Simulating protein-ligand binding with neural network potentials.
Simulating protein-ligand binding with neural network potentials.
复制标题
DOI：
10.1039/c9sc06017k
复制
发表时间：
2020-01-23
期刊：
影响因子：
8.4
通讯作者：
Rowley CN
中科院分区：
文献类型：
--
作者：
Lahey SJ;Rowley CN
药物分子在溶液和蛋白质结合状态下都具有一系列构象。结合药物的应变和降低的灵活性可以部分抵消驱动蛋白质-配体结合的分子间相互作用。为了准确的计算预测药物结合亲和力，计算化学家试图开发有效的经验模型，这些相互作用，虽然这些方法并不总是可靠的。机器学习允许开发高准确度的神经网络势（NNPs），它能够预测分子构象的稳定性，其准确度与最先进的量子化学计算相当，但计算成本仅为十亿分之一。在这里，我们证明，这些方法可以用来代表分子动力学模拟内的蛋白质结合药物的分子内力。这些模拟被证明是能够预测的蛋白质-配体结合的姿势和构象组件的绝对吉布斯能结合一组药物分子。值得注意的是，抗癌药物厄洛替尼与其靶标结合的构象能被分子力学模型大大高估，而NNP预测的值更适中。虽然ANI-1ccX NNP没有被训练来描述离子分子，但预测了带电配体的合理结合位姿，但这种方法不适合模拟溶液中的带电配体。神经网络电位提供了药物分子结构和稳定性的准确预测。我们提出了一种方法，使用这些新的潜力，在模拟药物结合蛋白质，使用现有的分子模拟代码。
Drug molecules adopt a range of conformations both in solution and in their protein-bound state. The strain and reduced flexibility of bound drugs can partially counter the intermolecular interactions that drive protein–ligand binding. To make accurate computational predictions of drug binding affinities, computational chemists have attempted to develop efficient empirical models of these interactions, although these methods are not always reliable. Machine learning has allowed the development of highly-accurate neural-network potentials (NNPs), which are capable of predicting the stability of molecular conformations with accuracy comparable to state-of-the-art quantum chemical calculations but at a billionth of the computational cost. Here, we demonstrate that these methods can be used to represent the intramolecular forces of protein-bound drugs within molecular dynamics simulations. These simulations are shown to be capable of predicting the protein–ligand binding pose and conformational component of the absolute Gibbs energy of binding for a set of drug molecules. Notably, the conformational energy for anti-cancer drug erlotinib binding to its target was found to be considerably overestimated by a molecular mechanical model, while the NNP predicts a more moderate value. Although the ANI-1ccX NNP was not trained to describe ionic molecules, reasonable binding poses are predicted for charged ligands, but this method is not suitable for modeling charged ligands in solution. Neural network potentials provide accurate predictions of the structures and stabilities of drug molecules. We present a method to use these new potentials in simulations of drugs binding to proteins using existing molecular simulation codes.
登录
查看更多内容
影响因子：
14.9
作者：
Dodda LS;Cabeza de Vaca I;Tirado-Rives J;Jorgensen WL
通讯作者：
Jorgensen WL
影响因子：
3
作者：
Mayne, Christopher G.;Saam, Jan;Schulten, Klaus;Tajkhorshid, Emad;Gumbart, James C.
通讯作者：
Gumbart, James C.
影响因子：
8.6
作者：
Behler, Joerg;Parrinello, Michele
通讯作者：
Parrinello, Michele
影响因子：
4.4
作者：
JORGENSEN, WL;CHANDRASEKHAR, J;KLEIN, ML
通讯作者：
KLEIN, ML
影响因子：
5.5
作者：
Mobley, David L.;Chodera, John D.;Dill, Ken A.
通讯作者：
Dill, Ken A.