Abismal

Kevin M. Dalton Doris Mai

A Different Way of Modeling Diffraction

Historical models of diffraction have built upon the deep understanding of the scattering physics. This approach works very well in the context of small molecule crystals. However, large biological molecules like proteins and nucleic acids can be very challenging to treat from first principles. A recent breakthrough (Dalton et al., 2022) demonstrated how a deep-learning model could be trained using Bayesian inference to discover an appropriate physical model which is bespoke for each sample. This pioneering work had notable limitations which prevented it from treating the large data sets generated at the LCLS and other free-electron lasers. A new project, ABISMAL, is being developed to surpass these limitations and bring the power of neural networks to LCLS in order to understand the motions of biological molecules.

Graphical representation of the ABISMAL model.
Schematic representation of the ABISMAL implementation.

GitHub Repository

References

2022

  1. Crystallography
    dalton2022careless.png
    A unifying Bayesian framework for merging X-ray diffraction data
    Kevin M. Dalton, Jack B. Greisman, and Doeke R. Hekstra
    2022