New Research Published in ACS Central Science
Research from a collaborative project between CPGE and the Ferguson and de Pablo labs at the University of Chicago was published on June 5, 2023 in ACS Central Science. By leveraging convolutional neural networks and molecular dynamics simulations, the team developed a denoising autoencoder (DAE) capable of postprocessing experimental ChromSTEM images to provide nucleosome-level resolution. The DAE is trained on synthetic images generated from simulations of the chromatin fiber using the 1-cylinder per nucleosome (1CPN) model of chromatin. It is capable of removing noise commonly found in high-angle annular dark field (HAADF) STEM experiments and is able to learn structural features driven by the physics of chromatin folding. The DAE outperforms other well-known denoising algorithms without degradation of structural features and permits the resolution of α-tetrahedron tetranucleosome motifs that induce local chromatin compaction and mediate DNA accessibility. Notably, no evidence for the 30 nm fiber, which has been suggested to serve as the higher-order structure of the chromatin fiber, was found.