Background: Computational methods support nowadays each stage of drug design campaigns. They assist not only in the process of identification of new active compounds towards particular biological target, but also help in the evaluation and optimization of their physicochemical and pharmacokinetic properties. Such features are not less important in terms of the possible turn of a compound into a future drug than its desired affinity profile towards considered proteins. In the study, we focus on metabolic stability, which determines the time that the compound can act in the organism and play its role as a drug. Due to great complexity of xenobiotic transformation pathways in the living organisms, evaluation and optimization of metabolic stability remains a big challenge. Results: Here, we present a novel methodology for the evaluation and analysis of structural features influencing metabolic stability. To this end, we use a well-established explainability method called SHAP. We built several predictive models and analyse their predictions with the SHAP values to reveal how particular compound substructures influence the model’s prediction. The method can be widely applied by users thanks to the web service, which accompanies the article. It allows a detailed analysis of SHAP values obtained for compounds from the ChEMBL database, as well as their determination and analysis for any compound submitted by a user. Moreover, the service enables manual analysis of the possible structural modifications via the provision of analogous analysis for the most similar compound from the ChEMBL dataset. Conclusions: To our knowledge, this is the first attempt to employ SHAP to reveal which substructural features are utilized by machine learning models when evaluating compound metabolic stability. The accompanying web service for metabolic stability evaluation can be of great help for medicinal chemists. Its significant usefulness is related not only to the possibility of assessing compound stability, but also to the provision of information about substructures influencing this parameter. It can assist in the design of new ligands with improved metabolic stability, helping in the detection of privileged and unfavourable chemical moieties during stability optimization. The tool is available at https://metstab-shap.matinf.uj.edu.pl/.

Support Vector Machine has become one of the most popular machine learning tools used in virtual screening campaigns aimed at finding new drug candidates. Although it can be extremely effective in finding new potentially active compounds, its application requires the optimization of the hyperparameters with which the assessment is being run, particularly the C and $$\gamma$$ values. The optimization requirement in turn, establishes the need to develop fast and effective approaches to the optimization procedure, providing the best predictive power of the constructed model. In this study, we investigated the Bayesian and random search optimization of Support Vector Machine hyperparameters for classifying bioactive compounds. The effectiveness of these strategies was compared with the most popular optimization procedures—grid search and heuristic choice. We demonstrated that Bayesian optimization not only provides better, more efficient classification but is also much faster—the number of iterations it required for reaching optimal predictive performance was the lowest out of the all tested optimization methods. Moreover, for the Bayesian approach, the choice of parameters in subsequent iterations is directed and justified; therefore, the results obtained by using it are constantly improved and the range of hyperparameters tested provides the best overall performance of Support Vector Machine. Additionally, we showed that a random search optimization of hyperparameters leads to significantly better performance than grid search and heuristic-based approaches. The Bayesian approach to the optimization of Support Vector Machine parameters was demonstrated to outperform other optimization methods for tasks concerned with the bioactivity assessment of chemical compounds. This strategy not only provides a higher accuracy of classification, but is also much faster and more directed than other approaches for optimization. It appears that, despite its simplicity, random search optimization strategy should be used as a second choice if Bayesian approach application is not feasible.

Metabolic stability is an important parameter to be optimized during the complex process of designing new active compounds. Tuning this parameter with the simultaneous maintenance of a desired compound’s activity is not an easy task due to the extreme complexity of metabolic pathways in living organisms. In this study, the platform for in silico qualitative evaluation of metabolic stability, expressed as half-lifetime and clearance was developed. The platform is based on the application of machine learning methods and separate models for human, rat and mouse data were constructed. The compounds’ evaluation is qualitative and two types of experiments can be performed—regression, which is when the compound is assigned to one of the metabolic stability classes (low, medium, high) on the basis of numerical value of the predicted half-lifetime, and classification, in which the molecule is directly assessed as low, medium or high stability. The results show that the models have good predictive power, with accuracy values over 0.7 for all cases, for Sequential Minimal Optimization (SMO), k-nearest neighbor (IBk) and Random Forest algorithms. Additionally, for each of the analyzed compounds, 10 of the most similar structures from the training set (in terms of Tanimoto metric similarity) are identified and made available for download as separate files for more detailed manual inspection. The predictive power of the models was confronted with the external dataset, containing metabolic stability assessment via the GUSAR software, leading to good consistency of results for SMOreg and Naïve Bayes (~0.8 on average). The tool is available online.

Designing compounds with desired properties is a key element of the drug discovery process. However, measuring progress in the field has been challenging due to the lack of realistic retrospective benchmarks, and the large cost of prospective validation. To close this gap, we propose a benchmark based on docking, a widely used computational method for assessing molecule binding to a protein. Concretely, the goal is to generate drug-like molecules that are scored highly by SMINA, a popular docking software. We observe that various graph-based generative models fail to propose molecules with a high docking score when trained using a realistically sized training set. This suggests a limitation of the current incarnation of models for de novo drug design. Finally, we also include simpler tasks in the benchmark based on a simpler scoring function. We release the benchmark as an easy to use package available at https://github.com/cieplinski-tobiasz/smina-docking-benchmark. We hope that our benchmark will serve as a stepping stone toward the goal of automatically generating promising drug candidates.

In an attempt to extend recent studies showing that some clinically evaluated histamine H₃ receptor (H₃R) antagonists possess nanomolar affinity at sigma-1 receptors (σ₁R), we selected 20 representative structures among our previously reported H₃R ligands to investigate their affinity at σRs. Most of the tested compounds interact with both sigma receptors to different degrees. However, only six of them showed higher affinity toward σ₁R than σ₂R with the highest binding preference to σ₁R for compounds 5, 11, and 12. Moreover, all these ligands share a common structural feature: the piperidine moiety as the fundamental part of the molecule. It is most likely a critical structural element for dual H₃/σ₁ receptor activity as can be seen by comparing the data for compounds 4 and 5 (hH₃R K_i = 3.17 and 7.70 nM, σ₁R K_i = 1531 and 3.64 nM, respectively), where piperidine is replaced by piperazine. We identified the putative protein–ligand interactions responsible for their high affinity using molecular modeling techniques and selected compounds 5 and 11 as lead structures for further evaluation. Interestingly, both ligands turned out to be high-affinity histamine H₃ and σ₁ receptor antagonists with negligible affinity at the other histamine receptor subtypes and promising antinociceptive activity in vivo. Considering that many literature data clearly indicate high preclinical efficacy of individual selective σ₁ or H₃R ligands in various pain models, our research might be a breakthrough in the search for novel, dual-acting compounds that can improve existing pain therapies. Determining whether such ligands are more effective than single-selective drugs will be the subject of our future studies.

Alzheimer's disease (AD) has a complex and not-fully-understood etiology. Recently, the serotonin receptor 5-HT₆ emerged as a promising target for AD treatment; thus, here a new series of 5-HT₆R ligands with a 1,3,5-triazine core and selenoether linkers was explored. Among them, the 2-naphthyl derivatives exhibited strong 5-HT₆R affinity and selectivity over 5-HT_1AR (13-15), 5-HT₇R (14 and 15), and 5-HT_2AR (13). Compound 15 displayed high selectivity for 5-HT₆R over other central nervous system receptors and exhibited low risk of cardio-, hepato-, and nephrotoxicity and no mutagenicity, indicating its "drug-like" potential. Compound 15 also demonstrated neuroprotection against rotenone-induced neurotoxicity as well as antioxidant and glutathione peroxidase (GPx)-like activity and regulated antioxidant and pro-inflammatory genes and NRF2 nuclear translocation. In rats, 15 showed satisfying pharmacokinetics, penetrated the blood-brain barrier, reversed MK-801-induced memory impairment, and exhibited anxiolytic-like properties. 15's neuroprotective and procognitive-like effects, stronger than those of the approved drug donepezil, may pave the way for the use of selenotriazines to inhibit both causes and symptoms in AD therapy.