1.

Data-driven model for the prediction of protein transmembrane regions

The data about sequences and transmembrane regions were collected from PDB (Protein Data Bank). The entire studied set consists of 5800 segments. Protein sequences were represented with 20x20 matrices, where each element indicates a pair of neighbouring amino-acids. Using the couterpropagation neural network we construct the model which separates the transmembrane regions.

COBISS.SI-ID: 4344090

2.

Clustering of protein transmembrane regions using chemometric tools

Based on mathematical descriptors of protein sequences, self-organizing Kohonen maps are used to cluster the transmembrane and nontransmembrane regions of membrane spanning proteins into different groups, later used to cluster the transmembrane regions according to the functional classification of the transmembrane proteins. Studying structural and functional properties of transmembrane proteins is a difficult procedure. Using chemometric approaches along with traditional experimental methods could be useful in understanding transmembrane proteins.

COBISS.SI-ID: 4274458