Block copolymer (BCP) self-assembly has attracted considerable attention for many decades because it can yield ordered structures in a wide range of morphologies, including spheres, cylinders, bicontinuous structures, lamellae, vesicles, and many other complex or hierarchical assemblies. These aggregates provide potential or practical applications in many fields. The present tutorial review introduces the primary principles of BCP self-assembly in bulk and in solution, by describing experiments, theories, accessible morphologies and morphological transitions, factors affecting the morphology, thermodynamics and kinetics, among others. As one specific example at a more advanced level, BCP vesicles (polymersomes) and their potential applications are discussed in some detail.

/pdf/self-assembly-of-block-copolymers-381hzqnmce.pdf

Self-assembly of block copolymers

Materials discovery and design using machine learning

The rise and fall of artificial neural networks is well documented in the scientific literature of both computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on multilayer neural networks. Within the last few years, we have seen the transformative impact of deep learning in many domains, particularly in speech recognition and computer vision, to the extent that the majority of expert practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties that distinguish them from traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including quantitative structure activity relationship, virtual screening, protein structure prediction, quantum chemistry, materials design, and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non-neural networks state-of-the-art models across disparate research topics, and deep neural network-based models often exceeded the "glass ceiling" expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a valuable tool for computational chemistry. © 2017 Wiley Periodicals, Inc.

Deep learning for computational chemistry

On a simple approach for determining applicability domain of QSAR models

Ionic liquids (ILs) offer a wide range of promising applications because of their much enhanced properties. However, further development of such materials depends on the fundamental understanding of their hierarchical structures and behaviors, which requires multiscale strategies to provide coupling among various length scales. In this review, we first introduce the structures and properties of these typical ILs. Then, we introduce the multiscale modeling methods that have been applied to the ILs, covering from molecular scale (QM/MM), to mesoscale (CG, DPD), to macroscale (CFD for unit scale and thermodynamics COSMO-RS model and environmental assessment GD method for process scale). In the following section, we discuss in some detail their applications to the four scales of ILs, including molecular scale structures, mesoscale aggregates and dynamics, and unit scale reactor design and process design and optimization of typical IL applications. Finally, we address the concluding remarks of multiscale strat...

Multiscale Studies on Ionic Liquids

Quantitative Structure Property Relationship Modeling of Diverse Materials Properties Tu Le, V. Chandana Epa, Frank R. Burden, and David A. Winkler* CSIRO Materials Science and Engineering, Bag 10, Clayton South MDC 3169, Australia CSIRO Materials Science and Engineering, 343 Royal Parade, Parkville 3052, Australia Monash Institute of Pharmaceutical Sciences, 381 Royal Parade, Parkville 3052, Australia

Quantitative Structure–Property Relationship Modeling of Diverse Materials Properties

Future nanoscale soft matter design will be guided to a large extent by the teachings of amphiphile (lipid or surfactant) self-assembly. Ordered nanostructured lyotropic liquid crystalline mesophases may form in select mixtures of amphiphile and solvent. To reproducibly engineer the low energy amphiphile self-assembly of materials for the future, we must first learn the design principles. In this critical review we discuss the evolution of these design rules and in particular discuss recent key findings regarding (i) what drives amphiphile self-assembly, (ii) what governs the self-assembly structures that are formed, and (iii) how can amphiphile self-assembly materials be used to enhance product formulations, including drug delivery vehicles, medical imaging contrast agents, and integral membrane protein crystallisation media. We focus upon the generation of ‘dilutable’ lyotropic liquid crystal phases with two- and three-dimensional geometries from amphiphilic small molecules (225 references).

Lyotropic liquid crystal engineering–ordered nanostructured small molecule amphiphile self-assembly materials by design

Materials science is undergoing a revolution, generating valuable new materials such as flexible solar panels, biomaterials and printable tissues, new catalysts, polymers, and porous materials with unprecedented properties. However, the number of potentially accessible materials is immense. Artificial evolutionary methods such as genetic algorithms, which explore large, complex search spaces very efficiently, can be applied to the identification and optimization of novel materials more rapidly than by physical experiments alone. Machine learning models can augment experimental measurements of materials fitness to accelerate identification of useful and novel materials in vast materials composition or property spaces. This review discusses the problems of large materials spaces, the types of evolutionary algorithms employed to identify or optimize materials, and how materials can be represented mathematically as genomes, describes fitness landscapes and mutation operators commonly employed in materials evo...

Discovery and Optimization of Materials Using Evolutionary Approaches.

Neural networks have generated valuable Quantitative Structure-Activity/Property Relationships (QSAR/QSPR) models for a wide variety of small molecules and materials properties They have grown in sophistication and many of their initial problems have been overcome by modern mathematical techniques QSAR studies have almost always used so-called "shallow" neural networks in which there is a single hidden layer between the input and output layers Recently, a new and potentially paradigm-shifting type of neural network based on Deep Learning has appeared Deep learning methods have generated impressive improvements in image and voice recognition, and are now being applied to QSAR and QSAR modelling This paper describes the differences in approach between deep and shallow neural networks, compares their abilities to predict the properties of test sets for 15 large drug data sets (the kaggle set), discusses the results in terms of the Universal Approximation theorem for neural networks, and describes how DNN may ameliorate or remove troublesome "activity cliffs" in QSAR data sets

https://onlinelibrary.wiley.com/doi/pdf/10.1002/minf.201781141

Performance of Deep and Shallow Neural Networks, the Universal Approximation Theorem, Activity Cliffs, and QSAR

Aqueous solubility is a very important physical property of small molecule drugs and drug candidates but also one of the most difficult to predict accurately. Aqueous solubility plays a major role in drug delivery and pharmacokinetics. It is believed that crystal lattice interactions are important in solubility and that including them in solubility models should improve the accuracy of the models. We used calculated values for lattice energy and sublimation enthalpy of organic molecules as descriptors to determine whether these would improve the accuracy of the aqueous solubility models. Multiple linear regression employing an expectation maximization algorithm and a sparse prior (MLREM) method and a nonlinear Bayesian regularized artificial neural network with a Laplacian prior (BRANNLP) were used to derive optimal predictive models of aqueous solubility of a large and highly diverse data set of 4558 organic compounds over a normal ambient temperature range of 20–30 °C (293–303 K). A randomly selected te...

Tu C. Le

Papers

Quantitative Structure–Property Relationship Modeling of Diverse Materials Properties

Lyotropic liquid crystal engineering–ordered nanostructured small molecule amphiphile self-assembly materials by design

Discovery and Optimization of Materials Using Evolutionary Approaches.

Performance of Deep and Shallow Neural Networks, the Universal Approximation Theorem, Activity Cliffs, and QSAR

Aqueous solubility prediction: do crystal lattice interactions help?