Identifying, synthesizing, and developing novel, sustainable polymers which can be sourced from biomass or materials waste streams is key for establishing a circular carbon economy. The development of new materials requires extensive experimental efforts and the search space based on available bioderived monomers is large and cannot be reasonably probed using an Edisionian approach. To aid experimentalists in the down selection of material targets, a message passing neural network (MPNN) which is able to predict 8 material properties, glass transition temperature, melt temperature, density, modulus, and the gas permeability of O2, N2, CO2, and H2O, was developed. Within the computation effort database development, in silico synthesis of 2D polymers structures from combinatorial monomer databases, MPNN architecture and hyperparameter optimization, and domain of validity testing were performed. The pipeline was applied to monomers sourced from the BiGG database, a “knowledgebase of genome-scale metabolic network reconstructions”, which generated &gt;1,200 polyester and polyamide target candidates. These targets were further down selected based on theoretical yield, biosynthetic pathway, material performance, and material synthesis scheme to identify biosourceable targets for replacement of polyethylene terephthalate. Predictions of glass transition were then benchmarked against experimentally determined glass transition temperatures to demonstrate the ability to predict properties of polymers that have not been previously synthesized. The development of a machine learning based, polymer prediction tool will increase the rate at which sustainable materials can be discovered.

Message passing neural networks for prediction of sustainable polymers

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

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