Rational design of highly antifouling materials is crucial for a wide range of fundamental research and practical applications. The immense variety and complexity of intrinsic physicochemical properties of materials (i.e. chemical structure, hydrophobicity, charge distribution, molecular weight) and their surface coating properties (i.e. packing density, film thickness and roughness, and chain conformation) make it challenging to experimentally control, probe, or understand atomic-scale structure-property relationships of antifouling materials design. In this work, we propose a step-by-step data-driven strategy to explore and design antifouling materials. Briefly, we first construct a reliable database containing antifouling self-assembled monolayers (SAMs) with well characterized materials and surface properties. Then, we develop a machine learning technique – a combination of factor analysis of functional group (FAFG), random forest (RF), and artificial neural network (ANN) algorithms – to obtain fingerprint descriptors capable of correlating structure/chemical/surface features with antifouling activity of SAMs. Finally, the resulting models are used to predict and design new antifouling SAMs from experiments. SPR results of the designed SAMs exhibit high surface resistance to protein adsorption from undiluted blood serum and plasma, validating the model predictions. This data-driven machine-learning model has demonstrated its effective ability to not only design new antifouling materials, but also evaluate the antifouling activity of critical functional groups, leading to a promising direction for the rational design of functional materials.

Machine learning-enabled design of antifouling self-assembling monolayers

ACS Spring Meeting 2021

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.