A deep learning solution for crystallographic structure determination
The general de novo solution of the crystallographic phase problem is difficult and only possible under certain conditions. This paper develops an initial pathway to a deep learning neural network approach for the phase problem in protein crystallography, based on a synthetic dataset of small fragme...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
International Union of Crystallography
2023-07-01
|
| Series: | IUCrJ |
| Subjects: | |
| Online Access: | http://scripts.iucr.org/cgi-bin/paper?S2052252523004293 |
| _version_ | 1797785859421896704 |
|---|---|
| author | Tom Pan Shikai Jin Mitchell D. Miller Anastasios Kyrillidis George N. Phillips Jr |
| author_facet | Tom Pan Shikai Jin Mitchell D. Miller Anastasios Kyrillidis George N. Phillips Jr |
| author_sort | Tom Pan |
| collection | DOAJ |
| description | The general de novo solution of the crystallographic phase problem is difficult and only possible under certain conditions. This paper develops an initial pathway to a deep learning neural network approach for the phase problem in protein crystallography, based on a synthetic dataset of small fragments derived from a large well curated subset of solved structures in the Protein Data Bank (PDB). In particular, electron-density estimates of simple artificial systems are produced directly from corresponding Patterson maps using a convolutional neural network architecture as a proof of concept. |
| first_indexed | 2024-03-13T01:00:01Z |
| format | Article |
| id | doaj.art-5f4e3dbe014048a3be76cba849b381eb |
| institution | Directory Open Access Journal |
| issn | 2052-2525 |
| language | English |
| last_indexed | 2024-03-13T01:00:01Z |
| publishDate | 2023-07-01 |
| publisher | International Union of Crystallography |
| record_format | Article |
| series | IUCrJ |
| spelling | doaj.art-5f4e3dbe014048a3be76cba849b381eb2023-07-06T13:03:09ZengInternational Union of CrystallographyIUCrJ2052-25252023-07-0110448749610.1107/S2052252523004293mf5063A deep learning solution for crystallographic structure determinationTom Pan0Shikai Jin1Mitchell D. Miller2Anastasios Kyrillidis3George N. Phillips Jr4Department of Computer Science, Rice University, Houston, Texas, USADepartment of Biosciences, Rice University, Houston, Texas, USADepartment of Biosciences, Rice University, Houston, Texas, USADepartment of Computer Science, Rice University, Houston, Texas, USADepartment of Biosciences, Rice University, Houston, Texas, USAThe general de novo solution of the crystallographic phase problem is difficult and only possible under certain conditions. This paper develops an initial pathway to a deep learning neural network approach for the phase problem in protein crystallography, based on a synthetic dataset of small fragments derived from a large well curated subset of solved structures in the Protein Data Bank (PDB). In particular, electron-density estimates of simple artificial systems are produced directly from corresponding Patterson maps using a convolutional neural network architecture as a proof of concept.http://scripts.iucr.org/cgi-bin/paper?S2052252523004293structure predictionstructure determinationx-ray crystallographydeep learning |
| spellingShingle | Tom Pan Shikai Jin Mitchell D. Miller Anastasios Kyrillidis George N. Phillips Jr A deep learning solution for crystallographic structure determination IUCrJ structure prediction structure determination x-ray crystallography deep learning |
| title | A deep learning solution for crystallographic structure determination |
| title_full | A deep learning solution for crystallographic structure determination |
| title_fullStr | A deep learning solution for crystallographic structure determination |
| title_full_unstemmed | A deep learning solution for crystallographic structure determination |
| title_short | A deep learning solution for crystallographic structure determination |
| title_sort | deep learning solution for crystallographic structure determination |
| topic | structure prediction structure determination x-ray crystallography deep learning |
| url | http://scripts.iucr.org/cgi-bin/paper?S2052252523004293 |
| work_keys_str_mv | AT tompan adeeplearningsolutionforcrystallographicstructuredetermination AT shikaijin adeeplearningsolutionforcrystallographicstructuredetermination AT mitchelldmiller adeeplearningsolutionforcrystallographicstructuredetermination AT anastasioskyrillidis adeeplearningsolutionforcrystallographicstructuredetermination AT georgenphillipsjr adeeplearningsolutionforcrystallographicstructuredetermination AT tompan deeplearningsolutionforcrystallographicstructuredetermination AT shikaijin deeplearningsolutionforcrystallographicstructuredetermination AT mitchelldmiller deeplearningsolutionforcrystallographicstructuredetermination AT anastasioskyrillidis deeplearningsolutionforcrystallographicstructuredetermination AT georgenphillipsjr deeplearningsolutionforcrystallographicstructuredetermination |