2021
DOI: 10.1101/2021.09.07.459290
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Improved Docking of Protein Models by a Combination of Alphafold2 and ClusPro

Abstract: It has been demonstrated earlier that the neural network based program AlphaFold2 can be used to dock proteins given the two sequences separated by a gap as the input. The protocol presented here combines AlphaFold2 with the physics based docking program ClusPro. The monomers of the model generated by AlphaFold2 are separated, re-docked using ClusPro, and the resulting 10 models are refined by AlphaFold2. Finally, the five original AlphaFold2 models are added to the 10 AlphaFold2 refined ClusPro models, and th… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

3
72
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
9

Relationship

1
8

Authors

Journals

citations
Cited by 62 publications
(75 citation statements)
references
References 19 publications
3
72
0
Order By: Relevance
“…We were able to obtain these results after only minor optimization of the default AF2 monomer structure prediction protocol for peptide docking (see Methods). Most importantly, we also modeled the interaction with separate chains, as has already been suggested for protein docking 33,34,37 . This implementation provided complementary results (see Supplementary Fig.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…We were able to obtain these results after only minor optimization of the default AF2 monomer structure prediction protocol for peptide docking (see Methods). Most importantly, we also modeled the interaction with separate chains, as has already been suggested for protein docking 33,34,37 . This implementation provided complementary results (see Supplementary Fig.…”
Section: Resultsmentioning
confidence: 99%
“…Best performance is obtained by combining our linker-based strategy with modeling of peptide-protein complexes by presenting two separate chains to AF2. The latter has been implemented for the modeling of homoand hetero-multimers in several recent studies on AF2 36,37 .…”
mentioning
confidence: 99%
“…Similarly, a study across 11 different proteomes found that AlphaFold added structure determination for on average 25 percentage points of additional residues over existing experimental structures or those that could be derived by homology modelling 56 . Interestingly, despite being trained on single proteins, AlphaFold proved capable of modelling the structures of protein complexes 56 58 . Most recently, AlphaFold-Multimer has been released, featuring a model trained on multimeric protein structures, which clearly outperforms the standard AlphaFold for modelling protein complex structures 59 .…”
Section: Coevolution and Deep Learning Approachesmentioning
confidence: 99%
“…ColabFold, offering both AlphaFold and Ro-seTTAFold to the non-expert user, used a fast multiple sequence alignment generation by MMseqs2 to predict homo-and heterocomplexes (Mirdita et al, 2021). One study showed an improved performance of PPI docking by combining AlphaFold and ClusPro (Ghani et al, 2021). Despite the unprecedented success of such approaches and the extent to which they have empowered research in various branches of the life sciences, they do occasionally produce erroneous models and therefore still need to be followed up by in-depth analysis and validation, until we establish reliable metrics for model quality.…”
Section: Machine Learning-based Predictionmentioning
confidence: 99%