An advanced workflow for single-particle imaging with the limited data at an X-ray free-electron laser

Assalauova, Dameli; Kim, Young Yong; Bobkov, Sergey; Khubbutdinov, Ruslan; Rose, M. Franklin; Alvarez, Roberto; Andreasson, Jakob; Balaur, Eugeniu; Contreras, Alice; DeMi̇rci̇, Hasan; Gelisio, Luca; Hajdu, János; Hunter, Mark S.; Kurta, Ruslan P.; Li, Haoyuan; McFadden, Matthew; Nazari, Reza; Schwander, Peter; Teslyuk, Anton; Walter, Peter; Xavier, P. Lourdu; Yoon, Chun Hong; Zaare, Sahba; Ilyin, V.; Kirian, Richard A.; Hogue, Brenda G.; Aquila, Andrew; Vartanyants, Ivan A.

doi:10.1107/s2052252520012798

Cited by 19 publications

(38 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Validation remains a problem for the nonstandard ways of sharing the data, but at least it is available to the public. In the future, single particle coherent X-ray diffraction images may yield new structural data (125), and these studies can and should also be shared in easily accessible digital form (126).…”

Section: Data Management and Sharing Of Dynamics Resultsmentioning

confidence: 99%

Moving beyond static snapshots: Protein dynamics and the Protein Data Bank

Miller

Phillips

2021

Journal of Biological Chemistry

View full text Add to dashboard Cite

Section: Data Management and Sharing Of Dynamics Resultsmentioning

confidence: 99%

Moving beyond static snapshots: Protein dynamics and the Protein Data Bank

Miller

Phillips

2021

Journal of Biological Chemistry

View full text Add to dashboard Cite

“…A general analysis pipeline for SPI data consists of several steps as first proposed in [2] and further extended in [11,12]. One of the important steps is the classification of all diffraction patterns measured in a XFEL experiment, and specifically identification of single hits, i.e.…”

Section: Introductionmentioning

confidence: 99%

“…Earlier this task was performed by different methods such as: principle component analysis (PCA) or support vector machine (SVM) [13]. In a recent work [12], classification of single hits was performed using expectation-maximization (EM) algorithms developed in cryogenic electron microscopy [14]. In this work, we propose to select single hits from experimental data set using a convolutional neural network (CNN) approach.…”

Section: Introductionmentioning

confidence: 99%

Classification of diffraction patterns in single particle imaging experiments performed at x-ray free-electron lasers using a convolutional neural network

Ignatenko¹,

Assalauova²,

Bobkov³

et al. 2021

Mach. Learn.: Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Single particle imaging (SPI) is a promising method of native structure determination, which has undergone fast progress with the development of x-ray free-electron lasers. Large amounts of data are collected during SPI experiments, driving the need for automated data analysis. The necessary data analysis pipeline has a number of steps including binary object classification (single versus non-single hits). Classification and object detection are areas where deep neural networks currently outperform other approaches. In this work, we use the fast object detector networks YOLOv2 and YOLOv3. By exploiting transfer learning, a moderate amount of data is sufficient to train the neural network. We demonstrate here that a convolutional neural network can be successfully used to classify data from SPI experiments. We compare the results of classification for the two different networks, with different depth and architecture, by applying them to the same SPI data with different data representation. The best results are obtained for diffracted intensity represented by color images on a linear scale using YOLOv2 for classification. It shows an accuracy of about 95% with precision and recall of about 50% and 60%, respectively, in comparison to manual data classification.

show abstract

“…In this regard, initial effort was based on unsupervised classification methods, such as manifold embedding, 16,26 which clusters similar diffraction patterns into regions in a low-dimensional feature space, and Principal Component Analysis (PCA) that quantifies correlations among diffraction patterns. 27,28 It is worth mentioning a recent unsupervised method 29 that employs an iterative expectation-maximization algorithm, 30 similar to the ones used in single-particle cryo-EM to classify images. 31 In fact, the data processing workflows for cryo-EM and SPI are quite similar, and both share a common requirement to achieve a high-resolution reconstruction: the single-particle identification step must retrieve a large number of snapshots, in order to overcome the noise from the low signal levels.…”

Section: Introductionmentioning

confidence: 99%

Selecting XFEL single-particle snapshots by geometric machine learning

Cruz-Chú

Hosseinizadeh

Mashayekhi

et al. 2021

Structural Dynamics

Self Cite

View full text Add to dashboard Cite

A promising new route for structural biology is single-particle imaging with an X-ray Free-Electron Laser (XFEL). This method has the advantage that the samples do not require crystallization and can be examined at room temperature. However, high-resolution structures can only be obtained from a sufficiently large number of diffraction patterns of individual molecules, so-called single particles. Here, we present a method that allows for efficient identification of single particles in very large XFEL datasets, operates at low signal levels, and is tolerant to background. This method uses supervised Geometric Machine Learning (GML) to extract low-dimensional feature vectors from a training dataset, fuse test datasets into the feature space of training datasets, and separate the data into binary distributions of “single particles” and “non-single particles.” As a proof of principle, we tested simulated and experimental datasets of the Coliphage PR772 virus. We created a training dataset and classified three types of test datasets: First, a noise-free simulated test dataset, which gave near perfect separation. Second, simulated test datasets that were modified to reflect different levels of photon counts and background noise. These modified datasets were used to quantify the predictive limits of our approach. Third, an experimental dataset collected at the Stanford Linear Accelerator Center. The single-particle identification for this experimental dataset was compared with previously published results and it was found that GML covers a wide photon-count range, outperforming other single-particle identification methods. Moreover, a major advantage of GML is its ability to retrieve single particles in the presence of structural variability.

show abstract

An advanced workflow for single-particle imaging with the limited data at an X-ray free-electron laser

Cited by 19 publications

References 59 publications

Moving beyond static snapshots: Protein dynamics and the Protein Data Bank

Moving beyond static snapshots: Protein dynamics and the Protein Data Bank

Classification of diffraction patterns in single particle imaging experiments performed at x-ray free-electron lasers using a convolutional neural network

Selecting XFEL single-particle snapshots by geometric machine learning

Contact Info

Product

Resources

About