Exploring QSAR models for activity-cliff prediction.

INTRODUCTION AND METHODOLOGY: Pairs of similar compounds that only differ by a small structural modification but exhibit a large difference in their binding affinity for a given target are known as activity cliffs (ACs). It has been hypothesised that QSAR models struggle to predict ACs and that ACs thus form a major source of prediction error. However, the AC-prediction power of modern QSAR methods and its quantitative relationship to general QSAR-prediction performance is still underexplored. We systematically construct nine distinct QSAR models by combining three molecular representation methods (extended-connectivity fingerprints, physicochemical-descriptor vectors and graph isomorphism networks) with three regression techniques (random forests, k-nearest neighbours and multilayer perceptrons); we then use each resulting model to classify pairs of similar compounds as ACs or non-ACs and to predict the activities of individual molecules in three case studies: dopamine receptor D2, factor Xa, and SARS-CoV-2 main protease. RESULTS AND CONCLUSIONS: Our results provide strong support for the hypothesis that indeed QSAR models frequently fail to predict ACs. We observe low AC-sensitivity amongst the evaluated models when the activities of both compounds are unknown, but a substantial increase in AC-sensitivity when the actual activity of one of the compounds is given. Graph isomorphism features are found to be competitive with or superior to classical molecular representations for AC-classification and can thus be employed as baseline AC-prediction models or simple compound-optimisation tools. For general QSAR-prediction, however, extended-connectivity fingerprints still consistently deliver the best performance amongs the tested input representations. A potential future pathway to improve QSAR-modelling performance might be the development of techniques to increase AC-sensitivity.

Coumarin-based combined computational study to design novel drugs against Candida albicans.

Candida species cause the most prevalent fungal illness, candidiasis. Candida albicans is known to cause bloodstream infections. This species is a commensal bacterium, but it can cause hospital-acquired diseases, particularly in COVID-19 patients with impaired immune systems. Candida infections have increased in patients with acute respiratory distress syndrome. Coumarins are both naturally occurring and synthetically produced. In this study, the biological activity of 40 coumarin derivatives was used to create a three-dimensional quantitative structure activity relationship (3D-QSAR) model. The training and test minimum inhibitory concentration values of C. albicans active compounds were split, and a regression model based on statistical data was established. This model served as a foundation for the creation of coumarin derivative QSARs. This is a unique way to create new therapeutic compounds for various ailments. We constructed novel structural coumarin derivatives using the derived QSAR model, and the models were confirmed using molecular docking and molecular dynamics simulation.