Scholarlink

<p>The dynamic mutational landscape of SARS-CoV-2, especially within the spike glycoprotein's RBD, continues to undermine the effectiveness of available therapeutics. Although ACE2-derived peptides have previously been explored as spike inhibitors, their rational optimization has largely lacked systematic, data-driven selection strategies. This article describes an integrative computer-aided approach involving molecular dynamics (MD) simulations and machine learning-assisted peptide engineering to engineer potent peptide-based inhibitors targeting the RBD–ACE2 interface. Molecular dynamics simulations of wild-type and variant RBD–ACE2 complexes were first employed to identify energetically unfavorable interfacial residues, enabling the rational extraction and refinement of a 19-residue ACE2-derived peptide. A supervised regression model of the type XGBoost, trained using experimentally obtained peptide-protein affinity matrices (R<sup>2</sup> = 0.6958), estimated binding potentials for 54 synthetically designed peptide variants. The best lead, M1 (HAHTFLETFNYEAQTLSYE), exhibited improved docking energies (–257.35&#xa0;kcal/mol for Omicron and –234.24&#xa0;kcal/mol for wild-type) and improved free-binding energies (–35.67&#xa0;kcal/mol and –21.63&#xa0;kcal/mol, respectively), relative to the native peptide, with binding energies comparable to or exceeding reported RBD–hACE2 interaction benchmarks (− 13 to − 18&#xa0;kcal/mol). Molecular dynamics analyses further confirmed enhanced conformational stability, sustained hydrogen bonding, and favourable energetic landscapes for the M1–RBD complexes. Collectively, this study demonstrates that integrating energetic decomposition with ML-driven peptide optimization provides a scalable and mechanistically informed strategy for developing peptide-based inhibitors against rapidly evolving viral pathogens.</p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning-guided rational engineering of ACE2-derived peptides for broad-spectrum neutralization of SARS-CoV-2 variants

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月31日

查看全文
  • Mubarak A. Alamri,
  • Abdullah S. Alawam

摘要

The dynamic mutational landscape of SARS-CoV-2, especially within the spike glycoprotein's RBD, continues to undermine the effectiveness of available therapeutics. Although ACE2-derived peptides have previously been explored as spike inhibitors, their rational optimization has largely lacked systematic, data-driven selection strategies. This article describes an integrative computer-aided approach involving molecular dynamics (MD) simulations and machine learning-assisted peptide engineering to engineer potent peptide-based inhibitors targeting the RBD–ACE2 interface. Molecular dynamics simulations of wild-type and variant RBD–ACE2 complexes were first employed to identify energetically unfavorable interfacial residues, enabling the rational extraction and refinement of a 19-residue ACE2-derived peptide. A supervised regression model of the type XGBoost, trained using experimentally obtained peptide-protein affinity matrices (R2 = 0.6958), estimated binding potentials for 54 synthetically designed peptide variants. The best lead, M1 (HAHTFLETFNYEAQTLSYE), exhibited improved docking energies (–257.35 kcal/mol for Omicron and –234.24 kcal/mol for wild-type) and improved free-binding energies (–35.67 kcal/mol and –21.63 kcal/mol, respectively), relative to the native peptide, with binding energies comparable to or exceeding reported RBD–hACE2 interaction benchmarks (− 13 to − 18 kcal/mol). Molecular dynamics analyses further confirmed enhanced conformational stability, sustained hydrogen bonding, and favourable energetic landscapes for the M1–RBD complexes. Collectively, this study demonstrates that integrating energetic decomposition with ML-driven peptide optimization provides a scalable and mechanistically informed strategy for developing peptide-based inhibitors against rapidly evolving viral pathogens.

Graphical Abstract