Diffusion model assisted designing self-assembling collagen mimetic peptides as biocompatible materials.

Collagen self-assembly supports its mechanical function, but controlling collagen mimetic peptides (CMPs) to self-assemble into higher-order oligomers with numerous functions remains challenging due to the vast potential amino acid sequence space. Herein, we developed a diffusion model to learn features from different types of human collagens and generate CMPs; obtaining 66% of synthetic CMPs could self-assemble into triple helices. Triple-helical and untwisting states were probed by melting temperature (Tm); hence, we developed a model to predict collagen Tm, achieving a state-of-art Pearson's correlation (PC) of 0.

Machine learning-assisted substrate binding pocket engineering based on structural information.

Engineering enzyme-substrate binding pockets is the most efficient approach for modifying catalytic activity, but is limited if the substrate binding sites are indistinct. Here, we developed a 3D convolutional neural network for predicting protein-ligand binding sites. The network was integrated by DenseNet, UNet, and self-attention for extracting features and recovering sample size.

Identification of a human type XVII collagen fragment with high capacity for maintaining skin health.

Collagen XVII (COL17) is a transmembrane protein that mediates skin homeostasis. Due to expression of full length collagen was hard to achieve in microorganisms, arising the needs for selection of collagen fragments with desired functions for microbial biosynthesis. Here, COL17 fragments (27-33 amino acids) were extracted and replicated 16 times for recombinant expression in .