RESUMO
Protein-DNA interactions are pivotal to various cellular processes. Precise identification of the hotspot residues for protein-DNA interactions holds great significance for revealing the intricate mechanisms in protein-DNA recognition and for providing essential guidance for protein engineering. Aiming at protein-DNA interaction hotspots, this work introduces an effective prediction method, ESPDHot based on a stacked ensemble machine learning framework. Here, the interface residue whose mutation leads to a binding free energy change (ΔΔG) exceeding 2 kcal/mol is defined as a hotspot. To tackle the imbalanced data set issue, the adaptive synthetic sampling (ADASYN), an oversampling technique, is adopted to synthetically generate new minority samples, thereby rectifying data imbalance. As for molecular characteristics, besides traditional features, we introduce three new characteristic types including residue interface preference proposed by us, residue fluctuation dynamics characteristics, and coevolutionary features. Combining the Boruta method with our previously developed Random Grouping strategy, we obtained an optimal set of features. Finally, a stacking classifier is constructed to output prediction results, which integrates three classical predictors, Support Vector Machine (SVM), XGBoost, and Artificial Neural Network (ANN) as the first layer, and Logistic Regression (LR) algorithm as the second one. Notably, ESPDHot outperforms the current state-of-the-art predictors, achieving superior performance on the independent test data set, with F1, MCC, and AUC reaching 0.571, 0.516, and 0.870, respectively.
Assuntos
DNA , Aprendizado de Máquina , DNA/química , DNA/metabolismo , Ligação Proteica , Redes Neurais de Computação , Proteínas/química , Proteínas/metabolismo , Termodinâmica , Proteínas de Ligação a DNA/metabolismo , Proteínas de Ligação a DNA/química , Máquina de Vetores de Suporte , AlgoritmosRESUMO
Allostery is one of the most direct and efficient ways to regulate protein functions. The diverse allosteric sites make it possible to design allosteric modulators of differential selectivity and improved safety compared with those of orthosteric drugs targeting conserved orthosteric sites. Here, we develop an ensemble machine learning method AllosES to predict protein allosteric sites in which the new and effective features are utilized, including the entropy transfer-based dynamic property, secondary structure features, and our previously proposed spatial neighbor-based evolutionary information besides the traditional physicochemical properties. To overcome the class imbalance problem, the multiple grouping strategy is proposed, which is applied to feature selection and model construction. The ensemble model is constructed where multiple submodels are trained on multiple training subsets, respectively, and their results are then integrated to be the final output. AllosES achieves a prediction performance of 0.556 MCC on the independent test set D24, and additionally, AllosES can rank the real allosteric sites in the top three for 83.3/89.3% of allosteric proteins from the test set D24/D28, outperforming the state-of-the-art peer methods. The comprehensive results demonstrate that AllosES is a promising method for protein allosteric site prediction. The source code is available at https://github.com/ChunhuaLab/AllosES.
Assuntos
Sítio Alostérico , Entropia , Proteínas , Proteínas/química , Proteínas/metabolismo , Aprendizado de Máquina , Modelos MolecularesRESUMO
Within over 800 members of G-protein-coupled receptors, there are numerous orphan receptors whose endogenous ligands are largely unknown, providing many opportunities for novel drug discovery. However, the lack of an in-depth understanding of the intrinsic working mechanism for orphan receptors severely limits the related rational drug design. The G-protein-coupled receptor 52 (GPR52) is a unique orphan receptor that constitutively increases cellular 5'-cyclic adenosine monophosphate (cAMP) levels without binding any exogenous agonists and has been identified as a promising therapeutic target for central nervous system disorders. Although recent structural biology studies have provided snapshots of both active and inactive states of GPR52, the mechanism of the conformational transition between these states remains unclear. Here, an acceptable self-activation pathway for GPR52 was proposed through 6 µs Gaussian accelerated molecular dynamics (GaMD) simulations, in which the receptor spontaneously transitions from the active state to that matching the inactive crystal structure. According to the three intermediate states of the receptor obtained by constructing a reweighted potential of mean force, how the allosteric regulation occurs between the extracellular orthosteric binding pocket and the intracellular G-protein-binding site is revealed. Combined with the independent gradient model, several important microswitch residues and the allosteric communication pathway that directly links the two regions are both identified. Transfer entropy calculations not only reveal the complex allosteric signaling within GPR52 but also confirm the unique role of ECL2 in allosteric regulation, which is mutually validated with the results of GaMD simulations. Overall, this work elucidates the allosteric mechanism of GPR52 at the atomic level, providing the most detailed information to date on the self-activation of the orphan receptor.