Machine Learning on a Robotic Platform for the Design of Polymer-Protein Hybrids

24 January 2022, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


Polymer-protein hybrids are intriguing materials that can bolster protein stability in non-native environments, thereby enhancing their utility in diverse medicinal, commercial, and industrial applications. One stabilization strategy involves designing synthetic random copolymers with compositions attuned to the protein surface, but rational design is complicated by a vast chemical and composition space. Here, we report a strategy to design protein-stabilizing copolymers based on active machine learning, facilitated by automated material synthesis and characterization platforms. The versatility and robustness of the approach is demonstrated by the successful identification of copolymers that preserve, or even enhance, the activity of three chemically distinct enzymes following exposure to thermal denaturing conditions. Although systematic screening results in mixed success, active learning appropriately identifies unique chemistries for each enzyme. Overall, this work broadens our capabilities to design fit-for-purpose synthetic copolymers that promote or otherwise manipulate protein activity, with extensions towards the design of robust polymer-protein hybrid materials.


machine learning
artificial intelligence
materials design
automated synthesis
polymer-protein complex
single-enzyme nanoparticle
protein formulation
enzyme catalysis

Supplementary materials

Supporting Information for Machine Learning on a Robotic Platform for the Design of Polymer-Protein Hybrids
Chemical Space of Seed Dataset Polymer Featurization and Initial Modeling REA Distributions Through Iterations of Design Model Robustness to Noise Characterization of EP1 Circular Dichroism Spectroscopy Small Angle X-Ray Scattering Dynamic Light Scattering Quartz Crystal Microbalance Penalty Function Classifier Implementation Polymer Seed Library Active Learning Polymer Iterations – Horseradish Peroxidase (HRP) Active Learning Polymer Iterations – Glucose Oxidase (GOx) Active Learning Polymer Iterations – Lipase (Lip)


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.