Slavica Jonić

The paper demonstrates a method to predict atomic coordinates from cryo-EM images using a convolutional auto-encoder and regression network, achieving low RMSD in synthetic datasets.

The paper introduces MW-RaMViD, a diffusion model for correcting missing-wedge artifacts in cryo-ET by generating missing tilt images, showing improved reconstruction fidelity with smaller step sizes and larger conditioning windows.

This paper introduces DeepMDTOMO, a deep learning framework for predicting atomic coordinates from cryo-ET subtomograms, showing it works well with noise and missing-wedge artifacts.

The paper presents a cryo-EM conformational heterogeneity challenge to evaluate and improve methods for analyzing molecular motions in heterogeneous samples.

MDTOMO analyzes continuous conformational variability in cryo-ET subtomograms using MD simulations to generate atomic-scale models and free-energy landscapes.

The paper introduces HEMNMA-3D for analyzing continuous conformational variability in cryo-ET data and compares it to traditional methods on a simulated nucleosome dataset.