Alfonso E. Márquez Chamorro

A decision tree-based method for protein contact map prediction

In this paper, we focus on protein contact map prediction. We describe a method where contact maps are predicted using decision tree-based model. The algorithm includes the subsequence information between the couple of analyzed amino acids. In order to evaluate the method generalization capabilities, we carry out an experiment using 173 non-homologous proteins of known structures. Our results indicate that the method can assign protein contacts with an average accuracy of 0.34, superior to the 0.25 obtained by the FNETCSS method. This shows that our algorithm improves the accuracy with respect to the methods compared, especially with the increase of protein length.

A multi-objective genetic algorithm for the Protein Structure Prediction

The Protein Structure Prediction (PSP) problem consists of predicting the structure of a protein from its amino acids sequence, and have received much attention lately. In fact, being able to predict the structure of a protein, would allow to know the function of the protein. In this paper, we propose a multi-objective evolutionary algorithm for the PSP problem. The prediction model consists of a set of rules that determine possible contacts between amino acids. Such rules are based on four specific amino acid properties, which are involved in the folding process: hydrophobicity, polarity, net charge and residue size. In order to increase the interpretability of the results, rules are organized in a 20x20 matrix where each cell contains the specific rules for a possible pair of residues. The high accuracy values obtained confirm the validity of our proposal.

An evolutionary approach for protein contact map prediction

In this study, we present a residue-residue contact prediction approach based on evolutionary computation. Some amino acid properties are employed according to their importance in the folding process: hydrophobicity, polarity, charge and residue size. Our evolutionary algorithm provides a set of rules which determine different cases where two amino acids are in contact. A rule represents two windows of three amino acids. Each amino acid is characterized by these four properties. We also include a statistical study for the propensities of contacts between each pair of amino acids, according to their types, hydrophobicity and polarity. Different experiments were also performed to determine the best selection of properties for the structure prediction among the cited properties.

An Efficient Nearest Neighbor Method for Protein Contact Prediction

A variety of approaches for protein inter-residue contact prediction have been developed in recent years. However, this problem is far from being solved yet. In this article, we present an efficient nearest neighbor (NN) approach, called PKK-PCP, and an application for the protein inter-residue contact prediction. The great strength of using this approach is its adaptability to that problem. Furthermore, our method improves considerably the efficiency with regard to other NN approaches. Our NN-based method combines parallel execution with k-d tree as search algorithm. The input data used by our algorithm is based on structural features and physico-chemical properties of amino acids besides of evolutionary information. Results obtained show better efficiency rates, in terms of time and memory consumption, than other similar approaches.

Improving the Efficiency of MECoMaP: A Protein Residue-Residue Contact Predictor

This work proposes an improvement of the multi-objective evolutionary method for the protein residue-residue contact prediction called MECoMaP. This method bases its prediction on physico-chemical properties of amino acids, structural features and evolutionary information of the proteins. The evolutionary algorithm produces a set of decision rules that identifies contacts between amino acids. These decision rules generated by the algorithm represent a set of conditions to predict residue-residue contacts. A new encoding used, a fast evaluation of the examples from the training data set and a treatment of unbalanced classes of data were considered to improve the the efficiency of the algorithm.

Evolutionary protein contact maps prediction based on amino acid properties

Protein structure prediction is one of the main challenges in Bioinformatics. An useful representation for protein 3D structure is the protein contact map. In this work, we propose an evolutionary approach for contact map prediction based on amino acids physicochemical properties. The evolutionary algorithm produces a set of rules that identifies contacts between amino acids. The rules obtained by the algorithm imposes a set of conditions on four amino acid properties in order to predict contacts. Results obtained confirm the validity of the proposal.

A nearest neighbour-based approach for viral protein structure prediction

Protein tertiary structure prediction consists of determining the three-dimensional conformation of a protein based solely on its amino acid sequence. This study proposes a method in which protein fragments are assembled according to their physicochemical similarities, using information extracted from known protein structures. Several existing protein tertiary structure prediction methods produce contact maps as their output. Our proposed method produces a distance map, which provides more information about the structure of a protein than a contact map. In addition, many existing approaches use the physicochemical properties of amino acids, generally hydrophobicity, polarity and charge, to predict structure. In our method, we used three different physicochemical properties of amino acids obtained from the literature. Using this method, we performed tertiary structure predictions on 63 viral capsid proteins with a maximum identity of 30% obtained from the Protein Data Bank. We achieved a precision of 0.75 with an 8-angstrom cut-off and a minimum sequence separation of 7 amino acids. Thus, for the studied proteins, our results provide a notable improvement over those of other methods.

Evolutionary computation for the prediction of secondary protein structures

We have developed an evolutionary computation approach to predict secondary structure motifs using some main amino acid physical-chemical properties. The prediction model will consist of rules that predict both the beginning and the end of the regions corresponding to a secondary structure state conformation (α-helix or β-strand). A study about propensities of each pair of amino acids in capping regions of α-helix and β-strand are also performed with a data set of 12,830 non-homologous and non-redundant protein sequences.

Prediction of Protein Distance Maps by Assembling Fragments According to Physicochemical Similarities

The prediction of protein structures is a current issue of great significance in structural bioinformatics. More specifically, the prediction of the tertiary structure of a protein consists of determining its three-dimensional conformation based solely on its amino acid sequence. This study proposes a method in which protein fragments are assembled according to their physicochemical similarities, using information extracted from known protein structures. Many approaches cited in the literature use the physicochemical properties of amino acids, generally hydrophobicity, polarity and charge, to predict structure. In our method, implemented with parallel multithreading, a set of 30 physicochemical amino acid properties selected from the AAindex database were used. Several protein tertiary structure prediction methods produce a contact map. Our proposed method produces a distance map, which provides more information about the structure of a protein than a contact map. The results of experiments with several non-homologous protein sets demonstrate the generality of this method and its prediction quality using the amino acid properties considered.

Residue-Residue Contact Prediction Based on Evolutionary Computation

In this study, a novel residue-residue contacts prediction approach based on evolutionary computation is presented. The prediction is based on four amino acids properties. In particular, we consider the hydrophobicity, the polarity, the charge and residues size. The prediction model consists of a set of rules that identifies contacts between amino acids.