Zhe Zhang

The paper introduces MobiSeq, a method combining deep mutational scanning and mobility-based selection to predict RNA tertiary structures by analyzing covariational signals and improving energy-based predictions.

The paper shows that using artificially generated, structure-stability-selected homologous sequences improves AlphaFold2's accuracy for protein structure prediction, achieving better than 2 Å RMSD for most tested proteins.

The paper identifies a self-cleaving ribozyme in ancient LINE-1 elements, showing its emergence 40 million years ago and extinction 30 million years ago.

The paper uses deep mutational scanning to accurately infer the full base-pairing structure of RNA with high precision.