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

Abstract

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 the vast chemical and composition space. Here, a strategy is reported 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 and effective copolymer chemistries for the stabilization of each enzyme. Overall, this work broadens the capabilities to design fit‐for‐purpose synthetic copolymers that promote or otherwise manipulate protein activity, with extensions toward the design of robust polymer–protein hybrid materials.

A High-Throughput Platform for Efficient Exploration of Functional polypeptides Chemical Space

“…This situation motivates the use of a model-guided optimization strategy to help prioritize experiments and accelerate discovery. Bayesian optimization (BO) is a powerful tool for various design problems 94 and is receiving increasing attention in the chemistry community 43,[95][96][97] . Because of the data efficiency of BO relative to brute force or random screening, it is especially useful for problems where evaluation is expensive.…”

“…38,39 Boyer et al used photo-induced electron transfer-reversible additionfragmentation chain transfer (PET-RAFT) for the HTS of poly(acryl amide)s to explore polymers with protein binding 40 and antimicrobial activity 41 . More recently, Leibfarth and Gormley et al applied controlled radical polymerization in combination with automated synthesis and ML to identify polymers for enhanced magnetic resonance signals 18 and protein preservation 42,43 , respectively. As a complementary approach to the aforementioned parallel polymerization, post-polymerization modifications (PPM) 44,45 is also common for library generation.…”

A graph representation of molecular ensembles for polymer property prediction

“…Machine learning (ML) is now playing a significant role in supporting the discovery and synthesis of new functional organic molecules with specialized applications, 20,26,27 thanks to its ability to capture subtle chemical patterns when enough data is available. The field of polymer informatics has also attracted increasing attention, with a number of studies demonstrating the use of ML for the prediction of thermal, 28–35 thermodynamic, 28,36–38 electronic, 39–44 optical, 41,45,46 and mechanical 41,47 properties of polymers and copolymers.…”

Data-Driven Design of Protein-Like Single-Chain Polymer Nanoparticles

“…67 By accomplishing these tasks, a data-driven approach can make predictions about material features of interest and further our understanding of how these features can be designed in future experiments. [68][69][70] In this study, we combined high-throughput polymer synthesis and characterization with ML to aid the design of novel SCNPs that are compact and exhibit similar flexibility to ordered proteins.…”