During the last few years a couple of computational methods have been developed to predict ion channels
and classify them by their gating mechanism. Most of the methods rely on machine learning algorithms,
like support vector machines and random forests, which utilize features extracted by protein sequence characteristics.
However, there is currently no method available to predict and classify Ligand-Gated
Ion Channels specifically.
LiGIoNs is a profile Hidden Markov Model based method capable of predicting Ligand-Gated Ion Channels utilizing their special topological information. The method consists of a library of 35 pHMMs, built from the alignment of transmembrane segments of representative LGIC sequences. In addition, 14 Pfam pHMMs are used to further annotate and correctly classify unknown protein sequences into one of the 10 LGIC subfamilies.
Supplementary Data after the application of LiGIoNs in eukaryotic reference proteomes can be found here
Evaluation script the scripts to rebuild and evaluate hmm profiles can be found here
Current Version of LiGIoNs: v1.0
Katerina C. Nastou, Georgios N. Petichakis, Zoi I. Litou and Vassiliki A. Iconomidou
LiGIoNs: Α Computational Method for the Detection and Classification of Ligand-Gated Ion Channels