Efficacy of different protein descriptors in predicting protein functional families.

BACKGROUND: Sequence-derived structural and physicochemical descriptors have frequently been used in machine learning prediction of protein functional families, thus there is a need to comparatively evaluate the effectiveness of these descriptor-sets by using the same method and parameter optimization algorithm, and to examine whether the combined use of these descriptor-sets help to improve predictive performance. Six individual descriptor-sets and four combination-sets were evaluated in support vector machines (SVM) prediction of six protein functional families. RESULTS: The performance of these descriptor-sets were ranked by Matthews correlation coefficient (MCC), and categorized into two groups based on their performance. While there is no overwhelmingly favourable choice of descriptor-sets, certain trends were found. The combination-sets tend to give slightly but consistently higher MCC values and thus overall best performance such that three out of four combination-sets show slightly better performance compared to one out of six individual descriptor-sets. CONCLUSION: Our study suggests that currently used descriptor-sets are generally useful for classifying proteins and the prediction performance may be enhanced by exploring combinations of descriptors.

Biochemical implications of sequence comparisons of the cystic fibrosis transmembrane conductance regulator.

The cystic fibrosis transmembrane conductance regulator (CFTR) is a chloride channel that is both of medical significance in humans and of interest with regard to osmoregulation in aquatic organisms. CFTR is composed of five domains: two membrane-spanning domains, two nucleotide-binding domains, and a regulatory domain. Notwithstanding the plethora of information concerning the structure and function of CFTR, the biochemistry of many facets of CFTR are not completely understood. In this regard, we have performed a sequence alignment of representative vertebrate CFTR with the aim of generating hypotheses on the functional significance of conserved and variable residues. Postulates on function common to all organisms are: (i) Thr338 in the sixth transmembrane segment could have a function related to that of the pore-lining residue Lys335, and it is possible that Thr338 hydrogen bonds to Lys335, thus indirectly affecting anion permeability; (ii) the fragment (111)PDNKE could be an ion sensor; (iii) motifs in the two nucleotide-binding domains reflect differential ATP binding and hydrolysis; and (iv) an interaction in the R domain involving (765)RRQSVL and the C terminal end of the domain results in an inhibitory conformation. Major adaptations in fishes include variations in the postulated ion sensor (111)PDNKE, and the absence of a proline residue in the R domain with consequent higher chloride efflux.