UNRAVEL: UN-biased high-Resolution Analysis and Validation of Ensembles using Light sheet images

This project builds machine learning models to automatically detect and classify protein complexes in cryo-electron tomography (cryoET) images, enabling scalable analysis of cellular structures and supporting advanced biological and medical research.

Automated detection of protein complexes in cryo-electron tomography (cryoET) data. ML models identify five particle classes using a weighted F-β (β=4) metric focused on recall, especially for hard targets, helping reveal cellular “dark matter” and advance biological discovery.

[Imported from FU's GitLab] Master's Thesis Project at Freie Uni. Pipeline that registers a LIF stack of drosophila brains to a template, and then uses the reverse transform to label the brain regions. Resulting analysis (e.g. asymmetry) of the different regions should also be found here although this is not the main interest.