An Informatics Framework for the Design of Sustainable, Chemically Recyclable, Synthetically-Accessible and Durable Polymers

TL;DR

This paper introduces a digital and machine learning-based framework for designing sustainable, recyclable, and durable polymers, enabling rapid screening of millions of candidates for environmentally friendly applications.

Contribution

The study develops a novel virtual synthesis and machine learning approach to identify promising recyclable polymers, including validation of new candidates in laboratory experiments.

Findings

Generated over 7 million hypothetical ROP polymers.

Identified 35,000 candidates with optimal sustainability and utility.

Validated one new recyclable polymer experimentally.

Abstract

We present a novel approach to design durable and chemically recyclable ring-opening polymerization (ROP) class polymers. This approach employs digital reactions using virtual forward synthesis (VFS) to generate over 7 million ROP polymers and machine learning techniques to rapidly predict thermal, thermodynamic and mechanical properties crucial for application-specific performance and recyclability. This combined methodology enables the generation and evaluation of millions of hypothetical ROP polymers from known and commercially available molecules, guiding the selection of approximately 35,000 candidates with optimal features for sustainability and practical utility. Three of these recommended candidates have passed validation tests in the physical lab - two of the three by others, as published previously elsewhere, and one of them is a new thiocane polymer synthesized, tested and reported here. This paper presents the framework, methodology, and initial findings of our study, highlighting the potential of VFS and machine learning to enable a large-scale search of the polymer universe and advance the development of recyclable and environmentally benign polymers.