Paulette Greenidge

Evaluation of machine-learning methods for ligand-based virtual screening

Machine-learning methods can be used for virtual screening by analysing the structural characteristics of molecules of known (in)activity, and we here discuss the use of kernel discrimination and naive Bayesian classifier (NBC) methods for this purpose. We report a kernel method that allows the processing of molecules represented by binary, integer and real-valued descriptors, and show that it is little different in screening performance from a previously described kernel that had been developed specifically for the analysis of binary fingerprint representations of molecular structure. We then evaluate the performance of an NBC when the training-set contains only a very few active molecules. In such cases, a simpler approach based on group fusion would appear to provide superior screening performance, especially when structurally heterogeneous datasets are to be processed.

Improving Docking Results via Reranking of Ensembles of Ligand Poses in Multiple X-ray Protein Conformations with MM-GBSA

There is a tendency in the literature to be critical of scoring functions when docking programs perform poorly. The assumption is that existing scoring functions need to be enhanced or new ones developed in order to improve the performance of docking programs for tasks such as pose prediction and virtual screening. However, failures can result from either sampling or scoring (or a combination of the two), although less emphasis tends to be given to the former. In this work, we use the programs GOLD and Glide on a high-quality data set to explore whether failures in pose prediction and binding affinity estimation can be attributable more to sampling or scoring. We show that identification of the correct pose (docking power) can be improved by incorporating ligand strain into the scoring function or rescoring an ensemble of diverse docking poses with MM-GBSA in a postprocessing step. We explore the use of nondefault docking settings and find that enhancing ligand sampling also improves docking power, again suggesting that sampling is more limiting than scoring for the docking programs investigated in this work. In cross-docking calculations (docking a ligand to a noncognate receptor structure) we observe a significant reduction in the accuracy of pose ranking, as expected and has been reported by others; however, we demonstrate that these alternate poses may in fact be more complementary between the ligand and the rigid receptor conformation, emphasizing that treating the receptor rigidly is an artificial constraint on the docking problem. We simulate protein flexibility by the use of multiple crystallographic conformations of a protein and demonstrate that docking results can be improved with this level of protein sampling. This work indicates the need for better sampling in docking programs, especially for the receptor. This study also highlights the variable descriptive value of RMSD as the sole arbiter of pose replication quality. It is shown that ligand poses within 2 Å of the crystallographic one can show dramatic differences in calculated relative protein-ligand energies. MM-GBSA rescoring of distinct poses overcomes some of the sensitivities of pose ranking experienced by the docking scoring functions due to protein preparation and binding site definition.

Discovery of novel indolinone-based, potent, selective and brain penetrant inhibitors of LRRK2

Mutations in leucine-rich repeat kinase-2 (LRRK2) are the most common genetic cause of Parkinsons disease (PD). The most frequent kinase-enhancing mutation is the G2019S residing in the kinase activation domain. This opens up a promising therapeutic avenue for drug discovery targeting the kinase activity of LRRK2 in PD. Several LRRK2 inhibitors have been reported to date. Here, we report a selective, brain penetrant LRRK2 inhibitor and demonstrate by a competition pulldown assay in vivo target engagement in mice.

Introducing the Consensus Modeling Concept in Genetic Algorithms: Application to Interpretable Discriminant Analysis

An evolutionary statistical learning method was applied to classify drugs according to their biological target and also to discriminate between a compilation of oral and nonoral drugs. The emphasis was placed not only on how well the models predict but also on their interpretability. In an enhancement to previous studies, the consistency of the model weights over several runs of the genetic algorithm was considered with the goal of producing comprehensible models. Via this approach, the descriptors and their ranges that contribute most to class discrimination were identified. Selecting a bin step size that enables the average descriptor properties of the class being trained to be captured improves the interpretability and discriminatory power of a model. The performance, consistency, and robustness of such models were further enhanced by using two novel approaches that reduce the variability between individual solutions: consensus and splice modeling. Finally, the ability of the genetic algorithm to discriminate between activity classes was compared with a similarity searching method, while naïve Bayes classifiers and support vector machines were applied in discriminating the oral and nonoral drugs.

Boosting Pose Ranking Performance via Rescoring with MM‐GBSA

In this self‐docking study, we address the so‐called scoring problem. The ‘scoring problem’ is the inability to unambiguously identify biologically the most relevant pose, when the docking score is the main selection criterion. We use the Molecular Mechanics/Generalized Born Surface Area and ChemPLP scoring functions to assess the structure reproduction performance. Heavy‐atom root‐mean‐squared deviation values are used to compare the docked poses with the crystallographic ones. ‘Partial matching’ is introduced. This algorithm captures the visual observation that the majority of a ligand can be well docked, but yet report a root‐mean‐squared deviation value of >2.0 Å. Often this is attributable to arbitrary placements of flexible side chains in undefined solvent regions. The metrics introduced by this algorithm are applicable for assessing the contribution of ligand sampling to the scoring problem. It is shown that rescoring ChemPLP poses with the Molecular Mechanics/Generalized Born Surface Area scoring function improves pose ranking by better discriminating against non‐cognate‐like poses. We conclude that poses should not be retained solely on their ranks, but on the score difference relative to the best‐ranked pose.