A general approach for developing system‐specific functions to score protein–ligand docked complexes using support vector inductive logic programming

Abstract

Despite the increased recent use of protein-ligand and protein-protein docking in the drug discovery process due to the increases in computational power, the difficulty of accurately ranking the binding affinities of a series of ligands or a series of proteins docked to a protein receptor remains largely unsolved. This problem is of major concern in lead optimization procedures and has lead to the development of scoring functions tailored to rank the binding affinities of a series of ligands to a specific system. However, such methods can take a long time to develop and their transferability to other systems remains open to question. Here we demonstrate that given a suitable amount of background information a new approach using support vector inductive logic programming (SVILP) can be used to produce system-specific scoring functions. Inductive logic programming (ILP) learns logic-based rules for a given dataset that can be used to describe properties of each member of the set in a qualitative manner. By combining ILP with support vector machine regression, a quantitative set of rules can be obtained. SVILP has previously been used in a biological context to examine datasets containing a series of singular molecular structures and properties. Here we describe the use of SVILP to produce binding affinity predictions of a series of ligands to a particular protein. We also for the first time examine the applicability of SVILP techniques to datasets consisting of protein-ligand complexes. Our results show that SVILP performs comparably with other state-of-the-art methods on five protein-ligand systems as judged by similar cross-validated squares of their correlation coefficients. A McNemar test comparing SVILP to CoMFA and CoMSIA across the five systems indicates our method to be significantly better on one occasion. The ability to graphically display and understand the SVILP-produced rules is demonstrated and this feature of ILP can be used to derive hypothesis for future ligand design in lead optimization procedures. The approach can readily be extended to evaluate the binding affinities of a series of protein-protein complexes.

A Comparative Assessment of Predictive Accuracies of Conventional and Machine Learning Scoring Functions for Protein-Ligand Binding Affinity Prediction

“…There are also significant differences in the experiments we conduct, e.g., in the various combinations of ML techniques and feature types we explore and the impact on BA prediction accuracy of various combinations of feature types and of limiting BLAST sequence similarity between binding sites of proteins in training and test complexes to assess the performance of ML SFs on novel targets. Prior to RF-Score, Deng et al applied kernel partial least squares modeling to geometrical features characterizing complexes [25] and Amini et al considered support vector regression [29] for protein-ligand BA prediction. Both of these studies showed promising results for ML methods, but considered small test sets.…”

In pursuit of virtual lead optimization: The role of the receptor structure and ensembles in accurate docking

“…Despite advances in scoring algorithms, incorporation of protein and ligand flexibility and the treatment of solvent, all of which increase docking accuracy, 1,2 achieving proper ranking remains a significant and difficult problem that is largely unsolved. 3,4 A crucial component of a successful virtual screen with accurate ligand ranking is the experimental or modeling source of the receptor structure used for docking. High resolution crystal structures are typically chosen if available.…”

Improving molecular docking through eHiTS’ tunable scoring function

“…Mooij and Verdonk developed receptor-targeted scoring functions by modifying the atoms pair-wise interaction potential based on statistical analysis of complexes [29]. More recent studies used support vector machine and other approaches to develop target specific scoring functions [30,31]. However, none of the published methods has been applied on a large scale to achieve extensive protein-family coverage, or has been integrated into a standard docking tool.…”