Leng Yuanming, Ding Huitong, Alvin Ang Ting Fang, Au Rhoda, Doraiswamy P Murali, Liu Chunyu
Department of Biostatistics, Boston University School of Public Health, Boston, MA, 02118, USA.
Department of Anatomy and Neurobiology, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, 02118, USA.
medRxiv. 2024 Sep 23:2024.09.21.24314123. doi: 10.1101/2024.09.21.24314123.
BACKGROUND: Protein abundance levels, sensitive to both physiological changes and external interventions, are useful for assessing the Alzheimer's disease (AD) risk and treatment efficacy. However, identifying proteomic prognostic markers for AD is challenging by their high dimensionality and inherent correlations. METHODS: Our study analyzed 1128 plasma proteins, measured by the SOMAscan platform, from 858 participants 55 years and older (mean age 63 years, 52.9% women) of the Framingham Heart Study (FHS) Offspring cohort. We conducted regression analysis and machine learning models, including LASSO-based Cox proportional hazard regression model (LASSO) and generalized boosted regression model (GBM), to identify protein prognostic markers. These markers were used to construct a weighted proteomic composite score, the AD prediction performance of which was assessed using time-dependent area under the curve (AUC). The association between the composite score and memory domain was examined in 339 (of the 858) participants with available memory scores, and in an independent group of 430 participants younger than 55 years (mean age 46, 56.7% women). RESULTS: Over a mean follow-up of 20 years, 132 (15.4%) participants developed AD. After adjusting for baseline age, sex, education, and APOE ε4+ status, regression models identified 309 proteins ( ≤ 0.2). After applying machine learning methods, nine of these proteins were selected to develop a composite score. This score improved AD prediction beyond the factors of age, sex, education, and APOE ε4+ status across 15 to 25 years of follow-up, achieving its peak AUC of 0.84 in the LASSO model at the 22-year follow-up. It also showed a consistent negative association with memory scores in 339 participants (beta = -0.061, = 0.046), 430 independent participants (beta = -0.060, = 0.018), and the pooled 769 samples (beta = -0.058, = 0.003). CONCLUSION: These findings highlight the utility of proteomic markers in improving AD prediction and emphasize the complex pathology of AD. The composite score may aid early AD detection and efficacy monitoring, warranting further validation in diverse populations.
背景：蛋白质丰度水平对生理变化和外部干预均敏感，有助于评估阿尔茨海默病（AD）风险及治疗效果。然而，由于蛋白质组学数据的高维度性和内在相关性，识别AD的蛋白质组学预后标志物具有挑战性。 方法：我们的研究分析了来自弗雷明汉心脏研究（FHS）子代队列中858名55岁及以上（平均年龄63岁，女性占52.9%）参与者的1128种血浆蛋白质，这些蛋白质通过SOMAscan平台进行测量。我们进行了回归分析和机器学习模型，包括基于套索（LASSO）的Cox比例风险回归模型（LASSO）和广义增强回归模型（GBM），以识别蛋白质预后标志物。这些标志物用于构建加权蛋白质组综合评分，其AD预测性能使用时间依赖曲线下面积（AUC）进行评估。在858名中有可用记忆评分的339名参与者以及一个由430名年龄小于55岁（平均年龄46岁，女性占56.7%）的独立组中，研究了综合评分与记忆领域之间的关联。 结果：在平均20年的随访中，132名（15.4%）参与者患上了AD。在调整基线年龄、性别、教育程度和APOE ε4+状态后，回归模型识别出309种蛋白质（≤0.2）。应用机器学习方法后，从这些蛋白质中选择了9种来制定综合评分。在15至25年的随访中，该评分在年龄、性别、教育程度和APOE ε4+状态等因素之外改善了AD预测，在22年随访时，LASSO模型中的AUC峰值达到0.84。在339名参与者（β=-0.061，P=0.046）、430名独立参与者（β=-0.060，P=0.018）以及合并的769个样本（β=-0.058，P=0.003）中，它还与记忆评分呈现出一致的负相关。 结论：这些发现突出了蛋白质组学标志物在改善AD预测方面的作用，并强调了AD复杂的病理学特征。综合评分可能有助于AD的早期检测和疗效监测，值得在不同人群中进一步验证。
Health Technol Assess. 2006-9
Cochrane Database Syst Rev. 2021-4-19
Cochrane Database Syst Rev. 2017-12-22
Cochrane Database Syst Rev. 2003
Cochrane Database Syst Rev. 2022-9-26
Cochrane Database Syst Rev. 2017-11-22
Alzheimers Dement (Amst). 2024-3-27
Nat Aging. 2024-2
Transl Neurodegener. 2024-1-9
Mol Aspects Med. 2023-4
Alzheimers Res Ther. 2022-8-13
Front Aging Neurosci. 2022-7-12
Zotero 插件
