C-I-TASSER (Contact-guided Iterative Threading ASSEmbly Refinement) is a
composite approach that uses contact information to enhance the accuracy of
protein structure and function predictions. Starting from a sequence,
C-I-TASSER first generates contact-map of all residue pairs using
ResTriplet, and TripletRes.
It then identifies structural templates from the PDB by multiple threading
approach LOMETS, with full-length atomic models
constructed by contact-map guided fragment assembly simulations. Functions of
the target are derived from the structure model by
COFACTOR. C-I-TASSER (as 'Zhang-Server')
was ranked as the No. 1 server for protein structure prediction
in the community-wide
The benchmark data showed that C-I-TASSER could generate significantly
more accurate models than
especially for the sequences that do not have homologous templates
in the PDB.
[View example output]
[Check previous jobs]
C-I-TASSER On-line Server
Wei Zheng, Yang Li, Chengxin Zhang, Robin Pearce, S. M. Mortuza, Yang Zhang.
"Deep-learning contact-map guided protein structure prediction in CASP13."
Proteins: Structure, Function, and Bioinformatics, 87: 1149-1164 (2019).
Chengxin Zhang, S M Mortuza, Baoji He, Yanting Wang, and Yang Zhang.
"Template-based and free modeling of I-TASSER and QUARK pipelines using predicted contact maps in CASP12."
Proteins: Structure, Function, and Bioinformatics (2017). doi: 10.1002/prot.25414
- Baoji He, S M Mortuza, Yanting Wang, Hongbin Shen, Yang Zhang.
NeBcon: Protein contact map prediction using neural network training coupled with naïve Bayes classifiers.
Bioinformatics (2017) doi: 10.1093/bioinformatics/btx164.
[PDF] [Support Information]
Yang Li, Jun Hu, Chengxin Zhang, Dong-Jun Yu, and Yang Zhang.
"ResPRE: high-accuracy protein contact map prediction by coupling precision matrix with deep residual neural networks." Bioinformatics (2019)