSS-Palm 4.0 much better than CSS-Palm 3.0?

A: Yes! Firstly, the fourth-generation GPS (Group-based Prediction System) algorithm was applied in CSS-Palm 4.0. The prediction performance was greatly improved against our previous tools. Also, the training data set of CSS-Palm 4.0 was updated by searching the scientific literature published before September 2013. Thus, the prediction accuracy of CSS-Palm 4.0 was significantly improved. Furthermore, compared with the former arithmetic, the calculation efficiency of CSS-Palm 4.0 has risen greatly. It only cost a few minutes to predict palmitoylation sites in human proteome using an average desktop computer.


4. Q: I have 20,000 proteins for prediction, what should I do?

A: For a large-scale prediction, we recommend two approaches for you. You can use the web service but input the sequences for 20 times, with 1,000 proteins per time. Also, please download a stand-alone software of CSS-Palm 4.0 linked as below. In the stand-alone versions, the limitation of sequences number is removed. You can use "Batch Predictor" in the local software for a large-scale prediction.


5. Q: I have a few questions which are not listed above, how can I contact the authors of CSS-Palm 4.0?

A: Please contact Dr. Jian Ren and Dr. Yu Xue for details.


6. Q: I was trying to install the software in Mac OS but my installer says the file is damaged. How can I properly install the software in Mac OS?

A: By default, Mac OS 10.8 or later only allows users to install applications from 'verified sources'. In effect, this means that users are unable to install most applications downloaded from the internet. You can follow the directions below to prevent this error message from appearing.

(1) Open the Preferences. This can be done by either clicking on the System Preferences icon in the Dock or by going to Apple Menu > System Preferences.
(2) Open the Security & Privacy pane by clicking Security & Privacy.
(3) Make sure that the General section of the the Security & Privacy pane is selected. Click the icon labeled Click the lock to prevent further changes.
(4) Enter your username and password into the prompt that appears and click Unlock.
(5) Under the section labeled Allow applications downloaded from, select Anywhere. On the prompt that appears, click Allow From Anywhere.
(6) Exit System Preferences by clicking the red button in the upper left of the window. You should now be able to install applications downloaded from the internet.




Performance evaluation

  As presented in Figure A below, the prediction performance of CSS-Palm was evaluated with both LOO and n-fold validation. The Receiver Operating Characteristic (ROC) curves were plotted. The areas under the ROCs (AROCs) curves were calculated to be 0.905 (LOO), 0.885 (4-fold), 0.893 (6-fold), 0.895 (8-fold) and 0.891 (10-fold). The ROC curves of 4-, 6-, 8-, 10-fold cross validations were found to be close to LOO validation, indicating that the CSS-Palm 4.0 is a robust predictor.

  Furthermore, the CSS-Palm 4.0 was compared with other predictors. Up to now, three predictors have been developed, including CSS-Palm ( Ren, et al., 2008; Xue, et al., 2011; Zhou, et al., 2006 ), CKSAAP-Palm ( Wang, et al., 2009 ) and IFS-Palm ( Hu, et al., 2011 ) . Since the IFS-Palm tool was not provided in the original paper, comparison was carried out among the CSS-Palm 4.0, CSS-Palm 3.0 and CKSAAP-Palm. For comparison, the LOO validation was carried out, and the ROC curves were plotted in Figure B. The AROCs were calculated to be 0.825 (CKSAAP-Palm), 0.868 (CSS-Palm 3.0) and 0.905 (CSS-Palm 4.0). It shows that the performance of both of the two versions of the CSS-Palm were superior to the CKSAAP-Palm. In addition, the prediction capability of the CSS-Palm 4.0 was significantly improved over the CSS-Palm 3.0.