RESUMO
Proteins often have both orthosteric and allosteric binding sites. Endogenous ligands, such as hormones and neurotransmitters, bind to the orthosteric site, while synthetic ligands may bind to orthosteric or allosteric sites, which has become a focal point in drug discovery. Usually, such allosteric modulators bind to a protein noncompetitively with its endogenous ligand or substrate. The growing interest in allosteric modulators has resulted in a substantial increase of these entities and their features such as binding data in chemical libraries and databases. Although this data surge fuels research focused on allosteric modulators, binding data is unfortunately not always clearly indicated as being allosteric or orthosteric. Therefore, allosteric binding data is difficult to retrieve from databases that contain a mixture of allosteric and orthosteric compounds. This decreases model performance when statistical methods, such as machine learning models, are applied. In previous work we generated an allosteric data subset of ChEMBL release 14. In the current study an improved text mining approach is used to retrieve the allosteric and orthosteric binding types from the literature in ChEMBL release 22. Moreover, convolutional deep neural networks were constructed to predict the binding types of compounds for class A G protein-coupled receptors (GPCRs). Temporal split validation showed the model predictiveness with Matthews correlation coefficient (MCC) = 0.54, sensitivity allosteric = 0.54, and sensitivity orthosteric = 0.94. Finally, this study shows that the inclusion of accurate binding types increases binding predictions by including them as descriptor (MCC = 0.27 improved to MCC = 0.34; validated for class A GPCRs, trained on all GPCRs). Although the focus of this study is mainly on class A GPCRs, binding types for all protein classes in ChEMBL were obtained and explored. The data set is included as a supplement to this study, allowing the reader to select the compounds and binding types of interest.
Assuntos
Descoberta de Drogas , Receptores Acoplados a Proteínas G , Regulação Alostérica , Sítio Alostérico , LigantesRESUMO
Predicting the effect of single-point mutations on protein stability or protein-ligand binding is a major challenge in computational biology. Free energy calculations constitute the most rigorous approach to this problem, though the estimation of converged values for amino acid mutations remains challenging. To overcome this limitation, we developed tailored protocols to calculate free energy shifts associated with single-point mutations. We herein describe the QresFEP protocol, which includes an extension of our recent protocols to cover all amino acids mutations, based on the latest versions of the OPLS-AA force field. QresFEP is implemented in an application programming interface framework and the graphic interface QGui, for the molecular dynamics software Q. The complete protocol is benchmarked in several model systems, optimizing a number of sampling parameters and the implementation of Zwanzig's exponential formula and Bennet's acceptance ratio methods. QresFEP shows an excellent performance on estimating the hydration free energies of amino acid side-chain mimics, including their charged analogues. We also examined its performance on a protein-ligand binding problem of pharmaceutical relevance, the antagonism of neuropeptide Y1 G protein-coupled receptor. Here, the calculations show very good agreement with the experimental effect of 16 mutations on the binding of antagonists BIBP3226, in line with our recent applications in this field. Finally, the characterization of 43 mutations of T4-lysozyme reveals the capacity of our protocol to assess variations of the thermal stability of proteins, achieving a similar performance to alternative free energy perturbation (FEP) approaches. In summary, QresFEP is a robust, versatile, and user-friendly computational FEP protocol to examine biochemical effects of single-point mutations with high accuracy.