Ring Repeating Unit: An Upgraded Structure Representation of Linear Condensation Polymers for Property Prediction

Abstract

Unique structure representation of polymers plays a crucial role in developing models for polymer property prediction and polymer design by data-centric approaches. Currently, monomer and repeating unit (RU) approximations are widely used to represent polymer structures for generating feature descriptors in the modeling of quantitative structure−property relationships (QSPR). However, such conventional structure representations may not uniquely approximate heterochain polymers due to the diversity of monomer combinations and the potential multi-RUs. In this study, the so-called ring repeating unit (RRU) method that can uniquely represent polymers with a broad range of structure diversity is proposed for the first time. As a proof of concept, an RRU-based QSPR model was developed to predict the associated glass transition temperature (T g ) of polyimides (PIs) with deterministic values. Comprehensive model validations including external, internal, and Y-random validations were performed. Also, an RU-based QSPR model developed based on the same large database of 1321 PIs provides nonunique prediction results, which further prove the necessity of RRU-based structure representation. Promising results obtained by the application of the RRU-based model confirm that the as-developed RRU method provides an effective representation that accurately captures the sequence of repeat units and thus realizes reliable polymer property prediction by data-driven approaches.

Leveraging data‐driven strategy for accelerating the discovery of polyesters with targeted glass transition temperatures

“… Polymer structure representation. Unique representation of the polyester molecular structure was done by using RRU, which is developed in our previous work 43 Descriptor generation.…”

“…Herein, we report a data-driven strategy to enable evaluation of the relationship between molecular structure and T g of polyesters and further guide the design of polyesters with specific T g s. The workflow is illustrated in Figure 1. First, a multiple linear regression (MLR)-based QSPR model was developed by employing ring repeating unit (RRU)based structural representation 43,44 to uniquely represent polyesters and norm descriptors for feature engineering. The predictability, robustness, and chance correlation of the model were evaluated by external validation, internal validation, and Y-randomized analysis, respectively.…”

Augmenting Polymer Datasets by Iterative Rearrangement

“…There are numerous molecular representations and ML models to choose from, and the performance of each combination can be task-dependent. , We evaluated some of the most common ML (SVM, RF, XGBoost) and DL (NN, LSTM) models to study the impact of polymer representations on model performance. To understand the impact of data augmentation, we compared canonical SMILES, augmented SMILES, , OHE of polymers (where each polymer is represented by a unique binary bit in the vector, see example in Figure S1 and Table S1), one-hot encoded molecular fragments (nonaugmented and augmented), string-based molecular fragments (iteratively rearranged and iteratively rearranged recombined fragments), ECFP6 for periodic polymer graphs, , and other common representations (SELFIES, BRICS (OHE), and ECFP6 of the monomer) …”

“…One of the most promising solutions that capture the repetitive or periodic nature of a polymer is the periodic graph representation where the two terminal ends of the polymer chain are connected, forming a ring. , Although this representation is not physically accurate, the periodic polymer graph effectively captures the bonding environment and periodicity of a polymer, outperforming the monomer, dimer, and trimer graph in several unique polymer prediction tasks …”

“…27,28 One of the most promising solutions that capture the repetitive or periodic nature of a polymer is the periodic graph representation where the two terminal ends of the polymer chain are connected, forming a ring. 29,30 Although this representation is not physically accurate, the periodic polymer graph effectively captures the bonding environment and periodicity of a polymer, outperforming the monomer, dimer, and trimer graph in several unique polymer prediction tasks. 30 Data augmentation has been extremely successful in computer vision and natural language processing 31,32 because it maximizes the amount of information that can be learned from scarce data by performing transformations which allow ML models to be insensitive to translation, rotation, and permutation variances.…”