PhAI: A deep learning approach to solve the crystallographic phase problem

移相器 相位问题 从头算 人工神经网络 衍射 相(物质) 分辨率(逻辑) 计算机科学 结晶学 物理 算法 人工智能 化学 量子力学 光学
作者
Anders Ø. Madsen,Anders S. Larsen,Toms Rekis
标识
DOI:10.26434/chemrxiv-2023-fcdps
摘要

For more than 100 years, X-ray crystallography has provided a unique view on the three-dimensional structure of atoms and molecules in crystals. However, to determine even the simplest structures now and a hundred years ago, one needs to overcome a mathematical hurdle for which the solution is not known even to this day. To reconstruct the 3-dimensional electron density map, from which the structure can be inferred, the complex structure factors F = |F| exp(iφ) of a sufficiently large number of diffracted reflections must be known. In a conventional diffraction experiment, only the amplitudes |F| are obtained, while the phases φ are lost. This is the crystallographic phase problem. Seventy years of research has established successful ab initio phasing methods such as direct methods and charge flipping. However, these methods are limited to atomic- resolution data, complicating structure determination from weakly-scattering crystals. Here, we show that a neural network can solve the crystallographic phase problem at a resolution of only 2 Å. We have developed an approach to generate millions of artificial structures and respective diffraction data for training of a neural network. We demonstrate that ab initio phasing based on this neural network is possible using 10 % to 20 % of the data needed for present-day methods, breaking the paradigm that atomic resolution is necessary for ab initio structure solution. The current neural network works in common centrosymmetric space groups and for modest unit cell dimensions, and suggests that neural networks can be used to solve the phase problem in the general case. This approach will enable structure solution for weakly-scattering crystals such as metal-organic frameworks or nanometer-sized crystals investigated using electron diffraction.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
lmh发布了新的文献求助10
刚刚
不安太阳完成签到,获得积分10
1秒前
2秒前
Jasper应助Chemberry采纳,获得10
2秒前
fill完成签到,获得积分20
3秒前
如意的书桃完成签到,获得积分10
4秒前
HH发布了新的文献求助10
4秒前
CipherSage应助务实锦程采纳,获得10
4秒前
dinglingling完成签到 ,获得积分10
5秒前
6秒前
6秒前
我ppp完成签到 ,获得积分10
7秒前
淡然依凝完成签到,获得积分10
7秒前
8秒前
8秒前
sonder发布了新的文献求助10
9秒前
机灵柚子应助小科采纳,获得10
10秒前
安详的一曲完成签到 ,获得积分10
10秒前
fill发布了新的文献求助30
10秒前
传奇3应助真水无香123采纳,获得10
11秒前
11秒前
hoongyan完成签到 ,获得积分10
12秒前
asss发布了新的文献求助10
12秒前
星辰大海应助yihuiqing采纳,获得10
12秒前
ding应助一只龟龟采纳,获得10
12秒前
la发布了新的文献求助10
13秒前
14秒前
14秒前
乐乐应助sonder采纳,获得10
15秒前
Chemberry发布了新的文献求助10
16秒前
小马甲应助王厚旺采纳,获得10
18秒前
cwansh完成签到,获得积分10
18秒前
甜美凡霜发布了新的文献求助10
19秒前
李健的粉丝团团长应助YPP采纳,获得10
19秒前
21秒前
顾矜应助科研通管家采纳,获得10
22秒前
斯文败类应助科研通管家采纳,获得10
22秒前
科研通AI2S应助科研通管家采纳,获得10
22秒前
FashionBoy应助科研通管家采纳,获得10
22秒前
Lucas应助科研通管家采纳,获得10
22秒前
高分求助中
(禁止应助)【重要!!请各位详细阅读】【科研通的精品贴汇总】 10000
Qualitative Inquiry and Research Design: Choosing Among Five Approaches 5th Edition 2000
International Code of Nomenclature for algae, fungi, and plants (Madrid Code) (Regnum Vegetabile) 1500
Linear and Nonlinear Functional Analysis with Applications, Second Edition 1200
Stereoelectronic Effects 1000
Robot-supported joining of reinforcement textiles with one-sided sewing heads 860
SPSS for Windows Step by Step: A Simple Study Guide and Reference, 17.0 Update (10th Edition) 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4195620
求助须知:如何正确求助?哪些是违规求助? 3731222
关于积分的说明 11751606
捐赠科研通 3405924
什么是DOI,文献DOI怎么找? 1868691
邀请新用户注册赠送积分活动 924906
科研通“疑难数据库(出版商)”最低求助积分说明 835549