Background/Objectives: Human epidermal growth factor receptor 2 (HER2) is overexpressed in several malignancies, such as breast, gastric, ovarian, and lung cancers, where it promotes aggressive tumor proliferation and unfavorable prognosis. Targeting HER2 has thus emerged as a crucial therapeutic strategy, particularly for HER2-positive malignancies. The present study focusses on the design and optimization of peptide inhibitors targeting HER2, utilizing machine learning to identify and enhance peptide candidates with elevated binding affinities. The aim is to provide novel therapeutic options for malignancies linked to HER2 overexpression. Methods: This study started with the extraction and structural examination of the HER2 protein, succeeded by designing the peptide sequences derived from essential interaction residues. A machine learning technique (XGBRegressor model) was employed to predict binding affinities, identifying the top 20 peptide possibilities. The candidates underwent further screening via the FreeSASA methodology and binding free energy calculations, resulting in the selection of four primary candidates (pep-17, pep-7, pep-2, and pep-15). Density functional theory (DFT) calculations were utilized to evaluate molecular and reactivity characteristics, while molecular dynamics simulations were performed to investigate inhibitory mechanisms and selectivity effects. Advanced computational methods, such as QM/MM simulations, offered more understanding of peptide–protein interactions. Results: Among the four principal peptides, pep-7 exhibited the most elevated DFT values (−3386.93 kcal/mol) and the maximum dipole moment (10,761.58 Debye), whereas pep-17 had the lowest DFT value (−5788.49 kcal/mol) and the minimal dipole moment (2654.25 Debye). Molecular dynamics simulations indicated that pep-7 had a steady binding free energy of −12.88 kcal/mol and consistently bound inside the HER2 pocket during a 300 ns simulation. The QM/MM simulations showed that the overall total energy of the system, which combines both QM and MM contributions, remained around −79,000 ± 400 kcal/mol, suggesting that the entire protein–peptide complex was in a stable state, with pep-7 maintaining a strong, well-integrated binding. Conclusions: Pep-7 emerged as the most promising therapeutic peptide, displaying strong binding stability, favorable binding free energy, and molecular stability in HER2-overexpressing cancer models. These findings suggest pep-7 as a viable therapeutic candidate for HER2-positive cancers, offering a potential novel treatment strategy against HER2-driven malignancies.
背景/目的：人表皮生长因子受体2（HER2）在多种恶性肿瘤（如乳腺癌、胃癌、卵巢癌和肺癌）中过度表达，促进肿瘤的侵袭性增殖和不良预后。因此，靶向HER2已成为关键的治疗策略，尤其针对HER2阳性恶性肿瘤。本研究聚焦于靶向HER2的肽类抑制剂的设计与优化，利用机器学习技术识别并提升具有高结合亲和力的候选肽。旨在为HER2过表达相关恶性肿瘤提供新的治疗选择。方法：本研究首先提取并分析了HER2蛋白的结构，随后基于关键相互作用残基设计肽序列。采用机器学习技术（XGBRegressor模型）预测结合亲和力，筛选出前20个候选肽。通过FreeSASA方法和结合自由能计算进一步筛选，最终选出四个主要候选肽（pep-17、pep-7、pep-2和pep-15）。利用密度泛函理论（DFT）计算评估分子及反应特性，同时进行分子动力学模拟以研究抑制机制和选择性效应。高级计算方法如QM/MM模拟进一步揭示了肽-蛋白相互作用的细节。结果：在四个主要候选肽中，pep-7表现出最高的DFT值（−3386.93 kcal/mol）和最大偶极矩（10,761.58 Debye），而pep-17的DFT值最低（−5788.49 kcal/mol），偶极矩最小（2654.25 Debye）。分子动力学模拟显示，pep-7的结合自由能稳定在−12.88 kcal/mol，且在300 ns模拟过程中持续结合于HER2口袋内。QM/MM模拟表明，系统的总能量（结合QM与MM贡献）维持在约−79,000 ± 400 kcal/mol，提示整个蛋白-肽复合物处于稳定状态，pep-7保持了强而稳定的结合。结论：Pep-7在HER2过表达癌症模型中表现出强结合稳定性、良好的结合自由能及分子稳定性，是最具潜力的治疗性候选肽。这些发现表明pep-7可作为HER2阳性癌症的可行治疗候选物，为HER2驱动型恶性肿瘤提供了一种潜在的新型治疗策略。
In Silico Design of Peptide Inhibitors Targeting HER2 for Lung Cancer Therapy
肿瘤(癌症)患者之家