Search

Polymer composite performance depends significantly on the polymer matrix, additives, processing conditions, and measurement setups. Traditional physics-based optimization methods for these parameters can be slow, labor-intensive, and costly, as they require physical manufacturing and testing. Here, we introduce a first step in extending Polymer Informatics, an AI-based approach proven effective for neat polymer design, into the realm of polymer composites. We curate a comprehensive database of commercially available polymer composites, develop a scheme for machine-readable data representation, and train machine-learning models for 15 flame-resistant, mechanical, thermal, and electrical properties, validating them on entirely unseen data. Future advancements are planned to drive the AI-assisted design of functional and sustainable polymer composites.

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., Comment: 26 pages, 6 figures

Achieving superior polymeric components through additive manufacturing (AM) relies on precise control of rheology. One key rheological property particularly relevant to AM is melt viscosity ($\eta$). Melt viscosity is influenced by polymer chemistry, molecular weight ($M_w$), polydispersity, induced shear rate ($\dot\gamma$), and processing temperature ($T$). The relationship of $\eta$ with $M_w$, $\dot\gamma$, and $T$ may be captured by parameterized equations. Several physical experiments are required to fit the parameters, so predicting $\eta$ of a new polymer material in unexplored physical domains is a laborious process. Here, we develop a Physics-Enforced Neural Network (PENN) model that predicts the empirical parameters and encodes the parametrized equations to calculate $\eta$ as a function of polymer chemistry, $M_w$, polydispersity, $\dot\gamma$, and $T$. We benchmark our PENN against physics-unaware Artificial Neural Network (ANN) and Gaussian Process Regression (GPR) models. Finally, we demonstrate that the PENN offers superior values of $\eta$ when extrapolating to unseen values of $M_w$, $\dot\gamma$, and $T$ for sparsely seen polymers.

Machine learning (ML) models for predicting gas permeability through polymers have traditionally relied on experimental data. While these models exhibit robustness within familiar chemical domains, reliability wanes when applied to new spaces. To address this challenge, we present a multi-tiered multi-task learning framework empowered with advanced machine-crafted polymer fingerprinting algorithms and data fusion techniques. This framework combines scarce "high-fidelity" experimental data with abundant diverse "low-fidelity" simulation or synthetic data, resulting in predictive models that display a high level of generalizability across novel chemical spaces. Additionally, this multi-task scheme capitalizes on known physics and interrelated properties, such as gas diffusivity and solubility, both of which are closely tied to permeability. By amalgamating high-throughput generated simulation data with available experimental data for gas permeability, diffusivity, and solubility for various gases, we construct multi-task deep learning models. These models can simultaneously predict all three properties for all gases under consideration. With markedly enhanced predictive accuracy, particularly compared to traditional models reliant solely on experimental data for a singular property. This strategy underscores the potential of coupling high-throughput classical simulations with data fusion methodologies to yield state-of-the-art property predictors, especially when experimental data for targeted properties is scarce., Comment: Submitted to npj Computational Materials

Anion exchange membranes are used in alkaline fuel cells and offer a promising alternative to the more expensive proton exchange membrane fuel cells. However, hydroxide ion conductivity in anion exchange membranes is low, and the quest for membranes with superior ion conductivity, mechanical robustness, and chemical stability is ongoing. In this study, we use classical molecular dynamics simulations to study hydroxide ion transport and mechanical properties of eight different hydrated polyolefin-based membranes, to provide a molecular-level understanding of the structure-function relationships in these systems. We examine the microstructure of the membranes and find that polymers with narrow cavity size distribution have tighter packing of water molecules around hydroxide ions. We estimate the self-diffusion coefficient of water and hydroxide ions and find that water molecules have a higher diffusion than hydroxide ions across all systems. The trends in hydroxide diffusion align well with experimental conductivity measurements. Water facilitates hydroxide diffusion, and this is clearly observed when the hydration level is varied for the same polymer chemistry. In systems with narrow cavities and tightly bound hydroxide ions, hydroxide diffusion is the lowest, underscoring the fact that water channels facilitate hydroxide transport. Finally, we apply uniaxial deformation to calculate the mechanical properties of these systems and find that polymers with higher hydration levels show poor mechanical properties. Atomistic molecular dynamics models can accurately capture the trade-off between hydroxide transport and mechanical performance in anion exchange membranes and allow us to screen new candidates more efficiently.

We present a simulation of various active learning strategies for the discovery of polymer solar cell donor/acceptor pairs using data extracted from the literature spanning $\sim$20 years by a natural language processing pipeline. While data-driven methods have been well established to discover novel materials faster than Edisonian trial-and-error approaches, their benefits have not been quantified for material discovery problems that can take decades. Our approach demonstrates a potential reduction in discovery time by approximately 75 %, equivalent to a 15 year acceleration in material innovation. Our pipeline enables us to extract data from greater than 3300 papers which is $\sim$5 times larger and therefore more diverse than similar data sets reported by others. We also trained machine learning models to predict the power conversion efficiency and used our model to identify promising donor-acceptor combinations that are as yet unreported. We thus demonstrate a pipeline that goes from published literature to extracted material property data which in turn is used to obtain data-driven insights. Our insights include active learning strategies that can be used to train strong predictive models of material properties or be robust to the initial material system used. This work provides a valuable framework for data-driven research in materials science.

Large language models (LLMs) have demonstrated impressive abilities in generating unstructured natural language according to instructions. However, their performance can be inconsistent when tasked with producing text that adheres to specific structured formats, which is crucial in applications like named entity recognition (NER) or relation extraction (RE). To address this issue, this paper introduces an efficient method, G&O, to enhance their structured text generation capabilities. It breaks the generation into a two-step pipeline: initially, LLMs generate answers in natural language as intermediate responses. Subsequently, LLMs are asked to organize the output into the desired structure, using the intermediate responses as context. G&O effectively separates the generation of content from the structuring process, reducing the pressure of completing two orthogonal tasks simultaneously. Tested on zero-shot NER and RE, the results indicate a significant improvement in LLM performance with minimal additional efforts. This straightforward and adaptable prompting technique can also be combined with other strategies, like self-consistency, to further elevate LLM capabilities in various structured text generation tasks., Comment: 15 pages, 5 figures, 5 tables

Scientific information extraction (SciIE), which aims to automatically extract information from scientific literature, is becoming more important than ever. However, there are no existing SciIE datasets for polymer materials, which is an important class of materials used ubiquitously in our daily lives. To bridge this gap, we introduce POLYIE, a new SciIE dataset for polymer materials. POLYIE is curated from 146 full-length polymer scholarly articles, which are annotated with different named entities (i.e., materials, properties, values, conditions) as well as their N-ary relations by domain experts. POLYIE presents several unique challenges due to diverse lexical formats of entities, ambiguity between entities, and variable-length relations. We evaluate state-of-the-art named entity extraction and relation extraction models on POLYIE, analyze their strengths and weaknesses, and highlight some difficult cases for these models. To the best of our knowledge, POLYIE is the first SciIE benchmark for polymer materials, and we hope it will lead to more research efforts from the community on this challenging task. Our code and data are available on: https://github.com/jerry3027/PolyIE., Comment: Work in progress

Polymer simulation with both accuracy and efficiency is a challenging task. Machine learning (ML) forcefields have been developed to achieve both the accuracy of ab initio methods and the efficiency of empirical force fields. However, existing ML force fields are usually limited to single-molecule settings, and their simulations are not robust enough. In this paper, we present PolyGET, a new framework for Polymer Forcefields with Generalizable Equivariant Transformers. PolyGET is designed to capture complex quantum interactions between atoms and generalize across various polymer families, using a deep learning model called Equivariant Transformers. We propose a new training paradigm that focuses exclusively on optimizing forces, which is different from existing methods that jointly optimize forces and energy. This simple force-centric objective function avoids competing objectives between energy and forces, thereby allowing for learning a unified forcefield ML model over different polymer families. We evaluated PolyGET on a large-scale dataset of 24 distinct polymer types and demonstrated state-of-the-art performance in force accuracy and robust MD simulations. Furthermore, PolyGET can simulate large polymers with high fidelity to the reference ab initio DFT method while being able to generalize to unseen polymers.

Recent works have shown the promise of learning pre-trained models for 3D molecular representation. However, existing pre-training models focus predominantly on equilibrium data and largely overlook off-equilibrium conformations. It is challenging to extend these methods to off-equilibrium data because their training objective relies on assumptions of conformations being the local energy minima. We address this gap by proposing a force-centric pretraining model for 3D molecular conformations covering both equilibrium and off-equilibrium data. For off-equilibrium data, our model learns directly from their atomic forces. For equilibrium data, we introduce zero-force regularization and forced-based denoising techniques to approximate near-equilibrium forces. We obtain a unified pre-trained model for 3D molecular representation with over 15 million diverse conformations. Experiments show that, with our pre-training objective, we increase forces accuracy by around 3 times compared to the un-pre-trained Equivariant Transformer model. By incorporating regularizations on equilibrium data, we solved the problem of unstable MD simulations in vanilla Equivariant Transformers, achieving state-of-the-art simulation performance with 2.45 times faster inference time than NequIP. As a powerful molecular encoder, our pre-trained model achieves on-par performance with state-of-the-art property prediction tasks.

Polymers are diverse and versatile materials that have met a wide range of material application demands. They come in several flavors and architectures, e.g., homopolymers, copolymers, polymer blends, and polymers with additives. Searching this enormous space for suitable materials with a specific set of property/performance targets is thus non-trivial, painstaking, and expensive. Such a search process can be made effective by the creation of rapid and accurate property predictors. In this work, we present a machine-learning framework to predict the thermal properties of homopolymers, copolymers, and polymer blends. A universal fingerprinting scheme capable of handling this entire polymer chemical class has been developed and a multi-task deep learning algorithm is trained simultaneously on a large dataset of glass transition, melting, and degradation temperatures. The developed models are accurate, fast, flexible, and scalable to other properties when suitable data become available.

Modern fuel cell technologies use Nafion as the material of choice for the proton exchange membrane (PEM) and as the binding material (ionomer), used to assemble the catalyst layers of the anode and cathode. These applications demand high proton conductivity as well as other requirements. For example, PEM is expected to block electrons, oxygen, and hydrogen from penetrating and diffusing while the anode/cathode ionomer should allow hydrogen/oxygen to move easily, so that they can reach the catalyst nanoparticles. Given some of the well-known limits of Nafion, such as low glass-transition temperature, the community is in the midst of an active search for Nafion replacements. In this work, we present an informatics-based scheme to search large polymer chemical spaces, which includes establishing a list of properties needed for the targeted applications, developing predictive machine-learning models for these properties, defining a search space, and using the developed models to screen the search space. Using the scheme, we have identified 60 new polymer candidates for PEM, anode ionomer, and cathode ionomer that we hope will be advanced to the next step, i.e., validating the designs through synthesis and testing. The proposed informatics scheme is generic, and can be used to select polymers for multiple applications in the future., Comment: in press, JPCC

A central problem of materials science is to determine whether a hypothetical material is stable without being synthesized, which is mathematically equivalent to a global optimization problem on a highly non-linear and multi-modal potential energy surface (PES). This optimization problem poses multiple outstanding challenges, including the exceedingly high dimensionality of the PES and that PES must be constructed from a reliable, sophisticated, parameters-free, and thus, very expensive computational method, for which density functional theory (DFT) is an example. DFT is a quantum mechanics based method that can predict, among other things, the total potential energy of a given configuration of atoms. DFT, while accurate, is computationally expensive. In this work, we propose a novel expansion-exploration-exploitation framework to find the global minimum of the PES. Starting from a few atomic configurations, this ``known'' space is expanded to construct a big candidate set. The expansion begins in a non-adaptive manner, where new configurations are added without considering their potential energy. A novel feature of this step is that it tends to generate a space-filling design without the knowledge of the boundaries of the domain space. If needed, the non-adaptive expansion of the space of configurations is followed by adaptive expansion, where ``promising regions'' of the domain space (those with low energy configurations) are further expanded. Once a candidate set of configurations is obtained, it is simultaneously explored and exploited using Bayesian optimization to find the global minimum. The methodology is demonstrated using a problem of finding the most stable crystal structure of Aluminum.

Polymers are a vital part of everyday life. Their chemical universe is so large that it presents unprecedented opportunities as well as significant challenges to identify suitable application-specific candidates. We present a complete end-to-end machine-driven polymer informatics pipeline that can search this space for suitable candidates at unprecedented speed and accuracy. This pipeline includes a polymer chemical fingerprinting capability called polyBERT (inspired by Natural Language Processing concepts), and a multitask learning approach that maps the polyBERT fingerprints to a host of properties. polyBERT is a chemical linguist that treats the chemical structure of polymers as a chemical language. The present approach outstrips the best presently available concepts for polymer property prediction based on handcrafted fingerprint schemes in speed by two orders of magnitude while preserving accuracy, thus making it a strong candidate for deployment in scalable architectures including cloud infrastructures.

Artificial intelligence-based methods are becoming increasingly effective at screening libraries of polymers down to a selection that is manageable for experimental inquiry. The vast majority of presently adopted approaches for polymer screening rely on handcrafted chemostructural features extracted from polymer repeat units -- a burdensome task as polymer libraries, which approximate the polymer chemical search space, progressively grow over time. Here, we demonstrate that directly "machine-learning" important features from a polymer repeat unit is a cheap and viable alternative to extracting expensive features by hand. Our approach -- based on graph neural networks, multitask learning, and other advanced deep learning techniques -- speeds up feature extraction by one to two orders of magnitude relative to presently adopted handcrafted methods without compromising model accuracy for a variety of polymer property prediction tasks. We anticipate that our approach, which unlocks the screening of truly massive polymer libraries at scale, will enable more sophisticated and large scale screening technologies in the field of polymer informatics.

The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from published literature. We used natural language processing (NLP) methods to automatically extract material property data from the abstracts of polymer literature. As a component of our pipeline, we trained MaterialsBERT, a language model, using 2.4 million materials science abstracts, which outperforms other baseline models in three out of five named entity recognition datasets when used as the encoder for text. Using this pipeline, we obtained ~300,000 material property records from ~130,000 abstracts in 60 hours. The extracted data was analyzed for a diverse range of applications such as fuel cells, supercapacitors, and polymer solar cells to recover non-trivial insights. The data extracted through our pipeline is made available through a web platform at https://polymerscholar.org which can be used to locate material property data recorded in abstracts conveniently. This work demonstrates the feasibility of an automatic pipeline that starts from published literature and ends with a complete set of extracted material property information.

Non-degradable plastic waste stays for decades on land and in water, jeopardizing our environment; yet our modern lifestyle and current technologies are impossible to sustain without plastics. Bio-synthesized and biodegradable alternatives such as the polymer family of polyhydroxyalkanoates (PHAs) have the potential to replace large portions of the world's plastic supply with cradle-to-cradle materials, but their chemical complexity and diversity limit traditional resource-intensive experimentation. In this work, we develop multitask deep neural network property predictors using available experimental data for a diverse set of nearly 23000 homo- and copolymer chemistries. Using the predictors, we identify 14 PHA-based bioplastics from a search space of almost 1.4 million candidates which could serve as potential replacements for seven petroleum-based commodity plastics that account for 75% of the world's yearly plastic production. We discuss possible synthesis routes for these identified promising materials. The developed multitask polymer property predictors are made available as a part of the Polymer Genome project at https://PolymerGenome.org.

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.

Learning 3D representations that generalize well to arbitrarily oriented inputs is a challenge of practical importance in applications varying from computer vision to physics and chemistry. We propose a novel multi-resolution convolutional architecture for learning over concentric spherical feature maps, of which the single sphere representation is a special case. Our hierarchical architecture is based on alternatively learning to incorporate both intra-sphere and inter-sphere information. We show the applicability of our method for two different types of 3D inputs, mesh objects, which can be regularly sampled, and point clouds, which are irregularly distributed. We also propose an efficient mapping of point clouds to concentric spherical images, thereby bridging spherical convolutions on grids with general point clouds. We demonstrate the effectiveness of our approach in improving state-of-the-art performance on 3D classification tasks with rotated data., Comment: This paper has been submitted for conference review

The increased energy and power density required in modern electronics poses a challenge for designing new dielectric polymer materials with high energy density while maintaining low loss at high applied electric fields. Recently, an advanced computational screening method coupled with hierarchical modelling has accelerated the identification of promising high energy density materials. It is well known that the dielectric response of polymeric materials is largely influenced by their phases and local heterogeneous structures as well as operational temperature. Such inputs are crucial to accelerate the design and discovery of potential polymer candidates. However, an efficient computational framework to probe temperature dependence of the dielectric properties of polymers, while incorporating effects controlled by their morphology is still lacking. In this paper, we propose a scalable computational framework based on reactive molecular dynamics with a valence-state aware polarizable charge model, which is capable of handling practically relevant polymer morphologies and simultaneously provide near-quantum accuracy in estimating dielectric properties of various polymer systems. We demonstrate the predictive power of our framework on high energy density polymer systems recently identified through rational experimental-theoretical co-design. Our scalable and automated framework may be used for high-throughput theoretical screenings of combinatorial large design space to identify next-generation high energy density polymer materials.

The design/discovery of new materials is highly non-trivial owing to the near-infinite possibilities of material candidates, and multiple required property/performance objectives. Thus, machine learning tools are now commonly employed to virtually screen material candidates with desired properties by learning a theoretical mapping from material-to-property space, referred to as the \emph{forward} problem. However, this approach is inefficient, and severely constrained by the candidates that human imagination can conceive. Thus, in this work on polymers, we tackle the materials discovery challenge by solving the \emph{inverse} problem: directly generating candidates that satisfy desired property/performance objectives. We utilize syntax-directed variational autoencoders (VAE) in tandem with Gaussian process regression (GPR) models to discover polymers expected to be robust under three extreme conditions: (1) high temperatures, (2) high electric field, and (3) high temperature \emph{and} high electric field, useful for critical structural, electrical and energy storage applications. This approach to learn from (and augment) human ingenuity is general, and can be extended to discover polymers with other targeted properties and performance measures.

Artificial intelligence (AI) based approaches are beginning to impact several domains of human life, science and technology. Polymer informatics is one such domain where AI and machine learning (ML) tools are being used in the efficient development, design and discovery of polymers. Surrogate models are trained on available polymer data for instant property prediction, allowing screening of promising polymer candidates with specific target property requirements. Questions regarding synthesizability, and potential (retro)synthesis steps to create a target polymer, are being explored using statistical means. Data-driven strategies to tackle unique challenges resulting from the extraordinary chemical and physical diversity of polymers at small and large scales are being explored. Other major hurdles for polymer informatics are the lack of widespread availability of curated and organized data, and approaches to create machine-readable representations that capture not just the structure of complex polymeric situations but also synthesis and processing conditions. Methods to solve inverse problems, wherein polymer recommendations are made using advanced AI algorithms that meet application targets, are being investigated. As various parts of the burgeoning polymer informatics ecosystem mature and become integrated, efficiency improvements, accelerated discoveries and increased productivity can result. Here, we review emergent components of this polymer informatics ecosystem and discuss imminent challenges and opportunities.

Modern data-driven tools are transforming application-specific polymer development cycles. Surrogate models that can be trained to predict the properties of new polymers are becoming commonplace. Nevertheless, these models do not utilize the full breadth of the knowledge available in datasets, which are oftentimes sparse; inherent correlations between different property datasets are disregarded. Here, we demonstrate the potency of multi-task learning approaches that exploit such inherent correlations effectively, particularly when some property dataset sizes are small. Data pertaining to 36 different properties of over $13, 000$ polymers (corresponding to over $23,000$ data points) are coalesced and supplied to deep-learning multi-task architectures. Compared to conventional single-task learning models (that are trained on individual property datasets independently), the multi-task approach is accurate, efficient, scalable, and amenable to transfer learning as more data on the same or different properties become available. Moreover, these models are interpretable. Chemical rules, that explain how certain features control trends in specific property values, emerge from the present work, paving the way for the rational design of application specific polymers meeting desired property or performance objectives.

Parameterization of interatomic forcefields is a necessary first step in performing molecular dynamics simulations. This is a non-trivial global optimization problem involving quantification of multiple empirical variables against one or more properties. We present EZFF, a lightweight Python library for parameterization of several types of interatomic forcefields implemented in several molecular dynamics engines against multiple objectives using genetic-algorithm-based global optimization methods. The EZFF scheme provides unique functionality such as the parameterization of hybrid forcefields composed of multiple forcefield interactions as well as built-in quantification of uncertainty in forcefield parameters and can be easily extended to other forcefield functional forms as well as MD engines.

The world has witnessed unprecedented human and economic loss from the COVID-19 disease, caused by the novel coronavirus SARS-CoV-2. Extensive research is being conducted across the globe to identify therapeutic agents against the SARS-CoV-2. Here, we use a powerful and efficient computational strategy by combining machine learning (ML) based models and high-fidelity ensemble docking simulations to enable rapid screening of possible therapeutic molecules (or ligands). Our screening is based on the binding affinity to either the isolated SARS-CoV-2 S-protein at its host receptor region or to the Sprotein-human ACE2 interface complex, thereby potentially limiting and/or disrupting the host-virus interactions. We first apply our screening strategy to two drug datasets (CureFFI and DrugCentral) to identify hundreds of ligands that bind strongly to the aforementioned two systems. Candidate ligands were then validated by all atom docking simulations. The validated ML models were subsequently used to screen a large bio-molecule dataset (with nearly a million entries) to provide a rank-ordered list of ~19,000 potentially useful compounds for further validation. Overall, this work not only expands our knowledge of small-molecule treatment against COVID-19, but also provides an efficient pathway to perform high-throughput computational drug screening by combining quick ML surrogate models with expensive high-fidelity simulations, for accelerating the therapeutic cure of diseases.

The lattice thermal conductivity ($\kappa_{\rm L} $) is a critical property of thermoelectrics, thermal barrier coating materials and semiconductors. While accurate empirical measurements of $\kappa_{\rm L} $ are extremely challenging, it is usually approximated through computational approaches, such as semi-empirical models, Green-Kubo formalism coupled with molecular dynamics simulations, and first-principles based methods. However, these theoretical methods are not only limited in terms of their accuracy, but sometimes become computationally intractable owing to their cost. Thus, in this work, we build a machine learning (ML)-based model to accurately and instantly predict $\kappa_{\rm L}$ of inorganic materials, using a benchmark data set of experimentally measured $\kappa_{\rm L} $ of about 100 inorganic solids. We use advanced and universal feature engineering techniques along with the Gaussian process regression algorithm, and compare the performance of our ML model with past theoretical works. The trained ML model is not only helpful for rational design and screening of novel materials, but we also identify key features governing the thermal transport behavior in non-metals.