bims-lances 2024-04-28 papers

Issue of 2024‒04‒28
two papers selected by
James M. Krieger, National Centre for Biotechnology

Curr Opin Struct Biol. 2024 Apr 23. pii: S0959-440X(24)00042-3. [Epub ahead of print]86 102815

Confronting heterogeneity in cryogenic electron microscopy data: Innovative strategies and future perspectives with data-driven methods.

Dari Kimanius, Johannes Schwab.

The surge in the influx of data from cryogenic electron microscopy (cryo-EM) experiments has intensified the demand for robust algorithms capable of autonomously managing structurally heterogeneous datasets. This presents a wealth of exciting opportunities from a data science viewpoint, inspiring the development of numerous innovative, application-specific methods, many of which leverage contemporary data-driven techniques. However, addressing the challenges posed by heterogeneous datasets remains a paramount yet unresolved issue in the field. Here, we explore the subtleties of this challenge and the array of strategies devised to confront it. We pinpoint the shortcomings of existing methodologies and deliberate on prospective avenues for improvement. Specifically, our discussion focuses on strategies to mitigate model overfitting and manage data noise, as well as the effects of constraints, priors, and invariances on the optimization process.

Keywords: Cryo-EM; Deep Learning; Generalization; Representation Learning; Robustness

DOI: https://doi.org/10.1016/j.sbi.2024.102815

IUCrJ. 2024 May 01.

KINNTREX: a neural network to unveil protein mechanisms from time-resolved X-ray crystallography.

Gabriel Biener, Tek Narsingh Malla, Peter Schwander, Marius Schmidt.

Here, a machine-learning method based on a kinetically informed neural network (NN) is introduced. The proposed method is designed to analyze a time series of difference electron-density maps from a time-resolved X-ray crystallographic experiment. The method is named KINNTREX (kinetics-informed NN for time-resolved X-ray crystallography). To validate KINNTREX, multiple realistic scenarios were simulated with increasing levels of complexity. For the simulations, time-resolved X-ray data were generated that mimic data collected from the photocycle of the photoactive yellow protein. KINNTREX only requires the number of intermediates and approximate relaxation times (both obtained from a singular valued decomposition) and does not require an assumption of a candidate mechanism. It successfully predicts a consistent chemical kinetic mechanism, together with difference electron-density maps of the intermediates that appear during the reaction. These features make KINNTREX attractive for tackling a wide range of biomolecular questions. In addition, the versatility of KINNTREX can inspire more NN-based applications to time-resolved data from biological macromolecules obtained by other methods.

Keywords: difference maps; electron density; kinetics; loss functions; machine learning; neural networks; protein mechanisms; reaction-rate coefficients; singular value decomposition; time-resolved X-ray crystallography

DOI: https://doi.org/10.1107/S2052252524002392