Shi Jiale, Quevillon Michael J, Amorim Valença Pedro H, Whitmer Jonathan K
Department of Chemical and Biomolecular Engineering, University of Notre Dame, Notre Dame, Indiana 46556, United States.
Department of Chemistry and Biochemistry, University of Notre Dame, Notre Dame, Indiana 46556, United States.
ACS Appl Mater Interfaces. 2022 Aug 17;14(32):37161-37169. doi: 10.1021/acsami.2c08891. Epub 2022 Aug 2.
Polymer-surface interactions are crucial to many biological processes and industrial applications. Here we propose a machine learning method to connect a model polymer's sequence with its adhesion to decorated surfaces. We simulate the adhesive free energies of 20000 unique coarse-grained one-dimensional polymer sequences interacting with functionalized surfaces and build support vector regression models that demonstrate inexpensive and reliable prediction of the adhesive free energy as a function of sequence. Our work highlights the promising integration of coarse-grained simulation with data-driven machine learning methods for the design of functional polymers and represents an important step toward linking polymer compositions with polymer-surface interactions.
聚合物与表面的相互作用对许多生物过程和工业应用至关重要。在此，我们提出一种机器学习方法，将模型聚合物的序列与其在修饰表面上的粘附性联系起来。我们模拟了20000个独特的粗粒度一维聚合物序列与功能化表面相互作用的粘附自由能，并构建了支持向量回归模型，该模型证明了作为序列函数的粘附自由能的低成本且可靠的预测。我们的工作突出了粗粒度模拟与数据驱动的机器学习方法在功能聚合物设计方面的有前景的整合，并代表了将聚合物组成与聚合物 - 表面相互作用联系起来的重要一步。
