CryoSiam: self-supervised representation learning for automated analysis of cryo-electron tomograms Cryo-electron tomography (cryo-ET) enables visualization of macromolecular complexes in their native cellular context, but interpretation remains challenging due to high noise levels, missing informat...

Another beautiful example of new methods for biological discovery: #CryoSIAM is an embedding representation framework that can denoise, segment and pick particles – which the authors then used to pick RNA #polymerase in the Chlamy dataset!