Application of activity cliffs to virtual screening for identify lactate dehydrogenase inhibitors using machine learning approaches

Activity Cliffs (ACs) are groups of structurally identical active chemicals with significant potency variances.Since ACs are so common in SAR data, it's crucial for modern computer-aided drug design and discovery tobe able to deal with them effectively. ACs, on the other hand, pose considerable challenges for bioactivitysuperviseddiscovery approaches that presume smooth and continuous structure-activity connections. Manyligand-based approaches have high-performance predictions, indicating that the hypothesis is correct.However, there are certain limitations. They are unable to explain the activity cliff , and their results for newcompounds are suboptimal. The ACs verified to yield pharmacophore and machine learning models that wereequivalent to known ligand- and structure-based pharmacophores in terms of accuracy. We applied the ACsto investigate the protein Lactate dehydrogenase which has a high-resolution crystallographic structure anda number of known inhibitors. The number of ACs was determined in each protein's inhibitor population.The missing edges (e.g. unknown interactions) are predicted using various kinds of Machine Learningmodels. Then, we have searched a large number of machine learners (MLs) to see if we could link proteinfeatures to the existence or absence of ACs in the ligand population. Therefore, by identifying ACs that hadnot been previously considered, the presence of different atomic shares and the differential effects of powerassociated with ACs formation are determined, which indicated the occurrence of unknown interactions.Finally, using the information deriving from the activity cliff analysis to suggest how virtual screeningprotocols might be improved to favor the early identification of potent and selective lactate dehydrogenaseinhibitors in molecular databases.

کلیدواژه ها:

Activity Cliffs ، Machine Learning ، Lactate dehydrogenase ، virtual screening