Predicting target-ligand interactions using protein ligand-binding site and ligand substructures

Abstract

BackgroundCell proliferation, differentiation, Gene expression, metabolism, immunization and signal transduction require the participation of ligands and targets. It is a great challenge to identify rules governing molecular recognition between chemical topological substructures of ligands and the binding sites of the targets.MethodsWe suppose that the ligand-target interactions are determined by ligand substructures as well as the physical-chemical properties of the binding sites. Therefore, we propose a fragment interaction model (FIM) to describe the interactions between ligands and targets, with the purpose of facilitating the chemical interpretation of ligand-target binding. First we extract target-ligand complexes from sc-PDB database, based on which, we get the target binding sites and the ligands. Then we represent each binding site as a fragment vector based on a target fragment dictionary that is composed of 199 clusters (denoted as fragements in this work) obtained by clustering 4200 trimers according to their physical-chemical properties. And then, we represent each ligand as a substructure vector based on a dictionary containing 747 substructures. Finally, we build the FIM by generating the interaction matrix M (representing the fragment interaction network), and the FIM can later be used for predicting unknown ligand-target interactions as well as providing the binding details of the interactions.ResultsThe five-fold cross validation results show that the proposed model can get higher AUC score (92%) than three prevalence algorithms CS-PD (80%), BLM-NII (85%) and RF (85%), demonstrating the remarkable predictive ability of FIM. We also show that the ligand binding sites (local information) overweight the sequence similarities (global information) in ligand-target binding, and introducing too much global information would be harmful to the predictive ability. Moreover, The derived fragment interaction network can provide the chemical insights on the interactions.ConclusionsThe target and ligand bindings are local events, and the local information dominate the binding ability. Though integrating of the global information can promote the predictive ability, the role is very limited. The fragment interaction network is helpful for understanding the mechanism of the ligand-target interaction.

Multi-fields model for predicting target–ligand interaction

“…Just as in our preliminary work [21], we represent each binding site as a 199-dimensional vector, each element in which denotes the occurring frequency of a set of trimers in the binding site (a trimer is a three-residues fragment of the binding site, and all possible trimers are clustered into 199 types according to their physical-chemical properties by Nagamine and Sakakibara [24,25]); we represent each ligand as a 413-dimensional binary vector, each element corresponds to the presence/absence of one chemical substructure (fragment) in the ligand dictionary (413 substructures in all).…”

“…In this work, we use the data set constructed in our preliminary work [21]. There are totally 836 targets and 2710 corresponding ligands.…”

Predicting drug–target interaction for new drugs using enhanced similarity measures and super-target clustering

“…Up to now, there is almost no existing approach which is able to handle missing interactions in the databases. Wang et al attempted to work on this issue [13]. However, their approach requires all-atoms coordinates of protein-ligand complexes of which the acquirement is very difficult, especially for the targets located in cell membrane.…”

Algorithm for Extraction of Sub-Structure from Co-Crystallized PDB Ligand for Selective Targeting

“…In a study for predicting ligand-protein interaction, information of binding site was used along with sub-structure of ligand. To extract substructure, physical-chemical properties of binding site based approach was used (Wang et al, 2015). In a genome-wide screening of drug-target interaction, without requirement of 3D structure of target protein, sparse canonical correspondence analysis was performed by analyzing profiles of drug and targets simultaneously to extract sets of chemical substructures.…”