Development of a protein–ligand-binding site prediction method based on interaction energy and sequence conservation

Abstract

We present a new method for predicting protein–ligand-binding sites based on protein three-dimensional structure and amino acid conservation. This method involves calculation of the van der Waals interaction energy between a protein and many probes placed on the protein surface and subsequent clustering of the probes with low interaction energies to identify the most energetically favorable locus. In addition, it uses amino acid conservation among homologous proteins. Ligand-binding sites were predicted by combining the interaction energy and the amino acid conservation score. The performance of our prediction method was evaluated using a non-redundant dataset of 348 ligand-bound and ligand-unbound protein structure pairs, constructed by filtering entries in a ligand-binding site structure database, LigASite. Ligand-bound structure prediction (bound prediction) indicated that 74.0 % of predicted ligand-binding sites overlapped with real ligand-binding sites by over 25 % of their volume. Ligand-unbound structure prediction (unbound prediction) indicated that 73.9 % of predicted ligand-binding residues overlapped with real ligand-binding residues. The amino acid conservation score improved the average prediction accuracy by 17.0 and 17.6 points for the bound and unbound predictions, respectively. These results demonstrate the effectiveness of the combined use of the interaction energy and amino acid conservation in the ligand-binding site prediction.Electronic supplementary materialThe online version of this article (doi:10.1007/s10969-016-9204-2) contains supplementary material, which is available to authorized users.

DeepPocket: Ligand Binding Site Detection and Segmentation using 3D Convolutional Neural Networks

“…These methods are highly dependent on the choice of probes and energy functions as well as the state of the protein structure. Such methods may not work well in scenarios where energetically stable sites are not sufficient enough to give accurate predictions . Furthermore, it is difficult to design a set of probes and energy functions that simulate chemical properties that can cover large amounts of small molecules and ligands .…”

“…not work well in scenarios where energetically stable sites are not sufficient enough to give accurate predictions. 21 Furthermore, it is difficult to design a set of probes and energy functions that simulate chemical properties that can cover large amounts of small molecules and ligands. 22 Therefore, the design of such methods may lead to biases that could result in inaccurate predictions of binding sites on protein structures.…”

Docking study of flavonoid derivatives as potent inhibitors of influenza H1N1 virus neuraminidase

“…In this regard, docking as the first medical computational design tool provides a method based on the prediction of binder energy interactions (using platforms including MetaPocket, GRAMM-X and HEX Protein Docking). The optimum orientation and interaction of the molecules with the lowest binding energy can be thus determined with the three-dimensional information index of the protein-protein binding (33)(34)(35).…”

DeepPocket: Ligand Binding Site Detection and Segmentation using 3D Convolutional Neural Networks

“…Such methods may not work well in scenarios where energetically stable sites are not sufficient enough to give accurate predictions. 21 Furthermore, it is difficult to design a set of probes and energy functions that simulate chemical properties that can cover large amounts of small molecules and ligands. 22 Therefore, the design of such methods may lead to biases that could result in inaccurate predictions of binding sites on protein structures.…”