3D protein structure prediction using Imperialist Competitive algorithm and half sphere exposure prediction

Estimating Bifurcating Consensus Phylogenetic Trees Using Evolutionary Imperialist Competitive Algorithm

Background:

One of the important goals of phylogenetic studies is the estimation of species-level phylogeny. A phylogenetic tree is an evolutionary classification of different species of creatures. There are several methods to generate such trees, where each method may produce a number of different trees for the species. By choosing the same proteins of all species, it is possible that the topology and arrangement of trees would be different.

Objective:

There are methods by which biologists summarize different phylogenetic trees to a tree, called consensus tree. A consensus method deals with the combination of gene trees to estimate a species tree. As the phylogenetic trees grow and their number is increased, estimating a consensus tree based on the species-level phylogenetic trees becomes a challenge.

Methods:

The current study aims at using the Imperialist Competitive Algorithm (ICA) to estimate bifurcating consensus trees. Evolutionary algorithms like ICA are suitable to resolve problems with the large space of candidate solutions.

Results:

The obtained consensus tree has more similarity to the native phylogenetic tree than related studies.

Conclusion:

The proposed method enjoys mechanisms and policies that enable us more than other evolutionary algorithms in tuning the proposed algorithm. Thanks to these policies and the mechanisms, the algorithm enjoyed efficiently in obtaining the optimum consensus tree. The algorithm increased the possibility of selecting an optimum solution by imposing some changes in its parameters.

A neural network learning approach for improving the prediction of residue depth based on sequence-derived features

Residue depth is a solvent exposure measure that quantitatively describes the depth of a residue from the protein surface.