A-Prot: protein structure modeling using MSA transformer
Abstract Background The accuracy of protein 3D structure prediction has been dramatically improved with the help of advances in deep learning. In the recent CASP14, Deepmind demonstrated that their new version of AlphaFold (AF) produces highly accurate 3D models almost close to experimental structur...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-03-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-022-04628-8 |
| _version_ | 1818446155827118080 |
|---|---|
| author | Yiyu Hong Juyong Lee Junsu Ko |
| author_facet | Yiyu Hong Juyong Lee Junsu Ko |
| author_sort | Yiyu Hong |
| collection | DOAJ |
| description | Abstract Background The accuracy of protein 3D structure prediction has been dramatically improved with the help of advances in deep learning. In the recent CASP14, Deepmind demonstrated that their new version of AlphaFold (AF) produces highly accurate 3D models almost close to experimental structures. The success of AF shows that the multiple sequence alignment of a sequence contains rich evolutionary information, leading to accurate 3D models. Despite the success of AF, only the prediction code is open, and training a similar model requires a vast amount of computational resources. Thus, developing a lighter prediction model is still necessary. Results In this study, we propose a new protein 3D structure modeling method, A-Prot, using MSA Transformer, one of the state-of-the-art protein language models. An MSA feature tensor and row attention maps are extracted and converted into 2D residue-residue distance and dihedral angle predictions for a given MSA. We demonstrated that A-Prot predicts long-range contacts better than the existing methods. Additionally, we modeled the 3D structures of the free modeling and hard template-based modeling targets of CASP14. The assessment shows that the A-Prot models are more accurate than most top server groups of CASP14. Conclusion These results imply that A-Prot accurately captures the evolutionary and structural information of proteins with relatively low computational cost. Thus, A-Prot can provide a clue for the development of other protein property prediction methods. |
| first_indexed | 2024-12-14T19:43:14Z |
| format | Article |
| id | doaj.art-2517f8bf0bef4da298141e1ed78a2b84 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-14T19:43:14Z |
| publishDate | 2022-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-2517f8bf0bef4da298141e1ed78a2b842022-12-21T22:49:38ZengBMCBMC Bioinformatics1471-21052022-03-0123111110.1186/s12859-022-04628-8A-Prot: protein structure modeling using MSA transformerYiyu Hong0Juyong Lee1Junsu Ko2Arontier CoArontier CoArontier CoAbstract Background The accuracy of protein 3D structure prediction has been dramatically improved with the help of advances in deep learning. In the recent CASP14, Deepmind demonstrated that their new version of AlphaFold (AF) produces highly accurate 3D models almost close to experimental structures. The success of AF shows that the multiple sequence alignment of a sequence contains rich evolutionary information, leading to accurate 3D models. Despite the success of AF, only the prediction code is open, and training a similar model requires a vast amount of computational resources. Thus, developing a lighter prediction model is still necessary. Results In this study, we propose a new protein 3D structure modeling method, A-Prot, using MSA Transformer, one of the state-of-the-art protein language models. An MSA feature tensor and row attention maps are extracted and converted into 2D residue-residue distance and dihedral angle predictions for a given MSA. We demonstrated that A-Prot predicts long-range contacts better than the existing methods. Additionally, we modeled the 3D structures of the free modeling and hard template-based modeling targets of CASP14. The assessment shows that the A-Prot models are more accurate than most top server groups of CASP14. Conclusion These results imply that A-Prot accurately captures the evolutionary and structural information of proteins with relatively low computational cost. Thus, A-Prot can provide a clue for the development of other protein property prediction methods.https://doi.org/10.1186/s12859-022-04628-8Protein structure predictionMultiple sequence alignmentProtein language modelDeep learning |
| spellingShingle | Yiyu Hong Juyong Lee Junsu Ko A-Prot: protein structure modeling using MSA transformer BMC Bioinformatics Protein structure prediction Multiple sequence alignment Protein language model Deep learning |
| title | A-Prot: protein structure modeling using MSA transformer |
| title_full | A-Prot: protein structure modeling using MSA transformer |
| title_fullStr | A-Prot: protein structure modeling using MSA transformer |
| title_full_unstemmed | A-Prot: protein structure modeling using MSA transformer |
| title_short | A-Prot: protein structure modeling using MSA transformer |
| title_sort | a prot protein structure modeling using msa transformer |
| topic | Protein structure prediction Multiple sequence alignment Protein language model Deep learning |
| url | https://doi.org/10.1186/s12859-022-04628-8 |
| work_keys_str_mv | AT yiyuhong aprotproteinstructuremodelingusingmsatransformer AT juyonglee aprotproteinstructuremodelingusingmsatransformer AT junsuko aprotproteinstructuremodelingusingmsatransformer |