Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
PhAI: A deep-learning approach to solve the crystallographic phase problem. |
| Συγγραφείς: |
Larsen, Anders S.1, Rekis, Toms1, Madsen, Anders Ø.1 a.madsen@sund.ku.dk |
| Πηγή: |
Science (pre-March 2025). 8/2/2024, Vol. 385 Issue 6708, p522-528. 7p. 6 Diagrams. |
| Θεματικοί όροι: |
*X-ray crystallography, *Space groups, *Crystal structure, *Problem solving |
| Περίληψη: |
X-ray crystallography provides a distinctive view on the three-dimensional structure of crystals. To reconstruct the electron density map, the complex structure factors F = |F|exp(if) of a sufficiently large number of diffracted reflections must be known. In a conventional experiment, only the amplitudes |F| are obtained, and the phases flare lost. This is the crystallographic phase problem. In this work, we show that a neural network, trained on millions of artificial structure data, can solve the phase problem at a resolution of only 2 angstroms, using only 10 to 20% of the data needed for direct methods. The network works in common space groups and for modest unit-cell dimensions and suggests that neural networks could be used to solve the phase problem in the general case for weakly scattering crystals. [ABSTRACT FROM AUTHOR] |
| Βάση Δεδομένων: |
Academic Search Index |