Generative modeling of protein ensembles guided by crystallographic electron densities
This work addresses the challenge of protein dynamics modeling for structural biology, but it is incremental as it builds on existing generative models.
The authors tackled the problem of modeling protein conformational ensembles from crystallographic electron densities, an ill-posed inverse problem, and demonstrated that their non-i.i.d. ensemble guidance approach accurately recovers multi-modal alternate protein backbone conformations observed in single crystal measurements.
Proteins are dynamic, adopting ensembles of conformations. The nature of this conformational heterogenity is imprinted in the raw electron density measurements obtained from X-ray crystallography experiments. Fitting an ensemble of protein structures to these measurements is a challenging, ill-posed inverse problem. We propose a non-i.i.d. ensemble guidance approach to solve this problem using existing protein structure generative models and demonstrate that it accurately recovers complicated multi-modal alternate protein backbone conformations observed in certain single crystal measurements.