Online Services

●I-TASSER ●D-I-TASSER ●I-TASSER-MTD ●C-I-TASSER ●CR-I-TASSER ●QUARK ●C-QUARK ●D-QUARK ●DRfold ●DRfold2 ●LOMETS ●MUSTER ●CEthreader ●SEGMER ●DeepFold ●DeepFoldRNA ●FoldDesign ●COFACTOR ●COACH ●MetaGO ●TripletGO ●ATGO ●IonCom ●FG-MD ●ModRefiner ●REMO ●DEMO ●DEMO-EM ●PPLM ●DMFold ●SPRING ●COTH ●Threpp ●PEPPI ●BSpred ●ANGLOR ●EDock ●BSP-SLIM ●SAXSTER ●FUpred ●ThreaDom ●ThreaDomEx ●EvoDesign ●BindProf ●BindProfX ●SSIPe ●GPCR-I-TASSER ●MAGELLAN ●ResQ ●STRUM ●DeepTherm ●DAMpred ●TCRfinder

●TM-score ●TM-align ●US-align ●MM-align ●RNA-align ●NW-align ●LS-align ●TM-search ●EDTSurf ●MVP ●MVP-Fit ●SPICKER ●HAAD ●PSSpred ●3DRobot ●MR-REX ●I-TASSER-MR ●SVMSEQ ●NeBcon ●ResPRE ●TripletRes ●DeepPotential ●WDL-RF ●ATPbind ●DockRMSD ●DeepMSA ●DeepMSA2 ●rMSA ●FASPR ●EM-Refiner ●GPU-I-TASSER

●BioLiP ●HPmod ●E. coli ●UniBioMap ●GLASS ●GPCR-HGmod ●GPCR-RD ●GPCR-EXP ●Tara-3D ●TM-fold ●DECOYS ●ProteinConform ●POTENTIAL ●RW/RWplus ●EvoEF ●HPSF ●THE-DB ●ADDRESS ●Alpaca-Antibody ●CASP7 ●CASP8 ●CASP9 ●CASP10 ●CASP11 ●CASP12 ●CASP13 ●CASP14

[an error occurred while processing this directive]

I-TASSER (Iterative Threading ASSEmbly Refinement) is a hierarchical approach to protein structure prediction and structure-based function annotation. It first identifies structural templates from the PDB by multiple threading approach LOMETS, with full-length atomic models constructed by iterative template-based fragment assembly simulations. Function insights of the target are then derived by re-threading the 3D models through protein function database BioLiP. I-TASSER (as 'Zhang-Server') was ranked as the No 1 server for protein structure prediction in recent community-wide CASP7, CASP8, CASP9, CASP10, CASP11, CASP12, CASP13, and CASP14 experiments. It was also ranked the best for function prediction in CASP9. The server is in active development with the goal to provide the most accurate protein structure and function predictions using state-of-the-art algorithms. The server is only for non-commercial use. Please report problems and questions at I-TASSER message board and our developers will study and answer the questions accordingly. (>> More about the server ...)

D-I-TASSER: A new deep learning–based method outperforming AlphaFold2 and AlphaFold3

[Queue] [Forum] [Download] [Example] [Search] [Registration] [Statistics] [Remove] [Potential] [Decoys] [News] [Annotation] [About] [FAQ]

Due to a webserver outage, the I-TASSER service is temporarily unavailable. Our team is actively working to restore the system, and we expect it to be back online by the last week of October. We sincerely apologize for any inconvenience this may cause and appreciate your patience.

---

I-TASSER On-line Server (View an example of I-TASSER output):

Copy and paste your sequence within [10, 1500] residues in FASTA format. Click here for a sample input: Or upload the sequence from your local computer: Email: (mandatory, where results will be sent to) Password: (mandatory, please click here if you do not have a password) ID: (optional, your given name of the protein) Option I: Assign additional restraints & templates to guide I-TASSER modeling. Assign contact/distance restraints Atom-atom restraints Explanation Specify template without alignment Type a PDB ID Explanation Specify template without alignment Upload a structure Explanation Specify template with alignment Template & alignment Explanation (Read more explanation on how to add restraints) Assign contact/distance restraints Atom-atom restraints Explanation Specify template without alignment Type a PDB ID Explanation Specify template without alignment Upload a structure Explanation Specify template with alignment Template & alignment Explanation Option II: Exclude some templates from I-TASSER template library. Exclude homologous templates Type a cutoff (e.g. '60%') Explanation Exclude specific template proteins Upload a file listing all PDB IDs Explanation Exclude homologous templates Type a cutoff (e.g. '60%') Explanation Exclude specific template proteins Upload a file listing all PDB IDs Explanation Option III: Specify secondary structure for specific residues. Specify secondary structure Upload a file listing secondary structure Explanation Keep my results public (uncheck this box if you want to keep your job private, and a key will be assigned for you to access the results. We received numerous requests from users who loss their key to access result. To save your time, please keep results public, or ensure you remember the key if you choose to keep job private) (Please submit a new job only after your old job is completed)

---

I-TASSER Suite:

Download I-TASSER Standalone Package (Version 5.1)

---

I-TASSER News:

• 2025/4/1: The deep learning-based I-TASSER method, D-I-TASSER, achieved superior performance over AlphaFold2 and AlphaFold3 in both large-scale benchmarks and blind CASP evaluations. The corresponding results were recently published in Nature Biotechnology.
• 2022/12/15: An updated version of I-TASSER powered by deep learning, D-I-TASSER, was ranked as the No. 1 server/predictor in the 15th CASP experiment, in all three categories of protein structure predictions including Multi-domain Targets, Single-domain Targets, and Multi-chain Targets .
• 2022/04/13: A new platform, I-TASSER-MTD, specifically designed to model structure and function of multi-domain proteins, was accepted for publication in Nature Protocols.
• 2022/02/08: CR-I-TASSER couples I-TASSER simulation with cryo-EM density maps and significantly improves accuracy of protein structure determination; the article was published in Nature Methods.
• 2021/07/26: A new version of I-TASSER, C-I-TASSER, was published in Cell Reports Methods, which incorporates deep-learning contact-maps and significantly improve I-TASSER's ability in modeling non-homologous proteins.

  >> Read more I-TASSER news ...

---

References:

• W Zheng, Q Wuyun, Y Li, Q Liu, X Zhou, C Peng, Y Zhu, L Freddolino, Y Zhang. Deep-learning-based single-domain and multidomain protein structure prediction with D-I-TASSER. Nature Biotechnology, https://doi.org/10.1038/s41587-025-02654-4 (2025). (PDF and Support Information).
• X Zhou, W Zheng, Y Li, R Pearce, C Zhang, EW Bell, G Zhang, Y Zhang. I-TASSER-MTD: A deep-learning based platform for multi-domain protein structure and function prediction. Nature Protocols, 17: 2326-2353 (2022). (PDF and Support Information).
• W Zheng, C Zhang, Y Li, R Pearce, EW Bell, Y Zhang. Folding non-homology proteins by coupling deep-learning contact maps with I-TASSER assembly simulations. Cell Reports Methods, 1: 100014 (2021). (PDF and Support Information).