Dataset Information

Evaluation of the performance of classification algorithms for XFEL single-particle imaging data.

ABSTRACT: Using X-ray free-electron lasers (XFELs), it is possible to determine three-dimensional structures of nanoscale particles using single-particle imaging methods. Classification algorithms are needed to sort out the single-particle diffraction patterns from the large amount of XFEL experimental data. However, different methods often yield inconsistent results. This study compared the performance of three classification algorithms: convolutional neural network, graph cut and diffusion map manifold embedding methods. The identified single-particle diffraction data of the PR772 virus particles were assembled in the three-dimensional Fourier space for real-space model reconstruction. The comparison showed that these three classification methods lead to different datasets and subsequently result in different electron density maps of the reconstructed models. Interestingly, the common dataset selected by these three methods improved the quality of the merged diffraction volume, as well as the resolutions of the reconstructed maps.

SUBMITTER: Shi Y

PROVIDER: S-EPMC6400180 | biostudies-literature | 2019 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evaluation of the performance of classification algorithms for XFEL single-particle imaging data.

Shi Yingchen Y Yin Ke K Tai Xuecheng X DeMirci Hasan H Hosseinizadeh Ahmad A Hogue Brenda G BG Li Haoyuan H Ourmazd Abbas A Schwander Peter P Vartanyants Ivan A IA Yoon Chun Hong CH Aquila Andrew A Liu Haiguang H

IUCrJ 20190228 Pt 2

Using X-ray free-electron lasers (XFELs), it is possible to determine three-dimensional structures of nanoscale particles using single-particle imaging methods. Classification algorithms are needed to sort out the single-particle diffraction patterns from the large amount of XFEL experimental data. However, different methods often yield inconsistent results. This study compared the performance of three classification algorithms: convolutional neural network, graph cut and diffusion map manifold ...[more]

PMID: 30867930

Similar Datasets

Project description:X-ray free-electron laser (XFEL) is the latest generation of the X-ray source that could become an invaluable technique in structural biology. XFEL has ultrashort pulse duration, extreme peak brilliance, and high spatial coherence, which could enable the observation of the biological molecules in near nature state at room temperature without crystallization. However, for biological systems, due to their low diffraction power and complexity of sample delivery, experiments and data analysis are not straightforward, making it extremely challenging to reconstruct three-dimensional (3D) structures from single particle XFEL data. Given the current limitations to the amount and resolution of the data from such XFEL experiments, we propose a new hybrid approach for characterizing biomolecular conformational transitions by using a single 2D low-resolution XFEL diffraction pattern in combination with another known conformation. In our method, we represent the molecular structure with a coarse-grained model, the Gaussian mixture model, to describe large conformational transitions from low-resolution XFEL data. We obtain plausible 3D structural models that are consistent with the XFEL diffraction pattern by deforming an initial structural model to maximize the similarity between the target pattern and the simulated diffraction patterns from the candidate models. We tested the proposed algorithm on two biomolecules of different sizes with different complexities of conformational transitions, adenylate kinase, and elongation factor 2, using synthetic XFEL data. The results show that, with the proposed algorithm, we can successfully describe the conformational transitions by flexibly fitting the coarse-grained model of one conformation to become consistent with an XFEL diffraction pattern simulated from another conformation. In addition, we showed that the incident beam orientation has some effect on the accuracy of the 3D structure modeling and discussed the reasons for the inaccuracies for certain orientations. The proposed method could serve as an alternative approach for retrieving information on 3D conformational transitions from the XFEL diffraction patterns to interpret experimental data. Since the molecules are represented by Gaussian kernels and no atomic structure is needed in principle, such a method could also be used as a tool to seek initial models for 3D reconstruction algorithms.

Project description:The new technology of single-cell RNA sequencing (scRNA-seq) can yield valuable insights into gene expression and give critical information about the cellular compositions of complex tissues. In recent years, vast numbers of scRNA-seq datasets have been generated and made publicly available, and this has enabled researchers to train supervised machine learning models for predicting or classifying various cell-level phenotypes. This has led to the development of many new methods for analyzing scRNA-seq data. Despite the popularity of such applications, there has as yet been no systematic investigation of the performance of these supervised algorithms using predictors from various sizes of scRNA-seq datasets. In this study, 13 popular supervised machine learning algorithms for cell phenotype classification were evaluated using published real and simulated datasets with diverse cell sizes. This benchmark comprises two parts. In the first, real datasets were used to assess the computing speed and cell phenotype classification performance of popular supervised algorithms. The classification performances were evaluated using the area under the receiver operating characteristic curve, F1-score, Precision, Recall, and false-positive rate. In the second part, we evaluated gene-selection performance using published simulated datasets with a known list of real genes. The results showed that ElasticNet with interactions performed the best for small and medium-sized datasets. The NaiveBayes classifier was found to be another appropriate method for medium-sized datasets. With large datasets, the performance of the XGBoost algorithm was found to be excellent. Ensemble algorithms were not found to be significantly superior to individual machine learning methods. Including interactions in the ElasticNet algorithm caused a significant performance improvement for small datasets. The linear discriminant analysis algorithm was found to be the best choice when speed is critical; it is the fastest method, it can scale to handle large sample sizes, and its performance is not much worse than the top performers.

Project description:BACKGROUND:Recent advancements in high-throughput sequencing technologies have generated an unprecedented amount of genomic data that must be stored, processed, and transmitted over the network for sharing. Lossy genomic data compression, especially of the base quality values of sequencing data, is emerging as an efficient way to handle this challenge due to its superior compression performance compared to lossless compression methods. Many lossy compression algorithms have been developed for and evaluated using DNA sequencing data. However, whether these algorithms can be used on RNA sequencing (RNA-seq) data remains unclear. RESULTS:In this study, we evaluated the impacts of lossy quality value compression on common RNA-seq data analysis pipelines including expression quantification, transcriptome assembly, and short variants detection using RNA-seq data from different species and sequencing platforms. Our study shows that lossy quality value compression could effectively improve RNA-seq data compression. In some cases, lossy algorithms achieved up to 1.2-3 times further reduction on the overall RNA-seq data size compared to existing lossless algorithms. However, lossy quality value compression could affect the results of some RNA-seq data processing pipelines, and hence its impacts to RNA-seq studies cannot be ignored in some cases. Pipelines using HISAT2 for alignment were most significantly affected by lossy quality value compression, while the effects of lossy compression on pipelines that do not depend on quality values, e.g., STAR-based expression quantification and transcriptome assembly pipelines, were not observed. Moreover, regardless of using either STAR or HISAT2 as the aligner, variant detection results were affected by lossy quality value compression, albeit to a lesser extent when STAR-based pipeline was used. Our results also show that the impacts of lossy quality value compression depend on the compression algorithms being used and the compression levels if the algorithm supports setting of multiple compression levels. CONCLUSIONS:Lossy quality value compression can be incorporated into existing RNA-seq analysis pipelines to alleviate the data storage and transmission burdens. However, care should be taken on the selection of compression tools and levels based on the requirements of the downstream analysis pipelines to avoid introducing undesirable adverse effects on the analysis results.

Dataset Information

Evaluation of the performance of classification algorithms for XFEL single-particle imaging data.

Publications

Evaluation of the performance of classification algorithms for XFEL single-particle imaging data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets