Optimal affinity ranking for automated virtual screening validated in prospective D3R grand challenges

Abstract

The goal of virtual screening is to generate a substantially reduced and enriched subset of compounds from a large virtual chemistry space. Critical in these efforts are methods to properly rank the binding affinity of compounds. Prospective evaluations of ranking strategies in the D3R grand challenges show that for targets with deep pockets the best correlations (Spearman ρ ~ 0.5) were obtained by our submissions that docked compounds to the holo-receptors with the most chemically similar ligand. On the other hand, for targets with open pockets using multiple receptor structures is not a good strategy. Instead, docking to a single optimal receptor led to the best correlations (Spearman ρ ~ 0.5), and overall performs better than any other method. Yet, choosing a suboptimal receptor for crossdocking can significantly undermine the affinity rankings. Our submissions that evaluated the free energy of congeneric compounds were also among the best in the community experiment. Error bars of around 1 kcal/mol are still too large to significantly improve the overall rankings. Collectively, our top of the line predictions show that automated virtual screening with rigid receptors perform better than flexible docking and other more complex methods.

Improving small molecule virtual screening strategies for the next generation of therapeutics

“…Despite progress in the area of CADD, there are still obvious areas of improvements. New force fields and scoring functions are promising[21], yet we have shown that in prospective evaluations with blind data sets simpler virtual screening methods can outperform more complex ones[36,38]. In all likelihood, pose prediction and affinity ranking might have exhausted the benefits of rigid receptors and implicit solvent models.…”

“…Given compounds as SMILES strings[35], predictions for targets for which there are one or more publicly available co-crystal structures (Protein Data Bank (PDB)[4]), are generally performed using three major approaches: alignment-based[36–40], standard docking as discussed above[36–39,41–43], or simulation-based[37,41,44]. Alignment- and docking- based methods have been more consistent in prospective tests[11,12]s. In the former, conformers of each compound are generated[45] and aligned to the ligand of an available co-crystal structure.…”

“…Alignment- and docking- based methods have been more consistent in prospective tests[11,12]s. In the former, conformers of each compound are generated[45] and aligned to the ligand of an available co-crystal structure. Alignment metrics can involve chemical similarity measured by Tanimoto similarity[36–38], 3D shape similarity[40], and hybrid 3D shape/pharmacophore feature similarity method[39]. Poses are then minimized and ranked.…”

“…Thus, so-called “close” methods that use as receptor the co-crystal structure that had the most similar known ligand perform the best. For example, in the D3R competitions[38] we show that “alignclose” (alignment and minimization) or “dock-close” (docking to closest receptor) methods lead to top-of-the-line predictions, with median predicted poses under 2 Å RMSD[36,38,46], a standard metric for measuring success of pose predictions. We found that the quality of docking vs alignment-based methods depends on both the type of binding pocket being targeted (Figure 1) as well as the similarity level of known ligands[36,38] (Figure 2).…”

“…However, selecting the optimal receptor for docking is not always clear. When there is sufficient data with similar congenerics, rankings are robust[36,38,46], the high degree of compound similarity causing the receptor to have similar binding pocket conformation. Though it is still possible to choose a receptor that doesn’t generalize well to your test set, which can lead to essentially random rankings[38].…”