Information
| Summary
|
P2SL
infers protein targeting based on implicit motif
frequency distribution of protein sequences. Targeting-signal is
modeled based on the distribution of subsequence occurrences (implicit
motifs) using self-organizing maps. The boundaries among the classes
were then determined by a set of support vector machines. P2SL is a
hybrid computational system that predicts over ER targeted, cytosolic,
mitochondrial and nuclear protein localization classes. |
| Input
|
Input
is a amino acid sequence of a eukaryotic protein. It should only
contain the following amino acid codes ARNDCQEGHILKMFPSTWYV
Any characters other than these will be discarded. |
| Output |
Output of P2SL indicates the prediction of one or more subcellular localization(s) to which
your protein is predicted to be targeted. Predicted localizations can be among Endoplasmic
Reticulum, Cytoplasm, Mitochondria and Nucleus. In addition, P2SL gives the computed possibilities associated
to these localizations which can assist for further analysis.
|
| Sample |
sequences
|
| Reference |
Atalay V. and Cetin-Atalay R., Implicit Motif Distribution based
Hybrid Computational Kernel for Sequence Classification, Bioinformatics,
21(8): 1429 - 1436, 2005.
|
| Contact
|
Rengul Atalay , Volkan Atalay
|
|