SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold Multimer
Rapid advancements in protein sequencing technology have resulted in gaps between proteins with identified sequences and those with mapped structures. Although sequence-based predictions offer insights, they can be incomplete due to the absence of structural details. Conversely, structure-based meth...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S200103702400062X |
| _version_ | 1827311810425913344 |
|---|---|
| author | Wenxing Hu Masahito Ohue |
| author_facet | Wenxing Hu Masahito Ohue |
| author_sort | Wenxing Hu |
| collection | DOAJ |
| description | Rapid advancements in protein sequencing technology have resulted in gaps between proteins with identified sequences and those with mapped structures. Although sequence-based predictions offer insights, they can be incomplete due to the absence of structural details. Conversely, structure-based methods face challenges with respect to newly sequenced proteins. The AlphaFold Multimer has remarkable accuracy in predicting the structure of protein complexes. However, it cannot distinguish whether the input protein sequences can interact. Nonetheless, by analyzing the information in the models predicted by the AlphaFold Multimer, we propose a highly accurate method for predicting protein interactions. This study focuses on the use of deep neural networks, specifically to analyze protein complex structures predicted by the AlphaFold Multimer. By transforming atomic coordinates and utilizing sophisticated image-processing techniques, vital 3D structural details were extracted from protein complexes. Recognizing the significance of evaluating residue distances in protein interactions, this study leveraged image recognition approaches by integrating Densely Connected Convolutional Networks (DenseNet) and Deep Residual Network (ResNet) within 3D convolutional networks for protein 3D structure analysis. When benchmarked against leading protein-protein interaction prediction methods, such as SpeedPPI, D-script, DeepTrio, and PEPPI, our proposed method, named SpatialPPI, exhibited notable efficacy, emphasizing the promising role of 3D spatial processing in advancing the realm of structural biology. The SpatialPPI code is available at: https://github.com/ohuelab/SpatialPPI. |
| first_indexed | 2024-04-24T20:26:00Z |
| format | Article |
| id | doaj.art-88280cb7ec0e408198c39d55acc062a9 |
| institution | Directory Open Access Journal |
| issn | 2001-0370 |
| language | English |
| last_indexed | 2024-04-24T20:26:00Z |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj.art-88280cb7ec0e408198c39d55acc062a92024-03-22T05:39:11ZengElsevierComputational and Structural Biotechnology Journal2001-03702024-12-012312141225SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold MultimerWenxing Hu0Masahito Ohue1Department of Computer Science, School of Computing, Tokyo Institute of Technology, Yokohama, Kanagawa 226–8501, JapanCorresponding author.; Department of Computer Science, School of Computing, Tokyo Institute of Technology, Yokohama, Kanagawa 226–8501, JapanRapid advancements in protein sequencing technology have resulted in gaps between proteins with identified sequences and those with mapped structures. Although sequence-based predictions offer insights, they can be incomplete due to the absence of structural details. Conversely, structure-based methods face challenges with respect to newly sequenced proteins. The AlphaFold Multimer has remarkable accuracy in predicting the structure of protein complexes. However, it cannot distinguish whether the input protein sequences can interact. Nonetheless, by analyzing the information in the models predicted by the AlphaFold Multimer, we propose a highly accurate method for predicting protein interactions. This study focuses on the use of deep neural networks, specifically to analyze protein complex structures predicted by the AlphaFold Multimer. By transforming atomic coordinates and utilizing sophisticated image-processing techniques, vital 3D structural details were extracted from protein complexes. Recognizing the significance of evaluating residue distances in protein interactions, this study leveraged image recognition approaches by integrating Densely Connected Convolutional Networks (DenseNet) and Deep Residual Network (ResNet) within 3D convolutional networks for protein 3D structure analysis. When benchmarked against leading protein-protein interaction prediction methods, such as SpeedPPI, D-script, DeepTrio, and PEPPI, our proposed method, named SpatialPPI, exhibited notable efficacy, emphasizing the promising role of 3D spatial processing in advancing the realm of structural biology. The SpatialPPI code is available at: https://github.com/ohuelab/SpatialPPI.http://www.sciencedirect.com/science/article/pii/S200103702400062XProtein-protein interactionMachine LearningConvolutional Neural NetworkAlphaFold |
| spellingShingle | Wenxing Hu Masahito Ohue SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold Multimer Computational and Structural Biotechnology Journal Protein-protein interaction Machine Learning Convolutional Neural Network AlphaFold |
| title | SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold Multimer |
| title_full | SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold Multimer |
| title_fullStr | SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold Multimer |
| title_full_unstemmed | SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold Multimer |
| title_short | SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold Multimer |
| title_sort | spatialppi three dimensional space protein protein interaction prediction with alphafold multimer |
| topic | Protein-protein interaction Machine Learning Convolutional Neural Network AlphaFold |
| url | http://www.sciencedirect.com/science/article/pii/S200103702400062X |
| work_keys_str_mv | AT wenxinghu spatialppithreedimensionalspaceproteinproteininteractionpredictionwithalphafoldmultimer AT masahitoohue spatialppithreedimensionalspaceproteinproteininteractionpredictionwithalphafoldmultimer |