Structural properties and interaction energies affecting drug design. An approach combining molecular simulations, statistics, interaction energies and neural networks. (June 2015)

• Record Type: Journal Article
• Authors: Ioannidis, Dimitris; Papadopoulos, Georgios E.; Anastassopoulos, Georgios; Kortsaris, Alexandros; Anagnostopoulos, Konstantinos
• Is Part Of: Computational biology and chemistry. Volume 56(2015)
• Page Start: 7
• Page End: 12
• Publication Date: 2015-06
• Subjects: PDB Protein Data Bank -- MDS molecular dynamics simulation -- EM energy minimization -- MDS + EM molecular dynamics simulation followed by energy minimization; Drug design -- Molecular dynamics simulation -- Interaction energy -- Neural networks; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2015.02.016
• Languages: English
• ISSNs: 1476-9271

Abstract

Graphical abstract: Highlights: Molecular dynamics simulations were run on PDB structures containing protein and ligand. Interaction and structural parameters were extracted from the structures. Linear regression was used to check for correlation between these parameters. A neural network (NN) was used to predict ligand design parameters based on the protein. The NN performance improved when tweaking the protein structural parameters used. Abstract: In order to elucidate some basic principles for protein–ligand interactions, a subset of 87 structures of human proteins with their ligands was obtained from the PDB databank. After a short molecular dynamics simulation (to ensure structure stability), a variety of interaction energies and structural parameters were extracted. Linear regression was performed to determine which of these parameters have a potentially significant contribution to the protein–ligand interaction. The parameters exhibiting relatively high correlation coefficients were selected. Important factors seem to be the number of ligand atoms, the ratio of N, O and S atoms to total ligand atoms, the hydrophobic/polar aminoacid ratio and the ratio of cavity size to the sum of ligand plus water atoms in the cavity. An important factor also seems to be the immobile water molecules in the cavity. Nine of these parameters were used as known inputs to train a neural network in the prediction of seven other. Eight structures were left out of the training to test the quality of the predictions. After optimization of the neural network, the predictions were fairly accurate given the relatively small number of structures, especially in the prediction of the number of nitrogen and sulfur atoms of the ligand.