Reducing Data Requirements for Sequence-Property Prediction in Copolymer Compatibilizers via Deep Neural Network Tuning

TL;DR

This paper introduces a deep neural network tuning method that significantly reduces data requirements for designing sequence-controlled copolymer compatibilizers by leveraging low-fidelity data and rapid adaptation to different conditions.

Contribution

The study presents a novel AI strategy that enables rapid tuning of neural networks to predict polymer compatibilizer performance across various conditions with minimal data.

Findings

Deep neural networks can be effectively tuned using low-fidelity data.

The approach reduces the need for extensive datasets at each condition.

Predictions can be adapted to different conditions with minimal additional data.

Abstract

Synthetic sequence-controlled polymers promise to transform polymer science by combining the chemical versatility of synthetic polymers with the precise sequence-mediated functionality of biological proteins. However, design of these materials has proven extraordinarily challenging, because they lack the massive datasets of closely related evolved molecules that accelerate design of proteins. Here we report on a new Artifical Intelligence strategy to dramatically reduce the amount of data necessary to accelerate these materials' design. We focus on data connecting the repeat-unit-sequence of a \emph{compatibilizer} molecule to its ability to reduce the interfacial tension between distinct polymer domains. The optimal sequence of these molecules, which are essential for applications such as mixed-waste polymer recycling, depends strongly on variables such as concentration and chemical details of the polymer. With current methods, this would demand an entirely distinct dataset to enable design at each condition. Here we show that a deep neural network trained on low-fidelity data for sequence/interfacial tension relations at one set of conditions can be rapidly tuned to make higher-fidelity predictions at a distinct set of conditions, requiring far less data that would ordinarily be needed. This priming-and-tuning approach should allow a single low-fidelity parent dataset to dramatically accelerate prediction and design in an entire constellation of related systems. In the long run, it may also provide an approach to bootstrapping quantitative atomistic design with AI insights from fast, coarse simulations.