Molecules with bioactivity towards G protein-coupled receptors represent a subset of the vast space of small drug-like molecules. Here, we compare machine learning models, including dilated graph convolutional networks, that conduct binary classification to quickly identify molecules with activity towards G protein-coupled receptors. The models are trained and validated using a large set of over 600,000 active, inactive, and decoy compounds. The best performing machine learning model, dubbed GPCRLigNet, was a surprisingly simple feedforward dense neural network mapping from Morgan fingerprints to activity. Incorporation of GPCRLigNet into a high-throughput virtual screening workflow is demonstrated with molecular docking towards a particular G protein-coupled receptor, the pituitary adenylate cyclase-activating polypeptide receptor type 1. Through rigorous comparison of docking scores for molecules selected with and without using GPCRLigNet, we demonstrate an enrichment of potentially potent molecules using GPCRLigNet. This work provides a proof of principle that GPCRLigNet can effectively hone the chemical search space towards ligands with G protein-coupled receptor activity.

对 G 蛋白偶联受体具有生物活性的分子代表了广阔的类药物小分子的一个子集。在这里，我们比较了机器学习模型，包括扩张图卷积网络，这些模型进行二元分类以快速识别对 G 蛋白偶联受体具有活性的分子。这些模型使用超过 600,000 种活性、非活性和诱饵化合物进行训练和验证。性能最好的机器学习模型被称为 GPCRLigNet，是一个令人惊讶的简单的前馈密集神经网络，从摩根指纹到活动的映射。通过针对特定 G 蛋白偶联受体（垂体腺苷酸环化酶激活多肽受体 1 型）的分子对接，证明了将 GPCRLigNet 纳入高通量虚拟筛选工作流程。通过严格比较使用和不使用 GPCRLigNet 选择的分子的对接分数，我们展示了使用 GPCRLigNet 富集潜在有效分子。这项工作提供了原理证明，证明 GPCRLigNet 可以有效地将化学搜索空间磨练为具有 G 蛋白偶联受体活性的配体。