Search

Abstract Even though in silico drug ligand-based methods have been successful in predicting interactions with known target proteins, they struggle with new, unassessed targets. To address this challenge, we propose an approach that integrates structural data from AlphaFold 2 predicted protein structures into machine learning models. Our method extracts 3D structural protein fingerprints and combines them with ligand structural data to train a single machine learning model. This model captures the relationship between ligand properties and the unique structural features of various target proteins, enabling predictions for never before tested molecules and protein targets. To assess our model, we used a dataset of 144 Human G-protein Coupled Receptors (GPCRs) with over 140,000 measured inhibition constants (Ki) values. Results strongly suggest that our approach performs as well as state-of-the-art ligand-based methods. In a second modeling approach that used 129 targets for training and a separate test set of 15 different protein targets, our model correctly predicted interactions for 73% of targets, with explained variances exceeding 0.50 in 22% of cases. Our findings further verified that the usage of experimentally determined protein structures produced models that were statistically indistinct from the Alphafold synthetic structures. This study presents a proteo-chemometric drug screening approach that uses a simple and scalable method for extracting protein structural information for usage in machine learning models capable of predicting protein-molecule interactions even for orphan targets.

Acquired resistance to drugs that modulate specific protein functions, such as the human proteasome, presents a significant challenge in targeted therapies. This underscores the importance of devising new methodologies to predict drug binding and potential resistance due to specific protein mutations. In this work, we conducted an extensive computational analysis to ascertain the effects of selected mutations (Ala49Thr, Ala50Val, and Cys52Phe) within the active site of the human proteasome. Specifically, we sought to understand how these mutations might disrupt protein function either by altering protein stability or by impeding interactions with a clinical administered drug. Leveraging molecular dynamics simulations and molecular docking calculations, we assessed the effect of these mutations on protein stability and ligand affinity. Notably, our results indicate that the Cys52Phe mutation critically impacts protein-ligand binding, providing valuable insights into potential proteasome inhibitor resistance.

Tuberculosis (TB) continues to be a major global health challenge and a leading cause of death from infectious diseases. Inspired by the results from a previous work by our group on antimycobacterial N-alkylnitrobenzamides, which are structurally related to the nitrobenzamide family of decaprenylphosphoryl-β-d-ribose oxidase (DprE1) inhibitors, the present study explored a broad array of substituted benzamides. We particularly focused on previously unexplored 3,5-dinitrobenzamide derivatives. Starting with 3,5-dinitrobenzoic acid, we synthesized a diverse library of amides, incorporating both linear and cyclic amine moieties and also assessed the impact of terminal aromatic groups connected through ether, ester, or amide bonds on the bioactivity of the compounds. The synthesis primarily utilized nucleophilic addition/elimination, SN2, and Mitsunobu reactions. The activity was impacted mainly by two structural features, the addition of an aromatic moiety as a terminal group and the type of linker. The most interesting compounds (c2, d1, and d2, MIC = 0.031 μg/mL) exhibited activities against Mycobacterium Tuberculosis (Mtb) H37Rv comparable to isoniazid. Complementary computational studies helped elucidate potential interactions with DprE1, enhancing our understanding of the molecular basis of their action. Our findings suggest that the most active compounds provide a promising foundation for the continued development of new antimycobacterial agents.