Browse
Submit Data
Databases
API
Help

Dataset Information

34 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Model Reconstruction from Small-Angle X-Ray Scattering Data Using Deep Learning Methods.

ABSTRACT: Small-angle X-ray scattering (SAXS) method is widely used in investigating protein structures in solution, but high-quality 3D model reconstructions are challenging. We present a new algorithm based on a deep learning method for model reconstruction from SAXS data. An auto-encoder for protein 3D models was trained to compress 3D shape information into vectors of a 200-dimensional latent space, and the vectors are optimized using genetic algorithms to build 3D models that are consistent with the scattering data. The program has been tested with experimental SAXS data, demonstrating the capacity and robustness of accurate model reconstruction. Furthermore, the model size information can be optimized using this algorithm, enhancing the automation in model reconstruction directly from SAXS data. The program was implemented using Python with the TensorFlow framework, with source code and webserver available from http://liulab.csrc.ac.cn/decodeSAXS.

SUBMITTER: He H

PROVIDER: S-EPMC7037568 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Model Reconstruction from Small-Angle X-Ray Scattering Data Using Deep Learning Methods.

He Hao H Liu Can C Liu Haiguang H

iScience 20200213 3

Small-angle X-ray scattering (SAXS) method is widely used in investigating protein structures in solution, but high-quality 3D model reconstructions are challenging. We present a new algorithm based on a deep learning method for model reconstruction from SAXS data. An auto-encoder for protein 3D models was trained to compress 3D shape information into vectors of a 200-dimensional latent space, and the vectors are optimized using genetic algorithms to build 3D models that are consistent with the ...[more]

PMID: 32092702

Similar Datasets

Methods for analysis of size-exclusion chromatography-small-angle X-ray scattering and reconstruction of protein scattering.

Project description:Size-exclusion chromatography in line with small-angle X-ray scattering (SEC-SAXS) has emerged as an important method for investigation of heterogeneous and self-associating systems, but presents specific challenges for data processing including buffer subtraction and analysis of overlapping peaks. This paper presents novel methods based on singular value decomposition (SVD) and Guinier-optimized linear combination (LC) to facilitate analysis of SEC-SAXS data sets and high-quality reconstruction of protein scattering directly from peak regions. It is shown that Guinier-optimized buffer subtraction can reduce common subtraction artifacts and that Guinier-optimized linear combination of significant SVD basis components improves signal-to-noise and allows reconstruction of protein scattering, even in the absence of matching buffer regions. In test cases with conventional SAXS data sets for cytochrome c and SEC-SAXS data sets for the small GTPase Arf6 and the Arf GTPase exchange factors Grp1 and cytohesin-1, SVD-LC consistently provided higher quality reconstruction of protein scattering than either direct or Guinier-optimized buffer subtraction. These methods have been implemented in the context of a Python-extensible Mac OS X application known as Data Evaluation and Likelihood Analysis (DELA), which provides convenient tools for data-set selection, beam intensity normalization, SVD, and other relevant processing and analytical procedures, as well as automated Python scripts for common SAXS analyses and Guinier-optimized reconstruction of protein scattering.

| S-EPMC4520288 | biostudies-literature

Rapid interpretation of small-angle X-ray scattering data.

Project description:The fundamental aim of structural analyses in biophysics is to reveal a mutual relation between a molecule's dynamic structure and its physiological function. Small-angle X-ray scattering (SAXS) is an experimental technique for structural characterization of macromolecules in solution and enables time-resolved analysis of conformational changes under physiological conditions. As such experiments measure spatially averaged low-resolution scattering intensities only, the sparse information obtained is not sufficient to uniquely reconstruct a three-dimensional atomistic model. Here, we integrate the information from SAXS into molecular dynamics simulations using computationally efficient native structure-based models. Dynamically fitting an initial structure towards a scattering intensity, such simulations produce atomistic models in agreement with the target data. In this way, SAXS data can be rapidly interpreted while retaining physico-chemical knowledge and sampling power of the underlying force field. We demonstrate our method's performance using the example of three protein systems. Simulations are faster than full molecular dynamics approaches by more than two orders of magnitude and consistently achieve comparable accuracy. Computational demands are reduced sufficiently to run the simulations on commodity desktop computers instead of high-performance computing systems. These results underline that scattering-guided structure-based simulations provide a suitable framework for rapid early-stage refinement of structures towards SAXS data with particular focus on minimal computational resources and time.

| S-EPMC6447237 | biostudies-literature

The accurate assessment of small-angle X-ray scattering data.

Project description:Small-angle X-ray scattering (SAXS) has grown in popularity in recent times with the advent of bright synchrotron X-ray sources, powerful computational resources and algorithms enabling the calculation of increasingly complex models. However, the lack of standardized data-quality metrics presents difficulties for the growing user community in accurately assessing the quality of experimental SAXS data. Here, a series of metrics to quantitatively describe SAXS data in an objective manner using statistical evaluations are defined. These metrics are applied to identify the effects of radiation damage, concentration dependence and interparticle interactions on SAXS data from a set of 27 previously described targets for which high-resolution structures have been determined via X-ray crystallography or nuclear magnetic resonance (NMR) spectroscopy. The studies show that these metrics are sufficient to characterize SAXS data quality on a small sample set with statistical rigor and sensitivity similar to or better than manual analysis. The development of data-quality analysis strategies such as these initial efforts is needed to enable the accurate and unbiased assessment of SAXS data quality.

| S-EPMC4304685 | biostudies-literature

FAIR and scalable management of small-angle X-ray scattering data.

Project description:A modular research data management toolbox based on the programming language Python, the widely used computing platform Jupyter Notebook, the standardized data exchange format for analytical data (AnIML) and the generic repository Dataverse has been established and applied to analyze small-angle X-ray scattering (SAXS) data according to the FAIR data principles (findable, accessible, interoperable and reusable). The SAS-tools library is a community-driven effort to develop tools for data acquisition, analysis, visualization and publishing of SAXS data. Metadata from the experiment and the results of data analysis are stored as an AnIML document using the novel Python-native pyAnIML API. The AnIML document, measured raw data and plots resulting from the analysis are combined into an archive in OMEX format and uploaded to Dataverse using the novel easyDataverse API, which makes each data set accessible via a unique DOI and searchable via a structured metadata block. SAS-tools is applied to study the effects of alkyl chain length and counterions on the phase diagrams of alkyltrimethyl-ammonium surfactants in order to demonstrate the feasibility and usefulness of a scalable data management workflow for experiments in physical chemistry.

| S-EPMC10077856 | biostudies-literature

A correction procedure for secondary scattering contributions from windows in small-angle X-ray scattering and ultra-small-angle X-ray scattering.

Project description:This article describes a correction procedure for the removal of indirect background contributions to measured small-angle X-ray scattering patterns. The high scattering power of a sample in the ultra-small-angle region may serve as a secondary source for a window placed in front of the detector. The resulting secondary scattering appears as a sample-dependent background in the measured pattern that cannot be directly subtracted. This is an intricate problem in measurements at ultra-low angles, which can significantly reduce the useful dynamic range of detection. Two different procedures are presented to retrieve the real scattering profile of the sample.

| S-EPMC11001404 | biostudies-literature

SAXSDom: Modeling multidomain protein structures using small-angle X-ray scattering data.

Project description:Many proteins are composed of several domains that pack together into a complex tertiary structure. Multidomain proteins can be challenging for protein structure modeling, particularly those for which templates can be found for individual domains but not for the entire sequence. In such cases, homology modeling can generate high quality models of the domains but not for the orientations between domains. Small-angle X-ray scattering (SAXS) reports the structural properties of entire proteins and has the potential for guiding homology modeling of multidomain proteins. In this article, we describe a novel multidomain protein assembly modeling method, SAXSDom that integrates experimental knowledge from SAXS with probabilistic Input-Output Hidden Markov model to assemble the structures of individual domains together. Four SAXS-based scoring functions were developed and tested, and the method was evaluated on multidomain proteins from two public datasets. Incorporation of SAXS information improved the accuracy of domain assembly for 40 out of 46 critical assessment of protein structure prediction multidomain protein targets and 45 out of 73 multidomain protein targets from the ab initio domain assembly dataset. The results demonstrate that SAXS data can provide useful information to improve the accuracy of domain-domain assembly. The source code and tool packages are available at https://github.com/jianlin-cheng/SAXSDom.

| S-EPMC7230021 | biostudies-literature

Small angle x-ray scattering with edge-illumination.

Project description:Sensitivity to sub-pixel sample features has been demonstrated as a valuable capability of phase contrast x-ray imaging. Here, we report on a method to obtain angular-resolved small angle x-ray scattering distributions with edge-illumination- based imaging utilizing incoherent illumination from an x-ray tube. Our approach provides both the three established image modalities (absorption, differential phase and scatter strength), plus a number of additional contrasts related to unresolved sample features. The complementarity of these contrasts is experimentally validated by using different materials in powder form. As a significant application example we show that the extended complementary contrasts could allow the diagnosis of pulmonary emphysema in a murine model. In support of this, we demonstrate that the properties of the retrieved scattering distributions are consistent with the expectation of increased feature sizes related to pulmonary emphysema. Combined with the simplicity of implementation of edge-illumination, these findings suggest a high potential for exploiting extended sub-pixel contrasts in the diagnosis of lung diseases and beyond.

| S-EPMC4974648 | biostudies-literature

Modeling the structure of RNA molecules with small-angle X-ray scattering data.

Project description:We propose a novel fragment assembly method for low-resolution modeling of RNA and show how it may be used along with small-angle X-ray solution scattering (SAXS) data to model low-resolution structures of particles having as many as 12 independent secondary structure elements. We assessed this model-building procedure by using both artificial data on a previously proposed benchmark and publicly available data. With the artificial data, SAXS-guided models show better similarity to native structures than ROSETTA decoys. The publicly available data showed that SAXS-guided models can be used to reinterpret RNA structures previously deposited in the Protein Data Bank. Our approach allows for fast and efficient building of de novo models of RNA using approximate secondary structures that can be readily obtained from existing bioinformatic approaches. We also offer a rigorous assessment of the resolving power of SAXS in the case of small RNA structures, along with a small multimetric benchmark of the proposed method.

| S-EPMC3817170 | biostudies-literature

Simulation of small-angle X-ray scattering data of biological macromolecules in solution.

Project description:This article presents IMSIM, an application to simulate two-dimensional small-angle X-ray scattering patterns and, further, one-dimensional profiles from biological macromolecules in solution. IMSIM implements a statistical approach yielding two-dimensional images in TIFF, CBF or EDF format, which may be readily processed by existing data-analysis pipelines. Intensities and error estimates of one-dimensional patterns obtained from the radial average of the two-dimensional images exhibit the same statistical properties as observed with actual experimental data. With initial input on an absolute scale, [cm-1]/c[mg ml-1], the simulated data frames may also be scaled to absolute scale such that the forward scattering after subtraction of the background is proportional to the molecular weight of the solute. The effects of changes of concentration, exposure time, flux, wavelength, sample-detector distance, detector dimensions, pixel size, and the mask as well as incident beam position can be considered for the simulation. The simulated data may be used in method development, for educational purposes, and also to determine the most suitable beamline setup for a project prior to the application and use of the actual beamtime. IMSIM is available as part of the ATSAS software package (3.0.0) and is freely available for academic use (http://www.embl-hamburg.de/biosaxs/download.html).

| S-EPMC7133063 | biostudies-literature

Machine Learning Methods for X-Ray Scattering Data Analysis from Biomacromolecular Solutions.

Project description:Small-angle x-ray scattering (SAXS) of biological macromolecules in solutions is a widely employed method in structural biology. SAXS patterns include information about the overall shape and low-resolution structure of dissolved particles. Here, we describe how to transform experimental SAXS patterns to feature vectors and how a simple k-nearest neighbor approach is able to retrieve information on overall particle shape and maximal diameter (Dmax) as well as molecular mass directly from experimental scattering data. Based on this transformation, we develop a rapid multiclass shape-classification ranging from compact, extended, and flat categories to hollow and random-chain-like objects. This classification may be employed, e.g., as a decision block in automated data analysis pipelines. Further, we map protein structures from the Protein Data Bank into the classification space and, in a second step, use this mapping as a data source to obtain accurate estimates for the structural parameters (Dmax, molecular mass) of the macromolecule under study based on the experimental scattering pattern alone, without inverse Fourier transform for Dmax. All methods presented are implemented in a Fortran binary DATCLASS, part of the ATSAS data analysis suite, available on Linux, Mac, and Windows and free for academic use.

| S-EPMC6129182 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data