ANNOUNCEMENT: NetNGlyc 1.0 Prediction Server
-----------------------------------------------------------------------
http://www.cbs.dtu.dk/services/NetNGlyc/
A WWW server for predicting N-glycosylation sites is now available
online. The consensus triplet, Asn-Xaa-Ser/Thr (Xaa not Pro), is not
sufficient to discriminate glycosylated and non-glycosylated
asparagines. The server attempts to make this distinction.
The prediction method is based on artificial neural networks that
examine the surrounding sequence context. In a cross-validated
performance, the networks could identify 86% of the glycosylated and
61% of the non-glycosylated sequons, with an overall accuracy of 76%.
The method can be optimised for high specificity or high sensitivity.
The networks were trained on 344 SwissProt human protein sequences.
We would be very interested in receiving feedback and comments.
-----------------------------------------------------------------------
Ramneek Gupta
Centre for Biological Sequence Analysis
BioCentrum, Bldg-208 Tel: +45-4525-2472
Technical University of Denmark Fax: +45-4593-1585
Lyngby, DK-2800, Denmark ramneek at cbs.dtu.dk
