One of the main challenges of structure-based virtual screening (SBVS) is the incorporation of the receptor's flexibility, as its explicit representation in every docking run implies a high computational cost. Therefore, a common alternative to include the receptor's flexibility is the approach known as ensemble docking. Ensemble docking consists of using a set of receptor conformations and performing the docking assays over each of them. However, there is still no agreement on how to combine the ensemble docking results to obtain the final ligand ranking. A common choice is to use consensus strategies to aggregate the ensemble docking scores, but these strategies exhibit slight improvement regarding the single-structure approach. Here, we claim that using machine learning (ML) methodologies over the ensemble docking results could improve the predictive power of SBVS. To test this hypothesis, four proteins were selected as study cases: CDK2, FXa, EGFR, and HSP90. Protein conformational ensembles were built from crystallographic structures, whereas the evaluated compound library comprised up to three benchmarking data sets (DUD, DEKOIS 2.0, and CSAR-2012) and cocrystallized molecules. Ensemble docking results were processed through 30 repetitions of 4-fold cross-validation to train and validate two ML classifiers: logistic regression and gradient boosting trees. Our results indicate that the ML classifiers significantly outperform traditional consensus strategies and even the best performance case achieved with single-structure docking. We provide statistical evidence that supports the effectiveness of ML to improve the ensemble docking performance.
The oxidation of R-(+)-limonene by chloroperoxidase (CPO) from Caldariomyces fumago is reported. The reaction was performed in 60 mM phosphate buffer at pH 3.0 and 6.0, and in the absence and in the presence of chloride ions. In the absence of chloride ions, at both pH values, the reaction was regio and stereoselective with a diasteromeric excess (de) >99% of (1S,2S)-4R-limonene-1,2-diol. On the other hand, when the reaction was carried out in the presence of chloride ions an enhancement in the reaction rate was observed, maintaining the regioselectivity, but not the stereoselectivity (de <5.4). The reaction products under these conditions were identified as (1S,2S)-4R-limonene-1,2-diol and (1R,2R)-4R-limonene-1,2-diol. It seems that in the absence of chloride ions the stereoselectivity is determined by stereospecific interaction of limonene with CPO active site, as supported by docking analysis, while in the presence of potassium chloride the limonene oxidation also occurs by the produced hypochlorite without stereoselectivity.
Phosphotriesterase, a pesticide-degrading enzyme, from Flavobacterium sp. was cloned and expressed in Escherichia coli. The catalytic zinc ions were replaced by cobalt atoms increasing the catalytic activity of phosphotriesterase on different pesticides. This metal substitution increased the catalytic activity from 1.4 times to 4 times according to the pesticide. In order to explain this catalytic increase, QM/MM calculations were performed. Accordingly, the HOMO energy of the substrate is closer to the LUMO energy of the cobalt-substituted enzyme. The chemical modification of the enzyme surface with poly(ethylene glycol) increased the thermostability and stability against metal chelating agents of both metal phosphotriesterase preparations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.