Danneskiold-Samsøe Niels Banhos, Kavi Deniz, Jude Kevin M, Nissen Silas Boye, Wat Lianna W, Coassolo Laetitia, Zhao Meng, Santana-Oikawa Galia Asae, Broido Beatrice Blythe, Garcia K Christopher, Svensson Katrin J
Department of Pathology, Stanford University School of Medicine, Stanford, CA, USA.
Department of Biology, University of Copenhagen, Denmark.
bioRxiv. 2023 Dec 15:2023.03.16.531341. doi: 10.1101/2023.03.16.531341.
Secreted proteins play crucial roles in paracrine and endocrine signaling; however, identifying novel ligand-receptor interactions remains challenging. Here, we benchmarked AlphaFold as a screening approach to identify extracellular ligand-binding pairs using a structural library of single-pass transmembrane receptors. Key to the approach is the optimization of AlphaFold input and output for screening ligands against receptors to predict the most probable ligand-receptor interactions. Importantly, the predictions were performed on ligand-receptor pairs not used for AlphaFold training. We demonstrate high discriminatory power and a success rate of close to 90 % for known ligand-receptor pairs and 50 % for a diverse set of experimentally validated interactions. These results demonstrate proof-of-concept of a rapid and accurate screening platform to predict high-confidence cell-surface receptors for a diverse set of ligands by structural binding prediction, with potentially wide applicability for the understanding of cell-cell communication.
分泌蛋白在旁分泌和内分泌信号传导中发挥着关键作用；然而，识别新的配体-受体相互作用仍然具有挑战性。在这里，我们将AlphaFold作为一种筛选方法进行了基准测试，以使用单通道跨膜受体的结构库来识别细胞外配体-结合对。该方法的关键在于优化AlphaFold的输入和输出，以便针对受体筛选配体，从而预测最可能的配体-受体相互作用。重要的是，这些预测是针对未用于AlphaFold训练的配体-受体对进行的。我们证明，对于已知的配体-受体对，该方法具有很高的辨别力，成功率接近90%；对于一组经过实验验证的不同相互作用，成功率为50%。这些结果证明了一个快速准确的筛选平台的概念验证，该平台通过结构结合预测为各种配体预测高可信度的细胞表面受体，对理解细胞间通讯可能具有广泛的适用性。
