SUPR
AutoEncoder for SAXS reconstruction of Tr-WAXS data
Dnr:

NAISS 2025/22-1083

Type:

NAISS Small Compute

Principal Investigator:

Leonardo Monrroy

Affiliation:

Uppsala universitet

Start Date:

2025-08-15

End Date:

2026-03-01

Primary Classification:

10408: Biochemistry

Webpage:

Allocation

Abstract

We propose an AutoEncoder-based framework for reconstructing protein shapes from time-resolved SWAXS data. The model is trained on physically plausible protein deformations generated using AFsample2 and represented as 3D voxel models of proteins. By learning the deformation space, the trained network can be incorporated into a framework capable of generating candidate structures guided by fitting to time-resolved SWAXS profiles, enabling shape reconstruction directly from experimental measurements.