Predicting aggregate morphology of sequence-defined macromolecules with Recurrent Neural Networks

TL;DR

This paper demonstrates that supervised machine learning, especially Recurrent Neural Networks, can accurately predict the aggregate morphology of sequence-defined macromolecules, enabling high-throughput sequence screening for desired self-assembled structures.

Contribution

It introduces a machine learning approach, particularly RNNs, for predicting macromolecular aggregate morphology, outperforming traditional feature-based models and facilitating efficient sequence screening.

Findings

RNN-based regressors outperform other models in morphology prediction

High-throughput screening successfully identifies sequences for targeted structures

Implicit representation learning enhances prediction accuracy

Abstract

Self-assembly of dilute sequence-defined macromolecules is a complex phenomenon in which the local arrangement of chemical moieties can lead to the formation of long-range structure. The dependence of this structure on the sequence necessarily implies that a mapping between the two exists, yet it has been difficult to model so far. Predicting the aggregation behavior of these macromolecules is challenging due to the lack of effective order parameters, a vast design space, inherent variability, and high computational costs associated with currently available simulation techniques. Here, we accurately predict the morphology of aggregates self-assembled from sequence-defined macromolecules using supervised machine learning. We find that regression models with implicit representation learning perform significantly better than those based on engineered features such as $k$-mer counting, and a Recurrent-Neural-Network-based regressor performs the best out of nine model architectures we tested. Furthermore, we demonstrate the high-throughput screening of monomer sequences using the regression model to identify candidates for self-assembly into selected morphologies. Our strategy is shown to successfully identify multiple suitable sequences in every test we performed, so we hope the insights gained here can be extended to other increasingly complex design scenarios in the future, such as the design of sequences under polydispersity and at varying environmental conditions.