Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search
The accuracy of AlphaFold decreases with the number of protein chains and the available GPU memory limits the size of protein complexes that can be predicted. Here, the authors show that complexes with 10–30 chains can be assembled from predicted subcomponents using Monte Carlo tree search.
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-10-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-022-33729-4 |
| _version_ | 1811238798768472064 |
|---|---|
| author | Patrick Bryant Gabriele Pozzati Wensi Zhu Aditi Shenoy Petras Kundrotas Arne Elofsson |
| author_facet | Patrick Bryant Gabriele Pozzati Wensi Zhu Aditi Shenoy Petras Kundrotas Arne Elofsson |
| author_sort | Patrick Bryant |
| collection | DOAJ |
| description | The accuracy of AlphaFold decreases with the number of protein chains and the available GPU memory limits the size of protein complexes that can be predicted. Here, the authors show that complexes with 10–30 chains can be assembled from predicted subcomponents using Monte Carlo tree search. |
| first_indexed | 2024-04-12T12:48:33Z |
| format | Article |
| id | doaj.art-ba16c3928c6b4e7b987cfb650ae54d3b |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-04-12T12:48:33Z |
| publishDate | 2022-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-ba16c3928c6b4e7b987cfb650ae54d3b2022-12-22T03:32:32ZengNature PortfolioNature Communications2041-17232022-10-0113111410.1038/s41467-022-33729-4Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree searchPatrick Bryant0Gabriele Pozzati1Wensi Zhu2Aditi Shenoy3Petras Kundrotas4Arne Elofsson5Science for Life LaboratoryScience for Life LaboratoryScience for Life LaboratoryScience for Life LaboratoryScience for Life LaboratoryScience for Life LaboratoryThe accuracy of AlphaFold decreases with the number of protein chains and the available GPU memory limits the size of protein complexes that can be predicted. Here, the authors show that complexes with 10–30 chains can be assembled from predicted subcomponents using Monte Carlo tree search.https://doi.org/10.1038/s41467-022-33729-4 |
| spellingShingle | Patrick Bryant Gabriele Pozzati Wensi Zhu Aditi Shenoy Petras Kundrotas Arne Elofsson Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search Nature Communications |
| title | Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search |
| title_full | Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search |
| title_fullStr | Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search |
| title_full_unstemmed | Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search |
| title_short | Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search |
| title_sort | predicting the structure of large protein complexes using alphafold and monte carlo tree search |
| url | https://doi.org/10.1038/s41467-022-33729-4 |
| work_keys_str_mv | AT patrickbryant predictingthestructureoflargeproteincomplexesusingalphafoldandmontecarlotreesearch AT gabrielepozzati predictingthestructureoflargeproteincomplexesusingalphafoldandmontecarlotreesearch AT wensizhu predictingthestructureoflargeproteincomplexesusingalphafoldandmontecarlotreesearch AT aditishenoy predictingthestructureoflargeproteincomplexesusingalphafoldandmontecarlotreesearch AT petraskundrotas predictingthestructureoflargeproteincomplexesusingalphafoldandmontecarlotreesearch AT arneelofsson predictingthestructureoflargeproteincomplexesusingalphafoldandmontecarlotreesearch |