Currently, there is no effective antiviral drugs nor vaccine for coronavirus disease 2019 (COVID-19)caused by acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Due to its high conservativeness andlow similarity with human genes, SARS-CoV-2 main protease (Mpro) is one of the most favorable drug targets.However, the current understanding of the molecular mechanism of Mpro inhibition is limited by thelack of reliable binding affinity ranking and prediction of existing structures of Mpro-inhibitor complexes.This work integrates mathematics (i.e., algebraic topology) and deep learning (MathDL) to provide a reliableranking of the binding affinities of 137 SARS-CoV-2 Mpro inhibitor structures. We reveal that Gly143residue inMpro is the most attractive site to form hydrogen bonds, followed by Glu166, Cys145, and His163.We also identify 71 targeted covalent bonding inhibitors. MathDL was validated on the PDBbind v2016core set benchmark and a carefully curated SARS-CoV-2 inhibitor dataset to ensure the reliability of thepresent binding affinity prediction. The present binding affinity ranking, interaction analysis, and fragmentdecomposition offer a foundation for future drug discovery efforts.

中文翻译：

---

利用代数拓扑和深度学习从 137 个晶体结构揭示 SARS-CoV-2 主要蛋白酶抑制的分子机制


目前，对于由急性呼吸综合征冠状病毒 2 (SARS-CoV-2) 引起的 2019 年冠状病毒病 (COVID-19)，尚无有效的抗病毒药物或疫苗。由于其高度保守性和与人类基因的低相似性，SARS-CoV-2主蛋白酶（Mpro）是最有利的药物靶点之一。然而，由于缺乏可靠的结合亲和力，目前对Mpro抑制分子机制的理解受到限制。 Mpro 抑制剂复合物现有结构的排序和预测。这项工作整合了数学（即代数拓扑）和深度学习 (MathDL)，为 137 个 SARS-CoV-2 Mpro 抑制剂结构的结合亲和力提供了可靠的排序。我们发现，Mpro 中的 Gly143 残基是最有吸引力的形成氢键的位点，其次是 Glu166、Cys145 和 His163。我们还鉴定了 71 种靶向共价键抑制剂。 MathDL 在 PDBbind v2016 核心集基准和精心策划的 SARS-CoV-2 抑制剂数据集上进行了验证，以确保当前结合亲和力预测的可靠性。目前的结合亲和力排序、相互作用分析和片段分解为未来的药物发现工作奠定了基础。