With the breakthrough of AlphaFold2, nearly all single-domain protein structures can be built at experimental resolution. However, accurate modelling of full-chain structures of multidomain proteins, particularly all relevant conformations for those with multiple states remain a challenging problem. In this study, we develop M-SADA, a method for assembling multiple conformational states of multidomain proteins through a population-based evolutionary algorithm, with multiple energy functions constructed by combining homologous and analogous templates with deep learning predicted inter-domain distance. On a development set containing 72 multidomain proteins with multiple conformational states, the performance of M-SADA is significantly better than that of AlphaFold2 on multiple conformational states modelling, where M-SADA models achieve TM-score >0.90 for two highly distinct conformational states on 29 proteins. Furthermore, M-SADA is tested on a development set containing 296 multidomain proteins with single conformational state, and results show that the average TM-score of M-SADA on the best models is 0.913, which is 5.2% higher than that of AlphaFold2 models (0.868).

  M-SADA On-line Server [View example of output]

Input the multidomain protein full-chain sequence in FASTA format (mandatory, Click for an example input).

Or, upload the full-chain sequence file:

Input the protein domain model 1 in PDB format (mandatory, Click for an example input).

Or, upload the stuctural model file:

Input the protein domain model 2 in PDB format (mandatory, Click for an example input).

Or, upload the stuctural model file:

Click the "Add model" and "Remove model" buttons below to add or remove structural models.

Input the sequence identity:
(Default: 1.0, Used to exclude available templates)


Email: (optional, where results will be sent to)

Job name: (optional, your given name to this job)

User data is not collected by M-SADA server



  • Chun-Xiang Peng, Xiao-Gen Zhou, Yu-Hao Xia, Jun Liu, Ming-Hua Hou and Gui-Jun Zhang*.   Structural analogue-based protein structure domain assembly assisted by deep learning.   Bioinformatics, 2022, 38(19): 4513-4521.
  • Zhong-ze Yu, Chun-xiang Peng, Jun Liu, Biao Zhang, Xiao-gen Zhou and Gui-jun Zhang*. DomBpred: protein domain boundary prediction based on domain-residue clustering using inter-residue distance. IEEE/ACM Transactions on Computational Biology and Bioinformatics , 2022, 20(2): 912-922.
  • Fengqi Ge, Chunxiang Peng, Xinyue Cui, Yuhao Xia and Gui-jun Zhang*. Inter-domain distance prediction based on deep learning for domain assembly. Briefings in Bioinformatics , 2023, bbad100.
  • Chunxiang Peng, Xiaogen Zhou, Jun Liu, Minghua Hou, Stan Z. Li and Guijun Zhang*.   Multiple conformational states assembly of multidomain proteins using evolutionary algorithm based on structural analogues and sequential homologues.   Submitted.