<< Back to SADA home

SADA is a structural analogue-based protein structure domain assembly method assisted by deep learning, which includes 5 steps. (1) detects structural analogues of the full-chain from the constructed multi-domain protein structure database (MPDB) according to the input protein domain models; (2) Constructs an initial model based on the detected 1st-ranked analogue; (3) Utilizes a deep learning network to predict the inter-residue distance distribution; (4) Builds multi-domain protein specificity force field for guiding domain assembly based on the predicted residues distance distribution and the property of multi-domain protein; (5) Assembles the domain models to generate final full-chain model by the proposed two-stage differential evolution algorithm from the initial model. (see example for a SADA assembly result of 2-domains protein ).

SADA also provides other 2 functions. (1) Structural analogues detection; (2) Culling the whole MPDB according to input criteria.



  • Multi-domain protein structure database_v1, version: September, 2021 with 4,8225 entries (~3.4G).
  • Multi-domain protein structure database_v2, Current version: September, 2022 with 5,3125 entries (~3.8G).
  • Domain_boundary.txt, This file records the domain boundary for multi-domain proteins in Multi-domain protein structure database.

  • SADA news

  • 2021-09: The Multi-domain protein structure database (with 48,225 entries) was released by Dr. Guijun Zhang's research group at Zhejiang University of Technology.
  • 2022-09: The Multi-domain protein structure database was update, where these diverse multi-domain proteins with same sequence are added in MPDB (4,900 proteins were added).
  • 2022-12: The inter-domain distance prediction network with attention mechanisms was developed, in which the novel features and strategy for multi-domain proteins are designed.

  • Contact us: