DeepComplex: A Web Server of Predicting Protein Complex Structures by Deep Learning Inter-chain Contact Prediction and Distance-Based Modelling
importance 5/10
ai assisted
Protein Structure and Dynamics structural biology stage: research
Problem
Predicting the quaternary structure of dimeric protein complexes, which is useful for function analysis, protein engineering and drug design.
Why it matters
Protein complexes drive many biological functions and drug targets, but their structures are hard to determine experimentally.
What the AI did
DeepComplex uses deep learning to predict inter-chain contacts in homo- or heterodimers, then distance-based modelling builds the quaternary structure.
Results
not stated in source
Impact
Provides a free, registration-free web server for predicting dimeric protein complex structures.
Record
| Venue | Frontiers in Molecular Biosciences |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Farhan Quadir, Raj S. Roy, Elham Soltanikazemi, Jianlin Jack Cheng |
| Citations | 21 (OpenAlex, at import time) |
| References | 37 |
| Model or method | DeepComplex |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3389/fmolb.2021.716973 |
| Open access | gold |
| Keywords | deep learning, protein complexes, inter-chain contacts, web server, distance-based modelling |
Importance rating
5
real but narrower advance
Quaternary structure prediction aids function analysis, protein engineering, drug design; a free web-server tool, no scale or impact figures stated.