Graph Clustering Analyses of Discontinuous Molecular Dynamics Simulations: Study of Lysozyme Adsorption on a Graphene Surface

Abstract

Understanding the interfacial behaviors of biomolecules is crucial to applications in biomaterials and nanoparticle-based biosensing technologies. In this work, we utilized autoencoder-based graph clustering to analyze discontinuous molecular dynamics (DMD) simulations of lysozyme adsorption on a graphene surface. Our high-throughput DMD simulations integrated with a Go̅-like protein–surface interaction model makes it possible to explore protein adsorption at a large temporal scale with sufficient accuracy. The graph autoencoder extracts a low-dimensional feature vector from a contact map. The sequence of the extracted feature vectors is then clustered, and thus the evolution of the protein molecule structure in the absorption process is segmented into stages. Our study demonstrated that the residue–surface hydrophobic interactions and the π–π stacking interactions play key roles in the five-stage adsorption. Upon adsorption, the tertiary structure of lysozyme collapsed, and the secondary structure was also affected. The folding stages obtained by autoencoder-based graph clustering were consistent with detailed analyses of the protein structure. The combination of machine learning analysis and efficient DMD simulations developed in this work could be an important tool to study biomolecules’ interfacial behaviors.

Allosteric regulation in SARS-CoV-2 spike protein

“…To address this, data feature extractors, such as autoencoders combined with clustering algorithms, have been employed to identify phases of protein structure changes or fluctuations. 34,35 Selfsupervised learning stands as another ML category that can yield robust feature representations from unlabeled data for subsequent tasks. 36 Backbone models responsible for generating data feature representations are trained through solving ''pretext'' tasks, encompassing activities like predicting rotations, 37 learning inpainting, 38 solving jigsaw puzzles, 39 and image coloring.…”

Nanofibrous Membranes with High Mechanical Strength for the Separation and Purification of Lysozyme

“…It is found from the results in Figure 7a that the protein adsorption on RC-g-GA NFM adsorber is obviously pH-dependent. The isoelectric point (pI) of lysozyme is 11, so lysozyme is positively charged over a wide pH range, and there are also hydrophobic residues 40 on the surface of lysozyme that allow it to be adsorbed by MMC. The adsorption capacity of lysozyme increased first, then decreased in the range of pH-6−10, and reached the maximum value of 254 mg/g at pH 8.…”

Study of Friction and Wear Behavior of Graphene-Reinforced AA7075 Nanocomposites by Machine Learning

“…Friction, wear, and lubrication are all aspects of tribology, which studies the relationship between moving and contacting surfaces and the forces acting upon them. The tribological behavior of AA7075-graphene nanocomposites has been the subject of several recent reports [16,17]. The tribosurface of AA7075-graphene nanocomposites is coated with soft lubrication layers of graphene, making it suitable for sliding applications after a brief break-in period.…”