08/26/2022, The trRosetta server has predicted the structure models for >100,000 proteins.
07/26/2022, Predicted local accuracy was included for each model. The results page was redesigned to show local accuracy.
05/03/2022, The network was updated with an improved accuracy by ~10%.
01/06/2022, The maximum length of protein sequence was increased from 1000 to 1500.
12/23/2021, Single-sequence folding with trRosettaX-Single was included. It works well for orphan proteins and designed proteins.
12/23/2021, Folding for big proteins (>300 residues) was improved with refined set of constraints and more rounds of clash removement.
09/16/2021, A new paper to summarize the latest development of trRosetta was accepted to Advanced Science. All training codes, training data, pre-trained models and inference codes can be downloaded here.
08/31/2021, A new paper with detailed guidelines for using the trRosetta server and the standalone package was accepted to Nature Protocols.
06/24/2021, A new version of the trRosetta standalone package was released: download here.
03/04/2021, trRosetta predicts protein structures for every protein family in the Pfam database.
12/06/2020, trRosetta-based methods (BAKER, BAKER-ROSETTASERVER, Yang-Server) were assessed in the 14th CASP experiment. The BAKER group was ranked as
the second Human group after AlphaFold2; while the BAKER-ROSETTASERVER was ranked as the fourth Server group. The Yang-Server from our lab was ranked among the top 10 Server groups. The major difference between BAKER-ROSETTASERVER and Yang-Server is the former applied an additional step of large-scale refinement on the trRosetta models.
11/23/2020, An automated template detection was included to improve the modeling accuracy for easy targets.
11/23/2020, A new deep neural network was used, which is about 3% more accurate than the previous version.
09/25/2020, A script 'pdb2npz.py' included to calculate and visualize the interresidue distance and orientation from the input of a PDB structure.
08/27/2020, A script 'top_prob.py' the average probablity of the top L predicted long+medium range contacts.
07/22/2020, As requested by many users, a new script (npz_2_dist.py) was included in the trRosetta package to convert the distance distribution into distance and contact maps.
06/08/2020, Automated MSA selection was included in the server to improve the accuracy by 2-5%.
04/03/2020, The trRosetta structure models for 10 SARS-CoV-2 proteins that do not have homologous templates in PDB were released at: SARS-2-CoV.