串行晶体学数据筛选算法研究

doi:10.11889/j.0253-3219.2019.hjs.42.080102

Nuclear Techniques ›› 2019, Vol. 42 ›› Issue (8): 80102-080102.doi: 10.11889/j.0253-3219.2019.hjs.42.080102

• SYNCHROTRON RADIATION TECHNOLOGY AND APPLICATIONS • Previous Articles Next Articles

Research on serial crystallography data screening algorithm

Yueqi QIAN^1,²,Bo LIU³

1. Shanghai Institute of Applied Physics, Chinese Academy of Sciences, Shanghai 201800, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China

Received:2019-03-15 Revised:2019-05-17 Online:2019-08-10 Published:2019-08-26
About author:QIAN Yueqi, male, born in 1991, graduated from University of Science and Technology of China in 2014, master student, focusing on optics
Supported by:
National Key R&D Program of China "Research on XFEL Principle & Key Technologies"(2016YFA0401901)

Abstract

Abstract: Background

A number of machine learning-based methods have been developed for classification screening of serial femtosecond crystallography (SFX) data.

Purpose

This study aims to improve the data analysis technique to obtain more effectively screen SFX data from X-ray free electron lasers (XFELS).

Methods

First of all, experimental data of different samples were taken for screening and categorizing, Automatic image processing and convolutional neural network were employed for detection of Bragg points in diffraction patterns of crystals, hence, invalid experimental data were filtered out. Then, simulation was performed as the benchmark for many experiments. Finally, the reasons for the different accuracy of experimental prediction results were analyzed.

Results

Among many methods, convolutional neural network can obtain higher prediction accuracy whilst linear method only has better accuracy for some samples, but both of them are superior to traditional point-finding algorithm.

Conclusions

This approach provides an effective and convenient data screening tool for X-ray FEL experiments.

Key words: Free electron laser, Serial crystallography, Machine learning

CLC Number:

TP181，O722

Yueqi QIAN, Bo LIU. Research on serial crystallography data screening algorithm[J].Nuclear Techniques, 2019, 42(8): 80102-080102.

Figures/Tables 6

Fig.1

Fig.2

Table 1

Table 2

Fig.3

Fig.4

References 23

1	EmmaP, AkreR, ArthurJ, et al. First lasing and operation of an Ångstrom-wavelength free-electron laser[J]. Nature Photonics, 2010, 4(9): 641-647. DOI: 10.1016/S0268-005X(98)00069-1. doi: 10.1016/S0268-005X(98)00069-1
2	IshikawaTetsuya, AoyagiHideki, AsakaTakao, et al. A compact X-ray free-electron laser emitting in the sub-ngstrm region[J]. Nature Photonics, 2012, 6(8): 540-544. DOI: 10.1038/nphoton.2012.141. doi: 10.1038/nphoton.2012.141
3	AllariaE, CastronovoD, CinquegranaP, et al. Two-stage seeded soft-X-ray free-electron laser[J]. Nature Photonics, 2013, 7(11): 913-918. DOI: 10.1038/nphoton.2013.277. doi: 10.1038/nphoton.2013.277
4	ChapmanH N, FrommeP, BartyA, et al. Femtosecond X-ray protein nanocrystallography[J]. Nature, 2011, 470(7332): 73-77. DOI: 10.1038/nature09750. doi: 10.1038/nature09750
5	MarvinS M, TomasE, FilipeR, et al. Single mimivirus particles intercepted and imaged with an X-ray laser[J]. Nature, 2011, 470(7332): 78-81. DOI: 10.1038/nature09748. doi: 10.1038/nature09748
6	LutmanA A, CoffeeR, DingY, et al. Experimental demonstration of femtosecond two-color X-ray free-electron lasers[J]. Physical Review Letters, 2013, 110(13): 134801 -134806. DOI: 10.1103/physrevlett.110. 134801. doi: 10.1103/physrevlett.110. 134801
7	MarinelliA, RatnerD, LutmanA A, et al. High-intensity double-pulse X-ray free-electron laser[J]. Nature Communications, 2015, 6: 6369. DOI: 10.1038/ncomms7369. doi: 10.1038/ncomms7369
8	GlowniaJ M, CryanJ, AndreassonJ, et al. Time-resolved pump-probe experiments at the LCLS[J]. Optics Express, 2010, 18(17): 17620-17630. DOI: 10.1364/OE.18. 017620. doi: 10.1364/OE.18. 017620
9	BenjaminE, RebeccaB, SebastianT, et al. Imaging charge transfer in iodomethane upon X-ray photoabsorption[J]. Science, 2014, 345(6194): 288-291. DOI: 10.1126/science.1253607. doi: 10.1126/science.1253607
10	MarangosJ P. Introduction to the new science with X-ray free electron lasers[J]. Contemporary Physics, 2011, 52(6): 551-569. DOI: 10.1080/00107514.2011.607290. doi: 10.1080/00107514.2011.607290
11	ChelseaE, Liekhus-Schmaltz, TenneyIan, et al. Ultrafast isomerization initiated by X-ray core ionization[J]. Nature Communications, 2015, 6: 8199. DOI: 10.1038/ncomms9199. doi: 10.1038/ncomms9199
12	JoachimU, ArtemR, RobertM. Free-electron lasers: new avenues in molecular physics and photochemistry[J]. Annual Review of Physical Chemistry, 2012, 63: 635-660. DOI: 10.1146/annurev-physchem-032511-143720. doi: 10.1146/annurev-physchem-032511-143720
13	FergusonR, KenB, MaximilianG, et al. Transient lattice contraction in the solid-to-plasma transition[J]. Science Advances, 2016, 2(1): e1500837. DOI: 10.1126/sciadv. 1500837. doi: 10.1126/sciadv. 1500837
14	GoodfellowI, BengioY, CourvilleA. Deep learning[M/OL]. 2016. .
15	KeT W, BrewsterA S, YuS X, et al. A convolutional neural network-based screening tool for X-ray serial crystallography[J]. Journal of Synchrotron Radiation, 2018, 25: 655-670. DOI: 10.1107/S1600577518004873. doi: 10.1107/S1600577518004873
16	AlexK, SutskeverI, HintonG. Image net classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90. DOI: 10.1145/3065386. doi: 10.1145/3065386
17	FilipeR N C M. The coherent X-ray imaging data bank[J]. Nature Methods, 2012, 9: 854-855. DOI: 10.1038/nmeth.2110. doi: 10.1038/nmeth.2110
18	Edward Zhou, GaoX, XiangBarty, et al. X-ray laser diffraction for structure determination of the rhodopsin-arrestin complex[J]. Scientific Data, 2016, 3: 160021. DOI: 10.1038/sdata.2016.21. doi: 10.1038/sdata.2016.21
19	PetraE, HeikkiT, ElinC, et al. The room temperature crystal structure of a bacterial phytochrome determined by serial femtosecond crystallography[J]. Scientific Reports, 2016, 6: 35279. DOI: 10.1038/srep35279. doi: 10.1038/srep35279
20	KuboM, NangoE, TonoK, et al. Nanosecond pump–probe device for time-resolved serial femtosecond crystallography developed at SACLA[J]. Journal of Synchrotron Radiation, 2017, 24: 1086-1091. DOI: 10.1107/S160057751701030X. doi: 10.1107/S160057751701030X
21	KevinJ, KorayK, Marc'AurelioR, et al. What is the best multi-stage architecture for object recognition?[J]. IEEE 12th International Conference on Computer Vision, 2009, 12: 2146-2153. DOI: 10.1109/ICCV.2009.5459469. doi: 10.1109/ICCV.2009.5459469
22	DanielB. Realtime analysis of large-scale data[M]. KIT Scientific Publishing, 2017.
23	HantkeM F, EkebergT, MaiaF R N C. Condor: a simulation tool for flash X-ray imaging[J]. Journal of Applied Crystallography, 2016, 49: 1356-1362. DOI: 10.1107/S1600576716009213. doi: 10.1107/S1600576716009213

样品Samples	准确度Accuracy / %
嗜热菌蛋白酶Thermolysin	71.82
光系統 II Photosystem II	95.45
氢化酶Hydrogenase	94.89
亲环素A Cyclophilin A	94.24
光敏素Phytochrome	60.01
荧光素再生酶Luciferin-regenerating enzyme	90.41

样品Samples	CNN	线性Linear
Cyclophilin A	94.24	89.00
Thermolysin	71.82	52.20

[1]	Xuerui CHEN, Zhongwei ZHAO, Yuewen SUN, Guangchao LI, Peng CONG. Research on digital radiography classification learning method based on simulation data [J]. Nuclear Science and Techniques, 2019, 42(3): 30202-030202.
[2]	CHEN Jianqiao, WANG Qisheng, LI Bing, ZHOU Huan, CUI Ying, SUN Bo, WANG Zhijun, HE Jianhua. Electrospinning sample delivery for serial crystallography using synchrotron radiation [J]. Nuclear Techniques, 2017, 40(8): 80102-080102.
[3]	ZHAO Huan, DING Jianguo. Power supply control system of SDUV-FEL test facility [J]. Nuclear Techniques, 2013, 36(8): 80401-080401.
[4]	WANG Xingtao, LAN Taihe, LIU Bo, SHEN Lei, FENG Lie, YAO Haifeng, ZHANG Wenyan, WANG Dong. Seed laser transmission and injection system for the Shanghai Deep-Ultraviolet Free-Electron Laser test facility [J]. Nuclear Techniques, 2013, 36(5): 50103-050103.

Research on serial crystallography data screening algorithm

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References 23

Related Articles 4

Metrics

Comments

Recommended 10