Deep learning potential of mean force between polymer grafted nanoparticles

Coarse-Grained Many-Body Potentials of Ligand-Stabilized Nanoparticles from Machine-Learned Mean Forces

Colloidal nanoparticles self-assemble into a variety of superstructures with distinctive optical, structural, and electronic properties. These nanoparticles are usually stabilized by a capping layer of organic ligands to prevent aggregation in the solvent. When the ligands are sufficiently long compared to the dimensions of the nanocrystal cores, the effective coarse-grained forces between pairs of nanoparticles are largely affected by the presence of neighboring particles. In order to efficiently investigate the self-assembly behavior of these complex colloidal systems, we propose a machine-learning approach to construct effective coarse-grained many-body interaction potentials. The multiscale methodology presented in this work constitutes a general bottom-up coarse-graining strategy where the coarse-grained forces acting on coarse-grained sites are extracted from measuring the vectorial mean forces on these sites in reference fine-grained simulations. These effective coarse-grained forces, i.e., gradients of the potential of mean force or of the free-energy surface, are represented by a simple linear model in terms of gradients of structural descriptors, which are scalar functions that are rotationally invariant. In this way, we also directly obtain the free-energy surface of the coarse-grained model as a function of all coarse-grained coordinates. We expect that this simple yet accurate coarse-graining framework for the many-body potential of mean force will enable the characterization, understanding, and prediction of the structure and phase behavior of relevant soft-matter systems by direct simulations. The key advantage of this method is its generality, which allows it to be applicable to a broad range of systems. To demonstrate the generality of our method, we also apply it to a colloid-polymer model system, where coarse-grained many-body interactions are pronounced.

Deconstructing Electrostatics of Functionalized Metal Nanoparticles from Molecular Dynamics Simulations

Gold nanoparticles (NPs) with different surface functionalizations can selectively interact with specific proteins, allowing a wide range of possible applications in biotechnology and biomedicine. To prevent their tendency to aggregate and to modulate their interaction with charged biomolecules or substrates (e.g., for biosensing applications), they can be functionalized with charged groups, introducing a mutual interaction which can be modulated by changing the ionic strength of the solvent. In silico modeling of these systems is often addressed with low-resolution models, which must account for these effects in the, often implicit, solvent representation. Here, we present a systematic conformational dynamic characterization of ligand-coated gold nanoparticles with different sizes, charges, and functionalizations by means of atomistic molecular dynamics simulations. Based on these, we deconstruct their electrostatic properties and propose a general representation of their average-long-range interactions extendable to different sizes, charges, and ionic strengths. This study clarifies in detail the role of the different features of the NP (charge, size, structure) and of the ionic strength in determining the details of the interparticle interaction and represents the first step toward a general strategy for the parametrization of NP coarse-grained models able to account for varying ionic strengths.

Developing efficient deep learning model for predicting copolymer properties

Deep learning models are gaining popularity and potency in predicting polymer properties. These models can be built using pre-existing data and are useful for the rapid prediction of polymer properties. However, the performance of a deep learning model is intricately connected to its topology and the volume of training data. There is no facile protocol available to select a deep learning architecture, and there is a lack of a large volume of homogeneous sequence-property data of polymers. These two factors are the primary bottleneck for the efficient development of deep learning models for polymers. Here we assess the severity of these factors and propose strategies to address them. We show that a linear layer-by-layer expansion of a neural network can help in identifying the best neural network topology for a given problem. Moreover, we map the discrete sequence space of a polymer to a continuous one-dimensional latent space using a feature extraction technique to identify minimal data points for training a deep learning model. We implement these approaches for two representative cases of building sequence-property surrogate models, viz., the single-molecule radius of gyration of a copolymer and copolymer compatibilizer. This work demonstrates efficient methods for building deep learning models with minimal data and hyperparameters for predicting sequence-defined properties of polymers.