Copolymer Informatics with Multitask Deep Neural Networks

Abstract

Polymer informatics tools have been recently gaining ground to efficiently and effectively develop, design, and discover new polymers that meet specific application needs. So far, however, these data-driven efforts have largely focused on homopolymers. Here, we address the property prediction challenge for copolymers, extending the polymer informatics framework beyond homopolymers. Advanced polymer fingerprinting and deep-learning schemes that incorporate multi-task learning and meta-learning are proposed. A large data set containing over 18,000 data points of glass transition, melting, and degradation temperature of homopolymers and copolymers of up to two monomers is used to demonstrate the copolymer prediction efficacy. The developed models are accurate, fast, flexible, and scalable to more copolymer properties when suitable data become available.

Bioplastic Design using Multitask Deep Neural Networks

“…Homo-and copolymer data points of T g , T m , and T d , and homopolymer data points of µ g s, E, and σ b were already utilized in previous studies. [29][30][31][32][33] The copolymer data points belonging to µ g s, E, σ y , σ b , and b , and homopolymer data points of σ y and b were collected from the PolyInfo 34 repository for this study. For consistency and uniformity, only T g and T m data points measured via differential scanning calorimetry (DSC), T d data points measured via thermogravimetric analysis (TGA), and mechanical data points recorded around room temperature (300 K) were included in the data set.…”

“…Property Predictors Multitask deep neural networks with meta learners have shown best-in-class performance in past polymer informatics studies 32,33 due to their ability to utilize inherent correlations in data that helps to overcome data sparsity. Here, we create three multiproperty predictors (one for each category in Table 1) to predict, in total, 13 polymer properties using the data set and categories profiled in Table 1 and fingerprints outlined in the Methods section.…”

“…Polymer structures are represented as simplified molecular-input line-entry system (SMILES) 14 strings that use two stars to indicate the two endpoints of the repetitive unit of the polymers, but otherwise follow the SMILES syntax. The fingerprint vector (F) in this work has 849 components and is calculated based upon the SMILES string following a two-step protocol: 33 First, we compute hierarchical fingerprints that capture structural and key chemical features of each comonomer at three different length scales. 51 At the atomic scale, our fingerprints track the occurrence of a fixed set of atomic fragments (or motifs).…”

“…60 The training protocol of the predictors follows state-of-the-art techniques involving fivefold cross-validation and a meta learner that forecasts the final property values based upon the ensemble of cross-validation predictors. 33 The parameters of the cross-validation models are fixed when used in the meta learner. The meta learner has the same network architecture as the multitask predictors but receives the five outputs of the multitask predictors as inputs (rather than the copolymer fingerprint).…”

A Machine Learning Method for Material Property Prediction: Example Polymer Compatibility

“…Researchers have made active and effective attempts to apply ML method in exploring polymer syntheses and polymer materials [22]. The copolymer synthesis and defectivity [23,24,25], mechanical properties of polymer composites [26], liquid crystal behavior of copolyether [27], thermal conductivity [28], dielectric properties [29], glass transition, melting, and degradation temperature and quantum physical and chemical properties [30,31,32,33] have been applied with machine learning and good prediction accuracy is achieved. Muramatsu et al [34] have used ML method to investigate the relationship between the phase separation structure of polymer blend and Young's modulus, and builds a predictive framework based on two-dimensional images of polymer blend as the descriptor.…”