Department of Organic Chemistry, Faculty of Pharmacy, University of Santiago de Compostela 15782, Spain.
Eur J Med Chem. 2011 Dec;46(12):5838-51. doi: 10.1016/j.ejmech.2011.09.045. Epub 2011 Oct 1.
There are many pairs of possible Drug-Proteins Interactions that may take place or not (DPIs/nDPIs) between drugs with high affinity/non-affinity for different proteins. This fact makes expensive in terms of time and resources, for instance, the determination of all possible ligands-protein interactions for a single drug. In this sense, we can use Quantitative Structure-Activity Relationships (QSAR) models to carry out rational DPIs prediction. Unfortunately, almost all QSAR models predict activity against only one target. To solve this problem we can develop multi-target QSAR (mt-QSAR) models. In this work, we introduce the technique 2D MI-DRAGON a new predictor for DPIs based on two different well-known software. We use the software MARCH-INSIDE (MI) to calculate 3D structural parameters for targets and the software DRAGON was used to calculated 2D molecular descriptors all drugs showing known DPIs present in the Drug Bank (US FDA benchmark dataset). Both classes of parameters were used as input of different Artificial Neural Network (ANN) algorithms to seek an accurate non-linear mt-QSAR predictor. The best ANN model found is a Multi-Layer Perceptron (MLP) with profile MLP 21:21-31-1:1. This MLP classifies correctly 303 out of 339 DPIs (Sensitivity = 89.38%) and 480 out of 510 nDPIs (Specificity = 94.12%), corresponding to training Accuracy = 92.23%. The validation of the model was carried out by means of external predicting series with Sensitivity = 92.18% (625/678 DPIs; Specificity = 90.12% (730/780 nDPIs) and Accuracy = 91.06%. 2D MI-DRAGON offers a good opportunity for fast-track calculation of all possible DPIs of one drug enabling us to re-construct large drug-target or DPIs Complex Networks (CNs). For instance, we reconstructed the CN of the US FDA benchmark dataset with 855 nodes 519 drugs+336 targets). We predicted CN with similar topology (observed and predicted values of average distance are equal to 6.7 vs. 6.6). These CNs can be used to explore large DPIs databases in order to discover both new drugs and/or targets. Finally, we illustrated in one theoretic-experimental study the practical use of 2D MI-DRAGON. We reported the prediction, synthesis, and pharmacological assay of 10 different oxoisoaporphines with MAO-A inhibitory activity. The more active compound OXO5 presented IC(50) = 0.00083 μM, notably better than the control drug Clorgyline.
有许多对可能的药物-蛋白质相互作用（DPIs/nDPIs），这些相互作用可能发生在具有不同蛋白质高亲和力/非亲和力的药物之间。这一事实在时间和资源方面都非常昂贵，例如，确定单个药物的所有可能配体-蛋白质相互作用。在这种情况下，我们可以使用定量构效关系（QSAR）模型来进行合理的 DPIs 预测。不幸的是，几乎所有的 QSAR 模型都只能预测针对单一靶标的活性。为了解决这个问题，我们可以开发多靶标 QSAR（mt-QSAR）模型。在这项工作中，我们引入了一种新的基于两种不同知名软件的 DPIs 预测方法 2D MI-DRAGON。我们使用软件 MARCH-INSIDE（MI）来计算靶标 3D 结构参数，使用软件 DRAGON 来计算所有具有已知 DPIs 的药物的 2D 分子描述符，这些药物都存在于 Drug Bank（美国 FDA 基准数据集）中。这两类参数都被用作不同人工神经网络（ANN）算法的输入，以寻找准确的非线性 mt-QSAR 预测器。找到的最佳 ANN 模型是一个多层感知器（MLP），具有配置文件 MLP 21:21-31-1:1。这个 MLP 正确分类了 339 个 DPIs 中的 303 个（敏感性=89.38%）和 510 个 nDPIs 中的 480 个（特异性=94.12%），对应于训练准确性=92.23%。通过使用外部预测系列进行模型验证，得到了敏感性=92.18%（678 个 DPIs）、特异性=90.12%（780 个 nDPIs）和准确性=91.06%。2D MI-DRAGON 为快速计算一种药物的所有可能 DPIs 提供了一个很好的机会，使我们能够重新构建大型药物-靶标或 DPIs 复杂网络（CNs）。例如，我们用 855 个节点（519 种药物+336 个靶标）重建了美国 FDA 基准数据集的 CN。我们预测的 CN 具有相似的拓扑结构（观察到和预测的平均距离值相等，均为 6.7 比 6.6）。这些 CN 可用于探索大型 DPIs 数据库，以发现新的药物和/或靶标。最后，我们在一个理论-实验研究中说明了 2D MI-DRAGON 的实际用途。我们报告了 10 种不同的 MAO-A 抑制活性的氧化异阿朴啡的预测、合成和药理测定。活性较高的化合物 OXO5 呈现出 IC（50）=0.00083 μM，明显优于对照药物氯丙嗪。
