RosettaFold (sometimes stylized as RoseTTAfold) is a protein structure prediction method unveiled in mid-2021 (1). A second version, RosettaFold2, was released in early 2023 (2). Its architecture closely tracks that of AlphaFold2, with several changes, such as the use of an SE3-transformer.
1.
Baek M, DiMaio F, Anishchenko I, Dauparas J, Ovchinnikov S, Lee GR, et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science. 2021;373(6557):871–6. Available from: https://doi.org/10.1126/science.abj8754
2.
Baek M, Anishchenko I, Humphreys IR, Cong Q, Baker D, DiMaio F. Efficient and accurate prediction of protein structure using RoseTTAFold2. openRxiv; 2023. Available from: https://doi.org/10.1101/2023.05.24.542179