Predicting protein-small molecule binding sites, the initial step in structure-guided drug design, remains challenging for proteins lacking experimentally derived ligand-bound structures. Here, we propose CLAPE-SMB, which integrates a pre-trained protein language model with contrastive learning to provide high accuracy predictions of small molecule binding sites that can accommodate proteins without a published crystal structure. We trained and tested CLAPE-SMB on the SJC dataset, a non-redundant dataset based on sc-PDB, JOINED, and COACH420, and achieved an MCC of 0.529. We also compiled the UniProtSMB dataset, which merges sites from similar proteins based on raw data from UniProtKB database, and achieved an MCC of 0.699 on the test set. In addition, CLAPE-SMB achieved an MCC of 0.815 on our intrinsically disordered protein (IDP) dataset that contains 336 non-redundant sequences. Case studies of DAPK1, RebH, and Nep1 support the potential of this binding site prediction tool to aid in drug design. The code and datasets are freely available at https://github.com/JueWangTHU/CLAPE-SMB . CLAPE-SMB combines a pre-trained protein language model with contrastive learning to accurately predict protein-small molecule binding sites, especially for proteins without experimental structures, such as IDPs. Trained across various datasets, this model shows strong adaptability, making it a valuable tool for advancing drug design and understanding protein-small molecule interactions.

中文翻译：

---

基于对比学习的预训练蛋白质语言模型的蛋白质-小分子结合位点预测


预测蛋白质小分子结合位点是结构引导药物设计的第一步，对于缺乏实验衍生的配体结合结构的蛋白质来说仍然具有挑战性。在这里，我们提出了 CLAPE-SMB，它将预先训练的蛋白质语言模型与对比学习相结合，以提供对小分子结合位点的高精度预测，这些位点可以容纳没有已发表晶体结构的蛋白质。我们在 SJC 数据集上训练和测试了 CLAPE-SMB，这是一个基于 sc-PDB 、 JOINED 和 COACH420 的非冗余数据集，并实现了 0.529 的 MCC。我们还编译了 UniProtSMB 数据集，该数据集根据 UniProtKB 数据库的原始数据合并了来自相似蛋白质的位点，并在测试集上实现了 0.699 的 MCC。此外，CLAPE-SMB 在包含 336 个非冗余序列的固有无序蛋白 （IDP） 数据集上实现了 0.815 的 MCC。DAPK1、RebH 和 Nep1 的案例研究支持这种结合位点预测工具帮助药物设计的潜力。代码和数据集可在 https://github.com/JueWangTHU/CLAPE-SMB 免费获得。CLAPE-SMB 将预先训练的蛋白质语言模型与对比学习相结合，以准确预测蛋白质小分子结合位点，尤其是对于没有实验结构的蛋白质，例如 IDP。该模型在各种数据集中进行训练，显示出很强的适应性，使其成为推进药物设计和理解蛋白质-小分子相互作用的宝贵工具。