Predicting DNA structure using a deep learning method
Abstract Understanding the mechanisms of protein-DNA binding is critical in comprehending gene regulation. Three-dimensional DNA structure, also described as DNA shape, plays a key role in these mechanisms. In this study, we present a deep learning-based method, Deep DNAshape, that fundamentally cha...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-45191-5 |
| _version_ | 1827327009125040128 |
|---|---|
| author | Jinsen Li Tsu-Pei Chiu Remo Rohs |
| author_facet | Jinsen Li Tsu-Pei Chiu Remo Rohs |
| author_sort | Jinsen Li |
| collection | DOAJ |
| description | Abstract Understanding the mechanisms of protein-DNA binding is critical in comprehending gene regulation. Three-dimensional DNA structure, also described as DNA shape, plays a key role in these mechanisms. In this study, we present a deep learning-based method, Deep DNAshape, that fundamentally changes the current k-mer based high-throughput prediction of DNA shape features by accurately accounting for the influence of extended flanking regions, without the need for extensive molecular simulations or structural biology experiments. By using the Deep DNAshape method, DNA structural features can be predicted for any length and number of DNA sequences in a high-throughput manner, providing an understanding of the effects of flanking regions on DNA structure in a target region of a sequence. The Deep DNAshape method provides access to the influence of distant flanking regions on a region of interest. Our findings reveal that DNA shape readout mechanisms of a core target are quantitatively affected by flanking regions, including extended flanking regions, providing valuable insights into the detailed structural readout mechanisms of protein-DNA binding. Furthermore, when incorporated in machine learning models, the features generated by Deep DNAshape improve the model prediction accuracy. Collectively, Deep DNAshape can serve as versatile and powerful tool for diverse DNA structure-related studies. |
| first_indexed | 2024-03-07T14:53:44Z |
| format | Article |
| id | doaj.art-a235354de6824288b14bf09b3d23e2ce |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-07T14:53:44Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-a235354de6824288b14bf09b3d23e2ce2024-03-05T19:32:12ZengNature PortfolioNature Communications2041-17232024-02-0115111210.1038/s41467-024-45191-5Predicting DNA structure using a deep learning methodJinsen Li0Tsu-Pei Chiu1Remo Rohs2Department of Quantitative and Computational Biology, University of Southern CaliforniaDepartment of Quantitative and Computational Biology, University of Southern CaliforniaDepartment of Quantitative and Computational Biology, University of Southern CaliforniaAbstract Understanding the mechanisms of protein-DNA binding is critical in comprehending gene regulation. Three-dimensional DNA structure, also described as DNA shape, plays a key role in these mechanisms. In this study, we present a deep learning-based method, Deep DNAshape, that fundamentally changes the current k-mer based high-throughput prediction of DNA shape features by accurately accounting for the influence of extended flanking regions, without the need for extensive molecular simulations or structural biology experiments. By using the Deep DNAshape method, DNA structural features can be predicted for any length and number of DNA sequences in a high-throughput manner, providing an understanding of the effects of flanking regions on DNA structure in a target region of a sequence. The Deep DNAshape method provides access to the influence of distant flanking regions on a region of interest. Our findings reveal that DNA shape readout mechanisms of a core target are quantitatively affected by flanking regions, including extended flanking regions, providing valuable insights into the detailed structural readout mechanisms of protein-DNA binding. Furthermore, when incorporated in machine learning models, the features generated by Deep DNAshape improve the model prediction accuracy. Collectively, Deep DNAshape can serve as versatile and powerful tool for diverse DNA structure-related studies.https://doi.org/10.1038/s41467-024-45191-5 |
| spellingShingle | Jinsen Li Tsu-Pei Chiu Remo Rohs Predicting DNA structure using a deep learning method Nature Communications |
| title | Predicting DNA structure using a deep learning method |
| title_full | Predicting DNA structure using a deep learning method |
| title_fullStr | Predicting DNA structure using a deep learning method |
| title_full_unstemmed | Predicting DNA structure using a deep learning method |
| title_short | Predicting DNA structure using a deep learning method |
| title_sort | predicting dna structure using a deep learning method |
| url | https://doi.org/10.1038/s41467-024-45191-5 |
| work_keys_str_mv | AT jinsenli predictingdnastructureusingadeeplearningmethod AT tsupeichiu predictingdnastructureusingadeeplearningmethod AT remorohs predictingdnastructureusingadeeplearningmethod |