Molecular docking computationally predicts the conformation of a small molecule when binding to a receptor. Scoring functions are a vital piece of any molecular docking pipeline as they determine the fitness of sampled poses. Here we describe and evaluate the 1.0 release of the Gnina docking software, which utilizes an ensemble of convolutional neural networks (CNNs) as a scoring function. We also explore an array of parameter values for Gnina 1.0 to optimize docking performance and computational cost. Docking performance, as evaluated by the percentage of targets where the top pose is better than 2Å root mean square deviation (Top1), is compared to AutoDock Vina scoring when utilizing explicitly defined binding pockets or whole protein docking. Gnina, utilizing a CNN scoring function to rescore the output poses, outperforms AutoDock Vina scoring on redocking and cross-docking tasks when the binding pocket is defined (Top1 increases from 58% to 73% and from 27% to 37%, respectively) and when the whole protein defines the binding pocket (Top1 increases from 31% to 38% and from 12% to 16%, respectively). The derived ensemble of CNNs generalizes to unseen proteins and ligands and produces scores that correlate well with the root mean square deviation to the known binding pose. We provide the 1.0 version of Gnina under an open source license for use as a molecular docking tool at https://github.com/gnina/gnina .

中文翻译：

---

GNINA 1.0：与深度学习的分子对接


分子对接通过计算预测小分子与受体结合时的构象。评分函数是任何分子对接流程的重要组成部分，因为它们确定采样姿势的适合度。在这里，我们描述和评估 Gnina 对接软件 1.0 版本，该软件利用卷积神经网络 (CNN) 集合作为评分函数。我们还探索了 Gnina 1.0 的一系列参数值，以优化对接性能和计算成本。对接性能（通过顶部姿势优于 2Å 均方根偏差 (Top1) 的目标百分比来评估）与使用明确定义的结合袋或整个蛋白质对接时的 AutoDock Vina 评分进行比较。当定义绑定口袋时，Gnina 利用 CNN 评分函数对输出姿势重新评分，在重新对接和交叉对接任务上的表现优于 AutoDock Vina 评分（Top1 分别从 58% 增加到 73% 和从 27% 增加到 37%）当整个蛋白质定义结合口袋时（Top1 分别从 31% 增加到 38% 和从 12% 增加到 16%）。衍生的 CNN 整体可推广到看不见的蛋白质和配体，并产生与已知结合姿势的均方根偏差良好相关的分数。我们在开源许可下提供 1.0 版本的 Gnina，用作分子对接工具，网址为 https://github.com/gnina/gnina。