Accurately estimating protein–ligand binding free energy is crucial for drug design and biophysics, yet remains a challenging task. In this study, we applied the screening molecular mechanics/Poisson–Boltzmann surfa...Accurately estimating protein–ligand binding free energy is crucial for drug design and biophysics, yet remains a challenging task. In this study, we applied the screening molecular mechanics/Poisson–Boltzmann surface area(MM/PBSA)method in combination with various machine learning techniques to compute the binding free energies of protein–ligand interactions. Our results demonstrate that machine learning outperforms direct screening MM/PBSA calculations in predicting protein–ligand binding free energies. Notably, the random forest(RF) method exhibited the best predictive performance,with a Pearson correlation coefficient(rp) of 0.702 and a mean absolute error(MAE) of 1.379 kcal/mol. Furthermore, we analyzed feature importance rankings in the gradient boosting(GB), adaptive boosting(Ada Boost), and RF methods, and found that feature selection significantly impacted predictive performance. In particular, molecular weight(MW) and van der Waals(VDW) energies played a decisive role in the prediction. Overall, this study highlights the potential of combining machine learning methods with screening MM/PBSA for accurately predicting binding free energies in biosystems.展开更多
The molecular mechanics/Poisson-Boltzmann surface area(MM/PBSA) method has been widely used in predicting the binding affinity among ligands,proteins,and nucleic acids.However,the accuracy of the predicted binding ene...The molecular mechanics/Poisson-Boltzmann surface area(MM/PBSA) method has been widely used in predicting the binding affinity among ligands,proteins,and nucleic acids.However,the accuracy of the predicted binding energy by the standard MM/PBSA is not always good,especially in highly charged systems.In this work,we take the protein-nucleic acid complexes as an example,and showed that the use of screening electrostatic energy(instead of Coulomb electrostatic energy) in molecular mechanics can greatly improve the performance of MM/PBSA.In particular,the Pearson correlation coefficient of dataset Ⅱ in the modified MM/PBSA(i.e.,screening MM/PBSA) is about 0.52,much better than that(<0.33)in the standard MM/PBSA.Further,we also evaluate the effect of solute dielectric constant and salt concentration on the performance of the screening MM/PBSA.The present study highlights the potential power of the screening MM/PBSA for predicting the binding energy in highly charged bio-systems.展开更多
基金Project supported by the National Natural Science Foundation of China (Grant Nos. 12222506, 12347102, 12447164, and 12174184)。
文摘Accurately estimating protein–ligand binding free energy is crucial for drug design and biophysics, yet remains a challenging task. In this study, we applied the screening molecular mechanics/Poisson–Boltzmann surface area(MM/PBSA)method in combination with various machine learning techniques to compute the binding free energies of protein–ligand interactions. Our results demonstrate that machine learning outperforms direct screening MM/PBSA calculations in predicting protein–ligand binding free energies. Notably, the random forest(RF) method exhibited the best predictive performance,with a Pearson correlation coefficient(rp) of 0.702 and a mean absolute error(MAE) of 1.379 kcal/mol. Furthermore, we analyzed feature importance rankings in the gradient boosting(GB), adaptive boosting(Ada Boost), and RF methods, and found that feature selection significantly impacted predictive performance. In particular, molecular weight(MW) and van der Waals(VDW) energies played a decisive role in the prediction. Overall, this study highlights the potential of combining machine learning methods with screening MM/PBSA for accurately predicting binding free energies in biosystems.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11874045 and 11774147)。
文摘The molecular mechanics/Poisson-Boltzmann surface area(MM/PBSA) method has been widely used in predicting the binding affinity among ligands,proteins,and nucleic acids.However,the accuracy of the predicted binding energy by the standard MM/PBSA is not always good,especially in highly charged systems.In this work,we take the protein-nucleic acid complexes as an example,and showed that the use of screening electrostatic energy(instead of Coulomb electrostatic energy) in molecular mechanics can greatly improve the performance of MM/PBSA.In particular,the Pearson correlation coefficient of dataset Ⅱ in the modified MM/PBSA(i.e.,screening MM/PBSA) is about 0.52,much better than that(<0.33)in the standard MM/PBSA.Further,we also evaluate the effect of solute dielectric constant and salt concentration on the performance of the screening MM/PBSA.The present study highlights the potential power of the screening MM/PBSA for predicting the binding energy in highly charged bio-systems.
文摘细胞色素P450(以下简称CYP)与昆虫的抗药性密切相关。本研究运用Auto Dock分子对接技术和分子力学泊松-波尔兹曼表面积法(molecular mechanics Poisson-Boltzmann surface area,MM-PBSA)结合自由能计算方法,分析了甜菜夜蛾CYP9A11与3种杀虫剂结合的作用位点、作用力类型和大小。结果表明:CYP9A11与毒死蜱结合形成两个氢键,有8个氨基酸残基参与形成疏水作用力,二者结合自由能为–3 659.80 k J/mol;CYP9A11与灭多威结合形成5个氢键,有3个氨基酸残基形成疏水作用力,结合自由能为–470.92 k J/mol;CYP9A11中有7个氨基酸残基与氯氰菊酯结合形成疏水作用力,结合自由能为–473.44 k J/mol。范德华力是CYP9A11与毒死蜱结合的主要驱动力,极性溶剂化能是CYP9A11与氯氰菊酯和灭多威结合的主要驱动力,这些结果为阐明甜菜夜蛾CYP9A11与3种杀虫剂的结合机理提供了参考。
