Department of Chemical, Biomolecular, and Corrosion Engineering, The University of Akron, Ohio 44325, United States.
Department of Chemical Engineering, R&D Center for Membrane Technology, Chung Yuan Christian University, Taoyuan 32023, Taiwan.
ACS Appl Mater Interfaces. 2021 Mar 10;13(9):11306-11319. doi: 10.1021/acsami.1c00642. Epub 2021 Feb 26.
The rational design of highly antifouling materials is crucial for a wide range of fundamental research and practical applications. The immense variety and complexity of the intrinsic physicochemical properties of materials (i.e., chemical structure, hydrophobicity, charge distribution, and molecular weight) and their surface coating properties (i.e., packing density, film thickness and roughness, and chain conformation) make it challenging to rationally design antifouling materials and reveal their fundamental structure-property relationships. In this work, we developed a data-driven machine learning model, a combination of factor analysis of functional group (FAFG), Pearson analysis, random forest (RF) and artificial neural network (ANN) algorithms, and Bayesian statistics, to computationally extract structure/chemical/surface features in correlation with the antifouling activity of self-assembled monolayers (SAMs) from a self-construction data set. The resultant model demonstrates the robustness of = 0.90 and RMSE = 0.21 and the predictive ability of = 0.84 and RMSE = 0.28, determines key descriptors and functional groups important for the antifouling activity, and enables to design original antifouling SAMs using the predicted antifouling functional groups. Three computationally designed molecules were further coated onto the surfaces in different forms of SAMs and polymer brushes. The resultant coatings with negative fouling indexes exhibited strong surface resistance to protein adsorption from undiluted blood serum and plasma, validating the model predictions. The data-driven machine learning model demonstrates their design and predictive capacity for next-generation antifouling materials and surfaces, which hopefully help to accelerate the discovery and understanding of functional materials.
高度抗污材料的合理设计对于广泛的基础研究和实际应用至关重要。材料的固有物理化学性质（即化学结构、疏水性、电荷分布和分子量）及其表面涂层性质（即包装密度、膜厚和粗糙度以及链构象）的巨大多样性和复杂性使得合理设计抗污材料并揭示其基本结构-性能关系具有挑战性。在这项工作中，我们开发了一种数据驱动的机器学习模型，该模型结合了官能团因子分析（FAFG）、Pearson 分析、随机森林（RF）和人工神经网络（ANN）算法以及贝叶斯统计，从自构建数据集中计算提取与自组装单层（SAMs）抗污活性相关的结构/化学/表面特征。该模型的结果表明，其稳健性为 0.90，RMSE 为 0.21，预测能力为 0.84，RMSE 为 0.28，确定了对防污活性重要的关键描述符和官能团，并能够使用预测的防污官能团设计原始的防污 SAMs。随后将三个计算设计的分子以不同形式的 SAM 和聚合物刷涂覆到表面上。具有负污染指数的所得涂层对来自未稀释血清和血浆的蛋白质吸附具有很强的表面抵抗力，验证了模型预测。数据驱动的机器学习模型展示了它们对下一代抗污材料和表面的设计和预测能力，有望帮助加速功能材料的发现和理解。
