当前位置: X-MOL 学术Environ. Sci.: Nano › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Machine learning provides predictive analysis into silver nanoparticle protein corona formation from physicochemical properties†
Environmental Science: Nano ( IF 5.8 ) Pub Date : 2017-11-01 00:00:00 , DOI: 10.1039/c7en00466d
Matthew R Findlay 1 , Daniel N Freitas 1 , Maryam Mobed-Miremadi 1 , Korin E Wheeler 2
Affiliation  

Proteins encountered in biological and environmental systems bind to engineered nanomaterials (ENMs) to form a protein corona (PC) that alters the surface chemistry, reactivity, and fate of the ENMs. Complexities such as the diversity of the PC and variation with ENM properties and reaction conditions make the PC population difficult to predict. Here, we support the development of predictive models for PC populations by relating the biophysicochemical characteristics of proteins, ENMs, and solution conditions to PC formation using random forest classification. The resulting model offers a predictive analysis into the population of PC proteins in Ag ENM systems of various ENM sizes and surface coatings. With an area under the receiver operating characteristic curve of 0.83 and an F1-score of 0.81, a model with strong performance has been constructed based upon experimental data. The weighted contribution of each variable provides recommendations for mechanistic models based upon protein enrichment classification results. Protein biophysical properties such as pI and size are weighted heavily. Yet, ENM size, surface charge, and solution ionic strength also prove essential to an accurate model. The model can be readily modified and applied to other ENM PC populations. The model presented here represents the first step toward robust predictions of PC fingerprints.

中文翻译:


机器学习根据物理化学特性对银纳米颗粒蛋白电晕的形成进行预测分析†



生物和环境系统中遇到的蛋白质与工程纳米材料 (ENM) 结合,形成蛋白质冠 (PC),从而改变 ENM 的表面化学、反应性和命运。 PC 的多样性以及 ENM 特性和反应条件的变化等复杂性使得 PC 群体难以预测。在这里,我们通过使用随机森林分类将蛋白质、ENM 和溶液条件与 PC 形成相关联,支持 PC 群体预测模型的开发。由此产生的模型可以对各种 ENM 尺寸和表面涂层的 Ag ENM 系统中的 PC 蛋白群体进行预测分析。根据实验数据构建了一个性能较强的模型,受试者工作特征曲线下面积为0.83,F1分数为0.81。每个变量的加权贡献为基于蛋白质富集分类结果的机械模型提供建议。蛋白质生物物理特性(例如 pI 和大小)的权重很大。然而,ENM 尺寸、表面电荷和溶液离子强度也被证明对于准确的模型至关重要。该模型可以很容易地修改并应用于其他 ENM PC 群体。这里提出的模型代表了对 PC 指纹进行稳健预测的第一步。
更新日期:2017-11-01
down
wechat
bug