Protein ligand-binding site comparison by a reduced vector representation derived from multidimensional scaling of generalized description of binding sites

Site2Vec: a reference frame invariant algorithm for vector embedding of protein–ligand binding sites

Protein–ligand interactions are one of the fundamental types of molecular interactions in living systems. Ligands are small molecules that interact with protein molecules at specific regions on their surfaces called binding sites. Binding sites would also determine ADMET properties of a drug molecule. Tasks such as assessment of protein functional similarity and detection of side effects of drugs need identification of similar binding sites of disparate proteins across diverse pathways. To this end, methods for computing similarities between binding sites are still evolving and is an active area of research even today. Machine learning methods for similarity assessment require feature descriptors of binding sites. Traditional methods based on hand engineered motifs and atomic configurations are not scalable across several thousands of sites. In this regard, deep neural network algorithms are now deployed which can capture very complex input feature space. However, one fundamental challenge in applying deep learning to structures of binding sites is the input representation and the reference frame. We report here a novel algorithm, Site2Vec, that derives reference frame invariant vector embedding of a protein–ligand binding site. The method is based on pairwise distances between representative points and chemical compositions in terms of constituent amino acids of a site. The vector embedding serves as a locality sensitive hash function for proximity queries and determining similar sites. The method has been the top performer with more than 95% quality scores in extensive benchmarking studies carried over 10 data sets and against 23 other site comparison methods in the field. The algorithm serves for high throughput processing and has been evaluated for stability with respect to reference frame shifts, coordinate perturbations and residue mutations. We also provide the method as a standalone executable and a web service hosted at (http://services.iittp.ac.in/bioinfo/home).

Effects of the difference in similarity measures on the comparison of ligand-binding pockets using a reduced vector representation of pockets

Comprehensive analysis and comparison of protein ligand-binding pockets are important to predict the ligands which bind to parts of putative ligand binding pockets. Because of the recent increase of protein structure information, such analysis demands a fast and efficient method for comparing ligand binding pockets. Previously we proposed a fast alignment-free method based on a simple representation of a ligand binding pocket with one 11-dimensional vector, which is suitable for such analysis. Based on that method, we conducted this study to expand and revise similarity measures of binding pockets and to investigate the effects of those modifications with two datasets for improving the ability to detect similar binding pockets. The new method exhibits higher detection performance of similar binding pockets than the previous methods and another existing accurate alignment-dependent method: APoc. Results also show that the effects of the modifications depend on the difficulty of the dataset, implying some avenues for methods of improvement.