Browse
Submit Data
Databases
API
Help

Dataset Information

30 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Accurate Machine Learning Prediction of Protein Circular Dichroism Spectra with Embedded Density Descriptors.

ABSTRACT: A data-driven approach to simulate circular dichroism (CD) spectra is appealing for fast protein secondary structure determination, yet the challenge of predicting electric and magnetic transition dipole moments poses a substantial barrier for the goal. To address this problem, we designed a new machine learning (ML) protocol in which ordinary pure geometry-based descriptors are replaced with alternative embedded density descriptors and electric and magnetic transition dipole moments are successfully predicted with an accuracy comparable to first-principle calculation. The ML model is able to not only simulate protein CD spectra nearly 4 orders of magnitude faster than conventional first-principle simulation but also obtain CD spectra in good agreement with experiments. Finally, we predicted a series of CD spectra of the Trp-cage protein associated with continuous changes of protein configuration along its folding path, showing the potential of our ML model for supporting real-time CD spectroscopy study of protein dynamics.

SUBMITTER: Zhao L

PROVIDER: S-EPMC8715543 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

BeStSel: a web server for accurate protein secondary structure prediction and fold recognition from the circular dichroism spectra.

Project description:Circular dichroism (CD) spectroscopy is a widely used method to study the protein secondary structure. However, for decades, the general opinion was that the correct estimation of β-sheet content is challenging because of the large spectral and structural diversity of β-sheets. Recently, we showed that the orientation and twisting of β-sheets account for the observed spectral diversity, and developed a new method to estimate accurately the secondary structure (PNAS, 112, E3095). BeStSel web server provides the Beta Structure Selection method to analyze the CD spectra recorded by conventional or synchrotron radiation CD equipment. Both normalized and measured data can be uploaded to the server either as a single spectrum or series of spectra. The originality of BeStSel is that it carries out a detailed secondary structure analysis providing information on eight secondary structure components including parallel-β structure and antiparallel β-sheets with three different groups of twist. Based on these, it predicts the protein fold down to the topology/homology level of the CATH protein fold classification. The server also provides a module to analyze the structures deposited in the PDB for BeStSel secondary structure contents in relation to Dictionary of Secondary Structure of Proteins data. The BeStSel server is freely accessible at http://bestsel.elte.hu.

| S-EPMC6031044 | biostudies-literature

Developing a machine learning model for accurate nucleoside hydrogels prediction based on descriptors.

Project description:Supramolecular hydrogels derived from nucleosides have been gaining significant attention in the biomedical field due to their unique properties and excellent biocompatibility. However, a major challenge in this field is that there is no model for predicting whether nucleoside derivative will form a hydrogel. Here, we successfully develop a machine learning model to predict the hydrogel-forming ability of nucleoside derivatives. The optimal model with a 71% (95% Confidence Interval, 0.69-0.73) accuracy is established based on a dataset of 71 reported nucleoside derivatives. 24 molecules are selected via the optimal model external application and the hydrogel-forming ability is experimentally verified. Among these, two rarely reported cation-independent nucleoside hydrogels are found. Based on their self-assemble mechanisms, the cation-independent hydrogel is found to have potential applications in rapid visual detection of Ag+ and cysteine. Here, we show the machine learning model may provide a tool to predict nucleoside derivatives with hydrogel-forming ability.

| S-EPMC10960799 | biostudies-literature

Accurate secondary structure prediction and fold recognition for circular dichroism spectroscopy.

Project description:Circular dichroism (CD) spectroscopy is a widely used technique for the study of protein structure. Numerous algorithms have been developed for the estimation of the secondary structure composition from the CD spectra. These methods often fail to provide acceptable results on α/β-mixed or β-structure-rich proteins. The problem arises from the spectral diversity of β-structures, which has hitherto been considered as an intrinsic limitation of the technique. The predictions are less reliable for proteins of unusual β-structures such as membrane proteins, protein aggregates, and amyloid fibrils. Here, we show that the parallel/antiparallel orientation and the twisting of the β-sheets account for the observed spectral diversity. We have developed a method called β-structure selection (BeStSel) for the secondary structure estimation that takes into account the twist of β-structures. This method can reliably distinguish parallel and antiparallel β-sheets and accurately estimates the secondary structure for a broad range of proteins. Moreover, the secondary structure components applied by the method are characteristic to the protein fold, and thus the fold can be predicted to the level of topology in the CATH classification from a single CD spectrum. By constructing a web server, we offer a general tool for a quick and reliable structure analysis using conventional CD or synchrotron radiation CD (SRCD) spectroscopy for the protein science research community. The method is especially useful when X-ray or NMR techniques fail. Using BeStSel on data collected by SRCD spectroscopy, we investigated the structure of amyloid fibrils of various disease-related proteins and peptides.

| S-EPMC4475991 | biostudies-literature

Analyses of circular dichroism spectra of membrane proteins.

Project description:Circular dichroism (CD) spectroscopy is a valuable technique for the determination of protein secondary structures. Many linear and nonlinear algorithms have been developed for the empirical analysis of CD data, using reference databases derived from proteins of known structures. To date, the reference databases used by the various algorithms have all been derived from the spectra of soluble proteins. When applied to the analysis of soluble protein spectra, these methods generally produce calculated secondary structures that correspond well with crystallographic structures. In this study, however, it was shown that when applied to membrane protein spectra, the resulting calculations produce considerably poorer results. One source of this discrepancy may be the altered spectral peak positions (wavelength shifts) of membrane proteins due to the different dielectric of the membrane environment relative to that of water. These results have important consequences for studies that seek to use the existing soluble protein reference databases for the analyses of membrane proteins.

| S-EPMC2323856 | biostudies-literature

On the analysis of membrane protein circular dichroism spectra.

Project description:Analysis of circular dichroism spectra of proteins provides information about protein secondary structure. Analytical methods developed for such an analysis use structures and spectra of a set of reference proteins. The reference protein sets currently in use include soluble proteins with a wide range of secondary structures, and perform quite well in analyzing CD spectra of soluble proteins. The utility of soluble protein reference sets in analyzing membrane protein CD spectra, however, has been questioned in a recent study that found current reference protein sets to be inadequate for analyzing membrane proteins. We have examined the performance of reference protein sets available in the CDPro software package for analyzing CD spectra of 13 membrane proteins with available crystal structures. Our results indicate that the reference protein sets currently available for CD analysis perform reasonably well in analyzing membrane protein CD spectra, with performance indices comparable to those for soluble proteins. Soluble + membrane protein reference sets, which were constructed by combining membrane proteins with soluble protein reference sets, gave improved performance in both soluble and membrane protein CD analysis.

| S-EPMC2286510 | biostudies-literature

Using circular dichroism spectra to estimate protein secondary structure.

Project description:Circular dichroism (CD) is an excellent tool for rapid determination of the secondary structure and folding properties of proteins that have been obtained using recombinant techniques or purified from tissues. The most widely used applications of protein CD are to determine whether an expressed, purified protein is folded, or if a mutation affects its conformation or stability. In addition, it can be used to study protein interactions. This protocol details the basic steps of obtaining and interpreting CD data, and methods for analyzing spectra to estimate the secondary structural composition of proteins. CD has the advantage that measurements may be made on multiple samples containing < or =20 microg of proteins in physiological buffers in a few hours. However, it does not give the residue-specific information that can be obtained by x-ray crystallography or NMR.

| S-EPMC2728378 | biostudies-literature

How accurate is circular dichroism-based model validation?

Project description:Circular dichroism (CD) spectroscopy is highly sensitive to the secondary structure (SS) composition of proteins. Several methods exist to either estimate the SS composition of a protein or to validate existing structural models using its CD spectrum. The accuracy and precision of these methods depend on the quality of both the measured CD spectrum and the used reference structure. Using a large reference protein set with high-quality CD spectra and synthetic data derived from this set, we quantified deviations from both ideal spectra and reference structures due to experimental limitations. We also determined the impact of these deviations on SS estimation, CD prediction, and SS validation methods of the SESCA analysis package. With regard to the CD spectra, our results suggest intensity scaling errors and non-SS contributions as the main causes of inaccuracies. These factors also can lead to overestimated model errors during validation. The errors of the used reference structures combine non-additively with errors caused by the CD spectrum, which increases the uncertainty of model validation. We have further shown that the effects of scaling errors in the CD spectrum can be nearly eliminated by appropriate re-scaling, and that the accuracy of model validation methods can be improved by accounting for typical non-SS contributions. These improvements have now been implemented within the SESCA package and are available at: https://www.mpibpc.mpg.de/sesca .

| S-EPMC7456416 | biostudies-literature

Theoretical Prediction of Structures, Vibrational Circular Dichroism, and Infrared Spectra of Chiral Be4B8 Cluster at Different Temperatures.

Project description:Lowest-energy structures, the distribution of isomers, and their molecular properties depend significantly on geometry and temperature. Total energy computations using DFT methodology are typically carried out at a temperature of zero K; thereby, entropic contributions to the total energy are neglected, even though functional materials work at finite temperatures. In the present study, the probability of the occurrence of one particular Be4B8 isomer at temperature T is estimated by employing Gibbs free energy computed within the framework of quantum statistical mechanics and nanothermodynamics. To identify a list of all possible low-energy chiral and achiral structures, an exhaustive and efficient exploration of the potential/free energy surfaces is carried out using a multi-level multistep global genetic algorithm search coupled with DFT. In addition, we discuss the energetic ordering of structures computed at the DFT level against single-point energy calculations at the CCSD(T) level of theory. The total VCD/IR spectra as a function of temperature are computed using each isomer's probability of occurrence in a Boltzmann-weighted superposition of each isomer's spectrum. Additionally, we present chemical bonding analysis using the adaptive natural density partitioning method in the chiral putative global minimum. The transition state structures and the enantiomer-enantiomer and enantiomer-achiral activation energies as a function of temperature evidence that a change from an endergonic to an exergonic type of reaction occurs at a temperature of 739 K.

| S-EPMC8271876 | biostudies-literature

Human pol II promoter prediction: time series descriptors and machine learning.

Project description:Although several in silico promoter prediction methods have been developed to date, they are still limited in predictive performance. The limitations are due to the challenge of selecting appropriate features of promoters that distinguish them from non-promoters and the generalization or predictive ability of the machine-learning algorithms. In this paper we attempt to define a novel approach by using unique descriptors and machine-learning methods for the recognition of eukaryotic polymerase II promoters. In this study, non-linear time series descriptors along with non-linear machine-learning algorithms, such as support vector machine (SVM), are used to discriminate between promoter and non-promoter regions. The basic idea here is to use descriptors that do not depend on the primary DNA sequence and provide a clear distinction between promoter and non-promoter regions. The classification model built on a set of 1000 promoter and 1500 non-promoter sequences, showed a 10-fold cross-validation accuracy of 87% and an independent test set had an accuracy >85% in both promoter and non-promoter identification. This approach correctly identified all 20 experimentally verified promoters of human chromosome 22. The high sensitivity and selectivity indicates that n-mer frequencies along with non-linear time series descriptors, such as Lyapunov component stability and Tsallis entropy, and supervised machine-learning methods, such as SVMs, can be useful in the identification of pol II promoters.

| S-EPMC552959 | biostudies-literature

Human pol II promoter prediction: time series descriptors and machine learning

Project description: Not available

| S-EPMC1069632 | biostudies-literature