template structure files (2.6G, optional, no need to download if you do not want to use templates). Note: This is an improved version of trRosetta with a new network and homologous templates. It consists of the training scripts, the training data, the pre-trained models and the inference codes.
pre-trained network models (7G) Note: This is an improved version of trRosettaX for single sequence structure prediction. It consists of the training scripts, the training data, the pre-trained models and the inference codes.
trRosetta package (2.4M) Note: This is the original package for trRosetta. You are suggested downloading the latest version trRosettaX listed above.
Reference
Du et al, The trRosetta server for fast and accurate protein structure prediction, Nature Protocols, 16: 5634-5651 (2021). (PDF)
Wang et al, Single-sequence protein structure prediction using supervised transformer protein language models, Nature Computational Science, 2: 804-814 (2022). (PDF)
Su et al, Improved protein structure prediction using a new multi-scale network and homologous templates, Advanced Science, 8, 2102592 (2021). (PDF)