Skip to main content


Licensed according to this deed.

Published on


This will be a server for I-TASSER. I-TASSER is a hierarchical method developed in the PI’s lab that was designed to construct full-length protein structure models, starting from amino acid sequences, by assembling continuous fragments excised from threading template alignments, using iterative Replica-exchange Monte Carlo (REMC) simulations. The functional insights of the target proteins, including enzyme commission, gene ontology and ligand binding sites, are then derived by matching the structural models with the known protein function databases. The I-TASSER method has been consistently ranked as one of the best methods for automated protein structure prediction in the community-wide CASP (Critical Assessment of protein Structure Prediction) experiments. Meanwhile, the function prediction components of the I-TASSER pipeline, including COFACTOR and COACH, have been ranked at the top for protein function annotation in the community-wide CASP and CAMEO experiments. The I-TASSER server is one of the most widely used systems in the field for online, full-length protein structure and function prediction. As of June 28, 2016, the webserver has already predicted 280,269 protein structures for 69,573 users from 124 countries, with 17,813 users coming from the United States. With this science gateway, we bring to the users the ability to fully exploit the functionality of I-TASSER, COACH and COFACTOR through an easy-to-use web interface. The computational backend provided by XSEDE will help to eliminate user job submission restriction previous imposed by our own server due to lack of computing resources.





Cite this work

Researchers should cite this work as follows:

  • (2024), "I-TASSER,"

    BibTex | EndNote