Machine-Learning-Based Predictive Modeling of Glass Transition Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Copolymers

Green Synthesis of Bioplastics from Microalgae: A State-of-the-Art Review

The synthesis of conventional plastics has increased tremendously in the last decades due to rapid industrialization, population growth, and advancement in the use of modern technologies. However, overuse of these fossil fuel-based plastics has resulted in serious environmental and health hazards by causing pollution, global warming, etc. Therefore, the use of microalgae as a feedstock is a promising, green, and sustainable approach for the production of biobased plastics. Various biopolymers, such as polyhydroxybutyrate, polyurethane, polylactic acid, cellulose-based polymers, starch-based polymers, and protein-based polymers, can be produced from different strains of microalgae under varying culture conditions. Different techniques, including genetic engineering, metabolic engineering, the use of photobioreactors, response surface methodology, and artificial intelligence, are used to alter and improve microalgae stocks for the commercial synthesis of bioplastics at lower costs. In comparison to conventional plastics, these biobased plastics are biodegradable, biocompatible, recyclable, non-toxic, eco-friendly, and sustainable, with robust mechanical and thermoplastic properties. In addition, the bioplastics are suitable for a plethora of applications in the agriculture, construction, healthcare, electrical and electronics, and packaging industries. Thus, this review focuses on techniques for the production of biopolymers and bioplastics from microalgae. In addition, it discusses innovative and efficient strategies for large-scale bioplastic production while also providing insights into the life cycle assessment, end-of-life, and applications of bioplastics. Furthermore, some challenges affecting industrial scale bioplastics production and recommendations for future research are provided.

Structure-Based Multilevel Descriptors for High-throughput Screening of Elastomers

To discover new materials, high-throughput screening (HTS) with machine learning (ML) requires universally available descriptors that can accurately predict the desired properties. For elastomers, experimental and simulation data in current descriptors may not be available for all candidates of interest, hindering elastomer discovery through HTS. To address this challenge, we introduce structure-based multilevel (SM) descriptors of elastomers derived solely from molecular structure that is universally available. Our SM descriptors are hierarchically organized to capture both local soft and hard segment structures as well as the global structures of elastomers. With the SM-Morgan Fingerprint (SM-MF) descriptor, one of our SM descriptors, a machine learning model accurately predicts elastomer toughness with a remarkable accuracy of 0.91. Furthermore, an HTS pipeline is established to swiftly screen elastomers with targeted toughness. We also demonstrate the generality and applicability of SM descriptors by using them to construct HTS pipelines for screening elastomers with a targeted critical strain or Young's modulus. The user-friendliness and low computational cost of SM descriptors make them a promising tool to significantly enhance HTS in the search for novel materials.

Recent advances in the SISSO method and their implementation in the SISSO++ code

Accurate and explainable artificial-intelligence (AI) models are promising tools for accelerating the discovery of new materials. Recently, symbolic regression has become an increasingly popular tool for explainable AI because it yields models that are relatively simple analytical descriptions of target properties. Due to its deterministic nature, the sure-independence screening and sparsifying operator (SISSO) method is a particularly promising approach for this application. Here, we describe the new advancements of the SISSO algorithm, as implemented into SISSO++, a C++ code with Python bindings. We introduce a new representation of the mathematical expressions found by SISSO. This is a first step toward introducing "grammar" rules into the feature creation step. Importantly, by introducing a controlled nonlinear optimization to the feature creation step, we expand the range of possible descriptors found by the methodology. Finally, we introduce refinements to the solver algorithms for both regression and classification, which drastically increase the reliability and efficiency of SISSO. For all these improvements to the basic SISSO algorithm, we not only illustrate their potential impact but also fully detail how they operate both mathematically and computationally.

SMiPoly: Generation of a Synthesizable Polymer Virtual Library Using Rule-Based Polymerization Reactions

Recent advances in machine learning have led to the rapid adoption of various computational methods for de novo molecular design in polymer research, including high-throughput virtual screening and inverse molecular design. In such workflows, molecular generators play an essential role in creation or sequential modification of candidate polymer structures. Machine learning-assisted molecular design has made great technical progress over the past few years. However, the difficulty of identifying synthetic routes to such designed polymers remains unresolved. To address this technical limitation, we present Small Molecules into Polymers (SMiPoly), a Python library for virtual polymer generation that implements 22 chemical rules for commonly applied polymerization reactions. For given small organic molecules to form a candidate monomer set, the SMiPoly generator conducts possible polymerization reactions to generate an exhaustive list of potentially synthesizable polymers. In this study, using 1083 readily available monomers, we generated 169,347 unique polymers forming seven different molecular types: polyolefin, polyester, polyether, polyamide, polyimide, polyurethane, and polyoxazolidone. By comparing the distribution of the virtually created polymers with approximately 16,000 real polymers synthesized so far, it was found that the coverage and novelty of the SMiPoly-generated polymers can reach 48 and 53%, respectively. Incorporating the SMiPoly library into a molecular design workflow will accelerate the process of de novo polymer synthesis by shortening the step to select synthesizable candidate polymers.

Valorization of organic wastes using bioreactors for polyhydroxyalkanoate production: Recent advancement, sustainable approaches, challenges, and future perspectives

Microbial polyhydroxyalkanoates (PHA) are encouraging biodegradable polymers, which may ease the environmental problems caused by petroleum-derived plastics. However, there is a growing waste removal problem and the high price of pure feedstocks for PHA biosynthesis. This has directed to the forthcoming requirement to upgrade waste streams from various industries as feedstocks for PHA production. This review covers the state-of-the-art progress in utilizing low-cost carbon substrates, effective upstream and downstream processes, and waste stream recycling to sustain entire process circularity. This review also enlightens the use of various batch, fed-batch, continuous, and semi-continuous bioreactor systems with flexible results to enhance the productivity and simultaneously cost reduction. The life-cycle and techno-economic analyses, advanced tools and strategies for microbial PHA biosynthesis, and numerous factors affecting PHA commercialization were also covered. The review includes the ongoing and upcoming strategies viz. metabolic engineering, synthetic biology, morphology engineering, and automation to expand PHA diversity, diminish production costs, and improve PHA production with an objective of "zero-waste" and "circular bioeconomy" for a sustainable future.

Digital mapping of soil organic carbon density in China using an ensemble model

The soil organic carbon stock (SOCS) is considered as one of the largest carbon reservoirs in terrestrial ecosystems, and small changes in soil can cause significant changes in atmospheric CO2 concentration. Understanding organic carbon accumulation in soils is crucial if China is to meet its dual carbon target. In this study, the soil organic carbon density (SOCD) in China was digitally mapped using an ensemble machine learning (ML) model. First, based on SOCD data obtained at depths of 0-20 cm from 4356 sampling points (15 environmental covariates), we compared the performance of four ML models, namely random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and artificial neural network (ANN) models, in terms of coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) values. Then, we ensembled four models using Voting Regressor and the principle of stacking. The results showed that ensemble model (EM) accuracy was high (RMSE = 1.29, R2 = 0.85, MAE = 0.81), so that it could be a good choice for future research. Finally, the EM was used to predict the spatial distribution of SOCD in China, which ranged from 0.63 to 13.79 kg C/m2 (average = 4.09 (±1.90) kg C/m2). The SOC storage amount in surface soil (0-20 cm) was 39.40 Pg C. This study developed a novel, ensemble ML model for SOC prediction, and improved our understanding of the spatial distribution of SOC in China.

Applied machine learning as a driver for polymeric biomaterials design

Polymers are ubiquitous to almost every aspect of modern society and their use in medical products is similarly pervasive. Despite this, the diversity in commercial polymers used in medicine is stunningly low. Considerable time and resources have been extended over the years towards the development of new polymeric biomaterials which address unmet needs left by the current generation of medical-grade polymers. Machine learning (ML) presents an unprecedented opportunity in this field to bypass the need for trial-and-error synthesis, thus reducing the time and resources invested into new discoveries critical for advancing medical treatments. Current efforts pioneering applied ML in polymer design have employed combinatorial and high throughput experimental design to address data availability concerns. However, the lack of available and standardized characterization of parameters relevant to medicine, including degradation time and biocompatibility, represents a nearly insurmountable obstacle to ML-aided design of biomaterials. Herein, we identify a gap at the intersection of applied ML and biomedical polymer design, highlight current works at this junction more broadly and provide an outlook on challenges and future directions.

High-Throughput Screening and Prediction of High Modulus of Resilience Polymers Using Explainable Machine Learning

The ability to store and release elastic strain energy, as well as mechanical strength, are crucial factors in both natural and man-made mechanical systems. The modulus of resilience (R) indicates a material's capacity to absorb and release elastic strain energy, with the yield strength (σy) and Young's modulus (E) as R = σy2/(2E) for linear elastic solids. To improve the R in linear elastic solids, a high σy and low E combination in materials is sought after. However, achieving this combination is a significant challenge as both properties typically increase together. To address this challenge, we propose a computational method to quickly identify polymers with a high modulus of resilience using machine learning (ML) and validate the predictions through high-fidelity molecular dynamics (MD) simulations. Our approach commences by training single-task ML models, multitask ML models, and Evidential Deep Learning models to forecast the mechanical properties of polymers based on experimentally reported values. Utilizing explainable ML models, we were able to determine the critical substructures that significantly impact the mechanical properties of polymers, such as E and σy. This information can be utilized to create and develop new polymers with improved mechanical characteristics. Our single-task and multitask ML models can predict the properties of 12 854 real polymers and 8 million hypothetical polyimides and uncover 10 new real polymers and 10 hypothetical polyimides with exceptional modulus of resilience. The improved modulus of resilience of these novel polymers was validated through MD simulations. Our method efficiently speeds up the discovery of high-performing polymers using ML predictions and MD validation and can be applied to other polymer material discovery challenges, such as polymer membranes, dielectric polymers, and more.

Medium chain length polyhydroxyalkanoates as potential matrix materials for peripheral nerve regeneration

Polyhydroxyalkanoates are natural, biodegradable, thermoplastic and sustainable polymers with a huge potential in fabrication of bioresorbable implantable devices for tissue engineering. We describe a comparative evaluation of three medium chain length polyhydroxyalkanoates (mcl-PHAs), namely poly(3-hydroxyoctanoate), poly(3-hydroxyoctanoate-co-3-hydoxydecanoate) and poly(3-hydroxyoctanoate-co-3-hydroxydecanoate-co-3-hydroxydodecanoate), one short chain length polyhydroxyalkanoate, poly(3-hydroxybutyrate), P(3HB) and synthetic aliphatic polyesters (polycaprolactone and polylactide) with a specific focus on nerve regeneration, due to mechanical properties of mcl-PHAs closely matching nerve tissues. In vitro biological studies with NG108-15 neuronal cell and primary Schwann cells did not show a cytotoxic effect of the materials on both cell types. All mcl-PHAs supported cell adhesion and viability. Among the three mcl-PHAs, P(3HO-co-3HD) exhibited superior properties with regards to numbers of cells adhered and viable cells for both cell types, number of neurite extensions from NG108-15 cells, average length of neurite extensions and Schwann cells. Although, similar characteristics were observed for flat P(3HB) surfaces, high rigidity of this biomaterial, and FDA-approved polymers such as PLLA, limits their applications in peripheral nerve regeneration. Therefore, we have designed, synthesized and evaluated these materials for nerve tissue engineering and regenerative medicine, the interaction of mcl-PHAs with neuronal and Schwann cells, identifying mcl-PHAs as excellent materials to enhance nerve regeneration and potentially their clinical application in peripheral nerve repair.

polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics

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.

Emerging Trends in Machine Learning: A Polymer Perspective

In the last five years, there has been tremendous growth in machine learning and artificial intelligence as applied to polymer science. Here, we highlight the unique challenges presented by polymers and how the field is addressing them. We focus on emerging trends with an emphasis on topics that have received less attention in the review literature. Finally, we provide an outlook for the field, outline important growth areas in machine learning and artificial intelligence for polymer science and discuss important advances from the greater material science community.

Biomimetic natural biomaterials for tissue engineering and regenerative medicine: new biosynthesis methods, recent advances, and emerging applications

Biomimetic materials have emerged as attractive and competitive alternatives for tissue engineering (TE) and regenerative medicine. In contrast to conventional biomaterials or synthetic materials, biomimetic scaffolds based on natural biomaterial can offer cells a broad spectrum of biochemical and biophysical cues that mimic the in vivo extracellular matrix (ECM). Additionally, such materials have mechanical adaptability, microstructure interconnectivity, and inherent bioactivity, making them ideal for the design of living implants for specific applications in TE and regenerative medicine. This paper provides an overview for recent progress of biomimetic natural biomaterials (BNBMs), including advances in their preparation, functionality, potential applications and future challenges. We highlight recent advances in the fabrication of BNBMs and outline general strategies for functionalizing and tailoring the BNBMs with various biological and physicochemical characteristics of native ECM. Moreover, we offer an overview of recent key advances in the functionalization and applications of versatile BNBMs for TE applications. Finally, we conclude by offering our perspective on open challenges and future developments in this rapidly-evolving field.

Computational Design and Manufacturing of Sustainable Materials through First-Principles and Materiomics

Engineered materials are ubiquitous throughout society and are critical to the development of modern technology, yet many current material systems are inexorably tied to widespread deterioration of ecological processes. Next-generation material systems can address goals of environmental sustainability by providing alternatives to fossil fuel-based materials and by reducing destructive extraction processes, energy costs, and accumulation of solid waste. However, development of sustainable materials faces several key challenges including investigation, processing, and architecting of new feedstocks that are often relatively mechanically weak, complex, and difficult to characterize or standardize. In this review paper, we outline a framework for examining sustainability in material systems and discuss how recent developments in modeling, machine learning, and other computational tools can aid the discovery of novel sustainable materials. We consider these through the lens of materiomics, an approach that considers material systems holistically by incorporating perspectives of all relevant scales, beginning with first-principles approaches and extending through the macroscale to consider sustainable material design from the bottom-up. We follow with an examination of how computational methods are currently applied to select examples of sustainable material development, with particular emphasis on bioinspired and biobased materials, and conclude with perspectives on opportunities and open challenges.

Machine Learning with Enormous "Synthetic" Data Sets: Predicting Glass Transition Temperature of Polyimides Using Graph Convolutional Neural Networks

In the present work, we address the problem of utilizing machine learning (ML) methods to predict the thermal properties of polymers by establishing "structure-property" relationships. Having focused on a particular class of heterocyclic polymers, namely polyimides (PIs), we developed a graph convolutional neural network (GCNN), being one of the most promising tools for working with big data, to predict the PI glass transition temperature T g as an example of the fundamental property of polymers. To train the GCNN, we propose an original methodology based on using a "transfer learning" approach with an enormous "synthetic" data set for pretraining and a small experimental data set for its fine-tuning. The "synthetic" data set contains more than 6 million combinatorically generated repeating units of PIs and theoretical values of their T g values calculated using the well-established Askadskii's quantitative structure-property relationship (QSPR) computational scheme. Additionally, an experimental data set for 214 PIs was also collected from the literature for training, fine-tuning, and validation of the GCNN. Both "synthetic" and experimental data sets are included into a PolyAskInG database (Polymer Askadskii's Intelligent Gateway). By using the PolyAskInG database, we developed GCNN which allows estimation of T g of PI with a mean absolute error (MAE) of about 20 K, which is 1.5 times lower than in the case of Askadskii QSPR analysis (33 K). To prove the efficiency and usability of the proposed GCNN architecture and training methodology for predicting polymer properties, we also employed "transfer learning" to develop alternative GCNN pretrained on proxy-characteristics taken from the popular quantum-chemical QM9 database for small compounds and fine-tuned on an experimental T g values data set from PolyAskInG database. The obtained results indicate that pretraining of GCNN on the "synthetic" polymer data set provides MAE which is almost twice as low as that in the case of using the QM9 data set in the pretraining stage (∼41 K). Furthermore, we address the questions associated with the influence of the differences in the size of the experimental and "synthetic" data sets (so-called "reality gap" problem), as well as their chemical composition on the training quality. Our results state the overall priority of using polymer data sets for developing deep neural networks, and GCNN in particular, for efficient prediction of polymer properties. Moreover, our work opens up a challenge for the theoretically supported generation of large "synthetic" data sets of polymer properties for the training of the complex ML models. The proposed methodology is rather versatile and may be generalized for predicting other properties of different polymers and copolymers synthesized through the polycondensation reaction.

Novel Production Methods of Polyhydroxyalkanoates and Their Innovative Uses in Biomedicine and Industry

Polyhydroxyalkanoate (PHA), a biodegradable polymer obtained from microorganisms and plants, have been widely used in biomedical applications and devices, such as sutures, cardiac valves, bone scaffold, and drug delivery of compounds with pharmaceutical interests, as well as in food packaging. This review focuses on the use of polyhydroxyalkanoates beyond the most common uses, aiming to inform about the potential uses of the biopolymer as a biosensor, cosmetics, drug delivery, flame retardancy, and electrospinning, among other interesting uses. The novel applications are based on the production and composition of the polymer, which can be modified by genetic engineering, a semi-synthetic approach, by changing feeding carbon sources and/or supplement addition, among others. The future of PHA is promising, and despite its production costs being higher than petroleum-based plastics, tools given by synthetic biology, bioinformatics, and machine learning, among others, have allowed for great production yields, monomer and polymer functionalization, stability, and versatility, a key feature to increase the uses of this interesting family of polymers.

Unified machine learning protocol for copolymer structure-property predictions

Structure-property relationships are extremely valuable when predicting the properties of polymers. This protocol demonstrates a step-by-step approach, based on multiple machine learning (ML) architectures, which is capable of processing copolymer types such as alternating, random, block, and gradient copolymers. We detail steps for necessary software installation and construction of datasets. We further describe training and optimization steps for four neural network models and subsequent model visualization and comparison using training and test values. For complete details on the use and execution of this protocol, please refer to Tao et al. (2022).¹.

Machine-Learning-Based Predictions of Polymer and Postconsumer Recycled Polymer Properties: A Comprehensive Review

There has been a tremendous increase in demand for virgin and postconsumer recycled (PCR) polymers due to their wide range of chemical and physical characteristics. Despite the numerous potential benefits of using a data-driven approach to polymer design, major hurdles exist in the development of polymer informatics due to the complicated hierarchical polymer structures. In this review, a brief introduction on virgin polymer structure, PCR polymers, compatibilization of polymers to be recycled, and their characterization using sensor array technologies as well as factors affecting the polymer properties are provided. Machine-learning (ML) algorithms are gaining attention as cost-effective scalable solutions to exploit the physical and chemical structures of polymers. The basic steps for applying ML in polymer science such as fingerprinting, algorithms, open-source databases, representations, and polymer design are detailed in this review. Further, a state-of-the-art review of the prediction of various polymer material properties using ML is reviewed. Finally, we discuss open-ended research questions on ML application to PCR polymers as well as potential challenges in the prediction of their properties using artificial intelligence for more efficient and targeted PCR polymer discovery and development.

Machine learning strategies for the structure-property relationship of copolymers

Establishing the structure-property relationship is extremely valuable for the molecular design of copolymers. However, machine learning (ML) models can incorporate both chemical composition and sequence distribution of monomers, and have the generalization ability to process various copolymer types (e.g., alternating, random, block, and gradient copolymers) with a unified approach are missing. To address this challenge, we formulate four different ML models for investigation, including a feedforward neural network (FFNN) model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, and a combined FFNN/RNN (Fusion) model. We use various copolymer types to systematically validate the performance and generalizability of different models. We find that the RNN architecture that processes the monomer sequence information both forward and backward is a more suitable ML model for copolymers with better generalizability. As a supplement to polymer informatics, our proposed approach provides an efficient way for the evaluation of copolymers.

Decoding hexanitrobenzene (HNB) and 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) as two distinctive energetic nitrobenzene compounds by machine learning

Energetic materials (EMs) are a group of special energy materials, and it is generally full of safety risks and generally costs much to create new EMs. Thus, machine learning (ML)-aided discovery becomes highly desired for EMs, as ML is good at risk and cost reduction. This work decodes hexanitrobenzene (HNB) and 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) as two distinctive energetic nitrobenzene compounds by ML, in combination with theoretical calculations. Based on a series of highly accurate models of density, heat of formation, bond dissociation energy and molecular flatness, the ML predictions show that HNB is the most energetic among ∼370 000 000 single benzene ring-containing compounds, while TATB possesses a moderate energy content and very high safety, as determined experimentally. This work exhibits the significant power of ML and presents an instructive procedure for using it in the field of EMs. The ML-aided design and highly efficient synthesis and fabrication combined strategy is expected to accelerate the discovery of new EMs.

Predicting Young's Modulus of Linear Polyurethane and Polyurethane-Polyurea Elastomers: Bridging Length Scales with Physicochemical Modeling and Machine Learning

Predicting the properties of complex polymeric materials based on monomer chemistry requires modeling physical interactions that bridge molecular, interchain, microstructure, and bulk length scales. For polyurethanes, a polymer class with global commercial and industrial significance, these multiscale challenges are intrinsic due to the thermodynamic incompatibility of the urethane and polyol-rich domains, resulting in heterogeneities from molecular to microstructural length scales. Machine learning can model patterns in data to establish a relationship between the monomer chemistry and bulk material properties, but this is made difficult by small data sets and a diverse set of monomers. Using a data set of 63 industrially relevant and complex elastomers, we demonstrate that accurate machine learning predictions are possible when monomer chemistry is used to estimate interactions at interchain length scales. Here, these features were used to accurately (r² = 0.91) predict the Young's modulus of polyurethane and polyurethane-urea elastomers. Furthermore, by a query of the trained model for compositions that yield a target modulus within the range of accessible values, the capabilities of using this methodology as a design tool are demonstrated. The presented methodology could become increasingly useful in building models for materials with small data sets and may guide the interpretation of the underlying physicochemical forces.

Atomistic Understanding of Ion Exchange Strengthening of Boroaluminosilicate Glasses: Insights from Molecular Dynamics Simulations and QSPR Analysis

Ion exchange (IOX) is an effective and widely used method to enhance mechanical properties of various glass products ranging from the touch screen of consumer electronics to window shields of airplanes and spacecrafts. IOX or chemical strengthening is achieved through the creation of a compressive surface layer on the glass product. Although widely studied experimentally, the fundamental understanding of the IOX strengthening process is still limited. In this work, we have applied large-scale atomistic simulations to understand IOX-induced mechanical property changes and their relation to the glass composition and structural characteristics. Two series of borosilicate glasses are studied to elucidate the composition effect, with boron oxide for silica and alumina for silica substitutions, respectively, on the mechanical properties of different levels of K⁺ to Na⁺ ion exchanges by using molecular dynamics (MD) simulations with a set of recently developed effective partial charge potentials. The linear network dilation coefficient (LNDC), a common measure of IOX behaviors, was calculated for each of the glass compositions. Quantitative structural property relationship (QSPR) analysis based on the MD-generated structural features was used to establish the structure-property correlations of mechanical and other properties. The results show strong composition dependence of the LNDC, hence the suitability of IOX strengthening. This behavior is discussed based on glass structure features of the glasses. It was found that glass compositions with a higher amount of mixed glass formers, higher network connectivity, and less complex components tend to show higher calculated LNDC and higher surface compressive stress. MD simulations, in combination with QSPR analysis, can thus provide atomistic insights into how the glass composition and structural characteristics affect IOX behaviors.

Machine Learning-Assisted Design of Material Properties

Designing functional materials requires a deep search through multidimensional spaces for system parameters that yield desirable material properties. For cases where conventional parameter sweeps or trial-and-error sampling are impractical, inverse methods that frame design as a constrained optimization problem present an attractive alternative. However, even efficient algorithms require time- and resource-intensive characterization of material properties many times during optimization, imposing a design bottleneck. Approaches that incorporate machine learning can help address this limitation and accelerate the discovery of materials with targeted properties. In this article, we review how to leverage machine learning to reduce dimensionality in order to effectively explore design space, accelerate property evaluation, and generate unconventional material structures with optimal properties. We also discuss promising future directions, including integration of machine learning into multiple stages of a design algorithm and interpretation of machine learning models to understand how design parameters relate to material properties. Expected final online publication date for the Annual Review of Chemical and Biomolecular Engineering, Volume 13 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Data-Driven Methods for Accelerating Polymer Design

Optimal design of polymers is a challenging task due to their enormous chemical and configurational space. Recent advances in computations, machine learning, and increasing trends in data and software availability can potentially address this problem and accelerate the molecular-scale design of polymers. Here, the central problem of polymer design is reviewed, and the general ideas of data-driven methods and their working principles in the context of polymer design are discussed. This Review provides a historical perspective and a summary of current trends and outlines future scopes of data-driven methods for polymer research. A few representative case studies on the use of such data-driven methods for discovering new polymers with exceptional properties are presented. Moreover, attempts are made to highlight how data-driven strategies aid in establishing new correlations and advancing the fundamental understanding of polymers. This Review posits that the combination of machine learning, rapid computational characterization of polymers, and availability of large open-sourced homogeneous data will transform polymer research and development over the coming decades. It is hoped that this Review will serve as a useful reference to researchers who wish to develop and deploy data-driven methods for polymer research and education.

Machine Learning at the Interface of Polymer Science and Biology: How Far Can We Go?

This Perspective outlines recent progress and future directions for using machine learning (ML), a data-driven method, to address critical questions in the design, synthesis, processing, and characterization of biomacromolecules. The achievement of these tasks requires the navigation of vast and complex chemical and biological spaces, difficult to accomplish with reasonable speed. Using modern algorithms and supercomputers, quantum physics methods are able to examine systems containing a few hundred interacting species and determine the probability of finding them in a particular region of phase space, thereby anticipating their properties. Likewise, modern approaches in chemistry and biomolecular simulation, supported by high performance computing, have culminated in producing data sets of escalating size and intrinsically high complexity. Hence, using ML to extract relevant information from these fields is of paramount importance to advance our understanding of chemical and biomolecular systems. At the heart of ML approaches lie statistical algorithms, which by evaluating a portion of a given data set, identify, learn, and manipulate the underlying rules that govern the whole data set. The assembly of a quality model to represent the data followed by the predictions and elimination of error sources are the key steps in ML. In addition to a growing infrastructure of ML tools to address complex problems, an increasing number of aspects related to our understanding of the fundamental properties of biomacromolecules are exposed to ML. These fields, including those residing at the interface of polymer science and biology (i.e., structure determination, de novo design, folding, and dynamics), strive to adopt and take advantage of the transformative power offered by approaches in the ML domain, which clearly has the potential of accelerating research in the field of biomacromolecules.

Integration of Machine Learning and Coarse-Grained Molecular Simulations for Polymer Materials: Physical Understandings and Molecular Design

In recent years, the synthesis of monomer sequence-defined polymers has expanded into broad-spectrum applications in biomedical, chemical, and materials science fields. Pursuing the characterization and inverse design of these polymer systems requires our fundamental understanding not only at the individual monomer level, but also considering the chain scales, such as polymer configuration, self-assembly, and phase separation. However, our accessibility to this field is still rudimentary due to the limitations of traditional design approaches, the complexity of chemical space along with the burdened cost and time issues that prevent us from unveiling the underlying monomer sequence-structure-property relationships. Fortunately, thanks to the recent advancements in molecular dynamics simulations and machine learning (ML) algorithms, the bottlenecks in the tasks of establishing the structure-function correlation of the polymer chains can be overcome. In this review, we will discuss the applications of the integration between ML techniques and coarse-grained molecular dynamics (CGMD) simulations to solve the current issues in polymer science at the chain level. In particular, we focus on the case studies in three important topics-polymeric configuration characterization, feed-forward property prediction, and inverse design-in which CGMD simulations are leveraged to generate training datasets to develop ML-based surrogate models for specific polymer systems and designs. By doing so, this computational hybridization allows us to well establish the monomer sequence-functional behavior relationship of the polymers as well as guide us toward the best polymer chain candidates for the inverse design in undiscovered chemical space with reasonable computational cost and time. Even though there are still limitations and challenges ahead in this field, we finally conclude that this CGMD/ML integration is very promising, not only in the attempt of bridging the monomeric and macroscopic characterizations of polymer materials, but also enabling further tailored designs for sequence-specific polymers with superior properties in many practical applications.

Machine Learning-Driven Biomaterials Evolution

Biomaterials is an exciting and dynamic field, which uses a collection of diverse materials to achieve desired biological responses. While there is constant evolution and innovation in materials with time, biomaterials research has been hampered by the relatively long development period required. In recent years, driven by the need to accelerate materials development, the applications of machine learning in materials science has progressed in leaps and bounds. The combination of machine learning with high-throughput theoretical predictions and high-throughput experiments (HTE) has shifted the traditional Edisonian (trial and error) paradigm to a data-driven paradigm. In this review, each type of biomaterial and their key properties and use cases are systematically discussed, followed by how machine learning can be applied in the development and design process. The discussions are classified according to various types of materials used including polymers, metals, ceramics, and nanomaterials, and implants using additive manufacturing. Last, the current gaps and potential of machine learning to further aid biomaterials discovery and application are also discussed.

Characterization of Polyhydroxybutyrate-Based Composites Prepared by Injection Molding

The waste generated by single-use plastics is often non-recyclable and non-biodegradable, inevitably ending up in our landfills, ecosystems, and food chain. Through the introduction of biodegradable polymers as substitutes for common plastics, we can decrease our impact on the planet. In this study, we evaluate the changes in mechanical and thermal properties of polyhydroxybutyrate-based composites with various additives: Microspheres, carbon fibers or polyethylene glycol (2000, 10,000, and 20,000 MW). The mixtures were injection molded using an in-house mold attached to a commercial extruder. The resulting samples were characterized using microscopy and a series of spectroscopic, thermal, and mechanical techniques. We have shown that the addition of carbon fibers and microspheres had minimal impact on thermal stability, whereas polyethylene glycol showed slight improvements at higher molecular weights. All of the composite samples showed a decrease in hardness and compressibility. The findings described in this study will improve our understanding of polyhydroxybutyrate-based composites prepared by injection molding, enabling advancements in integrating biodegradable plastics into everyday products.

Benchmarking Machine Learning Models for Polymer Informatics: An Example of Glass Transition Temperature

In the field of polymer informatics, utilizing machine learning (ML) techniques to evaluate the glass transition temperature T_g and other properties of polymers has attracted extensive attention. This data-centric approach is much more efficient and practical than the laborious experimental measurements when encountered a daunting number of polymer structures. Various ML models are demonstrated to perform well for T_g prediction. Nevertheless, they are trained on different data sets, using different structure representations, and based on different feature engineering methods. Thus, the critical question arises on selecting a proper ML model to better handle the T_g prediction with generalization ability. To provide a fair comparison of different ML techniques and examine the key factors that affect the model performance, we carry out a systematic benchmark study by compiling 79 different ML models and training them on a large and diverse data set. The three major components in setting up an ML model are structure representations, feature representations, and ML algorithms. In terms of polymer structure representation, we consider the polymer monomer, repeat unit, and oligomer with longer chain structure. Based on that feature, representation is calculated, including Morgan fingerprinting with or without substructure frequency, RDKit descriptors, molecular embedding, molecular graph, etc. Afterward, the obtained feature input is trained using different ML algorithms, such as deep neural networks, convolutional neural networks, random forest, support vector machine, LASSO regression, and Gaussian process regression. We evaluate the performance of these ML models using a holdout test set and an extra unlabeled data set from high-throughput molecular dynamics simulation. The ML model's generalization ability on an unlabeled data set is especially focused, and the model's sensitivity to topology and the molecular weight of polymers is also taken into consideration. This benchmark study provides not only a guideline for the T_g prediction task but also a useful reference for other polymer informatics tasks.

Machine-Learning-Guided Discovery of 19F MRI Agents Enabled by Automated Copolymer Synthesis

Modern polymer science suffers from the curse of multidimensionality. The large chemical space imposed by including combinations of monomers into a statistical copolymer overwhelms polymer synthesis and characterization technology and limits the ability to systematically study structure-property relationships. To tackle this challenge in the context of 19F magnetic resonance imaging (MRI) agents, we pursued a computer-guided materials discovery approach that combines synergistic innovations in automated flow synthesis and machine learning (ML) method development. A software-controlled, continuous polymer synthesis platform was developed to enable iterative experimental-computational cycles that resulted in the synthesis of 397 unique copolymer compositions within a six-variable compositional space. The nonintuitive design criteria identified by ML, which were accomplished by exploring <0.9% of the overall compositional space, lead to the identification of >10 copolymer compositions that outperformed state-of-the-art materials.

Machine Learning: New Ideas and Tools in Environmental Science and Engineering

The rapid increase in both the quantity and complexity of data that are being generated daily in the field of environmental science and engineering (ESE) demands accompanied advancement in data analytics. Advanced data analysis approaches, such as machine learning (ML), have become indispensable tools for revealing hidden patterns or deducing correlations for which conventional analytical methods face limitations or challenges. However, ML concepts and practices have not been widely utilized by researchers in ESE. This feature explores the potential of ML to revolutionize data analysis and modeling in the ESE field, and covers the essential knowledge needed for such applications. First, we use five examples to illustrate how ML addresses complex ESE problems. We then summarize four major types of applications of ML in ESE: making predictions; extracting feature importance; detecting anomalies; and discovering new materials or chemicals. Next, we introduce the essential knowledge required and current shortcomings in ML applications in ESE, with a focus on three important but often overlooked components when applying ML: correct model development, proper model interpretation, and sound applicability analysis. Finally, we discuss challenges and future opportunities in the application of ML tools in ESE to highlight the potential of ML in this field.

"pySiRC": Machine Learning Combined with Molecular Fingerprints to Predict the Reaction Rate Constant of the Radical-Based Oxidation Processes of Aqueous Organic Contaminants

We developed a web application structured in a machine learning and molecular fingerprint algorithm for the automatic calculation of the reaction rate constant of the oxidative processes of organic pollutants by ^•OH and SO₄^•- radicals in the aqueous phase-the pySiRC platform. The model development followed the OECD principles: internal and external validation, applicability domain, and mechanistic interpretation. Three machine learning algorithms combined with molecular fingerprints were evaluated, and all the models resulted in high goodness-of-fit for the training set with R² > 0.931 for the ^•OH radical and R² > 0.916 for the SO₄^•- radical and good predictive capacity for the test set with R_ext² = Q_ext² values in the range of 0.639-0.823 and 0.767-0.824 for the ^•OH and SO₄^•- radicals. The model was interpreted using the SHAP (SHapley Additive exPlanations) method: the results showed that the model developed made the prediction based on a reasonable understanding of how electron-withdrawing and -donating groups interfere with the reactivity of the ^•OH and SO₄^•- radicals. We hope that our models and web interface can stimulate and expand the application and interpretation of kinetic research on contaminants in water treatment units based on advanced oxidative technologies.

Biomaterials by design: Harnessing data for future development

Biomaterials is an interdisciplinary field of research to achieve desired biological responses from new materials, regardless of material type. There have been many exciting innovations in this discipline, but commercialization suffers from a lengthy discovery to product pipeline, with many failures along the way. Success can be greatly accelerated by harnessing machine learning techniques to comb through large amounts of data. There are many potential benefits of moving from an unstructured empirical approach to a development strategy that is entrenched in data. Here, we discuss the recent work on the use of machine learning in the discovery and design of biomaterials, including new polymeric, metallic, ceramics, and nanomaterials, and how machine learning can interface with emerging use cases of 3D printing. We discuss the steps for closer integration of machine learning to make this exciting possibility a reality.

Predicting Polymers' Glass Transition Temperature by a Chemical Language Processing Model

We propose a chemical language processing model to predict polymers' glass transition temperature (Tg) through a polymer language (SMILES, Simplified Molecular Input Line Entry System) embedding and recurrent neural network. This model only receives the SMILES strings of a polymer's repeat units as inputs and considers the SMILES strings as sequential data at the character level. Using this method, there is no need to calculate any additional molecular descriptors or fingerprints of polymers, and thereby, being very computationally efficient. More importantly, it avoids the difficulties to generate molecular descriptors for repeat units containing polymerization point '*'. Results show that the trained model demonstrates reasonable prediction performance on unseen polymer's Tg. Besides, this model is further applied for high-throughput screening on an unlabeled polymer database to identify high-temperature polymers that are desired for applications in extreme environments. Our work demonstrates that the SMILES strings of polymer repeat units can be used as an effective feature representation to develop a chemical language processing model for predictions of polymer Tg. The framework of this model is general and can be used to construct structure-property relationships for other polymer properties.

QSPR modelling for intrinsic viscosity in polymer-solvent combinations based on density functional theory

Linear and nonlinear quantitative structure-property relationship (QSPR) models were developed based on a dataset with 65 polymer-solvent combinations. Seven quantum chemical descriptors, dipole moment, hardness, chemical potential, electrophilicity index, total energy, HOMO and LUMO orbital energies, were calculated with density functional theory at the B3LYP/6-31 G(d) level for polymers and solvents. Considering the strong correlation between intrinsic viscosity and weight, size, shape as well as topological structure of polymers and solvents, topological descriptors were also applied in this work. Meanwhile, the most appropriate polymer structure representation was investigated by considering 1-5 monomeric repeating units. The molecular descriptors were first screened by using the genetic algorithms-multiple linear regression (GA-MLR), with coefficient of determinations (r2) of 0.78 and 0.83 for the training set and the prediction set, respectively. The support vector machine model (SVM) model based on the selected descriptors subset showed a r2 value of 0.95 for the training set and 0.93 for the prediction set. All statistical results suggest that the established QSPR models have good predictability. Furthermore, a new test set obtained from the literature was used for further validation. The r2 values were 0.81 for the MLR model and 0.90 for the SVM model.

Polymer informatics with multi-task learning

Modern data-driven tools are transforming application-specific polymer development cycles. Surrogate models that can be trained to predict properties of 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. Data pertaining to 36 different properties of over 13,000 polymers are supplied to deep-learning multi-task architectures. Compared to conventional single-task learning models, 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 property values, emerge from the present work, paving the way for the rational design of application specific polymers meeting desired property or performance objectives.

•

We overcome data scarcity in polymer datasets using multi-task models

•

Our approach is expected to become the preferred training method for materials data

•

We derive chemical guidelines for the design of application specific polymers

Polymers display extraordinary diversity in their chemistry, structure, and applications. However, finding the ideal polymer possessing the right combination of properties for a given application is non-trivial as the chemical space of polymers is practically infinite. This daunting search problem can be mitigated by surrogate models, trained using machine learning algorithms on available property data, that can make instantaneous predictions of polymer properties. In this work, we present a versatile, interpretable, and scalable scheme to build such predictive models. Our “multi-task learning” approach is used for the first time within materials informatics and efficiently, effectively, and simultaneously learns and predicts multiple polymer properties. This development is expected to have a significant impact on data-driven materials discovery.

Machine learning discovery of high-temperature polymers

To formulate a machine learning (ML) model to establish the polymer's structure-property correlation for glass transition temperatureT g , we collect a diverse set of nearly 13,000 real homopolymers from the largest polymer database, PoLyInfo. We train the deep neural network (DNN) model with 6,923 experimentalT g values using Morgan fingerprint representations of chemical structures for these polymers. Interestingly, the trained DNN model can reasonably predict the unknownT g values of polymers with distinct molecular structures, in comparison with molecular dynamics simulations and experimental results. With the validated transferability and generalization ability, the ML model is utilized for high-throughput screening of nearly one million hypothetical polymers. We identify more than 65,000 promising candidates withT g > 200°C, which is 30 times more than existing known high-temperature polymers (∼2,000 from PoLyInfo). The discovery of this large number of promising candidates will be of significant interest in the development and design of high-temperature polymers.

Surface science of cosmetic substrates, cleansing actives and formulations

The development of shampoo and cleansing formulations in cosmetics is at a crossroads due to consumer demands for better performing, more natural products and also the strong commitment of cosmetic companies to improve the sustainability of cosmetic products. In order to go beyond traditional formulations, it is of great importance to clearly establish the science behind cleansing technologies and appreciate the specificity of cleansing biological surfaces such as hair and skin. In this review, we present recent advances in our knowledge of the physicochemical properties of the hair surface from both an experimental and a theoretical point of view. We discuss the opportunities and challenges that newer, sustainable formulations bring compared to petroleum-based ingredients. The inevitable evolution towards more bio-based, eco-friendly ingredients and sustainable formulations requires a complete rethink of many well-known physicochemical principles. The pivotal role of digital sciences and modelling in the understanding and conception of new ingredients and formulations is discussed. We describe recent numerical approaches that take into account the specificities of the hair surface in terms of structuration, different methods that study the adsorption of formulation ingredients and finally the success of new data-driven approaches. We conclude with practical examples on current formulation efforts incorporating bio-surfactants, controlling foaming and searching for new rheological properties.

A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers

The purpose of this study was to develop a data-driven machine learning model to predict the performance properties of polyhydroxyalkanoates (PHAs), a group of biosourced polyesters featuring excellent performance, to guide future design and synthesis experiments. A deep neural network (DNN) machine learning model was built for predicting the glass transition temperature, T_g, of PHA homo- and copolymers. Molecular fingerprints were used to capture the structural and atomic information of PHA monomers. The other input variables included the molecular weight, the polydispersity index, and the percentage of each monomer in the homo- and copolymers. The results indicate that the DNN model achieves high accuracy in estimation of the glass transition temperature of PHAs. In addition, the symmetry of the DNN model is ensured by incorporating symmetry data in the training process. The DNN model achieved better performance than the support vector machine (SVD), a nonlinear ML model and least absolute shrinkage and selection operator (LASSO), a sparse linear regression model. The relative importance of factors affecting the DNN model prediction were analyzed. Sensitivity of the DNN model, including strategies to deal with missing data, were also investigated. Compared with commonly used machine learning models incorporating quantitative structure-property (QSPR) relationships, it does not require an explicit descriptor selection step but shows a comparable performance. The machine learning model framework can be readily extended to predict other properties.

Machine Learning Predictions of Block Copolymer Self-Assembly

Directed self-assembly of block copolymers is a key enabler for nanofabrication of devices with sub-10 nm feature sizes, allowing patterning far below the resolution limit of conventional photolithography. Among all the process steps involved in block copolymer self-assembly, solvent annealing plays a dominant role in determining the film morphology and pattern quality, yet the interplay of the multiple parameters during solvent annealing, including the initial thickness, swelling, time, and solvent ratio, makes it difficult to predict and control the resultant self-assembled pattern. Here, machine learning tools are applied to analyze the solvent annealing process and predict the effect of process parameters on morphology and defectivity. Two neural networks are constructed and trained, yielding accurate prediction of the final morphology in agreement with experimental data. A ridge regression model is constructed to identify the critical parameters that determine the quality of line/space patterns. These results illustrate the potential of machine learning to inform nanomanufacturing processes.

Machine learning glass transition temperature of styrenic random copolymers

For styrenic random copolymers, the glass transition temperature, Tg, is an important thermophysical parameter, which is sometimes difficult to measure and determine by experiments. Approaches based on data-driven modeling provide alternative methods to predict Tg in a fast and robust way. The Gaussian process regression (GPR) model is investigated to present the statistical relationship between important quantum chemical descriptors and glass transition temperature for styrenic random copolymers. 48 samples with Tg that have been measured experimentally are explored, which range from 246 K to 426 K. The modeling approach demonstrates high accuracy and stability, and provides a novel and promising tool for efficient and low-cost estimations of copolymer Tg values.