Virtual screening (VS) is an outstanding cornerstone in the drug discovery pipeline. A variety of computational approaches, which are generally classified as ligand-based (LB) and structure-based (SB) techniques, exploit key structural and physicochemical properties of ligands and targets to enable the screening of virtual libraries in the search of active compounds. Though LB and SB methods have found widespread application in the discovery of novel drug-like candidates, their complementary natures have stimulated continued efforts toward the development of hybrid strategies that combine LB and SB techniques, integrating them in a holistic computational framework that exploits the available information of both ligand and target to enhance the success of drug discovery projects. In this review, we analyze the main strategies and concepts that have emerged in the last years for defining hybrid LB + SB computational schemes in VS studies. Particularly, attention is focused on the combination of molecular similarity and docking, illustrating them with selected applications taken from the literature.
26 January 2016 in Journal of Computational Chemistry
Ligand-based virtual screening (LBVS) methods are widely used to explore the vast chemical space in the search of novel compounds resorting to a variety of properties encoded in 1D, 2D or 3D descriptors. The success of 3D-LBVS is affected by the overlay of molecular pairs, thus making selection of the template compound, search of accessible conformational space and choice of the query conformation to be potential factors that modulate the successful retrieval of actives. This study examines the impact of adopting different choices for the query conformation of the template, paying also attention to the influence exerted by the structural similarity between templates and actives. The analysis is performed using PharmScreen, a 3D LBVS tool that relies on similarity measurements of the hydrophobic/philic pattern of molecules, and Phase Shape, which is based on the alignment of atom triplets followed by refinement of the volume overlap. The study is performed for the original DUD-E+ database and a Morgan Fingerprint filtered version (denoted DUD-E+-Diverse; available in https://github.com/Pharmacelera/Query-models-to-3DLBVS), which was prepared to minimize the 2D resemblance between template and actives. Although in most cases the query conformation exhibits a mild influence on the overall performance, a critical analysis is made to disclose factors, such as the content of structural features between template and actives and the induction of conformational strain in the template, that underlie the drastic impact of the query definition in the recovery of actives for certain targets. The findings of this research also provide valuable guidance for assisting the selection of the query definition in 3D LBVS campaigns. Graphical Abstract
28 April 2025 in Journal of Chemical Information and Modeling
The rapid expansion of ultralarge chemical libraries has revolutionized drug discovery, providing access to billions of compounds. However, this growth poses relevant challenges for traditional virtual screening (VS) methods. To address these limitations, synthon-based approaches have emerged as scalable alternatives, exploiting combinatorial chemistry principles to prioritize building blocks over enumerated molecules. In this work, we present exaScreen and exaDock, two novel synthon-based methodologies designed for ligand-based and structure-based VS, respectively. In the former case, synthon selection is guided by the 3D hydrophobic/philic distribution pattern in conjunction with a specific synthon alignment protocol based on a quadrupolar expansion over the atoms that participate in the linking bonds between fragments. On the other hand, accommodation to the binding site under a geometrically restrained docking of synthon-based hybrid compounds is used in the selection of the optimal synthon combinations. These strategies exhibit comparable performance to the search performed using fully enumerated libraries in identifying active compounds with significantly lower computational cost, offering computationally efficient strategies for VS in ultralarge chemical spaces.
Aim: Solubility prediction is an essential factor in rational drug design and many models have been developed with machine learning (ML) methods to enhance the predictive ability. However, most of the ML models are hard to interpret which limits the insights they can give in the lead optimization process. Here, an approach to construct and interpret solubility models with a combination of physicochemical properties and ML algorithms is presented. Methods: The models were trained, optimized, and tested in a dataset containing 12,983 compounds from two public datasets and further evaluated in two external test sets. More importantly, the SHapley Additive exPlanations (SHAP) and heat map coloring approaches were used to explain the predictive models and assess their suitability to guide compound optimization. Results: Among the different ML methods, random forest (RF) models obtain the best performance in the different test sets. From the interpretability perspective, fragment-based coloring offers a more robust interpretation than atom-based coloring and that normalizing the values further improves it. Conclusions: Overall, for certain applications simple ML algorithms such as RF work well and can outperform more complex methods and that combining them with fragment-coloring can offer guidance for chemists to modify the structure with a desired property. This interpretation strategy is publicly available at https://github.com/Pharmacelera/predictive-model-coloring and could be further applied in other property predictions to improve the interpretability of ML models.
Elucidating the correct binding mode of drug-like compounds is crucial to disclose the molecular determinants that underline the recognition by the target protein and estimate the binding affinity, thus guiding the ensuing hit-to-lead optimization. However, the choice of the near-native binding pose in docking experiments remains a major hurdle. Assuming that the hydropathic complementarity principle is the major driving force in ligand-protein recognition, the suitability of simple hydropathicity-based scoring functions to reveal the near-native pose was examined. A benchmarking dataset of 1000 ligand-protein complexes purposely designed to encompass bioactive and decoy poses was used to assess the performance of 3D hydropathicity atomic descriptors derived from empirical and quantum mechanical models. This strategy led to a predictive accuracy of ca. 90% when the non-negligible influence of the conformational stress is also considered. The results reveal the need to leverage nonpolar/polar chemical features for the successful discrimination of the near-native pose.